Настройки

Укажите год
-

Небесная энциклопедия

Космические корабли и станции, автоматические КА и методы их проектирования, бортовые комплексы управления, системы и средства жизнеобеспечения, особенности технологии производства ракетно-космических систем

Подробнее
-

Мониторинг СМИ

Мониторинг СМИ и социальных сетей. Сканирование интернета, новостных сайтов, специализированных контентных площадок на базе мессенджеров. Гибкие настройки фильтров и первоначальных источников.

Подробнее

Форма поиска

Поддерживает ввод нескольких поисковых фраз (по одной на строку). При поиске обеспечивает поддержку морфологии русского и английского языка
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Укажите год
Укажите год
Применить Всего найдено 143. Отображено 143.
02-10-2019 дата публикации

Generative Modellierung von neuronalen Netzen zum Transformieren von Sprachäußerungen und Erweitern von Trainingsdaten

Номер: DE102019107928A1
Автор: NARAYANAN PRAVEEN, SCARIA LISA, CHARETTE FRANCOIS, MICKS ASHLEY ELIZABETH, BURKE RYAN, Narayanan, Praveen, Scaria, Lisa, Charette, Francois, Micks, Ashley Elizabeth, Burke, Ryan
Принадлежит:

Diese Offenbarung stellt generative Modellierung von neuronalen Netzen zum Transformieren von Sprachäußerungen und Erweitern von Trainingsdaten bereit. Es werden Systeme, Verfahren und Vorrichtungen zur Sprachtransformation und zum Erzeugen von synthetischer Sprache unter Verwendung von tiefen generativen Modellen offenbart. Ein Verfahren der Offenbarung beinhaltet Empfangen von Eingabeaudiodaten, die eine Vielzahl von Iterationen einer Sprachäußerung von einer Vielzahl von Sprechern umfassen. Das Verfahren beinhaltet Erzeugen eines Eingabespektrogramms auf Grundlage der Eingabeaudiodaten und Übertragen des Eingabespektrogramms an ein neuronales Netz, das dazu konfiguriert ist, ein Ausgabespektrogramm zu erzeugen. Das Verfahren beinhaltet Empfangen des Ausgabespektrogramms von dem neuronalen Netz und auf Grundlage des Ausgabespektrogramms Erzeugen von synthetischen Audiodaten, die die Sprachäußerung umfassen.

Подробнее
Номер записи: 1
06-08-2019 дата публикации

Sinkhole detection systems and methods

Номер: US0010372128B2
Автор: Scott Vincent Myers, Ashley Elizabeth Micks, Alexandru Mihai Gurghian, Harpreetsingh Banvait, Parsa Mahmoudieh, MYERS SCOTT VINCENT, MICKS ASHLEY ELIZABETH, GURGHIAN ALEXANDRU MIHAI, BANVAIT HARPREETSINGH, MAHMOUDIEH PARSA, Myers, Scott Vincent, Micks, Ashley Elizabeth, Gurghian, Alexandru Mihai, Banvait, Harpreetsingh, Mahmoudieh, Parsa
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC, FORD GLOBAL TECH LLC, Ford Global Technologies, LLC

Example sinkhole detection systems and methods are described. In one implementation, a method receives data from multiple sensors mounted to a vehicle and analyzes the received data to identify a sinkhole in a roadway ahead of the vehicle. If a sinkhole is identified, the method adjusts vehicle operations and reports the sinkhole to a shared database and/or another vehicle.

Подробнее
Номер записи: 2
21-09-2021 дата публикации

Predicting vehicle movements based on driver body language

Номер: US0011126877B2
Автор: Ashley Elizabeth Micks, Harpreetsingh Banvait, Jinesh J Jain, Brielle Reiff, MICKS ASHLEY ELIZABETH, BANVAIT HARPREETSINGH, JAIN JINESH J, REIFF BRIELLE, Micks, Ashley Elizabeth, Banvait, Harpreetsingh, Jain, Jinesh J, Reiff, Brielle
Принадлежит: Ford Global Technologies, LLC., FORD GLOBAL TECH LLC

Systems, methods, and devices for predicting driver intent and future movements of a human driven vehicles are disclosed herein. A computer implemented method includes receiving an image of a proximal vehicle in a region near a vehicle. The method includes determining a region of the image that contains a driver of the proximal vehicle, wherein determining the region comprises determining based on a location of one or more windows of the proximal vehicle. The method includes processing image data only in the region of the image that contains the driver of the proximal vehicle to detect a driver's body language.

Подробнее
Номер записи: 3
06-08-2019 дата публикации

Rear camera stub detection

Номер: US0010369994B2
Автор: Scott Vincent Myers, Alexandru Mihai Gurghian, Ashley Elizabeth Micks, Alexandro Walsh, MYERS SCOTT VINCENT, GURGHIAN ALEXANDRU MIHAI, MICKS ASHLEY ELIZABETH, WALSH ALEXANDRO, Myers, Scott Vincent, Gurghian, Alexandru Mihai, Micks, Ashley Elizabeth, Walsh, Alexandro
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC, FORD GLOBAL TECH LLC, Ford Global Technologies, LLC

A method for detecting stubs or intersecting roadways includes receiving perception data from at least two sensors. The at least two sensors include a rear facing camera of a vehicle and another sensor. The perception data includes information for a current roadway on which the vehicle is located. The method includes detecting, based on the perception data, an intersecting roadway connecting with the current roadway. The method also includes storing an indication of a location and a direction of the intersecting roadway with respect to the current roadway.

Подробнее
Номер записи: 4
29-08-2019 дата публикации

SYSTEM AND METHODS FOR IDENTIFYING UNOCCUPIED PARKING POSITIONS

Номер: US20190266422A1
Автор: Harpreestsingh Banvait, Ashley Elizabeth MICKS, Jinesh J. JAIN, Scott Vincent Myers, BANVAIT HARPREESTSINGH, MICKS ASHLEY ELIZABETH, JAIN JINESH J, MYERS SCOTT VINCENT, Banvait, Harpreestsingh, MICKS, Ashley Elizabeth, JAIN, Jinesh J., Myers, Scott Vincent
Принадлежит: Ford Motor Co

A vehicle includes one or more laterally mounted microphones and a controller programmed to detect a signature of an unoccupied position adjacent the vehicle in outputs of the microphones. The signature may be identified using a machine learning algorithm. In response to detecting an unoccupied position, the controller may invoke autonomous parking, store the location of the unoccupied position for later use, and/or report the unoccupied position to a server, which then informs other vehicles of the available parking. The unoccupied position may be verified by evaluating whether map data indicates legal parking at that location. The unoccupied position may also be confirmed with one or more other sensors, such as a camera, LIDAR, RADAR, SONAR, or other type of sensor.

Подробнее
Номер записи: 5
28-09-2017 дата публикации

VERFAHREN UND SYSTEM ZUR VIRTUELLEN SENSORDATENERZEUGUNG MIT TIEFEN-GROUND-TRUTH-ANNOTATION

Номер: DE102017105628A1
Автор: GROH ALEXANDER, MICKS ASHLEY ELIZABETH, NARIYAMBUT MURALI VIDYA, Groh, Alexander, Micks, Ashley Elizabeth, Nariyambut Murali, Vidya
Принадлежит:

Es werden Verfahren und Systeme zum Erzeugen virtueller Sensordaten für die Entwicklung oder das Testen von Computerseherkennungsalgorithmen beschrieben. Bei einem System und einem Verfahren kann eine virtuelle Umgebung erzeugt werden. Beim System und beim Verfahren kann auch ein virtueller Sensor an einem ersten Ort in der virtuellen Umgebung positioniert werden. Beim System und beim Verfahren können auch Daten aufgezeichnet werden, welche die virtuelle Umgebung kennzeichnen, wobei die Daten vom virtuellen Sensor, der die virtuelle Umgebung erfasst, erzeugten Informationen entsprechen. Beim System und beim Verfahren können ferner die Daten mit einer Tiefenkarte annotiert werden, welche eine räumliche Beziehung zwischen dem virtuellen Sensor und der virtuellen Umgebung kennzeichnet.

Подробнее
Номер записи: 6
12-10-2017 дата публикации

SICHTBASIERTE REGENERKENNUNG UNTER VERWENDUNG DES TIEFEN LERNENS

Номер: DE102017107264A1
Автор: JAIN JINESH J, BANVAIT HARPREETSINGH, MICKS ASHLEY ELIZABETH, NARIYAMBUT MURALI VIDYA, Jain, Jinesh J., Banvait, Harpreetsingh, Micks, Ashley Elizabeth, Nariyambut Murali, Vidya
Принадлежит:

Es wird ein Verfahren zur Verwendung einer Kamera an Bord eines Fahrzeugs zum Feststellen, ob Niederschlag in der Nähe des Fahrzeugs fällt, offenbart. Das Verfahren kann das Erhalten mehrerer Bilder umfassen. Es kann bekannt sein, dass jedes der mehreren Bilder photographisch eine "Regen"-Bedingung oder eine "Kein-Regen"-Bedingung zeigt. Ein künstliches neuronales Netz kann anhand der mehreren Bilder gelehrt werden. Später kann das künstliche neuronale Netz ein oder mehrere von einer ersten Kamera, die an einem ersten Fahrzeug befestigt ist, erfasste Bilder analysieren. Auf der Grundlage dieser Analyse kann das künstliche neuronale Netz das erste Fahrzeug als sich in "Regen"-Wetter oder "Kein-Regen"-Wetter befindend klassifizieren.

Подробнее
Номер записи: 7
11-05-2017 дата публикации

Autonomous Driving At Intersections Based On Perception Data

Номер: US20170131719A1
Автор: Ashley Elizabeth Micks, Harpreetsingh Banvait, Jinesh J. Jain, Brielle Reiff, MICKS ASHLEY ELIZABETH, BANVAIT HARPREETSINGH, JAIN JINESH J, REIFF BRIELLE, Micks Ashley Elizabeth, Banvait Harpreetsingh, Jain Jinesh J., Reiff Brielle
Принадлежит:

Systems, methods, and devices for predicting a driver's intention and future movements of a proximal vehicle, whether an automated vehicle or a human driven vehicle, are disclosed herein. A system for predicting future movements of a vehicle includes an intersection component, a camera system, a boundary component, and a prediction component. The intersection component is configured to determine that a parent vehicle is near an intersection. The camera system is configured to capture an image of the proximal vehicle. The boundary component is configured to identify a sub-portion of the image containing a turn signal indicator on the proximal vehicle. The prediction component is configured to predict future movement of the proximal vehicle through the intersection based on a state of the turn signal indicator. 1. A system comprising:an intersection component configured to determine that a parent vehicle is near an intersection;a camera system configured to capture an image of a proximal vehicle;a boundary component configured to identify a sub-portion of the image containing a turn signal indicator on the proximal vehicle;a turn signal component configured to process image data in the sub-portion of the image to determine the state of the turn signal indicator; anda prediction component configured to predict future movement of the proximal vehicle through the intersection based on a state of the turn signal indicator.2. (canceled)3. The system of claim 1 , further comprising a previous state component configured to determine one or more previous states of the proximal vehicle based on wireless communications indicating the one or more previous states of the proximal vehicle claim 1 , wherein the prediction component is configured to predict future movements of the proximal vehicle based on the one or more previous states of the proximal vehicle.4. The system of claim 3 , wherein the wireless communication comprises one or more of a vehicle-to-vehicle (V2V) ...

Подробнее
Номер записи: 8
01-03-2018 дата публикации

VERFAHREN UND SYSTEME ZUM AUTOMATISCHEN ERFASSEN VON GEFÄHRLICHEN STRASSENBEDINGUNGEN UND REAGIEREN DARAUF

Номер: DE102017117579A1
Автор: MYERS SCOTT VINCENT, KADETOTAD SNEHA, MICKS ASHLEY ELIZABETH, BANVAIT HARPREETSINGH, Myers, Scott Vincent, Kadetotad, Sneha, Micks, Ashley Elizabeth, Banvait, Harpreetsingh
Принадлежит:

Ein Verfahren zum automatischen Erfassen und sicheren Überqueren einer Ansammlung von Eis auf einer bevorstehenden Brücke. Das Verfahren identifiziert automatisch durch das Fahrzeug das bevorstehende Annähern des Fahrzeugs an eine Brücke und fühlt eine Ansammlung von Eis auf der Brücke. Das Verfahren berechnet dann eine Geschwindigkeit des Fahrzeugs, die erforderlich ist, um einen Längsschlupf zwischen dem Fahrzeug und der Brücke zu verhindern und verlangsamt das Fahrzeug automatisch bei einer Rate, die ausreichend ist, um dem Fahrzeug zu ermöglichen, die berechnete Geschwindigkeit bis zu dem Zeitpunkt, zu dem es die Brücke erreicht, zu erreichen. Ein entsprechendes System wird ebenfalls hierin offenbart und beansprucht.

Подробнее
Номер записи: 9
11-01-2018 дата публикации

VIRTUELLES SENSORDATENERZEUGUNGSSYSTEM UND VERFAHREN ZUR UNTERSTÜTZUNG DER ENTWICKLUNG VON ALGORITHMEN, DIE EIN BEFAHREN VON BAHNÜBERGÄNGEN UNTER VARIIERENDEN WETTERBEDINGUNGEN ERMÖGLICHEN

Номер: DE102017115049A1
Автор: MICKS ASHLEY ELIZABETH, MYERS SCOTT VINCENT, BANVAIT HARPREETSINGH, KADETOTAD SNEHA, Micks, Ashley Elizabeth, Myers, Scott Vincent, Banvait, Harpreetsingh, Kadetotad, Sneha
Принадлежит:

Es wird ein Verfahren zum Erzeugen von Trainingsdaten offenbart. Das Verfahren kann ein Ausführen eines Simulationsprozesses beinhalten. Der Simulationsprozess kann ein Durchfahren eines virtuellen, nach vorn gerichteten Sensors über einer virtuellen Straßenoberfläche, die zumindest einen virtuellen Bahnübergang definiert, beinhalten. Während des Durchfahrens kann der virtuelle Sensor in Bezug auf die virtuelle Straßenoberfläche, wie durch ein Fahrzeugbewegungsmodell vorgegeben, das Bewegung von einem Fahrzeug modelliert, das auf der virtuellen Straßenoberfläche fährt, während es den einen oder die mehreren virtuellen Sensoren trägt, bewegt werden. Virtuelle Sensordaten, die die virtuelle Straßenoberfläche kennzeichnen, können aufgezeichnet werden. Die virtuellen Sensordaten können dem entsprechen, was ein realer Sensor ausgegeben hätte, wenn er die Straßenoberfläche in der realen Welt erfasst hätte.

Подробнее
Номер записи: 10
21-06-2018 дата публикации

AUTOMATISCHE LECKERKENNUNG BEI FAHRZEUGEN

Номер: DE102017130041A1
Автор: JAIN JINESH J, BANVAIT HARPREETSINGH, JALES COSTA BRUNO SIELLY, MICKS ASHLEY ELIZABETH, Jain, Jinesh J., Banvait, Harpreetsingh, Jales Costa, Bruno Sielly, Micks, Ashley Elizabeth
Принадлежит:

Eine Fahrzeugsteuerung empfängt bei Ankunft und Abfahrt Bilder von einer Kamera. Eine Position des Fahrzeugs kann erfasst werden und die durch die Kamera aufgenommenen Bilder können mit einer Position markiert werden. Mit einem Ankunftsbild kann ein Abfahrtsbild verglichen werden, das an der Position aufgenommen wurde, die am nächsten zu der Position wie der des Ankunftsbildes gelegen ist. Ein Restbild, das auf einem Unterschied zwischen dem Ankunfts- und dem Abfahrtsbild basiert, wird auf Anomalien hin ausgewertet. Eigenschaften der Anomalie, wie etwa Textur, Farbe und dergleichen, werden bestimmt und die Anomalie wird basierend auf den Eigenschaften klassifiziert. Wenn die Klassifizierung ein Automobilfluid anzeigt, wird ein Alarm erzeugt.

Подробнее
Номер записи: 11
12-07-2018 дата публикации

Erzeugen von Trainingsdaten zur automatischen Leckerkennung bei Fahrzeugen

Номер: DE102018100192A1
Автор: MICKS ASHLEY ELIZABETH, JAIN JINESH J, BANVAIT HARPREETSINGH, JALES COSTA BRUNO SIELLY, Micks, Ashley Elizabeth, Jain, Jinesh J., Banvait, Harpreetsingh, Jales Costa, Bruno Sielly
Принадлежит:

Eine Fahrzeugsteuerung empfängt bei Ankunft und Abfahrt Bilder von einer Kamera. Ein Standort des Fahrzeugs kann erfasst werden und die durch die Kamera aufgenommenen Bilder können mit einem Standort markiert werden. Mit einem Ankunftsbild kann ein Abfahrtsbild verglichen werden, das am nächsten zu dem Standort des Ankunftsbildes aufgenommen wurde. Ein Restbild auf Grundlage eines Unterschieds zwischen dem Ankunfts- und Abfahrtsbild wird auf Anomalien hin ausgewertet. Attribute der Anomalie, wie etwa Textur, Farbe und dergleichen, werden bestimmt und die Anomalie wird auf Grundlage der Attribute klassifiziert. Falls die Klassifizierung ein Automobilfluid anzeigt, wird ein Alarm erzeugt. Ein maschineller Lernalgorithmus zum Erzeugen von Klassifizierungen aus Bilddaten kann unter Verwendung von Ankunfts- und Abfahrtsbildern trainiert werden, die durch Rendern eines dreidimensionalen Modells oder durch Hinzufügen von simulierten Fluidflecken zu zweidimensionalen Bildern erlangt werden.

Подробнее
Номер записи: 12
03-08-2017 дата публикации

System und Verfahren zur Detektion von die Fahrbahn kreuzenden Anomalien

Номер: DE102017101447A1
Автор: BANVAIT HARPREETSINGH, MYERS SCOTT VINCENT, MICKS ASHLEY ELIZABETH, KADETOTAD SNEHA, Banvait, Harpreetsingh, Myers, Scott Vincent, Micks, Ashley Elizabeth, Kadetotad, Sneha
Принадлежит:

Verfahren zur Verbesserung von Sicherheit und Komfort eines Fahrzeugs, das über ein Eisenbahngleis, Viehgitter oder dergleichen fährt. Das Verfahren kann das Empfangen von einer oder mehreren Eingaben, die einem oder mehreren vorausschauenden Sensoren entsprechen, durch ein Rechnersystem aufweisen. Das Rechnersystem kann auch Daten empfangen, die eine Bewegung des Fahrzeugs kennzeichnen. Das Rechnersystem kann basierend auf der einen oder den mehreren Eingaben und den Daten eine Bewegung eines Fahrzeugs in Bezug auf ein Eisenbahngleis, Viehgitter oder dergleichen, das sich über eine Straße vor dem Fahrzeug erstreckt, schätzen. Dementsprechend kann das Rechnersystem eine Aufhängungseinstellung, Lenkungseinstellung oder dergleichen des Fahrzeugs ändern, um sicherer oder komfortabler über das Eisenbahngleis, Viehgitter oder dergleichen zu fahren.

Подробнее
Номер записи: 13
22-03-2018 дата публикации

SYSTEME UND VERFAHREN ZUR ERFASSUNG VON METALLBRÜCKEN

Номер: DE102017121590A1
Автор: MYERS SCOTT VINCENT, MICKS ASHLEY ELIZABETH, KADETOTAD SNEHA, BANVAIT HARPREETSINGH, Myers, Scott Vincent, Micks, Ashley Elizabeth, Kadetotad, Sneha, Banvait, Harpreetsingh
Принадлежит:

Beschrieben werden beispielhafte Systeme und Verfahren zur Erfassung von Metallbrücken. In einer Umsetzung empfängt ein Verfahren LIDAR-Daten von einem LIDAR-System, das an einem Fahrzeug angebracht ist, empfängt Kameradaten von einem Kamerasystem, das an dem Fahrzeug angebracht ist. Das Verfahren analysiert die empfangenen LIDAR-Daten und die Kameradaten, um eine Metallbrücke in der Nähe des Fahrzeugs zu identifizieren. Wenn eine Metallbrücke identifiziert wird, passt das Verfahren Fahrzeugoperationen an, um die Fahrzeugsteuerung zu verbessern, während es über die Metallbrücke fährt.

Подробнее
Номер записи: 14
21-12-2017 дата публикации

TRAININGSALGORITHMUS ZUR KOLLISIONSVERMEIDUNG UNTER VERWENDEN VON AUDITIVEN DATEN

Номер: DE102017112992A1
Автор: MICKS ASHLEY ELIZABETH, JAIN JINESH J, HAN KYU JEONG, BANVAIT HARPREETSINGH, Micks, Ashley Elizabeth, Jain, Jinesh J., Han, Kyu Jeong, Banvait, Harpreetsingh
Принадлежит:

Ein Maschinenlernmodell wird durch das Definieren eines Szenarios trainiert, das Modelle von Fahrzeugen und eine typische Fahrumgebung beinhaltet. Ein Modell eines betroffenen Fahrzeugs wird dem Szenario hinzugefügt, und Sensorstandorte werden auf dem betroffenen Fahrzeug definiert. Eine Wahrnehmung des Szenarios durch Sensoren an den Sensorstandorten wird simuliert. Das Szenario beinhaltet weiterhin ein Modell eines geparkten Fahrzeugs mit laufendem Motor. Der Standort des geparkten Fahrzeugs und die simulierten Ausgaben der Sensoren, die das Szenario wahrnehmen, werden in den Maschinenlernalgorithmus eingegeben, der ein Modell trainiert, um den Standort des geparkten Fahrzeugs auf der Grundlage der Sensorausgaben zu erkennen. Eine Fahrzeugsteuerung beinhaltet dann das Maschinenlernmodell und schätzt das Vorhandensein und/oder den Standort eines geparkten Fahrzeugs mit laufendem Motor auf der Grundlage von aktuellen Sensorausgaben, die in das Maschinenlernmodell eingegeben werden.

Подробнее
Номер записи: 15
28-04-2020 дата публикации

Virtual sensor data generation for wheel stop detection

Номер: US0010635912B2
Автор: Ashley Elizabeth Micks, Venkatapathi Raju Nallapa, Harpreetsingh Banvait, Scott Vincent Myers, MICKS ASHLEY ELIZABETH, NALLAPA VENKATAPATHI RAJU, BANVAIT HARPREETSINGH, MYERS SCOTT VINCENT, Micks, Ashley Elizabeth, Nallapa, Venkatapathi Raju, Banvait, Harpreetsingh, Myers, Scott Vincent
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC, FORD GLOBAL TECH LLC, Ford Global Technologies, LLC.

The disclosure relates to methods, systems, and apparatuses for virtual sensor data generation and more particularly relates to generation of virtual sensor data for training and testing models or algorithms to detect objects or obstacles. A method for generating virtual sensor data includes simulating, using one or more processors, a three-dimensional (3D) environment comprising one or more virtual objects. The method includes generating, using one or more processors, virtual sensor data for a plurality of positions of one or more sensors within the 3D environment. The method includes determining, using one or more processors, virtual ground truth corresponding to each of the plurality of positions, wherein the ground truth comprises a dimension or parameter of the one or more virtual objects. The method includes storing and associating the virtual sensor data and the virtual ground truth using one or more processors.

Подробнее
Номер записи: 16
27-07-2017 дата публикации

Drive History Parking Barrier Alert

Номер: US20170210291A1
Автор: Venkatapathi Raju Nallapa, Scott Vincent Myers, Harpreetsingh Banvait, Ashley Elizabeth Micks, NALLAPA VENKATAPATHI RAJU, MYERS SCOTT VINCENT, BANVAIT HARPREETSINGH, MICKS ASHLEY ELIZABETH, Nallapa Venkatapathi Raju, Myers Scott Vincent, Banvait Harpreetsingh, Micks Ashley Elizabeth
Принадлежит: FORD GLOBAL TECHNOLOGIES LLC

A driving assistance system includes a drive detection component, a presence component, and a notification component. The drive detection component is configured to determine that a vehicle or driver is exiting or preparing to exit a parking location. The presence component is configured to determine, from a drive history database, whether a parking barrier is present in front of or behind the parking location. The notification component is configured to provide an indication that the parking barrier is present to a human driver or an automated driving system of the vehicle.

Подробнее
Номер записи: 17
21-07-2016 дата публикации

Prüfstand für virtuelle Sensoren

Номер: DE102016100416A1
Автор: ALANIZ ARTHUR, NARIYAMBUT MURALI VIDYA, MICKS ASHLEY ELIZABETH, BANVAIT HARPREETSINGH, KADETOTAD SNEHA, Alaniz, Arthur, Nariyambut murali, Vidya, Micks, Ashley Elizabeth, Banvait, Harpreetsingh, Kadetotad, Sneha
Принадлежит:

Eine Computervorrichtung umfasst eine Verarbeitungsschaltung und ein Datenspeichermedium. Die Computervorrichtung ist programmiert, um virtuelle Sensordaten zu empfangen, die Daten repräsentieren, welche von einem virtuellen Sensor in Zusammenhang mit dem autonomen Betrieb eines virtuellen Fahrzeugs in einer virtuellen Umgebung gesammelt werden, wobei die virtuellen Sensordaten zum Identifizieren einer Einschränkung eines realen Sensors verarbeitet werden.

Подробнее
Номер записи: 18
27-07-2017 дата публикации

Training Algorithm for Collision Avoidance

Номер: US20170213149A1
Автор: ASHLEY ELIZABETH MICKS, JINESH J. JAIN, HARPREETSINGH BANVAIT, KYU JEONG HAN, MICKS ASHLEY ELIZABETH, JAIN JINESH J, BANVAIT HARPREETSINGH, HAN KYU JEONG, JAIN JINESH J.
Принадлежит: FORD GLOBAL TECHNOLOGIES LLC

A machine learning model is trained by defining a scenario including models of vehicles and a typical driving environment. A model of a subject vehicle is added to the scenario and sensor locations are defined on the subject vehicle. A perception of the scenario by sensors at the sensor locations is simulated. The scenario further includes a model of a lane-splitting vehicle. The location of the lane-splitting vehicle and the simulated outputs of the sensors perceiving the scenario are input to a machine learning algorithm that trains a model to detect the location of a lane-splitting vehicle based on the sensor outputs. A vehicle controller then incorporates the machine learning model and estimates the presence and/or location of a lane-splitting vehicle based on actual sensor outputs input to the machine learning model.

Подробнее
Номер записи: 19
11-12-2018 дата публикации

Drive history parking barrier alert

Номер: US0010150412B2
Автор: Venkatapathi Raju Nallapa, Scott Vincent Meyers, Harpreetsingh Banvait, Ashley Elizabeth Micks, NALLAPA VENKATAPATHI RAJU, MEYERS SCOTT VINCENT, BANVAIT HARPREETSINGH, MICKS ASHLEY ELIZABETH, Nallapa, Venkatapathi Raju, Meyers, Scott Vincent, Banvait, Harpreetsingh, Micks, Ashley Elizabeth
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC, FORD GLOBAL TECH LLC, Ford Global Technologies, LLC

A driving assistance system includes a drive detection component, a presence component, and a notification component. The drive detection component is configured to determine that a vehicle or driver is exiting or preparing to exit a parking location. The presence component is configured to determine, from a drive history database, whether a parking barrier is present in front of or behind the parking location. The notification component is configured to provide an indication that the parking barrier is present to a human driver or an automated driving system of the vehicle.

Подробнее
Номер записи: 20
04-05-2017 дата публикации

PRÄDIZIEREN VON FAHRZEUGBEWEGUNGEN ANHAND VON FAHRERKÖRPERSPRACHE

Номер: DE102016120507A1
Автор: MICKS ASHLEY ELIZABETH, BANVAIT HARPREETSINGH, JAIN JINESH J, REIFF BRIELLE, Micks, Ashley Elizabeth, Banvait, Harpreetsingh, Jain, Jinesh J., Reiff, Brielle
Принадлежит:

Es werden vorliegend Systeme, Verfahren und Vorrichtungen zum Prädizieren einer Fahrerintention und zukünftiger Bewegungen eines von einem Menschen gefahrenen Fahrzeugs offenbart. Ein System zum Prädizieren zukünftiger Bewegungen eines Fahrzeugs umfasst ein Kamerasystem, eine Begrenzungskomponente, eine Körpersprachenkomponente und eine Prädiktionskomponente. Das Kamerasystem ist ausgelegt, ein Bild eines Fahrzeugs aufzunehmen. Die Begrenzungskomponente ist ausgelegt, einen Teilabschnitt des Bildes zu identifizieren, der einem Bereich entspricht, in dem sich ein Fahrer eines Fahrzeugs befindet. Die Körpersprachenkomponente ist ausgelegt, eine Körpersprache eines Fahrers zu detektieren. Die Prädiktionskomponente ist ausgelegt, eine zukünftige Bewegung des Fahrzeugs anhand der von der Körpersprachenkomponente detektierten Körpersprache des Fahrers zu prädizieren.

Подробнее
Номер записи: 21
18-01-2018 дата публикации

Heads-Up-Anzeige zum Beobachten von Fahrzeugwahrnehmungsaktivität

Номер: DE102017115318A1
Автор: AHMAD MOHAMED, BANVAIT HARPREETSINGH, MICKS ASHLEY ELIZABETH, NAGRAJ RAO NIKHIL, Ahmad, Mohamed, Banvait, Harpreetsingh, Micks, Ashley Elizabeth, Nagraj Rao, Nikhil
Принадлежит:

Die vorliegende Erfindung bezieht sich auf Verfahren, Systeme und Computerprogrammprodukte für eine Heads-Up-Anzeige zum Beobachten von Fahrzeugwahrnehmungsaktivität. Während ein Fahrzeug in Betrieb ist, kann ein Insasse Objekte außerhalb des Fahrzeugs durch die Windschutzscheibe sehen. Fahrzeugsensoren können ebenfalls die Objekte außerhalb des Fahrzeugs erfassen. Ein Fahrzeugprojektionssystem kann eine Heads-Up-Anzeige für die erfassten Objekte auf die Windschutzscheibe projizieren. Die Heads-Up-Anzeige kann am Blickwinkel eines Fahrers ausgerichtet sein, sodass graphische Elemente, die auf eine Windschutzscheibe projiziert werden, die ihnen entsprechenden Objekte überlagern, die durch die Windschutzscheibe gesehen werden. Auf diese Weise kann ein Fahrer (z. B. ein Testtechniker) Algorithmusausgaben (z. B. Wahrnehmungsalgorithmusausgaben) sehen, ohne beim Fahren den Blick von der Straße abwenden zu müssen. Entsprechend ist das Testen von Fahrerunterstützungs- und Selbstfahrfunktionen ...

Подробнее
Номер записи: 22
22-06-2017 дата публикации

VIRTUELLE SENSORDATENERZEUGUNG ZUR RADANSCHLAGDETEKTION

Номер: DE102016123887A1
Автор: MICKS ASHLEY ELIZABETH, NALLAPA VENKATAPATHI RAJU, BANVAIT HARPREETSINGH, MYERS SCOTT VINCENT, Micks, Ashley Elizabeth, Nallapa, Venkatapathi Raju, Banvait, Harpreetsingh, Myers, Scott Vincent
Принадлежит:

Die Offenbarung betrifft Verfahren, Systeme und Vorrichtungen zur virtuellen Sensordatenerzeugung und betrifft insbesondere die Erzeugung von virtuellen Sensordaten zum Trainieren und Testen von Modellen und Algorithmen zum Detektieren von Objekten oder Hindernissen, wie etwa Radanschläge oder Parkbarrieren. Ein Verfahren zum Erzeugen von virtuellen Sensordaten beinhaltet Simulieren einer dreidimensionalen (3D) Umgebung, die ein oder mehrere Objekte umfasst. Das Verfahren beinhaltet Erzeugen von virtuellen Sensordaten für mehrere Positionen eines oder mehrerer Sensoren in der 3D-Umgebung. Das Verfahren beinhaltet Bestimmen der virtuellen Ground-Truth, die jeder der mehreren Positionen entspricht, wobei die Ground-Truth Informationen über mindestens ein Objekt in den virtuellen Sensordaten beinhaltet. Das Verfahren beinhaltet auch Speichern und Assoziieren der virtuellen Sensordaten und der virtuellen Ground-Truth.

Подробнее
Номер записи: 23
16-03-2017 дата публикации

ERZEUGUNG VON SENSORDATEN IN EINER VIRTUELLEN FAHRUMGEBUNG

Номер: DE102016216268A1
Автор: NALLAPA VENKATAPATHI RAJU, MICKS ASHLEY ELIZABETH, BLUE DOUGLAS, SAEGER MARTIN, Nallapa, Venkatapathi Raju, Micks, Ashley Elizabeth, Blue, Douglas, Saeger, Martin
Принадлежит:

Verfahren zum Erzeugen von Trainingsdaten. Das Verfahren kann ein Ausführen eines Simulationsprozesses beinhalten. Der Simulationsprozess kann ein Hinüberbewegen eines oder mehrerer virtueller Sensoren über eine virtuelle Straßenoberfläche beinhalten, die eine Vielzahl von virtuellen Anomalien definiert, von denen jede durch den einen oder die mehreren virtuellen Sensoren erfassbar ist. Während des Hinüberbewegens kann jeder aus dem einen oder den mehreren virtuellen Sensoren in Bezug auf die virtuelle Straßenoberfläche derart bewegt werden, wie es durch ein Fahrzeugbewegungsmodell vorgeschrieben wird, das eine Bewegung eines Fahrzeugs modelliert, das auf der virtuellen Straßenoberfläche fährt, während es den einen oder mehrere virtuelle Sensoren befördert. Virtuelle Sensordaten, die für die virtuelle Straßenoberfläche kennzeichnend sind, können aufgezeichnet werden. Die virtuellen Sensordaten können dem entsprechen, was ein realer Sensor ausgegeben hätte, wenn er die Straßenoberfläche ...

Подробнее
Номер записи: 24
20-04-2017 дата публикации

LANE BOUNDARY DETECTION DATA GENERATION IN VIRTUAL ENVIRONMENT

Номер: US20170109928A1
Автор: Ashley Elizabeth Micks, Venkatapathi Raju Nallapa, Brielle Reiff, Vidya Nariyambut Murali, Sneha Kadetotad, MICKS ASHLEY ELIZABETH, NALLAPA VENKATAPATHI RAJU, REIFF BRIELLE, NARIYAMBUT MURALI VIDYA, KADETOTAD SNEHA, Micks Ashley Elizabeth, Nallapa Venkatapathi Raju, Reiff Brielle, Nariyambut Murali Vidya, Kadetotad Sneha
Принадлежит: FORD GLOBAL TECHNOLOGIES LLC

A method and an apparatus pertaining to generating training data. The method may include executing a simulation process. The simulation process may include traversing one or more virtual sensors over a virtual driving environment defining a plurality of lane markings or virtual objects that are each sensible by the one or more virtual sensors. During the traversing, each of the one or more virtual sensors may be moved with respect to the virtual driving environment as dictated by a vehicle-dynamic model modeling motion of a vehicle driving on a virtual road surface of the virtual driving environment while carrying the one or more virtual sensors. Virtual sensor data characterizing the virtual driving environment may be recorded. The virtual sensor data may correspond to what an actual sensor would produce in a real-world environment that is similar or substantially matching the virtual driving environment.

Подробнее
Номер записи: 25
02-03-2021 дата публикации

Neural network generative modeling to transform speech utterances and augment training data

Номер: US0010937438B2
Автор: Praveen Narayanan, Lisa Scaria, Francois Charette, Ashley Elizabeth Micks, Ryan Burke, NARAYANAN PRAVEEN, SCARIA LISA, CHARETTE FRANCOIS, MICKS ASHLEY ELIZABETH, BURKE RYAN, Narayanan, Praveen, Scaria, Lisa, Charette, Francois, Micks, Ashley Elizabeth, Burke, Ryan
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC, FORD GLOBAL TECH LLC, Ford Global Technologies, LLC

Systems, methods, and devices for speech transformation and generating synthetic speech using deep generative models are disclosed. A method of the disclosure includes receiving input audio data comprising a plurality of iterations of a speech utterance from a plurality of speakers. The method includes generating an input spectrogram based on the input audio data and transmitting the input spectrogram to a neural network configured to generate an output spectrogram. The method includes receiving the output spectrogram from the neural network and, based on the output spectrogram, generating synthetic audio data comprising the speech utterance.

Подробнее
Номер записи: 26
27-06-2019 дата публикации

Bollard Receiver Identification

Номер: US20190197901A1
Автор: Harpreetsingh Banvait, Scott Vincent Myers, Ashley Elizabeth Micks, Sneha Kadetotad, BANVAIT HARPREETSINGH, MYERS SCOTT VINCENT, MICKS ASHLEY ELIZABETH, KADETOTAD SNEHA, Banvait, Harpreetsingh, Myers, Scott Vincent, Micks, Ashley Elizabeth, Kadetotad, Sneha
Принадлежит:

The disclosure relates generally to methods, systems, and apparatuses for automated or assisted driving and more particularly relates to identification, localization, and navigation with respect to bollard receivers. A method for detecting bollard receivers includes receiving perception data from one or more perception sensors of a vehicle. The method includes determining, based on the perception data, a location of one or more bollard receivers in relation to a body of the vehicle. The method also includes providing an indication of the location of the one or more bollard receivers to one or more of a driver and component or system that makes driving maneuver decisions. 1. A method comprising:receiving perception data from a perception sensor of a vehicle;determining, based on the perception data, a location of a bollard receiver in relation to a body of the vehicle; anddetermining a driving maneuver based on the location of the bollard receiver, wherein the driving maneuver causes one or more tires of the vehicle to impact the bollard receiver.2. The method of claim 1 , further comprising determining the location in relation to the body of the vehicle based on information from a controller area network (CAN) bus of the vehicle.3. The method of claim 1 , wherein determining the location comprises determining based on the perception data and further based on a vehicle driving history.4. The method of claim 1 , wherein the perception sensor comprises two or more of a camera claim 1 , a radar sensor claim 1 , a light detection and ranging (LIDAR) sensor claim 1 , and an ultrasound sensor.5. The method of claim 1 , wherein the driving maneuver causes one or more tires of the vehicle to impact the bollard receiver with a tread portion of the one or more tires such that a sidewall portion of the one or more tires does not come in contact with the bollard receiver.6. The method of claim 1 , further comprising determining a height of the bollard receiver based on the ...

Подробнее
Номер записи: 27
04-05-2017 дата публикации

PREDICTING VEHICLE MOVEMENTS BASED ON DRIVER BODY LANGUAGE

Номер: US20170124407A1
Автор: Ashley Elizabeth Micks, Harpreetsingh Banvait, Jinesh J. Jain, Brielle Reiff, MICKS ASHLEY ELIZABETH, BANVAIT HARPREETSINGH, JAIN JINESH J, REIFF BRIELLE, Micks Ashley Elizabeth, Banvait Harpreetsingh, Jain Jinesh J., Reiff Brielle
Принадлежит:

Systems, methods, and devices for predicting driver intent and future movements of a human driven vehicles are disclosed herein. A system for predicting future movements of a vehicle includes a camera system, a boundary component, a body language component, and a prediction component. The camera system is configured to capture an image of a vehicle. The boundary component is configured to identify a sub-portion of the image corresponding to an area where a driver of a vehicle is located. The body language component configured to detect a driver's body language. The prediction component configured to predict future motion of the vehicle based on the driver's body language detected by the body language component. 1. A system comprising:a camera system configured to capture an image of a vehicle;a boundary component configured to identify a sub-portion of the image corresponding to an area where a driver of a vehicle is located;a body language component configured to detect a driver's body language; anda prediction component configured to predict future motion of the vehicle based on the driver's body language detected by the body language component.2. The system of claim 1 , wherein the body language component is configured to detect a driver's body language by identifying one or more of a driver's head orientation claim 1 , a gaze direction claim 1 , and a gesture.3. The system of claim 1 , wherein the body language component is configured to process image data in the sub-portion of the image to detect the driver's body language.4. The system of claim 1 , wherein the boundary component is configured to locate the vehicle within the image.5. The system of claim 1 , wherein the boundary component is configured to identify the sub-portion of the image based one or more of:identification of one or more windows; andidentification of a region of the vehicle where a driver would likely be located.6. The system of claim 1 , wherein the prediction component is configured to ...

Подробнее
Номер записи: 28
06-04-2017 дата публикации

Parkbehinderungspositionierungsmittel und -Höhenschätzer

Номер: DE102016118365A1
Автор: NALLAPA VENKATAPATHI RAJU, BANVAIT HARPREETSINGH, MYERS SCOTT VINCENT, MICKS ASHLEY ELIZABETH, Nallapa, Venkatapathi Raju, Banvait, Harpreetsingh, Myers, Scott Vincent, Micks, Ashley Elizabeth
Принадлежит:

Systeme, Verfahren und Vorrichtungen zum Evaluieren, ob ein Fahrzeug ein Hindernis berühren wird, sind offenbart. Die Systeme, Verfahren und Vorrichtungen können eine Hinderniserfassungskomponente, die dazu konfiguriert ist, eine Position und eine Abmessung eines Hindernisses zu bestimmen, eine Fahrzeugerfassungskomponente, die dazu konfiguriert ist, eine Höhe eines Punktes des Fahrzeugs bezüglich des Bodens zu bestimmen, und eine Benachrichtigungskomponente, die dazu konfiguriert ist, einen Hinweis auf ein Vorhandensein des Hindernisses bereitzustellen, um einen menschlichen Fahrer oder ein automatisiertes Fahrsystem beim Parken des Fahrzeugs, ohne das Hindernis zu berühren, zu unterstützen.

Подробнее
Номер записи: 29
22-03-2018 дата публикации

VIRTUELLES STRASSENOBERFLÄCHENERFASSUNGS-TESTUMFELD

Номер: DE102016218196A1
Автор: SAEGER MARTIN, MICKS ASHLEY ELIZABETH, NALLAPA VENKATAPATHI RAJU, BLUE DOUGLAS, Saeger, Martin, Micks, Ashley Elizabeth, Nallapa, Venkatapathi Raju, Blue, Douglas
Принадлежит: FORD GLOBAL TECHNOLOGIES LLC

Verfahren zum Testen des Leistungsverhaltens eines oder mehrerer Anomaliedetektions-Algorithmen. Das Verfahren kann das Erhalten von Sensordaten umfassen, die durch einen das Leistungsverhalten eines Bildsensors modellierenden virtuellen Sensor ausgegeben werden. Die Sensordaten können einer Zeit entsprechen, zu der der virtuelle Sensor eine auf einer virtuellen Straßenoberfläche definierte virtuelle Anomalie abfühlte. Ein oder mehrere Algorithmen können auf die Sensordaten angewendet werden, um zumindest eine erfasste Dimension der virtuellen Anomalie zu erzeugen. Daraufhin kann das Leistungsverhalten des einen oder der mehreren Algorithmen durch Vergleichen der zumindest einen erfassten Dimension mit zumindest einer tatsächlichen Dimension der auf der virtuellen Straßenoberfläche definierten virtuellen Anomalie quantifiziert werden.

Подробнее
Номер записи: 30
29-05-2018 дата публикации

Autonomous driving at intersections based on perception data

Номер: US0009983591B2
Автор: Ashley Elizabeth Micks, Harpreetsingh Banvait, Jinesh J Jain, Brielle Reiff, MICKS ASHLEY ELIZABETH, BANVAIT HARPREETSINGH, JAIN JINESH J, REIFF BRIELLE, Micks, Ashley Elizabeth, Banvait, Harpreetsingh, Jain, Jinesh J, Reiff, Brielle
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC, FORD GLOBAL TECH LLC, Ford Global Technologies, LLC

Systems, methods, and devices for predicting a driver's intention and future movements of a proximal vehicle, whether an automated vehicle or a human driven vehicle, are disclosed herein. A system for predicting future movements of a vehicle includes an intersection component, a camera system, a boundary component, and a prediction component. The intersection component is configured to determine that a parent vehicle is near an intersection. The camera system is configured to capture an image of the proximal vehicle. The boundary component is configured to identify a sub-portion of the image containing a turn signal indicator on the proximal vehicle. The prediction component is configured to predict future movement of the proximal vehicle through the intersection based on a state of the turn signal indicator.

Подробнее
Номер записи: 31
30-03-2017 дата публикации

FAHRTENPROTOKOLL-PARKBEGRENZERWARNUNG

Номер: DE102016117365A1
Автор: NALLAPA VENKATAPATHI RAJU, BANVAIT HARPREETSINGH, MYERS SCOTT VINCENT, MICKS ASHLEY ELIZABETH, Nallapa, Venkatapathi Raju, Banvait, Harpreetsingh, Myers, Scott Vincent, Micks, Ashley Elizabeth
Принадлежит:

Ein Fahrassistenzsystem umfasst ein Fahrdetektionsbauteil, ein Präsenzbauteil und ein Benachrichtigungsbauteil. Das Fahrdetektionsbauteil ist konfiguriert, zu bestimmen, dass ein Fahrzeug oder Fahrer aus einer Parkposition ausfährt oder sich auf die Ausfahrt vorbereitet. Das Präsenzbauteil ist konfiguriert, anhand einer Fahrtenprotokolldatenbank zu bestimmen, ob ein Parkbegrenzer vor oder hinter der Parkposition vorhanden ist. Das Benachrichtigungsbauteil ist konfiguriert, einem Fahrzeugführer oder einem Selbstfahrsystem des Fahrzeugs eine Angabe bereitzustellen, dass der Parkbegrenzer vorhanden ist.

Подробнее
Номер записи: 32
11-05-2017 дата публикации

Autonomes Fahren an Kreuzungen basierend auf Wahrnehmungsdaten

Номер: DE102016120508A1
Автор: MICKS ASHLEY ELIZABETH, BANVAIT HARPREETSINGH, JAIN JINESH J, REIFF BRIELLE, Micks, Ashley Elizabeth, Banvait, Harpreetsingh, Jain, Jinesh J., Reiff, Brielle
Принадлежит:

Hier werden Systeme, Verfahren und Vorrichtungen zum Vorhersagen der Absicht eines Fahrers und der künftigen Bewegungen eines proximalen Fahrzeugs, entweder eines automatisierten Fahrzeugs oder eines von einem Menschen gefahrenen Fahrzeugs, offenbart. Ein System zum Vorhersagen der künftigen Bewegungen eines Fahrzeugs enthält eine Kreuzungskomponente, ein Kamerasystem, eine Begrenzungskomponente und eine Vorhersagekomponente. Die Kreuzungskomponente ist konfiguriert, zu bestimmen, dass sich ein Stammfahrzeug in der Nähe einer Kreuzung befindet. Das Kamerasystem ist konfiguriert, ein Bild des proximalen Fahrzeugs aufzunehmen. Die Begrenzungskomponente ist konfiguriert, einen Unterabschnitt des Bildes, der einen Fahrtrichtungsanzeiger des proximalen Fahrzeugs enthält, zu identifizieren. Die Vorhersagekomponente ist konfiguriert, die künftige Bewegung des proximalen Fahrzeugs durch die Kreuzung basierend auf einem Zustand des Fahrtrichtungsanzeigers vorherzusagen.

Подробнее
Номер записи: 33
28-11-2019 дата публикации

Predicting Vehicle Movements Based on Driver Body Language

Номер: US2019362168A1
Автор: MICKS ASHLEY ELIZABETH, BANVAIT HARPREETSINGH, JAIN JINESH J, REIFF BRIELLE, Micks, Ashley Elizabeth, Banvait, Harpreetsingh, Jain, Jinesh J., Reiff, Brielle
Принадлежит:

Systems, methods, and devices for predicting driver intent and future movements of a human driven vehicles are disclosed herein. A computer implemented method includes receiving an image of a proximal vehicle in a region near a vehicle. The method includes determining a region of the image that contains a driver of the proximal vehicle, wherein determining the region comprises determining based on a location of one or more windows of the proximal vehicle. The method includes processing image data only in the region of the image that contains the driver of the proximal vehicle to detect a driver's body language.

Подробнее
Номер записи: 34
29-07-2021 дата публикации

TRAINIEREN EINES NEURONALEN NETZWERKS EINES FAHRZEUGS

Номер: DE102021101270A1
Автор: CHAKRAVARTY PUNARJAY, MICKS ASHLEY ELIZABETH, Chakravarty, Punarjay, Micks, Ashley Elizabeth
Принадлежит:

Diese Offenbarung stellt Trainieren eines neuronalen Netzwerks eines Fahrzeugs bereit. Ein Computer, einschließlich eines Prozessors und eines Speichers, wobei der Speicher Anweisungen beinhaltet, die durch den Prozessor zu Folgendem ausgeführt werden sollen: Bestimmen von Daten von sechs Freiheitsgraden (DoF) für ein erstes Objekt in einem ersten Videobild, und Erzeugen eines synthetischen Videobilds, das dem ersten Videobild entspricht, das ein synthetisches Objekt und eine synthetische Objektkennung auf Grundlage der sechs DoF-Daten beinhaltet. Die Anweisungen können ferner Anweisungen zum Trainieren eines Generative Adversarial Network (GAN) auf Grundlage von einem gepaarten ersten Videobild und einem synthetischen Videobild dazu, ein modifiziertes synthetisches Bild zu erzeugen und Trainieren eines tiefen neuronales Netzwerks dazu beinhalten, das synthetische Objekt in dem modifizierten synthetischen Videobild auf Grundlage des synthetischen Objekts zu lokalisieren. Die Anweisungen ...

Подробнее
Номер записи: 35
12-10-2017 дата публикации

VISION-BASED RAIN DETECTION USING DEEP LEARNING

Номер: US20170293808A1
Автор: Jinesh J. Jain, Harpreetsingh Banvait, Ashley Elizabeth Micks, Vidya Nariyambut Murali, JAIN JINESH J, BANVAIT HARPREETSINGH, MICKS ASHLEY ELIZABETH, NARIYAMBUT MURALI VIDYA, Jain Jinesh J., Banvait Harpreetsingh, Micks Ashley Elizabeth, Nariyambut Murali Vidya
Принадлежит:

A method is disclosed for using a camera on-board a vehicle to determine whether precipitation is failing near the vehicle. The method may include obtaining multiple images. Each of the multiple images may be known to photographically depict a “rain” or a “no rain” condition. An artificial neural network may be trained on the multiple images. Later, the artificial neural network may analyze one or more images captured by a first camera secured to a first vehicle. Based on that analysis, the artificial neural network may classify the first vehicle as being in “rain” or “no rain” weather. 1. A method comprising:obtaining multiple images, each known to photographically depict a “rain” or a “no rain” condition;training, by an artificial neural network, on the multiple images;analyzing, by the artificial neural network after the training, one or more images captured by a first camera; andclassifying, by the artificial neural network based on the analyzing, the first camera as being in “rain” or “no rain” weather.2. The method of claim 1 , wherein the multiple images are captured by one or more cameras on-board one or more vehicles.3. The method of claim 1 , wherein the first camera is on-board a first vehicle.4. The method of claim 3 , wherein the analyzing occurs on-board the first vehicle.5. The method of claim 4 , wherein the classifying occurs on-board the first vehicle.6. The method of claim 3 , wherein the training occurs off-board the first vehicle.7. The method of claim 3 , wherein the training occurs while the artificial neural network is running on off-board computer hardware located remotely with respect to the first vehicle.8. The method of claim 3 , wherein the analyzing and the classifying occurs while the artificial neural network is running on on-board computer hardware carried on-board the first vehicle.9. The method of claim 1 , wherein the first camera is secured to a first vehicle and oriented so as to be forward facing.10. The method of claim 1 , ...

Подробнее
Номер записи: 36
25-01-2018 дата публикации

Verwenden von virtuellen Daten zum Testen und Trainieren von Parkplatzerfassungssystemen

Номер: DE102017116192A1
Автор: MICKS ASHLEY ELIZABETH, JAIN JINESH J, NARIYAMBUT MURALI VIDYA, BANVAIT HARPREETSINGH, KADETOTAD SNEHA, JOH PETER GYUMYEONG, Micks, Ashley Elizabeth, Jain, Jinesh J., Nariyambut Murali, Vidya, Banvait, Harpreetsingh, Kadetotad, Sneha, Joh, Peter Gyumyeong
Принадлежит:

Die vorliegende Erfindung erstreckt sich auf Verfahren, Systeme und Computerprogrammprodukte zum Verwenden von virtuellen Daten zum Testen und Trainieren von Parkplatzerfassungssystemen. Aspekte der Erfindung integrieren eine virtuelle Fahrumgebung mit Sensormodellen (z. B. von einem Radarsystem), um virtuelle Radardaten in relativ großen Mengen in einer relativen kurzen Zeitspanne bereitzustellen. Die Sensormodelle erfassen Werte für relevante Parameter eines Trainingsdatensatzes. Relevante Parameter können in den aufgezeichneten Daten randomisiert werden, um einen diversen Trainingsdatensatz mit minimalem Bias zu gewährleisten. Da die Fahrumgebung virtualisiert ist, kann der Trainingsdatensatz zusammen mit Ground-Truth-Daten generiert werden. Die Ground-Truth-Daten werden dazu verwendet, die tatsächlichen Positionen, die zum Trainieren eines Parkplatzklassifikationsalgorithmus zum Erfassen der Begrenzungen des freien Platzes verwendet werden, zu annotieren.

Подробнее
Номер записи: 37
19-07-2018 дата публикации

GENERIERTEN VON SIMULIERTEN SENSORDATEN ZUM TRAINIEREN UND ÜBERPRÜFEN VON ERKENNUNGSMODELLEN

Номер: DE102018100469A1
Автор: MICKS ASHLEY ELIZABETH, KADETOTAD SNEHA, JAIN JINESH J, LIU DONGRAN, GERARDO CASTRO MARCOS PAUL, NARIYAMBUT MURALI VIDYA, Micks, Ashley Elizabeth, Kadetotad, Sneha, Jain, Jinesh J., Liu, Dongran, Gerardo Castro, Marcos Paul, Nariyambut Murali, Vidya
Принадлежит:

Es wird ein Szenario definiert, das Modelle von Fahrzeugen und eine typische Fahrumgebung beinhaltet. Ein Modell eines Prüffahrzeugs wird zum Szenario hinzugefügt und Sensorstellen werden auf dem Prüffahrzeug definiert. Die Wahrnehmung des Szenarios durch Sensoren an den Sensorstellen wird simuliert, um simulierte Sensorausgaben zu erhalten. Die simulierten Sensorausgaben werden annotiert, um die Stelle von Hindernissen im Szenario anzugeben. Die annotierten Sensorausgaben können dann verwendet werden, um ein statistisches Modell zu überprüfen oder ein maschinelles Lernmodell zu trainieren. Die simulierten Sensorausgaben können mit ausreichender Genauigkeit modelliert werden, um Sensorrauschen zu beinhalten, oder können künstlich hinzugefügtes Rauschen beinhalten, um realistische Bedingungen zu simulieren.

Подробнее
Номер записи: 38
18-01-2018 дата публикации

VIRTUELLES SENSORDATENERZEUGUNGSSYSTEM UND VERFAHREN ZUM UNTERSTÜTZEN DER ENTWICKLUNG VON SICHTBASIERTEN REGENDETEKTIONSALGORITHMEN

Номер: DE102017115393A1
Автор: MICKS ASHLEY ELIZABETH, BANVAIT HARPREETSINGH, JAIN JINESH J, NARIYAMBUT MURALI VIDYA, Micks, Ashley Elizabeth, Banvait, Harpreetsingh, Jain, Jinesh J., Nariyambut Murali, Vidya
Принадлежит: FORD GLOBAL TECHNOLOGIES LLC

Es wird ein Verfahren zum Erzeugen von Trainingsdaten offenbart. Das Verfahren kann ein Ausführen eines Simulationsprozesses einschließen. Der Simulationsprozess kann das Durchfahren einer virtuellen Kamera durch eine virtuelle Fahrumgebung einschließen, umfassend mindestens eine virtuelle Niederschlagsbedingung und mindestens eine virtuelle Nicht-Niederschlagsbedingung. Während des Durchfahrens kann die virtuelle Kamera in Bezug auf die virtuelle Fahrumgebung, wie durch ein Fahrzeugbewegungsmodell vorgegeben, das Bewegung von einem Fahrzeug modelliert, das durch die virtuelle Fahrumgebung fährt, während es die virtuelle Kamera trägt, bewegt werden. Virtuelle Sensordaten, welche die virtuelle Fahrumgebung sowohl bei virtuellen Niederschlags- als auch virtuellen Nicht-Niederschlagsbedingungen charakterisieren, können aufgezeichnet werden. Die virtuellen Sensordaten können dem entsprechen, was ein realer Sensor ausgegeben hätte, wenn er die virtuelle Fahrumgebung in der realen Welt erfasst hätte.

Подробнее
Номер записи: 39
21-07-2016 дата публикации

Virtueller autonomer Antwortprüfstand

Номер: DE102016100492A1
Автор: ALANIZ ARTHUR, MICKS ASHLEY ELIZABETH, NARIYAMBUT MURALI VIDYA, KADETOTAD SNEHA, BANVAIT HARPREETSINGH, JAIN JINESH J, Alaniz, Arthur, Micks, Ashley Elizabeth, Nariyambut murali, Vidya, Kadetotad, Sneha, Banvait, Harpreetsingh, Jain, Jinesh J.
Принадлежит:

Eine Computervorrichtung beinhaltet eine Prozessorschaltung und ein Datenspeichermedium und ist programmiert zum Empfangen einer Benutzereingabe, die eine Fahrzeugsteueraktion darstellt, die mit Betrieb eines virtuellen Fahrzeugs in einer virtuellen Umwelt assoziiert ist, zum virtuellen Fahren des virtuellen Fahrzeugs durch die virtuelle Umwelt gemäß der Fahrzeugsteueraktion, zum Sammeln von Daten virtueller Sensoren und zum Verarbeiten der gesammelten Daten virtueller Sensoren.

Подробнее
Номер записи: 40
22-06-2017 дата публикации

FAHRZEUGBLINKSIGNALDETEKTION

Номер: DE102016123878A1
Автор: MICKS ASHLEY ELIZABETH, BANVAIT HARPREETSINGH, JAIN JINESH J, REIFF BRIELLE, KADETOTAD SNEHA, Micks, Ashley Elizabeth, Banvait, Harpreetsingh, Jain, Jinesh J., Reiff, Brielle, Kadetotad, Sneha
Принадлежит:

Systeme, Verfahren und Vorrichtungen zum Detektieren des Blinksignalstatus eines Fahrzeugs zum Vermeiden einer Kollision während Spurwechselmanövern oder anderweitig. Ein Verfahren umfasst das Detektieren am ersten Fahrzeug eines Vorhandenseins eines zweiten Fahrzeugs in einer benachbarten Spur. Das Verfahren umfasst das Identifizieren eines Ausschnitts, der eine Blinksignalanzeige des zweiten Fahrzeugs enthält, in einem Bild des zweiten Fahrzeugs. Das Verfahren umfasst das Verarbeiten des Ausschnitts des Bildes, um einen Zustand der Blinksignalanzeige zu bestimmen. Das Verfahren umfasst auf der Basis des Zustands der Blinksignalanzeige auch das Benachrichtigen eines Fahrers oder Durchführen eines Fahrmanövers am ersten Fahrzeug.

Подробнее
Номер записи: 41
27-07-2017 дата публикации

Trainingsalgorithmus zur Kollisionsvermeidung

Номер: DE102017101106A1
Автор: MICKS ASHLEY ELIZABETH, JAIN JINESH J, BANVAIT HARPREETSINGH, HAN KYO JEONG, Micks, Ashley Elizabeth, Jain, Jinesh J., Banvait, Harpreetsingh, Han, Kyo Jeong
Принадлежит:

Ein Maschinenlernmodell wird durch Definieren eines Szenarios trainiert, das Modelle von Fahrzeugen und einer typischen Fahrumgebung umfasst. Zu dem Szenario wird ein Modell eines betreffenden Fahrzeugs hinzugefügt und es werden Sensororte an dem betreffenden Fahrzeug definiert. Es wird eine Wahrnehmung des Szenarios durch Sensoren an den Sensororten simuliert. Das Szenario umfasst ferner ein Modell eines lane-splitting ausführenden Fahrzeugs. Der Ort des lane-splitting ausführenden Fahrzeugs und die simulierten Ausgaben der das Szenario wahrnehmenden Sensoren werden in einen Maschinenlernalgorithmus eingegeben, der ein Modell trainiert, den Ort eines lane-splitting ausführenden Fahrzeugs auf der Basis der Sensorausgaben zu erfassen. Eine Fahrzeugsteuerung enthält dann das Maschinenlernmodell und schätzt die Anwesenheit und/oder den Ort eines lane-splitting ausführenden Fahrzeugs auf der Basis tatsächlicher Sensorausgaben, die in das Maschinenlernmodell eingegeben werden.

Подробнее
Номер записи: 42
09-01-2018 дата публикации

Predicting vehicle movements based on driver body language

Номер: US0009864918B2
Автор: Ashley Elizabeth Micks, Harpreetsingh Banvait, Jinesh J Jain, Brielle Reiff, MICKS ASHLEY ELIZABETH, BANVAIT HARPREETSINGH, JAIN JINESH J, REIFF BRIELLE, Micks Ashley Elizabeth, Banvait Harpreetsingh, Jain Jinesh J, Reiff Brielle
Принадлежит: Ford Global Technologies, LLC, FORD GLOBAL TECH LLC

Systems, methods, and devices for predicting driver intent and future movements of a human driven vehicles are disclosed herein. A system for predicting future movements of a vehicle includes a camera system, a boundary component, a body language component, and a prediction component. The camera system is configured to capture an image of a vehicle. The boundary component is configured to identify a sub-portion of the image corresponding to an area where a driver of a vehicle is located. The body language component configured to detect a driver's body language. The prediction component configured to predict future motion of the vehicle based on the driver's body language detected by the body language component.

Подробнее
Номер записи: 43
21-08-2018 дата публикации

Training algorithm for collision avoidance using auditory data

Номер: US0010055675B2
Автор: Ashley Elizabeth Micks, Jinesh J Jain, Kyu Jeong Han, Harpreetsingh Banvait, MICKS ASHLEY ELIZABETH, JAIN JINESH J, HAN KYU JEONG, BANVAIT HARPREETSINGH, Micks, Ashley Elizabeth, Jain, Jinesh J, Han, Kyu Jeong, Banvait, Harpreetsingh
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC, FORD GLOBAL TECH LLC, Ford Global Technologies, LLC

A machine learning model is trained by defining a scenario including models of vehicles and a typical driving environment. A model of a subject vehicle is added to the scenario and sensor locations are defined on the subject vehicle. A perception of the scenario by sensors at the sensor locations is simulated. The scenario further includes a model of a parked vehicle with its engine running. The location of the parked vehicle and the simulated outputs of the sensors perceiving the scenario are input to a machine learning algorithm that trains a model to detect the location of the parked vehicle based on the sensor outputs. A vehicle controller then incorporates the machine learning model and estimates the presence and/or location of a parked vehicle with its engine running based on actual sensor outputs input to the machine learning model.

Подробнее
Номер записи: 44
11-01-2018 дата публикации

FUSSGÄNGERERKENNUNG BEIM RÜCKWÄRTSFAHREN EINES FAHRZEUGS

Номер: DE102017115011A1
Автор: MYERS SCOTT VINCENT, GURGHIAN ALEXANDRU MIHAI, MICKS ASHLEY ELIZABETH, KARANDIKAR RAMCHANDRA GANESH, Myers, Scott Vincent, Gurghian, Alexandru Mihai, Micks, Ashley Elizabeth, Karandikar, Ramchandra Ganesh
Принадлежит: FORD GLOBAL TECHNOLOGIES LLC

Techniken und Umsetzungen in Bezug auf die Detektion von sich bewegenden Objekten, wie Fußgängern, wenn sich ein Fahrzeug in einer Rückwärtsrichtung bewegt, werden beschrieben. Ein Verfahren kann Identifizieren eines Interessenbereichs beinhalten, wenn sich ein Fahrzeug in einer Rückwärtsrichtung bewegt. Das Verfahren kann Detektieren eines sich bewegenden Objekts im Interessenbereich beinhalten. Das Verfahren kann ebenfalls Bestimmen, ob eine Kollision mit dem sich bewegenden Objekt durch das Fahrzeug, das sich in der Rückwärtsrichtung bewegt, wahrscheinlich ist, beinhalten. Das Verfahren kann ferner Bereitstellen eines von einem Menschen wahrnehmbaren Signals als Reaktion auf eine Bestimmung, dass die Kollision wahrscheinlich ist, beinhalten.

Подробнее
Номер записи: 45
16-03-2017 дата публикации

Fahrzeugradarwahrnehmung und -lokalisierung

Номер: DE102016117123A1
Автор: MICKS ASHLEY ELIZABETH, NALLAPA VENKATAPATHI RAJU, NARIYAMBUT MURALI VIDYA, MYERS SCOTT VINCENT, Micks, Ashley Elizabeth, Nallapa, Venkatapathi Raju, Nariyambut Murali, Vidya, Myers, Scott Vincent
Принадлежит: FORD GLOBAL TECHNOLOGIES LLC

Diese Offenbarung bezieht sich auf Verfahren, Systeme und Einrichtungen für autonom fahrende Fahrzeuge oder Fahrassistenzsysteme und bezieht sich insbesondere auf die Fahrzeugradarwahrnehmung und -lokalisierung. Das offenbarte Fahrzeugfahrsystem kann Speichermedien, ein Radarsystem, eine Standortkomponente und eine Fahrsteuerung umfassen. Die Speichermedien speichern eine Karte von Fahrbahnen. Das Radarsystem ist dazu ausgelegt, Wahrnehmungsinformationen aus einer Region in der Nähe eines Fahrzeugs zu erzeugen. Die Standortkomponente ist dazu ausgelegt, auf der Basis der Radarwahrnehmungsinformationen und anderer navigationsbezogener Daten einen Standort des Fahrzeugs zu bestimmen. Die Fahrsteuerung ist dazu ausgelegt, das Fahren des Fahrzeugs auf der Basis der Karte und des bestimmten Standorts zu steuern. This disclosure relates to methods, systems and devices for autonomous vehicles or driver assistance systems, and more particularly relates to vehicle radar sensing and localization. The disclosed vehicle driving system may include storage media, a radar system, a location component, and a ride control. The storage media store a map of lanes. The radar system is configured to generate perceptual information from a region near a vehicle. The location component is configured to determine a location of the vehicle based on the radar awareness information and other navigation-related data. The travel controller is configured to control the driving of the vehicle based on the map and the particular location.

Подробнее
Номер записи: 46
12-03-2019 дата публикации

Sensor-data generation in virtual driving environment

Номер: US10229231B2
Автор: NALLAPA VENKATAPATHI RAJU, SAEGER MARTIN, MICKS ASHLEY ELIZABETH, BLUE DOUGLAS, Nallapa, Venkatapathi Raju, Saeger, Martin, Micks, Ashley Elizabeth, Blue, Douglas
Принадлежит: FORD GLOBAL TECH LLC, Ford Global Technologies, LLC

A method for generating training data. The method may include executing a simulation process. The simulation process may include traversing one or more virtual sensors over a virtual road surface defining a plurality of virtual anomalies that are each sensible by the one or more virtual sensors. During the traversing, each of the one or more virtual sensors may be moved with respect to the virtual road surface as dictated by a vehicle-motion model modeling motion of a vehicle driving on the virtual road surface while carrying the one or more virtual sensors. Virtual sensor data characterizing the virtual road surface may be recorded. The virtual sensor data may correspond to what a real sensor would have output had it sensed the road surface in the real world.

Подробнее
Номер записи: 47
27-06-2019 дата публикации

EIN SYSTEM UND VERFAHREN ZUM IDENTIFIZIEREN VON UNBELEGTEN PARKPOSITIONEN

Номер: DE112016007237T5
Автор: BANVAIT HARPREETSINGH, MICKS ASHLEY ELIZABETH, JAIN JINESH J, MYERS SCOTT VINCENT, Banvait, Harpreetsingh, Micks, Ashley Elizabeth, Jain, Jinesh J., Myers, Scott Vincent
Принадлежит: FORD MOTOR CO, Ford Motor Company

Diese Offenbarung stellt ein System und Verfahren zum Identifizieren von unbelegten Parkpositionen bereit. Ein Fahrzeug beinhaltet ein oder mehrere seitlich montierte Mikrofone und eine Steuerung, die dazu programmiert ist, eine Signatur einer unbelegten zu dem Fahrzeug benachbarten Position in Ausgaben der Mikrofone zu detektieren. Die Signatur kann unter Verwendung eines Algorithmus für maschinelles Lernen identifiziert werden. Als Reaktion darauf, dass eine unbelegte Position detektiert wird, kann die Steuerung autonomes Parken aufrufen, den Standort der unbelegten Position zur späteren Verwendung speichern und/oder die unbelegte Position einem Server melden, der dann andere Fahrzeuge über den verfügbaren Parkplatz informiert. Die unbelegte Position kann dadurch verifiziert werden, dass ausgewertet wird, ob Kartendaten zulässiges Parken an diesem Standort angeben. Die unbelegte Position kann zudem mit einem oder mehreren anderen Sensoren bestätigt werden, wie etwa einer Kamera, LIDAR ...

Подробнее
Номер записи: 48
21-07-2016 дата публикации

In virtuellen Umgebungen verfeinertes autonomes Fahren

Номер: DE102016100428A1
Автор: ALANIZ ARTHUR, BANVAIT HARPREETSINGH, NARIYAMBUT MURALI VIDYA, MICKS ASHLEY ELIZABETH, Alaniz, Arthur, Banvait, Harpreetsingh, Nariyambut murali, Vidya, Micks, Ashley Elizabeth
Принадлежит:

Ein Computervorrichtung beinhaltet eine Prozessorschaltung und ein Datenspeichermedium. Die Computersystem ist programmiert zum Empfangen einer Benutzereingabe, die mindestens einen Testparameter auswählt, der mit autonomem Betrieb eines virtuellen Fahrzeugs in einer virtuellen Umwelt assoziiert ist, zum Simulieren der virtuellen Umwelt, die den mindestens einen Testparameter umfasst, zum virtuellen Fahren des virtuellen Fahrzeugs durch die virtuelle Umwelt, zum Sammeln von Daten virtueller Sensoren und zum Verarbeiten der gesammelten Daten virtueller Sensoren.

Подробнее
Номер записи: 49
12-10-2017 дата публикации

Virtual Sensor Data Generation For Wheel Stop Detection

Номер: US20170293816A1
Автор: Ashley Elizabeth Micks, Venkatapathi Raju Nallapa, Harpreetsingh Banvait, Scott Vincent Myers, MICKS ASHLEY ELIZABETH, NALLAPA VENKATAPATHI RAJU, BANVAIT HARPREETSINGH, MYERS SCOTT VINCENT, Micks Ashley Elizabeth, Nallapa Venkatapathi Raju, Banvait Harpreetsingh, Myers Scott Vincent
Принадлежит:

The disclosure relates to methods, systems, and apparatuses for virtual sensor data generation and more particularly relates to generation of virtual sensor data for training and testing models or algorithms to detect objects or obstacles. A method for generating virtual sensor data includes simulating, using one or more processors, a three-dimensional (3D) environment comprising one or more virtual objects. The method includes generating, using one or more processors, virtual sensor data for a plurality of positions of one or more sensors within the 3D environment. The method includes determining, using one or more processors, virtual ground truth corresponding to each of the plurality of positions, wherein the ground truth comprises a dimension or parameter of the one or more virtual objects. The method includes storing and associating the virtual sensor data and the virtual ground truth using one or more processors. 1. A method comprising:simulating, using one or more processors, a three-dimensional (3D) environment comprising one or more virtual objects;generating, using one or more processors, virtual sensor data for a plurality of positions of one or more sensors within the 3D environment;determining, using one or more processors, virtual ground truth corresponding to each of the plurality of positions, wherein the ground truth comprises a dimension or parameter of the one or more virtual objects; andstoring and associating the virtual sensor data and the virtual ground truth using one or more processors.2. The method of claim 1 , further comprising providing one or more of the virtual sensor data and the virtual ground truth for training or testing of a machine learning algorithm or model.3. The method of claim 2 , wherein the machine learning model or algorithm comprises a neural network.4. The method of claim 2 , wherein training the machine learning algorithm or model comprises providing at least a portion of the virtual sensor data and corresponding ...

Подробнее
Номер записи: 50
01-03-2018 дата публикации

FAHRSPURERKENNUNG MIT RÜCKFAHRKAMERA

Номер: DE102017116213A1
Автор: MYERS SCOTT VINCENT, GURGHIAN ALEXANDRU MIHAI, MICKS ASHLEY ELIZABETH, WALSH ALEXANDRO, Myers, Scott Vincent, Gurghian, Alexandru Mihai, Micks, Ashley Elizabeth, Walsh, Alexandro
Принадлежит: FORD GLOBAL TECHNOLOGIES LLC

Ein Verfahren zum Bestimmen von Fahrspurinformationen beinhaltet Empfangen von Wahrnehmungsdaten von mindestens zwei Sensoren, wobei die mindestens zwei Sensoren eine nach hinten weisende Kamera eines Fahrzeugs beinhalten. Das Verfahren beinhaltet Bestimmen einer Anzahl von Fahrspuren auf einer Fahrbahn innerhalb eines Sichtfelds, das von den Wahrnehmungsdaten eingefangen wird, auf Grundlage der Wahrnehmungsdaten unter Verwendung eines neuronalen Netzes. Das Verfahren beinhaltet Bereitstellen einer Angabe der Anzahl von Fahrspuren für ein automatisiertes Fahrsystem oder Fahrassistenzsystem. A method for determining lane information includes receiving perceptual data from at least two sensors, wherein the at least two sensors include a rear-facing camera of a vehicle. The method includes determining a number of lanes on a lane within a field of view captured by the perceptual data based on the perceptual data using a neural network. The method includes providing an indication of the number of lanes for an automated driving system or driver assistance system.

Подробнее
Номер записи: 51
30-03-2017 дата публикации

Drive History Parking Barrier Alert

Номер: US20170088052A1
Автор: Venkatapathi Raju Nallapa, Harpreetsingh Banvait, Scott Vincent Myers, Ashley Elizabeth Micks, NALLAPA VENKATAPATHI RAJU, BANVAIT HARPREETSINGH, MYERS SCOTT VINCENT, MICKS ASHLEY ELIZABETH, Nallapa Venkatapathi Raju, Banvait Harpreetsingh, Myers Scott Vincent, Micks Ashley Elizabeth
Принадлежит:

A driving assistance system includes a drive detection component, a presence component, and a notification component. The drive detection component is configured to determine that a vehicle or driver is exiting or preparing to exit a parking location. The presence component is configured to determine, from a drive history database, whether a parking barrier is present in front of or behind the parking location. The notification component is configured to provide an indication that the parking barrier is present to a human driver or an automated driving system of the vehicle. 1. A system comprising:a drive detection component configured to determine that a vehicle or driver is exiting or preparing to exit a parking location;a presence component configured to determine, from a drive history database, whether a parking barrier is present at the parking location, wherein the presence component determines whether the parking barrier is present in response to determining that the vehicle or driver is exiting or preparing to exit the parking location; anda notification component configured to provide an indication that the parking barrier is present to a human driver or an automated driving system of the vehicle.2. The system of claim 1 , wherein the presence component is configured to determine whether the parking barrier is present in response to determining that the vehicle is currently parked at the parking location.3. The system of claim 1 , wherein the notification component is configured to provide one or more of a visual indication and an audio indication of the presence of the parking barrier to a human driver.4. The system of claim 1 , wherein the notification component is configured to provide the indication by sending a message to the automated driving system.5. The system of claim 1 , wherein the notification component is further configured to provide an indication of a location of the parking barrier.6. The system of claim 1 , wherein the drive detection ...

Подробнее
Номер записи: 52
21-07-2016 дата публикации

AUTONOMOUS DRIVING REFINED IN VIRTUAL ENVIRONMENTS

Номер: US20160210382A1
Автор: Arthur Alaniz, Harpreetsingh Banvait, Ashley Elizabeth Micks, Vidya Nariyambut murali, ALANIZ ARTHUR, BANVAIT HARPREETSINGH, MICKS ASHLEY ELIZABETH, NARIYAMBUT MURALI VIDYA
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC

A computing device includes a processing circuit and a data storage medium. The computing device is programmed to receive a user input selecting at least one testing parameter associated with autonomously operating a virtual vehicle in a virtual environment, simulate the virtual environment incorporating the at least one testing parameter, virtually navigate the virtual vehicle through the virtual environment, collect virtual sensor data, and processing the collected virtual sensor data. 1. A computing device comprising a processing circuit and a data storage medium , wherein the computing device is programmed to:receive a user input selecting at least one testing parameter associated with autonomously operating a virtual vehicle in a virtual environment;simulate the virtual environment incorporating the at least one testing parameter;virtually navigate the virtual vehicle through the virtual environment;collect virtual sensor data; andprocess the virtual sensor data collected.2. The computing device of claim 1 , wherein the computing device is programmed to generate the virtual sensor data based at least in part on the virtual navigation of the virtual vehicle through the virtual environment.3. The computing device of claim 1 , wherein the computing device is programmed to generate calibration data from the virtual sensor data and wherein the calibration data is uploaded to an autonomous vehicle.4. The computing device of claim 1 , wherein the computing device is programmed to virtually navigate the virtual vehicle through the virtual environment based at least in part on virtual sensors incorporated into the virtual vehicle.5. The computing device of claim 4 , wherein the virtual sensors are based at least in part on autonomous driving sensors incorporated into an autonomous vehicle.6. The computing device of claim 1 , wherein the computing device is programmed to generate the virtual environment based at least in part on the user input.7. The computing device of ...

Подробнее
Номер записи: 53
24-05-2018 дата публикации

SINKLOCHERFASSUNGSSYSTEME UND -VERFAHREN

Номер: DE102017127333A1
Автор: MYERS SCOTT VINCENT, MICKS ASHLEY ELIZABETH, GURGHIAN ALEXANDRU MIHAI, BANVAIT HARPREETSINGH, MAHMOUDIEH PARSA, Myers, Scott Vincent, Micks, Ashley Elizabeth, Gurghian, Alexandru Mihai, Banvait, Harpreetsingh, Mahmoudieh, Parsa
Принадлежит:

Es werden Beispiele für Sinklocherfassungssysteme und -verfahren beschrieben. In einer Ausführungsform empfängt ein Verfahren Daten von mehreren Sensoren, die an einem Fahrzeug angebracht sind, und analysiert die empfangenen Daten, um ein Sinkloch auf einer Fahrbahn vor dem Fahrzeug zu identifizieren. Wenn ein Sinkloch identifiziert wurde, passt das Verfahren Fahrzeugvorgänge an und meldet das Sinkloch einer geteilten Datenbank und/oder einem anderen Fahrzeug.

Подробнее
Номер записи: 54
20-04-2017 дата публикации

Prüfstand zur Fahrspurgrenzenerfassung in virtueller Fahrumgebung

Номер: DE102016119129A1
Автор: MICKS ASHLEY ELIZABETH, NALLAPA VENKATAPATHI RAJU, REIFF BRIELLE, NARIYAMBUT MURALI VIDYA, KADETOTAD SNEHA, Micks, Ashley Elizabeth, Nallapa, Venkatapathi Raju, Reiff, Brielle, Nariyambut Murali, Vidya, Kadetotad, Sneha
Принадлежит:

Verfahren und Gerät in Zusammenhang mit einem Prüfstand für Fahrspurgrenzenerfassung in einer virtuellen Fahrumgebung werden bereitgestellt. Ein Verfahren kann involvieren, dass durch ein Prozessor eine virtuelle Fahrumgebung erzeugt wird, die eine oder mehrere Fahrspuren, ein virtuelles Fahrzeug und einen oder mehrere virtuelle Sensoren, die auf dem virtuellen Fahrzeug installiert sind, die konfiguriert sind, um simulierte Daten zu erzeugen, während das virtuelle Fahrzeug innerhalb der virtuellen Umgebung durchquert, umfasst. Das Verfahren kann auch das Ausführen eines Algorithmus zum Verarbeiten der simulierten Daten involvieren, um die eine oder mehreren Fahrspuren zu erfassen. Das Verfahren kann ferner das Aufzeichnen einer Ausgabe des Algorithmus involvieren. Das Verfahren kann zusätzlich das Kommentieren der simulierten Daten mit der Ausgabe des Algorithmus involvieren.

Подробнее
Номер записи: 55
28-09-2017 дата публикации

METHOD AND SYSTEM FOR VIRTUAL SENSOR DATA GENERATION WITH DEPTH GROUND TRUTH ANNOTATION

Номер: US20170278303A1
Автор: Alexander Groh, Ashley Elizabeth Micks, Vidya Nariyambut Murali, GROH ALEXANDER, MICKS ASHLEY ELIZABETH, NARIYAMBUT MURALI VIDYA, Groh Alexander, Micks Ashley Elizabeth, Nariyambut Murali Vidya
Принадлежит:

Methods and systems for generating virtual sensor data for developing or testing computer vision detection algorithms are described. A system and a method may involve generating a virtual environment. The system and the method may also involve positioning a virtual sensor at a first location in the virtual environment. The system and the method may also involve recording data characterizing the virtual environment, the data corresponding to information generated by the virtual sensor sensing the virtual environment. The system and the method may further involves annotating the data with a depth map characterizing a spatial relationship between the virtual sensor and the virtual environment. 1. A method , comprising:generating, by a processor, a virtual environment;positioning, by the processor, a virtual sensor at a first location in the virtual environment;recording, by the processor, simulation-generated data characterizing the virtual environment, the data corresponding to information generated by the virtual sensor sensing the virtual environment; andannotating, by the processor, the data with a depth map characterizing a spatial relationship between the virtual sensor and the virtual environment.2. The method of claim 1 , further comprising:moving, by the processor, the virtual sensor from the first location to a second location in the virtual environment such that the virtual sensor is configured to sense the virtual environment from the second location, along a path between the first location and the second location, or both.3. The method of claim 1 , wherein the virtual environment comprises a plurality of virtual objects distributed therewithin claim 1 , each of the virtual objects either stationary or mobile relative to the virtual sensor claim 1 , and each of the virtual objects sensible by the virtual sensor.4. The method of claim 3 , wherein the spatial relationship comprises distance information of one or more of the plurality of virtual objects with ...

Подробнее
Номер записи: 56
20-04-2017 дата публикации

TESTBED FOR LANE BOUNDARY DETECTION IN VIRTUAL DRIVING ENVIRONMENT

Номер: US20170109458A1
Автор: Ashley Elizabeth Micks, Venkatapathi Raju Nallapa, Brielle Reiff, Vidya Nariyambut Murali, Sneha Kadetotad, MICKS ASHLEY ELIZABETH, NALLAPA VENKATAPATHI RAJU, REIFF BRIELLE, NARIYAMBUT MURALI VIDYA, KADETOTAD SNEHA, Micks Ashley Elizabeth, Nallapa Venkatapathi Raju, Reiff Brielle, Nariyambut Murali Vidya, Kadetotad Sneha
Принадлежит:

Methods and apparatus pertaining to a testbed for lane boundary detection in a virtual driving environment are provided. A method may involve generating, by a processor, a virtual driving environment comprising one or more driving lanes, a virtual vehicle, and one or more virtual sensors mounted on the virtual vehicle configured to generate simulated data as the virtual vehicle traverses within the virtual environment. The method may also involve executing an algorithm to process the simulated data to detect the one or more driving lanes. The method may further involve recording an output of the algorithm. The method may additionally involve annotating the simulated data with the output of the algorithm. 1. A method comprising:generating, by a processor, a virtual driving environment comprising one or more driving lanes, a virtual vehicle, and one or more virtual sensors mounted on the virtual vehicle configured to generate simulated data as the virtual vehicle traverses within the virtual environment;executing, by the processor, an algorithm to process the simulated data to detect the one or more driving lanes; andrecording, by the processor, an output of the algorithm.2. The method of claim 1 , further comprising:annotating the simulated data with the output of the algorithm.3. The method of claim 1 , wherein the virtual driving environment further comprises a plurality of lane markings corresponding to the one or more driving lanes and a plurality of virtual objects either stationary or mobile relative to the virtual driving environment claim 1 , each of the plurality of lane markings and each of the plurality of virtual objects sensible by the one or more virtual sensors claim 1 , and wherein the simulated data characterizes the virtual driving environment as perceived by the one or more virtual sensors sensing the plurality of lane markings and the plurality of virtual objects.4. The method of claim 1 , wherein the one or more virtual sensors comprise a virtual ...

Подробнее
Номер записи: 57
26-07-2018 дата публикации

TRAINIEREN EINES AUTOMATISCHEN AMPELERKENNUNGSMODULS UNTER VERWENDUNG SIMULIERTER BILDER

Номер: DE102018101465A1
Автор: SMITH SIMON MURTHA, MICKS ASHLEY ELIZABETH, MOOSAEI MARYAM, NARIYAMBUT MURALI VIDYA, GOH MADELINE J, Smith, Simon Murtha, Micks, Ashley Elizabeth, Moosaei, Maryam, Nariyambut Murali, Vidya, Goh, Madeline J.
Принадлежит:

Es wird ein Szenario definiert, das Modelle von Fahrzeugen und eine typische Fahrumgebung sowie eine Ampel, die einen Zustand (rot, grün, gelb) aufweist, beinhaltet. Ein Modell eines Prüffahrzeugs wird zum Szenario hinzugefügt und die Kamerastelle wird auf dem Prüffahrzeug definiert. Die Wahrnehmung des Szenarios durch eine Kamera wird simuliert, um ein Bild zu erhalten. Das Bild wird mit einer Stelle und einem Zustand der Ampel annotiert. Es können verschiedene annotierte Bilder für verschiedene Szenarien generiert werden, darunter Szenarien ohne Ampel oder mit Ampeln, welche das Prüffahrzeug nicht regeln. Ein maschinelles Lernmodell wird dann unter Verwendung der annotierten Bilder trainiert, um die Stelle und den Zustand von Ampeln, die das Prüffahrzeug regeln, zu identifizieren.

Подробнее
Номер записи: 58
11-01-2018 дата публикации

ERZEUGUNG VON VIRTUELLEN SENSORDATEN FÜR DIE ERFASSUNG VON POLLERAUFNAHMEN

Номер: DE102017115197A1
Автор: MICKS ASHLEY ELIZABETH, MYERS SCOTT VINCENT, BANVAIT HARPREETSINGH, KADETOTAD SNEHA, Micks, Ashley Elizabeth, Myers, Scott Vincent, Banvait, Harpreetsingh, Kadetotad, Sneha
Принадлежит:

Die Offenbarung betrifft Verfahren, Systeme und Vorrichtungen für die Erzeugung von virtuellen Sensordaten und betrifft insbesondere die Erzeugung von virtuellen Sensordaten für das Trainieren und Testen von Modellen oder Algorithmen, um Gegenstände oder Hindernisse wie zum Beispiel Polleraufnahmen zu erfassen. Ein Verfahren zum Erzeugen von virtuellen Sensordaten umfasst das Simulieren einer 3-dimensionalen (3D) Umgebung, die eine oder mehrere Gegenstände wie zum Beispiel Polleraufnahmen umfasst. Das Verfahren umfasst das Erzeugen von virtuellen Sensordaten für eine Vielzahl von Positionen von einem oder mehreren Sensoren in der 3D-Umgebung. Das Verfahren umfasst das Bestimmen von virtueller Ground Truth, die jeder aus der Vielzahl von Positionen entspricht. Die Ground Truth umfasst Informationen über mindestens eine Polleraufnahme in den Sensordaten. Zum Beispiel kann die Ground Truth eine Höhe von mindestens einer von den Parkschranken umfassen. Das Verfahren umfasst auch das Speichern ...

Подробнее
Номер записи: 59
03-08-2017 дата публикации

ERKENNUNG VON POLLER-AUFNAHMEELEMENTEN

Номер: DE102017101224A1
Автор: BANVAIT HARPREETSINGH, MYERS SCOTT VINCENT, MICKS ASHLEY ELIZABETH, KADETOTAD SNEHA, Banvait, Harpreetsingh, Myers, Scott Vincent, Micks, Ashley Elizabeth, Kadetotad, Sneha
Принадлежит:

Die Offenbarung betrifft generell Verfahren, Systeme und Vorrichtungen zum automatisierten oder unterstützten Fahren und betrifft insbesondere die Erkennung, Lokalisierung und Navigation in Bezug auf Poller-Aufnahmeelemente. Ein Verfahren zum Detektieren von Poller-Aufnahmeelementen umfasst das Empfangen von Wahrnehmungsdaten von einem oder mehreren Wahrnehmungssensoren eines Fahrzeugs. Das Verfahren umfasst das Bestimmen eines Standortes eines oder mehrerer Poller-Aufnahmeelemente in Bezug auf eine Karosserie des Fahrzeugs auf Basis der Wahrnehmungsdaten. Das Verfahren umfasst ebenso, einem oder mehreren aus einem Fahrer und einer/einem Komponente oder System, die/das Fahrmanöverentscheidungen trifft, eine Angabe des Standortes des einen oder der mehreren Poller-Aufnahmeelemente bereitzustellen.

Подробнее
Номер записи: 60
02-03-2017 дата публикации

Bewegungskompensation für bordinterne Fahrzeugsensoren

Номер: DE102016215143A1
Автор: SAEGER MARTIN, MICKS ASHLEY ELIZABETH, Saeger, Martin, Micks, Ashley Elizabeth
Принадлежит:

Ein Verfahren zum Verbessern der Genauigkeit, mit der ein Straßenprofil vor einem Fahrzeug bestimmt werden kann. Das Verfahren kann das Empfangen mehrerer Eingaben, die mehreren bordinternen Sensoren, die einem Fahrzeug entsprechen, entsprechen, enthalten. Ein bordinternes Computersystem kann die Bewegung des Fahrzeugs schätzen. Das bordinterne Computersystem kann die Daten, die einem vorausschauenden Sensor der mehreren bordinternen Sensoren entsprechen, durch das Berücksichtigen der Bewegung des Fahrzeugs korrigieren. Entsprechend kann das bordinterne Computersystem die korrigierten Daten verwenden, um genauere Informationen zu erzeugen, die die Fahrumgebung vor dem Fahrzeug charakterisieren. Diese genaueren Informationen können verwendet werden, um die Bewegung des Fahrzeugs in der Zukunft besser zu schätzen, wenn das Fahrzeug dieser Fahrumgebung begegnet, was die Korrekturen verbessern kann, die auf die Daten angewendet werden können, die zu diesem Zeitpunkt dem vorausschauenden Sensor ...

Подробнее
Номер записи: 61
01-03-2018 дата публикации

STRAßENANSATZERKENNUNG MIT RÜCKFAHRKAMERA

Номер: DE102017116212A1
Автор: MYERS SCOTT VINCENT, GURGHIAN ALEXANDRU MIHAI, MICKS ASHLEY ELIZABETH, WALSH ALEXANDRO, Myers, Scott Vincent, Gurghian, Alexandru Mihai, Micks, Ashley Elizabeth, Walsh, Alexandro
Принадлежит:

Ein Verfahren zum Erkennen von Straßenansätzen oder kreuzenden Fahrbahnen beinhaltet das Empfangen von Erfassungsdaten von mindestens zwei Sensoren. Die mindestens zwei Sensoren umfassen eine nach hinten gerichtete Kamera eines Fahrzeugs und einen anderen Sensor. Die Erfassungsdaten umfassen Informationen zu einer aktuellen Fahrbahn, auf der sich das Fahrzeug befindet. Das Verfahren beinhaltet das Erkennen einer kreuzenden Fahrbahn, die sich mit der aktuellen Fahrbahn verbindet, auf Grundlage der Erfassungsdaten. Das Verfahren umfasst darüber hinaus das Speichern einer Anzeige einer Position und einer Richtung der kreuzenden Fahrbahn in Bezug auf die aktuelle Fahrbahn.

Подробнее
Номер записи: 62
08-01-2019 дата публикации

Lane boundary detection data generation in virtual environment

Номер: US0010176634B2
Автор: Ashley Elizabeth Micks, Venkatapathi Raju Nallapa, Brielle Reiff, Vidya Nariyambut Murali, Sneha Kadetotad, MICKS ASHLEY ELIZABETH, NALLAPA VENKATAPATHI RAJU, REIFF BRIELLE, NARIYAMBUT MURALI VIDYA, KADETOTAD SNEHA, Micks, Ashley Elizabeth, Nallapa, Venkatapathi Raju, Reiff, Brielle, Nariyambut Murali, Vidya, Kadetotad, Sneha
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC, FORD GLOBAL TECH LLC, Ford Global Technologies, LLC

A method and an apparatus pertaining to generating training data. The method may include executing a simulation process. The simulation process may include traversing one or more virtual sensors over a virtual driving environment defining a plurality of lane markings or virtual objects that are each sensible by the one or more virtual sensors. During the traversing, each of the one or more virtual sensors may be moved with respect to the virtual driving environment as dictated by a vehicle-dynamic model modeling motion of a vehicle driving on a virtual road surface of the virtual driving environment while carrying the one or more virtual sensors. Virtual sensor data characterizing the virtual driving environment may be recorded. The virtual sensor data may correspond to what an actual sensor would produce in a real-world environment that is similar or substantially matching the virtual driving environment.

Подробнее
Номер записи: 63
14-08-2018 дата публикации

Vision-based rain detection using deep learning

Номер: US0010049284B2
Автор: Jinesh J Jain, Harpreetsingh Banvait, Ashley Elizabeth Micks, Vidya Nariyambut Murali, JAIN JINESH J, BANVAIT HARPREETSINGH, MICKS ASHLEY ELIZABETH, NARIYAMBUT MURALI VIDYA, Jain, Jinesh J, Banvait, Harpreetsingh, Micks, Ashley Elizabeth, Nariyambut Murali, Vidya
Принадлежит: Ford Global Technologies, FORD GLOBAL TECH LLC, FORD GLOBAL TECH, Ford Global Technologies, LLC

A method is disclosed for using a camera on-board a vehicle to determine whether precipitation is failing near the vehicle. The method may include obtaining multiple images. Each of the multiple images may be known to photographically depict a “rain” or a “no rain” condition. An artificial neural network may be trained on the multiple images. Later, the artificial neural network may analyze one or more images captured by a first camera secured to a first vehicle. Based on that analysis, the artificial neural network may classify the first vehicle as being in “rain” or “no rain” weather.

Подробнее
Номер записи: 64
12-03-2019 дата публикации

Generating simulated sensor data for training and validation of detection models

Номер: US10228693B2
Автор: MICKS ASHLEY ELIZABETH, KADETOTAD SNEHA, JAIN JINESH J, LIU DONGRAN, GERARDO CASTRO MARCOS PAUL, MURALI VIDYA NARIYAMBUT, Micks, Ashley Elizabeth, Kadetotad, Sneha, Jain, Jinesh J., Liu, Dongran, Gerardo Castro, Marcos Paul, Murali, Vidya Nariyambut
Принадлежит: FORD GLOBAL TECH LLC, Ford Global Technologies, LLC

A scenario is defined that including models of vehicles and a typical driving environment. A model of a subject vehicle is added to the scenario and sensor locations are defined on the subject vehicle. Perception of the scenario by sensors at the sensor locations is simulated to obtain simulated sensor outputs. The simulated sensor outputs are annotated to indicate the location of obstacles in the scenario. The annotated sensor outputs may then be used to validate a statistical model or to train a machine learning model. The simulates sensor outputs may be modeled with sufficient detail to include sensor noise or may include artificially added noise to simulate real world conditions.

Подробнее
Номер записи: 65
09-05-2018 дата публикации

EIS- UND SCHNEEERFASSUNGSSYSTEME UND -VERFAHREN

Номер: DE102017121622A1
Автор: MYERS SCOTT VINCENT, MICKS ASHLEY ELIZABETH, KADETOTAD SNEHA, BANVAIT HARPREETSINGH, RODRIGUES ASHOK E, Myers, Scott Vincent, Micks, Ashley Elizabeth, Kadetotad, Sneha, Banvait, Harpreetsingh, Rodrigues, Ashok E.
Принадлежит:

Beschrieben werden beispielhafte Eis- und Schneeerfassungssysteme und -verfahren. In einer Umsetzung aktiviert ein Verfahren ein Eis- und Schneeerfassungssystem als Reaktion auf das Empfangen von Wetterdaten, die eine Wahrscheinlichkeit von Eis oder Schnee auf einer Fahrbahn in der Nähe eines Fahrzeugs anzeigen. Das Verfahren empfängt Daten von mehreren Fahrzeugsensoren und analysiert die empfangenen Daten, um Eis oder Schnee auf der Fahrbahn zu identifizieren. Wenn Eis oder Schnee auf der Fahrbahn identifiziert wird, passt das Verfahren Fahrzeugoperationen an und berichtet die Eis- oder Schneeverhältnisse an eine gemeinsame Datenbank.

Подробнее
Номер записи: 66
20-04-2017 дата публикации

Fahrbahnbegrenzungsdetektions-Datenerzeugung in virtueller Umgebung

Номер: DE102016119128A1
Автор: MICKS ASHLEY ELIZABETH, NALLAPA VENKATAPATHI RAJU, REIFF BRIELLE, NARIYAMBUT MURALI VIDYA, KADETOTAD SNEHA, Micks, Ashley Elizabeth, Nallapa, Venkatapathi Raju, Reiff, Brielle, Nariyambut Murali, Vidya, Kadetotad, Sneha
Принадлежит:

Ein Verfahren und eine Vorrichtung beziehen sich auf ein Erzeugen von Trainingsdaten. Das Verfahren kann ein Ausführen eines Simulationsprozesses umfassen. Der Simulationsprozess kann ein Verschieben eines oder mehrerer virtuelle Sensoren über eine virtuelle Fahrumgebung umfassen, die mehrere Fahrbahnmarkierungen oder virtuelle Objekte definiert, die jeweils durch den einen oder die mehreren virtuellen Sensoren erfassbar sind. Während der Verschiebung kann jeder des einen oder der mehreren virtuellen Sensoren in Bezug auf die virtuelle Fahrumgebung bewegt werden, so wie es durch eine Modellierungsbewegung eines dynamischen Fahrzeugmodells eines Fahrzeugs, das auf einer virtuellen Straßenoberfläche der virtuellen Fahrumgebung fährt und dabei den einen oder die mehreren virtuellen Sensoren trägt, vorgeschrieben ist. Virtuelle Sensordaten, die die virtuelle Fahrumgebung charakterisieren, können aufgezeichnet werden. Die virtuellen Sensordaten können dem entsprechen, was ein tatsächlicher Sensor ...

Подробнее
Номер записи: 67
23-03-2017 дата публикации

VIRTUAL, ROAD-SURFACE-PERCEPTION TEST BED

Номер: US20170083794A1
Автор: Venkatapathi Raju Nallapa, Martin Saeger, Ashley Elizabeth Micks, Douglas Blue, NALLAPA VENKATAPATHI RAJU, SAEGER MARTIN, MICKS ASHLEY ELIZABETH, BLUE DOUGLAS, Nallapa Venkatapathi Raju, Saeger Martin, Micks Ashley Elizabeth, Blue Douglas
Принадлежит:

A method for testing the performance of one or more anomaly-detection algorithms. The method may include obtaining sensor data output by a virtual sensor modeling the behavior of an image sensor. The sensor data may correspond to a time when the virtual sensor was sensing a virtual anomaly defined within a virtual road surface. One or more algorithms may be applied to the sensor data to produce at least one perceived dimension of the virtual anomaly. Thereafter, the performance of the one or more algorithms may be quantified by comparing the at least one perceived dimension to at least one actual dimension of the virtual anomaly as defined in the virtual road surface. 1. A method comprising:obtaining, by a computer system, sensor data output by a virtual sensor modeling the behavior of an image sensor while the virtual sensor is sensing a virtual anomaly defined within a virtual road surface;producing, by one or more algorithms applied by the computer system to the sensor data, at least one perceived dimension of the virtual anomaly; andquantifying, by the computer system, performance of the one or more algorithms by comparing the at least one perceived dimension to at least one actual dimension of the virtual anomaly as defined in the virtual road surface.2. The method of claim 1 , wherein the image sensor is selected from the group consisting of a camera claim 1 , a laser scanner claim 1 , and a radar device.3. The method of claim 2 , further comprising obtaining claim 2 , by the computer system claim 2 , ground truth data comprising the at least one actual dimension.4. The method of claim 3 , further comprising using claim 3 , by the computer system claim 3 , the sensor data claim 3 , the ground truth data claim 3 , and supervised learning techniques to improve the performance of the one or more algorithms.5. The method of claim 4 , wherein the virtual anomaly is selected from the group consisting of a virtual pot hole claim 4 , a virtual speed bump claim 4 , a ...

Подробнее
Номер записи: 68
13-02-2018 дата публикации

Roadway-crossing-anomaly detection system and method

Номер: US0009889716B2
Автор: Harpreetsingh Banvait, Scott Vincent Myers, Ashley Elizabeth Micks, Sneha Kadetotad, BANVAIT HARPREETSINGH, MYERS SCOTT VINCENT, MICKS ASHLEY ELIZABETH, KADETOTAD SNEHA, Banvait Harpreetsingh, Myers Scott Vincent, Micks Ashley Elizabeth, Kadetotad Sneha
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC, FORD GLOBAL TECH LLC, Ford Global Technologies, LLC

A method for improving the safety and comfort of a vehicle driving over a railroad track, cattle guard, or the like. The method may include receiving, by a computer system, one or more inputs corresponding to one or more forward looking sensors. The computer system may also receive data characterizing a motion of the vehicle. The computer system may estimate, based on the one or more inputs and the data, a motion of a vehicle with respect to a railroad track, cattle guard, or the like extending across a road ahead of the vehicle. Accordingly, the computer system may change a suspension setting, steering setting, or the like of the vehicle to more safely or comfortably drive over the railroad track, cattle guard, or the like.

Подробнее
Номер записи: 69
12-11-2019 дата публикации

Training algorithm for collision avoidance

Номер: US0010474964B2
Автор: Ashley Elizabeth Micks, Jinesh J Jain, Harpreetsingh Banvait, Kyu Jeong Han, MICKS ASHLEY ELIZABETH, JAIN JINESH J, BANVAIT HARPREETSINGH, HAN KYU JEONG, Micks, Ashley Elizabeth, Jain, Jinesh J, Banvait, Harpreetsingh, Han, Kyu Jeong
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC, FORD GLOBAL TECH LLC, Ford Global Technologies, LLC

A machine learning model is trained by defining a scenario including models of vehicles and a typical driving environment. A model of a subject vehicle is added to the scenario and sensor locations are defined on the subject vehicle. A perception of the scenario by sensors at the sensor locations is simulated. The scenario further includes a model of a lane-splitting vehicle. The location of the lane-splitting vehicle and the simulated outputs of the sensors perceiving the scenario are input to a machine learning algorithm that trains a model to detect the location of a lane-splitting vehicle based on the sensor outputs. A vehicle controller then incorporates the machine learning model and estimates the presence and/or location of a lane-splitting vehicle based on actual sensor outputs input to the machine learning model.

Подробнее
Номер записи: 70
10-11-2020 дата публикации

Method and system for virtual sensor data generation with depth ground truth annotation

Номер: US0010832478B2
Автор: Alexander Groh, Ashley Elizabeth Micks, Vidya Nariyambut Murali, GROH ALEXANDER, MICKS ASHLEY ELIZABETH, NARIYAMBUT MURALI VIDYA, Groh, Alexander, Micks, Ashley Elizabeth, Nariyambut Murali, Vidya
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC, FORD GLOBAL TECH LLC, Ford Global Technologies, LLC.

Methods and systems for generating virtual sensor data for developing or testing computer vision detection algorithms are described. A system and a method may involve generating a virtual environment. The system and the method may also involve positioning a virtual sensor at a first location in the virtual environment. The system and the method may also involve recording data characterizing the virtual environment, the data corresponding to information generated by the virtual sensor sensing the virtual environment. The system and the method may further involves annotating the data with a depth map characterizing a spatial relationship between the virtual sensor and the virtual environment.

Подробнее
Номер записи: 71
19-02-2019 дата публикации

Roadway-crossing-anomaly detection system and method

Номер: US0010207560B2
Автор: Harpreetsingh Banvait, Scott Vincent Myers, Ashley Elizabeth Micks, Sneha Kadetotad, BANVAIT HARPREETSINGH, MYERS SCOTT VINCENT, MICKS ASHLEY ELIZABETH, KADETOTAD SNEHA, Banvait, Harpreetsingh, Myers, Scott Vincent, Micks, Ashley Elizabeth, Kadetotad, Sneha
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC, FORD GLOBAL TECH LLC, Ford Global Technologies, LLC.

A method for improving the safety and comfort of a vehicle driving over a railroad track, cattle guard, or the like. The method may include receiving, by a computer system, one or more inputs corresponding to one or more forward looking sensors. The computer system may also receive data characterizing a motion of the vehicle. The computer system may estimate, based on the one or more inputs and the data, a motion of a vehicle with respect to a railroad track, cattle guard, or the like extending across a road ahead of the vehicle. Accordingly, the computer system may change a suspension setting, steering setting, or the like of the vehicle to more safely or comfortably drive over the railroad track, cattle guard, or the like.

Подробнее
Номер записи: 72
03-08-2017 дата публикации

BOLLARD RECEIVER IDENTIFICATION

Номер: US20170221365A1
Автор: Harpreetsingh Banvait, Scott Vincent Myers, Ashley Elizabeth Micks, Sneha Kadetotad, BANVAIT HARPREETSINGH, MYERS SCOTT VINCENT, MICKS ASHLEY ELIZABETH, KADETOTAD SNEHA, Banvait Harpreetsingh, Myers Scott Vincent, Micks Ashley Elizabeth, Kadetotad Sneha
Принадлежит:

The disclosure relates generally to methods, systems, and apparatuses for automated or assisted driving and more particularly relates to identification, localization, and navigation with respect to bollard receivers. A method for detecting bollard receivers includes receiving perception data from one or more perception sensors of a vehicle. The method includes determining, based on the perception data, a location of one or more bollard receivers in relation to a body of the vehicle. The method also includes providing an indication of the location of the one or more bollard receivers to one or more of a driver and component or system that makes driving maneuver decisions. 1. A method comprising:receiving perception data from one or more perception sensors of a vehicle;determining, based on the perception data, a location of one or more bollard receivers in relation to a body of the vehicle, wherein determining the location comprises determining when corresponding bollards are removed from the one or more bollard receivers; andproviding an indication of the location of the one or more bollard receivers to one or more of a driver and driving maneuver decision component.2. The method of claim 1 , further comprising determining the location in relation to the body based on information from a controller area network (CAN) bus of the vehicle.3. The method of claim 1 , wherein determining the location comprises determining further based on a vehicle driving history.4. The method of claim 1 , wherein the one or more perception sensors comprise two or more of a camera claim 1 , a radar sensor claim 1 , a light detection and ranging (LIDAR) sensor claim 1 , a radar sensor claim 1 , and an ultrasound sensor.5. The method of claim 1 , further comprising determining a height of the bollard receiver based on the perception data.6. The method of claim 1 , further comprising determining a driving maneuver based on the location of the one or more bollard receivers.7. The method of ...

Подробнее
Номер записи: 73
13-10-2020 дата публикации

Vehicle turn signal detection

Номер: US0010800455B2
Автор: Ashley Elizabeth Micks, Harpreetsingh Banvait, Jinesh J Jain, Brielle Reiff, Sneha Kadetotad, MICKS ASHLEY ELIZABETH, BANVAIT HARPREETSINGH, JAIN JINESH J, REIFF BRIELLE, KADETOTAD SNEHA, Micks, Ashley Elizabeth, Banvait, Harpreetsingh, Jain, Jinesh J, Reiff, Brielle, Kadetotad, Sneha
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC, FORD GLOBAL TECH LLC, Ford Global Technologies, LLC

Systems, methods, and devices for detecting a vehicle's turn signal status for collision avoidance during lane-switching maneuvers or otherwise. A method includes detecting, at a first vehicle, a presence of a second vehicle in an adjacent lane. The method includes identifying, in an image of the second vehicle, a sub-portion containing a turn signal indicator of the second vehicle. The method includes processing the sub-portion of the image to determine a state of the turn signal indicator. The method also includes notifying a driver or performing a driving maneuver, at the first vehicle, based on the state of the turn signal indicator.

Подробнее
Номер записи: 74
12-03-2020 дата публикации

Method and System for Virtual Sensor Data Generation with Depth Ground Truth Annotation

Номер: US20200082622A1
Автор: Alexander Groh, Ashley Elizabeth Micks, Vidya Nariyambut Murali, GROH ALEXANDER, MICKS ASHLEY ELIZABETH, NARIYAMBUT MURALI VIDYA, Groh, Alexander, Micks, Ashley Elizabeth, Nariyambut Murali, Vidya
Принадлежит:

Methods and systems for generating virtual sensor data for developing or testing computer vision detection algorithms are described. A system and a method may involve generating a virtual environment. The system and the method may also involve positioning a virtual sensor at a first location in the virtual environment. The system and the method may also involve recording data characterizing the virtual environment, the data corresponding to information generated by the virtual sensor sensing the virtual environment. The system and the method may further involves annotating the data with a depth map characterizing a spatial relationship between the virtual sensor and the virtual environment. 1. A method , comprising: generating, by a processor, a virtual environment with a virtual sensor therein;', 'positioning, by the processor, the virtual sensor on a mobile virtual object in the virtual environment; and', 'generating, by the processor, simulation-generated data characterizing the virtual environment as perceived by the virtual sensor as the mobile virtual object and the virtual sensor move around in the virtual environment,, 'performing a process to develop, test or train a computer vision detection algorithm by modeling a real-word environment with a virtual environment, the process comprisingwherein the simulation-generated data represents information collected by one or more real-word sensors in the real-word environment.2. The method of claim 1 , wherein the virtual environment comprises a plurality of virtual objects distributed therewithin claim 1 , each of the virtual objects either stationary or mobile relative to the virtual sensor claim 1 , and each of the virtual objects sensible by the virtual sensor.3. The method of claim 2 , wherein the spatial relationship comprises distance information of one or more of the plurality of virtual objects with respect to the virtual sensor.4. The method of claim 2 , wherein the virtual sensor comprises a virtual ...

Подробнее
Номер записи: 75
16-04-2019 дата публикации

Bollard receiver identification

Номер: US0010262540B2
Автор: Harpreetsingh Banvait, Scott Vincent Myers, Ashley Elizabeth Micks, Sneha Kadetotad, BANVAIT HARPREETSINGH, MYERS SCOTT VINCENT, MICKS ASHLEY ELIZABETH, KADETOTAD SNEHA, Banvait, Harpreetsingh, Myers, Scott Vincent, Micks, Ashley Elizabeth, Kadetotad, Sneha
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC, FORD GLOBAL TECH LLC, Ford Global Technologies, LLC

The disclosure relates generally to methods, systems, and apparatuses for automated or assisted driving and more particularly relates to identification, localization, and navigation with respect to bollard receivers. A method for detecting bollard receivers includes receiving perception data from one or more perception sensors of a vehicle. The method includes determining, based on the perception data, a location of one or more bollard receivers in relation to a body of the vehicle. The method also includes providing an indication of the location of the one or more bollard receivers to one or more of a driver and component or system that makes driving maneuver decisions.

Подробнее
Номер записи: 76
25-09-2018 дата публикации

Vehicle radar perception and localization

Номер: US0010082797B2
Автор: Ashley Elizabeth Micks, Venkatapathi Raju Nallapa, Vidya Nariyambut Murali, Scott Vincent Myers, MICKS ASHLEY ELIZABETH, NALLAPA VENKATAPATHI RAJU, NARIYAMBUT MURALI VIDYA, MYERS SCOTT VINCENT, Micks, Ashley Elizabeth, Nallapa, Venkatapathi Raju, Nariyambut Murali, Vidya, Myers, Scott Vincent
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC, FORD GLOBAL TECH LLC, Ford Global Technologies, LLC

The disclosure relates to methods, systems, and apparatuses for autonomous driving vehicles or driving assistance systems and more particularly relates to vehicle radar perception and location. The vehicle driving system disclosed may include a storage media, a radar system, a location component and a driver controller. The storage media stores a map of roadways. The radar system is configured to generate perception information from a region near the vehicle. The location component is configured to determine a location of the vehicle on the map based on the radar perception information and other navigation related data. The drive controller is configured to control driving of the vehicle based on the map and the determined location.

Подробнее
Номер записи: 77
11-12-2018 дата публикации

Pedestrian detection when a vehicle is reversing

Номер: US0010150414B2
Автор: Scott Vincent Myers, Alexandru Mihai Gurghian, Ashley Elizabeth Micks, Ramchandra Ganesh Karandikar, MYERS SCOTT VINCENT, GURGHIAN ALEXANDRU MIHAI, MICKS ASHLEY ELIZABETH, KARANDIKAR RAMCHANDRA GANESH, Myers, Scott Vincent, Gurghian, Alexandru Mihai, Micks, Ashley Elizabeth, Karandikar, Ramchandra Ganesh
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC, FORD GLOBAL TECH LLC, Ford Global Technologies, LLC

Techniques and implementations pertaining to detection of moving objects, such as pedestrians, when a vehicle moves in a rearward direction are described. A method may involve identifying a region of interest when a vehicle moves in a rearward direction. The method may involve detecting a moving object in the region of interest. The method may also involve determining whether a collision with the moving object by the vehicle moving in the rearward direction is likely. The method may further involve providing a human-perceivable signal responsive to a determination that the collision is likely.

Подробнее
Номер записи: 78
06-04-2021 дата публикации

Bollard receiver identification

Номер: US0010971014B2
Автор: Harpreetsingh Banvait, Scott Vincent Myers, Ashley Elizabeth Micks, Sneha Kadetotad, BANVAIT HARPREETSINGH, MYERS SCOTT VINCENT, MICKS ASHLEY ELIZABETH, KADETOTAD SNEHA, Banvait, Harpreetsingh, Myers, Scott Vincent, Micks, Ashley Elizabeth, Kadetotad, Sneha
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC, FORD GLOBAL TECH LLC, Ford Global Technologies, LLC.

The disclosure relates generally to methods, systems, and apparatuses for automated or assisted driving and more particularly relates to identification, localization, and navigation with respect to bollard receivers. A method for detecting bollard receivers includes receiving perception data from one or more perception sensors of a vehicle. The method includes determining, based on the perception data, a location of one or more bollard receivers in relation to a body of the vehicle. The method also includes providing an indication of the location of the one or more bollard receivers to one or more of a driver and component or system that makes driving maneuver decisions.

Подробнее
Номер записи: 79
22-06-2017 дата публикации

Vehicle Turn Signal Detection

Номер: US20170174261A1
Автор: Ashley Elizabeth Micks, Harpreetsingh Banvait, Jinesh J Jain, Brielle Reiff, Sneha Kadetotad, MICKS ASHLEY ELIZABETH, BANVAIT HARPREETSINGH, JAIN JINESH J, REIFF BRIELLE, KADETOTAD SNEHA, Micks Ashley Elizabeth, Banvait Harpreetsingh, Jain Jinesh J, Reiff Brielle, Kadetotad Sneha
Принадлежит:

Systems, methods, and devices for detecting a vehicle's turn signal status for collision avoidance during lane-switching maneuvers or otherwise. A method includes detecting, at a first vehicle, a presence of a second vehicle in an adjacent lane. The method includes identifying, in an image of the second vehicle, a sub-portion containing a turn signal indicator of the second vehicle. The method includes processing the sub-portion of the image to determine a state of the turn signal indicator. The method also includes notifying a driver or performing a driving maneuver, at the first vehicle, based on the state of the turn signal indicator. 1. A method comprising:detecting, at a first vehicle, a presence of a second vehicle in an adjacent lane;identifying, in an image of the second vehicle, a sub-portion of the image containing a turn signal indicator of the second vehicle, wherein identifying the sub-portion containing the turn signal indicator comprises processing the image of the second vehicle using a first neural network trained to recognize one or more turn signal regions of interest;processing the sub-portion of the image to determine a state of the turn signal indicator using a second neural network trained to determine a state of one or more turn signal indicators; andnotifying a driver or performing a driving maneuver, at the first vehicle, based on the state of the turn signal indicator.2. (canceled)3. (canceled)4. The method of claim 1 , further comprising determining the driving maneuver for the first vehicle based on the state of the turn signal indicator.5. The method of claim 4 , wherein determining the driving maneuver comprises providing the state of the turn signal indicator into a lane-changing decision matrix and processing the lane-changing decision matrix to select the driving maneuver.6. The method of claim 4 , wherein notifying the driver comprises notifying the driver of the determined driving maneuver.7. The method of claim 1 , further ...

Подробнее
Номер записи: 80
28-03-2019 дата публикации

Lane Boundary Detection Data Generation In Virtual Environment

Номер: US2019096128A1
Автор: MICKS ASHLEY ELIZABETH, NALLAPA VENKATAPATHI RAJU, REIFF BRIELLE, NARIYAMBUT MURALI VIDYA, KADETOTAD SNEHA, Micks, Ashley Elizabeth, Nallapa, Venkatapathi Raju, Reiff, Brielle, Nariyambut Murali, Vidya, Kadetotad, Sneha
Принадлежит:

A method and an apparatus pertaining to generating training data. The method may include executing a simulation process. The simulation process may include traversing one or more virtual sensors over a virtual driving environment defining a plurality of lane markings or virtual objects that are each sensible by the one or more virtual sensors. During the traversing, each of the one or more virtual sensors may be moved with respect to the virtual driving environment as dictated by a vehicle-dynamic model modeling motion of a vehicle driving on a virtual road surface of the virtual driving environment while carrying the one or more virtual sensors. Virtual sensor data characterizing the virtual driving environment may be recorded. The virtual sensor data may correspond to what an actual sensor would produce in a real-world environment that is similar or substantially matching the virtual driving environment.

Подробнее
Номер записи: 81
27-10-2020 дата публикации

System and methods for identifying unoccupied parking positions

Номер: US0010817736B2
Автор: Harpreestsingh Banvait, Ashley Elizabeth Micks, Jinesh J. Jain, Scott Vincent Myers, BANVAIT HARPREESTSINGH, MICKS ASHLEY ELIZABETH, JAIN JINESH J, MYERS SCOTT VINCENT, Banvait, Harpreestsingh, Micks, Ashley Elizabeth, Jain, Jinesh J., Myers, Scott Vincent
Принадлежит: Ford Motor Company, FORD MOTOR CO

A vehicle includes one or more laterally mounted microphones and a controller programmed to detect a signature of an unoccupied position adjacent the vehicle in outputs of the microphones. The signature may be identified using a machine learning algorithm. In response to detecting an unoccupied position, the controller may invoke autonomous parking, store the location of the unoccupied position for later use, and/or report the unoccupied position to a server, which then informs other vehicles of the available parking. The unoccupied position may be verified by evaluating whether map data indicates legal parking at that location. The unoccupied position may also be confirmed with one or more other sensors, such as a camera, LIDAR, RADAR, SONAR, or other type of sensor.

Подробнее
Номер записи: 82
22-06-2017 дата публикации

Virtual Sensor Data Generation For Wheel Stop Detection

Номер: US20170177954A1
Автор: Ashley Elizabeth Micks, Venkatapathi Raju Nallapa, Harpreetsingh Banvait, Scott Vincent Myers, MICKS ASHLEY ELIZABETH, NALLAPA VENKATAPATHI RAJU, BANVAIT HARPREETSINGH, MYERS SCOTT VINCENT, Micks Ashley Elizabeth, Nallapa Venkatapathi Raju, Banvait Harpreetsingh, Myers Scott Vincent
Принадлежит: Ford Global Technologies, LLC

The disclosure relates to methods, systems, and apparatuses for virtual sensor data generation and more particularly relates to generation of virtual sensor data for training and testing models or algorithms to detect objects or obstacles, such as wheel stops or parking barriers. A method for generating virtual sensor data includes simulating a three-dimensional (3D) environment comprising one or more objects. The method includes generating virtual sensor data for a plurality of positions of one or more sensors within the 3D environment. The method includes determining virtual ground truth corresponding to each of the plurality of positions, wherein the ground truth includes information about at least one object within the virtual sensor data. The method also includes storing and associating the virtual sensor data and the virtual ground truth. 1. A method comprising:simulating, using one or more processors, a three-dimensional (3D) environment comprising one or more parking barriers;generating, using one or more processors, virtual sensor data for a plurality of positions of one or more sensors within the 3D environment;determining, using one or more processors, virtual ground truth corresponding to each of the plurality of positions, wherein the ground truth comprises a height of the at least one of the parking barriers; andstoring and associating the virtual sensor data and the virtual ground truth using one or more processors.2. The method of claim 1 , further comprising providing one or more of the virtual sensor data and the virtual ground truth for training or testing of a machine learning algorithm or model.3. The method of claim 2 , wherein the machine learning model or algorithm comprises a neural network.4. The method of claim 2 , wherein training the machine learning algorithm or model comprises providing at least a portion of the virtual sensor data and corresponding virtual ground truth to train the machine learning algorithm or model to determine one ...

Подробнее
Номер записи: 83
22-01-2019 дата публикации

Ice and snow detection systems and methods

Номер: US0010183677B2
Автор: Scott Vincent Myers, Ashley Elizabeth Micks, Sneha Kadetotad, Harpreetsingh Banvait, Ashok E. Rodrigues, MYERS SCOTT VINCENT, MICKS ASHLEY ELIZABETH, KADETOTAD SNEHA, BANVAIT HARPREETSINGH, RODRIGUES ASHOK E, Myers, Scott Vincent, Micks, Ashley Elizabeth, Kadetotad, Sneha, Banvait, Harpreetsingh, Rodrigues, Ashok E.
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC, FORD GLOBAL TECH LLC, Ford Global Technologies, LLC

Example ice and snow detection systems and methods are described. In one implementation, a method activates an ice and snow detection system in response to receiving weather data indicating a likelihood of ice or snow on a roadway near a vehicle. The method receives data from multiple vehicle sensors and analyzes the received data to identify ice or snow on the roadway. If ice or snow is identified on the roadway, the method adjusts vehicle operations and reports the ice or snow condition to a shared database.

Подробнее
Номер записи: 84
22-05-2018 дата публикации

Methods and systems for automatically detecting and responding to dangerous road conditions

Номер: US0009975547B2
Автор: Scott Vincent Myers, Sneha Kadetotad, Ashley Elizabeth Micks, Harpreetsingh Banvait, MYERS SCOTT VINCENT, KADETOTAD SNEHA, MICKS ASHLEY ELIZABETH, BANVAIT HARPREETSINGH, Myers, Scott Vincent, Kadetotad, Sneha, Micks, Ashley Elizabeth, Banvait, Harpreetsingh
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC, FORD GLOBAL TECH LLC, Ford Global Technologies, LLC

A method for automatically detecting and safely traversing an accumulation of ice on an impending bridge. The method automatically identifies, by the vehicle, impending approach of the vehicle to a bridge and senses an accumulation of ice on the bridge. The method then calculates a speed of the vehicle needed to prevent longitudinal slip between the vehicle and the bridge, and automatically slows the vehicle at a rate sufficient to enable the vehicle to reach the calculated speed by the time it reaches the bridge. A corresponding system is also disclosed and claimed herein.

Подробнее
Номер записи: 85
16-03-2017 дата публикации

VEHICLE RADAR PERCEPTION AND LOCALIZATION

Номер: US20170075355A1
Автор: Ashley Elizabeth Micks, Venkatapathi Raju Nallapa, Vidya Nariyambut Murali, Scott Vincent Myers, MICKS ASHLEY ELIZABETH, NALLAPA VENKATAPATHI RAJU, NARIYAMBUT MURALI VIDYA, MYERS SCOTT VINCENT, Micks Ashley Elizabeth, Nallapa Venkatapathi Raju, Nariyambut Murali Vidya, Myers Scott Vincent
Принадлежит:

The disclosure relates to methods, systems, and apparatuses for autonomous driving vehicles or driving assistance systems and more particularly relates to vehicle radar perception and location. The vehicle driving system disclosed may include a storage media, a radar system, a location component and a driver controller. The storage media stores a map of roadways. The radar system is configured to generate perception information from a region near the vehicle. The location component is configured to determine a location of the vehicle on the map based on the radar perception information and other navigation related data. The drive controller is configured to control driving of the vehicle based on the map and the determined location. 1. A vehicle driving system , comprising:storage media storing a map of roadways;a radar system configured to generate radar perception information from a region near a vehicle;a location component configured to determine a location of the vehicle on the map based on the radar perception information and other navigation related data; anda drive controller configured to control driving of the vehicle based on the map and the determined location.2. The vehicle driving system of claim 1 , wherein the vehicle driving system is autonomous and further comprises one or more additional sensor units and a data quality component configured to determine that one or more sensor units are not providing usable data or are damaged claim 1 , wherein the location component is configured to determine the location of the vehicle based on the radar perception information in response to determining that the one or more sensor units are not providing usable data or are damaged.3. The vehicle driving system of claim 2 , wherein the data quality component is configured to determine that the one or more sensor units are not providing usable data or are damaged based on one or more of:current weather conditions; anddetermining the one or more sensor units are not ...

Подробнее
Номер записи: 86
03-08-2017 дата публикации

Roadway-Crossing-Anomaly Detection System and Method

Номер: US20170217276A1
Автор: Harpreetsingh Banvait, Scott Vincent Myers, Ashley Elizabeth Micks, Sneha Kadetotad, BANVAIT HARPREETSINGH, MYERS SCOTT VINCENT, MICKS ASHLEY ELIZABETH, KADETOTAD SNEHA, Banvait Harpreetsingh, Myers Scott Vincent, Micks Ashley Elizabeth, Kadetotad Sneha
Принадлежит:

A method for improving the safety and comfort of a vehicle driving over a railroad track, cattle guard, or the like. The method may include receiving, by a computer system, one or more inputs corresponding to one or more forward looking sensors. The computer system may also receive data characterizing a motion of the vehicle. The computer system may estimate, based on the one or more inputs and the data, a motion of a vehicle with respect to a railroad track, cattle guard, or the like extending across a road ahead of the vehicle. Accordingly, the computer system may change a suspension setting, steering setting, or the like of the vehicle to more safely or comfortably drive over the railroad track, cattle guard, or the like. 1. A method comprising:receiving, by a computer system, one or more inputs corresponding to one or more sensors;estimating, by the computer system based on the one or more inputs, a motion of a vehicle with respect to a anomaly extending across a road ahead of the vehicle; andchanging, by the computer system, a suspension setting of the vehicle to more safely or comfortably drive over the anomaly.2. The method of claim 1 , wherein at least one of the one or more sensors comprises a forward-looking sensor characterizing a driving environment ahead of the vehicle.3. The method of claim 2 , wherein at least one of the one or more sensors comprises a device providing data to the computer system via a CAN bus of the vehicle.4. The method of claim 3 , wherein the anomaly is a railroad track or a cattle guard.5. The method of claim 4 , wherein the forward looking sensor is selected from the group consisting of an ultrasonic transducer claim 4 , a laser scanner claim 4 , a LiDAR device claim 4 , a radar device claim 4 , and a camera.6. The method of claim 5 , wherein the data provided by the device characterizes the attitude of the vehicle in at least one of pitch claim 5 , roll claim 5 , and yaw.7. The method of claim 6 , wherein:the anomaly is a ...

Подробнее
Номер записи: 87
20-12-2018 дата публикации

Method and System for Virtual Sensor Data Generation with Depth Ground Truth Annotation

Номер: US20180365895A1
Автор: Alexander Groh, Ashley Elizabeth Micks, Vidya Nariyambut Murali, GROH ALEXANDER, MICKS ASHLEY ELIZABETH, NARIYAMBUT MURALI VIDYA, Groh, Alexander, Micks, Ashley Elizabeth, Nariyambut Murali, Vidya
Принадлежит: FORD GLOBAL TECHNOLOGIES LLC

Methods and systems for generating virtual sensor data for developing or testing computer vision detection algorithms are described. A system and a method may involve generating a virtual environment. The system and the method may also involve positioning a virtual sensor at a first location in the virtual environment. The system and the method may also involve recording data characterizing the virtual environment, the data corresponding to information generated by the virtual sensor sensing the virtual environment. The system and the method may further involves annotating the data with a depth map characterizing a spatial relationship between the virtual sensor and the virtual environment.

Подробнее
Номер записи: 88
31-12-2019 дата публикации

Virtual sensor-data-generation system and method supporting development of vision-based rain-detection algorithms

Номер: US0010521677B2
Автор: Ashley Elizabeth Micks, Harpreetsingh Banvait, Jinesh J Jain, Vidya Nariyambut Murali, MICKS ASHLEY ELIZABETH, BANVAIT HARPREETSINGH, JAIN JINESH J, NARIYAMBUT MURALI VIDYA, Micks, Ashley Elizabeth, Banvait, Harpreetsingh, Jain, Jinesh J, Nariyambut Murali, Vidya
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC, FORD GLOBAL TECH LLC, Ford Global Technologies, LLC

A method for generating training data is disclosed. The method may include executing a simulation process. The simulation process may include traversing a virtual camera through a virtual driving environment comprising at least one virtual precipitation condition and at least one virtual no precipitation condition. During the traversing, the virtual camera may be moved with respect to the virtual driving environment as dictated by a vehicle-motion model modeling motion of a vehicle driving through the virtual driving environment while carrying the virtual camera. Virtual sensor data characterizing the virtual driving environment in both virtual precipitation and virtual no precipitation conditions may be recorded. The virtual sensor data may correspond to what a real sensor would have output had it sensed the virtual driving environment in the real world.

Подробнее
Номер записи: 89
03-10-2019 дата публикации

Neural Network Generative Modeling To Transform Speech Utterances And Augment Training Data

Номер: US20190304480A1
Автор: Praveen Narayanan, Lisa Scaria, Francois Charette, Ashley Elizabeth Micks, Ryan Burke, NARAYANAN PRAVEEN, SCARIA LISA, CHARETTE FRANCOIS, MICKS ASHLEY ELIZABETH, BURKE RYAN, Narayanan, Praveen, Scaria, Lisa, Charette, Francois, Micks, Ashley Elizabeth, Burke, Ryan
Принадлежит:

Systems, methods, and devices for speech transformation and generating synthetic speech using deep generative models are disclosed. A method of the disclosure includes receiving input audio data comprising a plurality of iterations of a speech utterance from a plurality of speakers. The method includes generating an input spectrogram based on the input audio data and transmitting the input spectrogram to a neural network configured to generate an output spectrogram. The method includes receiving the output spectrogram from the neural network and, based on the output spectrogram, generating synthetic audio data comprising the speech utterance. 1. A method for generating synthetic speech data , the method comprising:receiving input audio data comprising a plurality of iterations of a speech utterance from a plurality of speakers;generating an input spectrogram based on the input audio data;transmitting the input spectrogram to a neural network configured to generate an output spectrogram;receiving the output spectrogram from the neural network; andbased on the output spectrogram, generating synthetic audio data comprising the speech utterance.2. The method of claim 1 , wherein one or more of the input spectrogram and the output spectrogram comprises a two-dimensional audio spectrogram representation.3. The method of claim 1 , wherein the speech utterance comprises one or more of a word claim 1 , a phrase claim 1 , a sentence claim 1 , or a noise.4. The method of claim 1 , wherein the plurality of speakers comprises real-life speakers and synthetic speakers.5. The method of claim 1 , further comprising transmitting the synthetic audio data comprising the speech utterance to a training neural network configured to be trained using the synthetic audio data.6. The method of claim 1 , wherein the neural network comprises a modified neural network architecture comprising a convolutional layer in an encoder module and a deconvolutional layer in a decoder module.7. The method ...

Подробнее
Номер записи: 90
17-12-2019 дата публикации

Method and system for virtual sensor data generation with depth ground truth annotation

Номер: US0010510187B2
Автор: Alexander Groh, Ashley Elizabeth Micks, Vidya Nariyambut Murali, GROH ALEXANDER, MICKS ASHLEY ELIZABETH, NARIYAMBUT MURALI VIDYA, Groh, Alexander, Micks, Ashley Elizabeth, Nariyambut Murali, Vidya
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC, FORD GLOBAL TECH LLC, Ford Global Technologies, LLC

Methods and systems for generating virtual sensor data for developing or testing computer vision detection algorithms are described. A system and a method may involve generating a virtual environment. The system and the method may also involve positioning a virtual sensor at a first location in the virtual environment. The system and the method may also involve recording data characterizing the virtual environment, the data corresponding to information generated by the virtual sensor sensing the virtual environment. The system and the method may further involves annotating the data with a depth map characterizing a spatial relationship between the virtual sensor and the virtual environment.

Подробнее
Номер записи: 91
06-08-2019 дата публикации

Automatic vehicle leak detection

Номер: US0010372996B2
Автор: Jinesh J Jain, Harpreetsingh Banvait, Bruno Sielly Jales Costa, Ashley Elizabeth Micks, JAIN JINESH J, BANVAIT HARPREETSINGH, JALES COSTA BRUNO SIELLY, MICKS ASHLEY ELIZABETH, Jain, Jinesh J, Banvait, Harpreetsingh, Jales Costa, Bruno Sielly, Micks, Ashley Elizabeth
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC, FORD GLOBAL TECH LLC, Ford Global Technologies, LLC

A vehicle controller receives images from a camera upon arrival and upon departure. A location of the vehicle may be tracked and images captured by the camera may be tagged with a location. A departure image may be compared to an arrival image captured closest to the same location as the arrival image. A residual image based on a difference between the arrival and departure images is evaluated for anomalies. Attributes of the anomaly such as texture, color, and the like are determined and the anomaly is classified based on the attributes. If the classification indicates an automotive fluid, then an alert is generated.

Подробнее
Номер записи: 92
06-04-2017 дата публикации

Parking Obstruction Locator and Height Estimator

Номер: US20170096102A1
Автор: Venkatapathi Raju Nallapa, Harpreetsingh Banvait, Scott Vincent Myers, Ashley Elizabeth Micks, NALLAPA VENKATAPATHI RAJU, BANVAIT HARPREETSINGH, MYERS SCOTT VINCENT, MICKS ASHLEY ELIZABETH, Nallapa Venkatapathi Raju, Banvait Harpreetsingh, Myers Scott Vincent, Micks Ashley Elizabeth
Принадлежит:

Systems, methods and apparatuses are disclosed for assessing whether a vehicle will make contact with an obstacle. The systems, methods, and apparatuses may include an obstacle sensing component configured to determine a location and a dimension of an obstacle, a vehicle sensing component configured to determine a height of a point of the vehicle relative to the ground, and a notification component configured to provide an indication of a presence of the obstacle to assist a human driver or an automated driving system in parking the vehicle without making contact with the obstacle. 1. A system comprising:an obstacle sensing component configured to determine a location and a dimension of an obstacle, wherein the dimension comprises a height of the obstacle with respect to a ground surface;a vehicle sensing component configured to determine a height of a point on a vehicle relative to the ground surface, wherein the vehicle sensing component determines the height based on sensor data; update a drive history to include an indication of a presence and the height of the obstacle in response to the vehicle parking at a location near the obstacle;', 'retain the location of the object in memory in response to parking the vehicle or the vehicle being turned off; and', 'check the drive history for information about any obstacles near the parking location in response to the vehicle or driver preparing to exit the parking location; and, 'a drive history component configured toa notification component configured to provide an indication of a presence of the obstacle to assist a driver or vehicle in exiting the parking location without making contact with the obstacle.2. The system of claim 1 , wherein the obstacle sensing component receives data from one or more of a radar system claim 1 , an ultrasound system claim 1 , a LIDAR system claim 1 , a camera system claim 1 , a GPS system claim 1 , and a vehicle data storage device.3. The system of claim 1 , wherein the vehicle ...

Подробнее
Номер записи: 93
09-10-2018 дата публикации

Method and system for virtual sensor data generation with depth ground truth annotation

Номер: US0010096158B2
Автор: Alexander Groh, Ashley Elizabeth Micks, Vidya Nariyambut Murali, GROH ALEXANDER, MICKS ASHLEY ELIZABETH, NARIYAMBUT MURALI VIDYA, Groh, Alexander, Micks, Ashley Elizabeth, Nariyambut Murali, Vidya
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC, FORD GLOBAL TECH LLC, Ford Global Technologies, LLC

Methods and systems for generating virtual sensor data for developing or testing computer vision detection algorithms are described. A system and a method may involve generating a virtual environment. The system and the method may also involve positioning a virtual sensor at a first location in the virtual environment. The system and the method may also involve recording data characterizing the virtual environment, the data corresponding to information generated by the virtual sensor sensing the virtual environment. The system and the method may further involves annotating the data with a depth map characterizing a spatial relationship between the virtual sensor and the virtual environment.

Подробнее
Номер записи: 94
09-11-2021 дата публикации

Vehicle radar perception and localization

Номер: US0011169534B2
Автор: Ashley Elizabeth Micks, Venkatapathi Raju Nallapa, Vidya Nariyambut Murali, Scott Vincent Myers, MICKS ASHLEY ELIZABETH, NALLAPA VENKATAPATHI RAJU, NARIYAMBUT MURALI VIDYA, MYERS SCOTT VINCENT
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC, FORD GLOBAL TECH LLC

The disclosure relates to methods, systems, and apparatuses for autonomous driving vehicles or driving assistance systems and more particularly relates to vehicle radar perception and location. The vehicle driving system disclosed may include a storage media, a radar system, a location component and a driver controller. The storage media stores a map of roadways. The radar system is configured to generate perception information from a region near the vehicle. The location component is configured to determine a location of the vehicle on the map based on the radar perception information and other navigation related data. The drive controller is configured to control driving of the vehicle based on the map and the determined location.

Подробнее
Номер записи: 95
22-10-2019 дата публикации

Lane boundary detection data generation in virtual environment

Номер: US0010453256B2
Автор: Ashley Elizabeth Micks, Venkatapathi Raju Nallapa, Brielle Reiff, Vidya Nariyambut Murali, Sneha Kadetotad, MICKS ASHLEY ELIZABETH, NALLAPA VENKATAPATHI RAJU, REIFF BRIELLE, NARIYAMBUT MURALI VIDYA, KADETOTAD SNEHA, Micks, Ashley Elizabeth, Nallapa, Venkatapathi Raju, Reiff, Brielle, Nariyambut Murali, Vidya, Kadetotad, Sneha
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC, FORD GLOBAL TECH LLC, Ford Global Technologies, LLC

A method and an apparatus pertaining to generating training data. The method may include executing a simulation process. The simulation process may include traversing one or more virtual sensors over a virtual driving environment defining a plurality of lane markings or virtual objects that are each sensible by the one or more virtual sensors. During the traversing, each of the one or more virtual sensors may be moved with respect to the virtual driving environment as dictated by a vehicle-dynamic model modeling motion of a vehicle driving on a virtual road surface of the virtual driving environment while carrying the one or more virtual sensors. Virtual sensor data characterizing the virtual driving environment may be recorded. The virtual sensor data may correspond to what an actual sensor would produce in a real-world environment that is similar or substantially matching the virtual driving environment.

Подробнее
Номер записи: 96
21-07-2016 дата публикации

VIRTUAL SENSOR TESTBED

Номер: US20160210775A1
Автор: Arthur Alaniz, Vidya Nariyambut murali, Ashley Elizabeth Micks, Harpreetsingh Banvait, Sneha Kadetotad, ALANIZ ARTHUR, NARIYAMBUT MURALI VIDYA, MICKS ASHLEY ELIZABETH, BANVAIT HARPREETSINGH, KADETOTAD SNEHA
Принадлежит: Ford Global Technologies, LLC

A computing device comprising a processing circuit and a data storage medium. The computing device is programmed to receive virtual sensor data that represents data collected by a virtual sensor associated with autonomously operating a virtual vehicle in a virtual environment and process the virtual sensor data to identify a limitation of a real-world sensor. 1. A computing device comprising a processing circuit and a data storage medium , wherein the computing device is programmed to:receive virtual sensor data, wherein the virtual sensor data represents data collected by a virtual sensor associated with autonomously operating a virtual vehicle in a virtual environment;process the virtual sensor data to identify a limitation of a real-world sensor.2. The computing device of claim 1 , wherein the computing device is programmed to generate the virtual sensor data based at least in part on a virtual navigation of the virtual vehicle through the virtual environment.3. The computing device of claim 1 , wherein the virtual environment includes at least one object detected by the virtual sensor claim 1 , and wherein the virtual sensor data represents at least one of a relative position claim 1 , size claim 1 , and object type associated with the detected object.4. The computing device of claim 3 , wherein the computing device is programmed to identify the detected objected with an overlay displayed on a display screen.5. The computing device of claim 1 , wherein the virtual sensor is based at least in part on at least one autonomous driving sensor incorporated into an autonomous vehicle.6. The computing device of claim 1 , wherein the virtual sensor includes a virtual camera claim 1 , and wherein the virtual sensor data includes a virtual camera image.7. The computing device of claim 1 , wherein the virtual sensor includes a virtual camera claim 1 , and wherein the virtual sensor data includes a ray-traced image.8. The computing device of claim 1 , wherein processing the ...

Подробнее
Номер записи: 97
10-09-2019 дата публикации

Metal bridge detection systems and methods

Номер: US0010408937B2
Автор: Scott Vincent Myers, Ashley Elizabeth Micks, Sneha Kadetotad, Harpreetsingh Banvait, MYERS SCOTT VINCENT, MICKS ASHLEY ELIZABETH, KADETOTAD SNEHA, BANVAIT HARPREETSINGH, Myers, Scott Vincent, Micks, Ashley Elizabeth, Kadetotad, Sneha, Banvait, Harpreetsingh
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC, FORD GLOBAL TECH LLC, Ford Global Technologies, LLC

Example metal bridge detection systems and methods are described. In one implementation, a method receives LIDAR data from a LIDAR system mounted to a vehicle and receives camera data from a camera system mounted to the vehicle. The method analyzes the received LIDAR data and the camera data to identify a metal bridge proximate the vehicle. If a metal bridge is identified, the method adjusts vehicle operations to improve vehicle control as it drives across the metal bridge.

Подробнее
Номер записи: 98
13-06-2017 дата публикации

Drive history parking barrier alert

Номер: US0009676326B2
Автор: Venkatapathi Raju Nallapa, Harpreetsingh Banvait, Scott Vincent Myers, Ashley Elizabeth Micks, NALLAPA VENKATAPATHI RAJU, BANVAIT HARPREETSINGH, MYERS SCOTT VINCENT, MICKS ASHLEY ELIZABETH, Nallapa Venkatapathi Raju, Banvait Harpreetsingh, Myers Scott Vincent, Micks Ashley Elizabeth
Принадлежит: Ford Global Technologies, LLC, FORD GLOBAL TECH LLC

A driving assistance system includes a drive detection component, a presence component, and a notification component. The drive detection component is configured to determine that a vehicle or driver is exiting or preparing to exit a parking location. The presence component is configured to determine, from a drive history database, whether a parking barrier is present in front of or behind the parking location. The notification component is configured to provide an indication that the parking barrier is present to a human driver or an automated driving system of the vehicle.

Подробнее
Номер записи: 99
29-11-2018 дата публикации

Vehicle Radar Perception And Localization

Номер: US20180341273A1
Автор: Ashley Elizabeth Micks, Venkatapathi Raju Nallapa, Vidya Nariyambut Murali, Scott Vincent Myers, MICKS ASHLEY ELIZABETH, NALLAPA VENKATAPATHI RAJU, NARIYAMBUT MURALI VIDYA, MYERS SCOTT VINCENT, Micks, Ashley Elizabeth, Nallapa, Venkatapathi Raju, Nariyambut Murali, Vidya, Myers, Scott Vincent
Принадлежит:

The disclosure relates to methods, systems, and apparatuses for autonomous driving vehicles or driving assistance systems and more particularly relates to vehicle radar perception and location. The vehicle driving system disclosed may include a storage media, a radar system, a location component and a driver controller. The storage media stores a map of roadways. The radar system is configured to generate perception information from a region near the vehicle. The location component is configured to determine a location of the vehicle on the map based on the radar perception information and other navigation related data. The drive controller is configured to control driving of the vehicle based on the map and the determined location.

Подробнее
Номер записи: 100
11-01-2018 дата публикации

PEDESTRIAN DETECTION WHEN A VEHICLE IS REVERSING

Номер: US20180009378A1
Автор: Gurghian Alexandru Mihai, Karandikar Ramchandra Ganesh, Micks Ashley Elizabeth, Myers Scott Vincent
Принадлежит:

Techniques and implementations pertaining to detection of moving objects, such as pedestrians, when a vehicle moves in a rearward direction are described. A method may involve identifying a region of interest when a vehicle moves in a rearward direction. The method may involve detecting a moving object in the region of interest. The method may also involve determining whether a collision with the moving object by the vehicle moving in the rearward direction is likely. The method may further involve providing a human-perceivable signal responsive to a determination that the collision is likely. 1. A method , comprising:identifying a region of interest when a vehicle moves in a rearward direction;detecting a moving object in the region of interest;determining whether a collision with the moving object by the vehicle moving in the rearward direction is likely; andproviding a human-perceivable signal responsive to a determination that the collision is likely.2. The method of claim 1 , wherein the identifying of the region of interest comprises localizing the region of interest using one or more images captured by a rearward-facing camera in addition to drive history data claim 1 , one or more digital maps claim 1 , global positioning system (GPS) data claim 1 , data from one or more wirelessly-connected devices claim 1 , data from one or more wirelessly-connected sensors claim 1 , or any combination thereof.3. The method of claim 2 , wherein the identifying of the region of interest further comprises refining the localized region of interest using a light-detection-and-ranging (LIDAR) sensor claim 2 , a radar sensor claim 2 , an ultrasound sensor claim 2 , or any combination thereof.4. The method of claim 1 , wherein the detecting of the moving object in the region of interest comprises analyzing one or more images captured by a rearward-facing camera using a machine learning algorithm.5. The method of claim 4 , wherein the machine learning algorithm comprises a deep ...

Подробнее
Номер записи: 101
27-01-2022 дата публикации

Vehicle Radar Perception And Localization

Номер: US20220026919A1
Автор: Ashley Elizabeth Micks, Scott Vincent Myers, Venkatapathi Raju Nallapa, Vidya Nariyambut murali
Принадлежит: FORD GLOBAL TECHNOLOGIES LLC

The disclosure relates to methods, systems, and apparatuses for autonomous driving vehicles or driving assistance systems and more particularly relates to vehicle radar perception and location. The vehicle driving system disclosed may include a storage media, a radar system, a location component and a driver controller. The storage media stores a map of roadways. The radar system is configured to generate perception information from a region near the vehicle. The location component is configured to determine a location of the vehicle on the map based on the radar perception information and other navigation related data. The drive controller is configured to control driving of the vehicle based on the map and the determined location.

Подробнее
Номер записи: 102
11-01-2018 дата публикации

Virtual Sensor Data Generation for Bollard Receiver Detection

Номер: US20180011953A1
Автор: Banvait Harpreetsingh, Kadetotad Sneha, Micks Ashley Elizabeth, Myers Scott Vincent
Принадлежит:

The disclosure relates to methods, systems, and apparatuses for virtual sensor data generation and more particularly relates to generation of virtual sensor data for training and testing models or algorithms to detect objects or obstacles, such as bollard receivers. A method for generating virtual sensor data includes simulating a 3-dimensional (3D) environment that includes one or more objects, such as bollard receivers. The method includes generating virtual sensor data for a plurality of positions of one or more sensors within the 3D environment. The method includes determining virtual ground truth corresponding to each of the plurality of positions. The ground truth includes information about at least one bollard receiver within the sensor data. For example, the ground truth may include a height of the at least one of the parking barriers. The method also includes storing and associating the virtual sensor data and the virtual ground truth. 1. A method comprising:simulating a three-dimensional (3D) environment comprising one or more bollard receivers;generating virtual sensor data for a plurality of positions of one or more sensors within the 3D environment;determining virtual ground truth corresponding to each of the plurality of positions, the ground truth comprising information about at least one bollard receiver represented within the virtual sensor data; andstoring and associating the virtual sensor data and the virtual ground truth.2. The method of claim 1 , further comprising providing one or more of the virtual sensor data and the virtual ground truth for training or testing of a machine learning algorithm or model.3. The method of claim 2 , wherein training the machine learning algorithm or model comprises providing at least a portion of the virtual sensor data and corresponding virtual ground truth to train the machine learning algorithm or model to determine one or more of a height and a position of a bollard receiver represented within the portion of ...

Подробнее
Номер записи: 103
11-01-2018 дата публикации

Virtual Sensor-Data-Generation System and Method Supporting Development of Algorithms Facilitating Navigation of Railway Crossings in Varying Weather Conditions

Номер: US20180011954A1
Автор: Banvait Harpreetsingh, Kadetotad Sneha, Micks Ashley Elizabeth, Myers Scott Vincent
Принадлежит:

A method for generating training data is disclosed. The method may include executing a simulation process. The simulation process may include traversing a virtual, forward-looking sensor over a virtual road surface defining at least one virtual railroad crossing. During the traversing, the virtual sensor may be moved with respect to the virtual road surface as dictated by a vehicle-motion model modeling motion of a vehicle driving on the virtual road surface while carrying the virtual sensor. Virtual sensor data characterizing the virtual road surface may be recorded. The virtual sensor data may correspond to what a real sensor would have output had it sensed the road surface in the real world. 1. A method comprising:traversing, by a computer system, one or more virtual sensors over a virtual road surface in a simulation;recording, by the computer system, data corresponding to signals output by the one or more virtual sensors during the traversing, wherein the data characterizes a virtual railroad crossing in the virtual road surface; andannotating, by the computer system, the data with ground-truth data corresponding to the virtual railroad crossing.2. The method of claim 1 , wherein the virtual railroad crossing is one of a plurality of virtual railroad crossings distributed cross the virtual road surface claim 1 , each virtual railroad crossing of the plurality of virtual railroad crossings defining a structure sensible by the a first sensor of the one or more virtual sensors.3. The method of claim 2 , wherein the traversing comprises moving each of the one or more virtual sensors with respect to the virtual road surface as dictated by a vehicle-motion model modeling motion of a vehicle carrying the one or more virtual sensors and driving on the virtual road surface.4. The method of claim 3 , wherein the one or more virtual sensors comprise a forward-looking sensor positioned to sense a portion of the virtual road surface ahead of the vehicle.5. The method of ...

Подробнее
Номер записи: 104
11-01-2018 дата публикации

Predicting Vehicle Movements Based on Driver Body Language

Номер: US20180012093A1
Автор: Banvait Harpreetsingh, JAIN Jinesh J., Micks Ashley Elizabeth, Reiff Brielle
Принадлежит:

Systems, methods, and devices for predicting driver intent and future movements of a human driven vehicles are disclosed herein. A computer implemented method includes receiving an image of a proximal vehicle in a region near a vehicle. The method includes determining a region of the image that contains a driver of the proximal vehicle, wherein determining the region comprises determining based on a location of one or more windows of the proximal vehicle. The method includes processing image data only in the region of the image that contains the driver of the proximal vehicle to detect a driver's body language. 1. A computer implemented method comprising:determining a region of an image that contains a driver of a proximal vehicle based on a location of one or more windows of the proximal vehicle;processing image data only in the region of the image that contains the driver of the proximal vehicle to detect a driver's body language; anddetermining a vehicle maneuver for the vehicle based on the driver's body language.2. The computer implemented method of claim 1 , wherein detecting the driver's body language comprises detecting one or more of a head orientation claim 1 , a gaze direction claim 1 , and a gesture of the driver.3. The computer implemented method of claim 2 , further comprising accessing a database or model that correlates one or more of the head orientation claim 2 , the gaze direction claim 2 , and the gesture with one or more future vehicle movements for the proximal vehicle.4. The computer implemented method of claim 3 , wherein determining the vehicle maneuver based on the driver's body language comprises determining the vehicle maneuver based on one or more future vehicle movements of the proximal vehicle correlated with the driver's body language.5. The computer implemented method of claim 1 , further comprising locating the proximal vehicle within the image.6. The computer implemented method of claim 1 , wherein determining the region of the ...

Подробнее
Номер записи: 105
18-01-2018 дата публикации

Heads Up Display For Observing Vehicle Perception Activity

Номер: US20180017799A1
Автор: Ahmad Mohamed, Banvait Harpreetsingh, Micks Ashley Elizabeth, Nagraj Rao Nikhil
Принадлежит:

The present invention extends to methods, systems, and computer program products for a heads up display for observing vehicle perception activity. As a vehicle is operating, an occupant can see objects outside of the vehicle through the windshield. Vehicle sensors also sense the objects outside the vehicle. A vehicle projection system can project a heads up display for the sensed objects onto the windshield. The heads up display can be aligned with a driver's point of view so that graphical elements projected on a windshield overlap with their corresponding objects as seen through the windshield. As such, a driver (e.g., a test engineer) is able to view algorithm output (e.g., perception algorithm output) without having to look away from the road while driving. Accordingly, testing driver assist and autonomous driving features is both safer and more efficient. The heads up display can also be used as a driver assist. 1. A method for use at a vehicle , the method for presenting a display on a windshield , the method comprising:determining an occupant's point of view through the windshield;using vehicle sensors to sense an environment outside the vehicle;forming a display for objects of interest within the occupant's field of view in the environment; andaligning projection of the display on the windshield with the occupant's point of view.2. The method of claim 1 , wherein determining an occupant's point of view through the windshield comprises manually determining the occupant's point of view through the windshield.3. The method of claim 1 , wherein determining an occupant's point of view through the windshield comprises using sensors in the vehicle's cabin to automatically determining an occupant's field of view through the windshield.4. The method of claim 1 , wherein forming a display for objects of interest within the occupant's field of view comprises forming lane highlights for one or more lane boundaries on a roadway in the environment; andwherein aligning ...

Подробнее
Номер записи: 106
18-01-2018 дата публикации

Virtual Sensor-Data-Generation System And Method Supporting Development Of Vision-Based Rain-Detection Algorithms

Номер: US20180018527A1
Автор: Ashley Elizabeth Micks, Harpreetsingh Banvait, Jinesh J. Jain, Vidya Nariyambut murali
Принадлежит: FORD GLOBAL TECHNOLOGIES LLC

A method for generating training data is disclosed. The method may include executing a simulation process. The simulation process may include traversing a virtual camera through a virtual driving environment comprising at least one virtual precipitation condition and at least one virtual no precipitation condition. During the traversing, the virtual camera may be moved with respect to the virtual driving environment as dictated by a vehicle-motion model modeling motion of a vehicle driving through the virtual driving environment while carrying the virtual camera. Virtual sensor data characterizing the virtual driving environment in both virtual precipitation and virtual no precipitation conditions may be recorded. The virtual sensor data may correspond to what a real sensor would have output had it sensed the virtual driving environment in the real world.

Подробнее
Номер записи: 107
25-01-2018 дата публикации

REAR CAMERA STUB DETECTION

Номер: US20180022347A1
Автор: Gurghian Alexandru Mihai, Micks Ashley Elizabeth, Myers Scott Vincent, Walsh Alexandro
Принадлежит:

A method for detecting stubs or intersecting roadways includes receiving perception data from at least two sensors. The at least two sensors include a rear facing camera of a vehicle and another sensor. The perception data includes information for a current roadway on which the vehicle is located. The method includes detecting, based on the perception data, an intersecting roadway connecting with the current roadway. The method also includes storing an indication of a location and a direction of the intersecting roadway with respect to the current roadway. 1. A method comprising:receiving perception data from at least two sensors, the at least two sensors comprising a rear facing camera of a vehicle, wherein the perception data comprises information for a current roadway on which the vehicle is located;detecting, based on the perception data, an intersecting roadway connecting with the current roadway; andstoring an indication of a location and a direction of the intersecting roadway with respect to the current roadway.2. The method of claim 1 , wherein detecting the intersecting roadway comprises detecting one or more of: a gap in roadway markings claim 1 , a break in a shoulder for the current roadway claim 1 , or a variation or break in curb or barrier height.3. The method of claim 1 , wherein detecting the intersecting roadway comprises detecting using a deep neural network.4. The method of claim 1 , wherein the at least two sensors comprise the rear facing camera and one or more of a light detection and ranging (LIDAR) system claim 1 , a radar system claim 1 , an ultrasound sensing system claim 1 , or an infrared camera system.5. The method of claim 1 , wherein the direction indicates a side of the current roadway on which the intersecting roadway is located.6. The method of claim 1 , wherein storing the indication of the location and direction comprises uploading to a remote storage location accessible over a network.7. The method of claim 7 , further ...

Подробнее
Номер записи: 108
25-01-2018 дата публикации

REAR CAMERA LANE DETECTION

Номер: US20180025234A1
Автор: Gurghian Alexandru Mihai, Micks Ashley Elizabeth, Myers Scott Vincent, Walsh Alexandro
Принадлежит:

A method for determining lane information includes receiving perception data from at least two sensors, the at least two sensors including a rear facing camera of a vehicle. The method includes determining, based on the perception data, a number of lanes on a roadway within a field of view captured by the perception data using a neural network. The method includes providing an indication of the number of lanes to an automated driving system or driving assistance system. 1. A method comprising:receiving perception data from at least two sensors, the at least two sensors including a rear facing camera of a vehicle;determining, based on the perception data, a number of lanes on a roadway within a field of view captured by the perception data using a neural network; andproviding an indication of the number of lanes to an automated driving system or driving assistance system.2. The method of claim 1 , the method further comprising determining a current lane in which the vehicle is located using a neural network claim 1 , wherein the current lane corresponds to a lane position of the vehicle at a time when the perception data was obtained.3. The method of claim 1 , wherein the at least two sensors comprise the rear facing camera and one or more of a light detection and ranging (LIDAR) system claim 1 , a radar system claim 1 , an ultrasound sensing system claim 1 , or an infrared camera system.4. The method of claim 1 , further comprising determining claim 1 , based on the perception data claim 1 , road slope in one or more of a vertical direction or a horizontal direction.5. The method of claim 1 , further comprising determining one or more of a driving trajectory or collision avoidance options based on the number of lanes.6. The method of claim 1 , further comprising storing the indication of the number of lanes in a drive history for later access.7. The method of claim 1 , further comprising uploading the indication of the number of lanes to a remote storage location.8. ...

Подробнее
Номер записи: 109
25-01-2018 дата публикации

Using Virtual Data To Test And Train Parking Space Detection Systems

Номер: US20180025640A1
Автор: Banvait Harpreetsingh, JAIN Jinesh J., Joh Peter Gyumyeong, Kadetotad Sneha, Micks Ashley Elizabeth, Nariyambut Murali Vidya
Принадлежит:

The present invention extends to methods, systems, and computer program products for using virtual data to test and train parking space detection systems. Aspects of the invention integrate a virtual driving environment with sensor models (e.g., of a radar system) to provide virtual radar data in relatively large quantities in a relatively short amount of time. The sensor models perceive values for relevant parameters of a training data set. Relevant parameters can be randomized in the recorded data to ensure a diverse training data set with minimal bias. Since the driving environment is virtualized, the training data set can be generated alongside ground truth data. The ground truth data is used to annotate true locations, which are used to train a parking space classification algorithms to detect the free space boundaries. 1. A method for virtually testing parking space detection , the method comprising:creating a virtual environment, including one or more virtual parking spaces and a virtual vehicle with a virtual radar system;the virtual radar system generating virtual radar data indicating virtual object reflections from virtual objects within the virtual environment;classifying a virtual parking space as occupied or unoccupied based on the virtual radar data; anddetermining the accuracy of the classifications.2. The method of claim 1 , wherein classifying a virtual parking space as occupied or unoccupied based on the virtual radar data comprises a parking space classification algorithm classifying a parking space as occupied or unoccupied.3. The method of claim 1 , wherein creating a virtual environment comprises creating a virtual parking lot from simulation data.4. The method of claim 1 , further comprising accessing ground truth data indicating actual locations of one or more virtual vehicles within the virtual environment; andwherein determining the accuracy of the classifications comprises comparing the classifications to the ground truth data.5. The ...

Подробнее
Номер записи: 110
08-02-2018 дата публикации

Methods And Systems For Automatically Detecting And Responding To Dangerous Road Conditions

Номер: US20180037221A1
Автор: Banvait Harpreetsignh, Kadetotad Sneha, Micks Ashley Elizabeth, Myers Scott Vincent
Принадлежит:

A method for automatically detecting and safely traversing an accumulation of ice on an impending bridge. The method automatically identifies, by the vehicle, impending approach of the vehicle to a bridge and senses an accumulation of ice on the bridge. The method then calculates a speed of the vehicle needed to prevent longitudinal slip between the vehicle and the bridge, and automatically slows the vehicle at a rate sufficient to enable the vehicle to reach the calculated speed by the time it reaches the bridge. A corresponding system is also disclosed and claimed herein. 1. A method comprising:automatically identifying, by a vehicle, an impending traversal of the vehicle over a bridge;sensing, at the vehicle, at least one condition indicating an accumulation of ice on the bridge;calculating a speed of the vehicle needed to prevent longitudinal slip between the vehicle and the bridge; andautomatically slowing the vehicle at a rate sufficient to enable the vehicle to reach the calculated speed by the time it reaches the bridge.2. The method of claim 1 , wherein identifying the impending traversal further comprises using a global positioning system to determine a traveled route of the vehicle and a location of the vehicle on the traveled route.3. The method of claim 2 , wherein identifying the impending traversal further comprises determining claim 2 , using map data claim 2 , a location of the bridge on the traveled route.4. The method of claim 3 , wherein identifying the impending traversal further comprises determining a distance to the bridge by comparing the location of the vehicle to the location of the bridge along the traveled route.5. The method of claim 2 , further comprising automatically obtaining claim 2 , by the vehicle claim 2 , at least one of a current and historical weather report for a geographical area in which the bridge is located.6. The method of claim 1 , wherein sensing comprises sensing using at least one sensor selected from the group ...

Подробнее
Номер записи: 111
02-03-2017 дата публикации

MOTION COMPENSATION FOR ON-BOARD VEHICLE SENSORS

Номер: US20170061710A1
Автор: Micks Ashley Elizabeth, Saeger Martin
Принадлежит:

A method for improving the accuracy with which a road profile ahead of a vehicle may be determined. The method may include receiving a plurality of inputs corresponding to a plurality of on-board sensors corresponding to a vehicle. An on-board computer system may estimate motion of the vehicle. The on-board computer system may correct data corresponding to a forward-looking sensor of the plurality of on-board sensors by accounting for the motion of the vehicle. Accordingly, the on-board computer system may use the corrected data to produce more accurate information characterizing the driving environment ahead of the vehicle. This more accurate information may be used to better estimate the motion of the vehicle in the future as the vehicle encounters that driving environment, which may improve the corrections that may be applied to the data corresponding to the forward-looking sensor at that time. 1. A method comprising:receiving, by a computer system, a plurality of inputs corresponding to a plurality of sensors;estimating, by the computer system based on one or more inputs of the plurality of inputs, motion of a vehicle carrying the computer system and plurality of sensors; andcorrecting, by the computer system, data corresponding to one or more sensors of the plurality of sensors by accounting for the motion of the vehicle.2. The method of claim 1 , wherein at least one of the one or more sensors comprises a forward-looking sensor characterizing a driving environment ahead of the vehicle.3. The method of claim 2 , further comprising producing claim 2 , by the computer system claim 2 , information characterizing the driving environment ahead of the vehicle.4. The method of claim 3 , further comprising estimating claim 3 , by the computer system based at least in part on the information claim 3 , the motion of the vehicle at a future time when the driving environment ahead of the vehicle becomes a driving environment under the vehicle.5. The method of claim 3 , ...

Подробнее
Номер записи: 112
16-03-2017 дата публикации

Sensor-Data Generation in Virtual Driving Environment

Номер: US20170076019A1
Автор: Ashley Elizabeth Micks, Douglas Blue, Martin Saeger, Venkatapathi Raju Nallapa
Принадлежит: FORD GLOBAL TECHNOLOGIES LLC

A method for generating training data. The method may include executing a simulation process. The simulation process may include traversing one or more virtual sensors over a virtual road surface defining a plurality of virtual anomalies that are each sensible by the one or more virtual sensors. During the traversing, each of the one or more virtual sensors may be moved with respect to the virtual road surface as dictated by a vehicle-motion model modeling motion of a vehicle driving on the virtual road surface while carrying the one or more virtual sensors. Virtual sensor data characterizing the virtual road surface may be recorded. The virtual sensor data may correspond to what a real sensor would have output had it sensed the road surface in the real world.

Подробнее
Номер записи: 113
22-03-2018 дата публикации

ICE AND SNOW DETECTION SYSTEMS AND METHODS

Номер: US20180079424A1
Автор: Banvait Harpreetsingh, Kadetotad Sneha, Micks Ashley Elizabeth, Myers Scott Vincent, Rodrigues Ashok E.
Принадлежит:

Example ice and snow detection systems and methods are described. In one implementation, a method activates an ice and snow detection system in response to receiving weather data indicating a likelihood of ice or snow on a roadway near a vehicle. The method receives data from multiple vehicle sensors and analyzes the received data to identify ice or snow on the roadway. If ice or snow is identified on the roadway, the method adjusts vehicle operations and reports the ice or snow condition to a shared database. 1. A method comprising:activating an ice and snow detection system responsive to receiving weather data indicating a likelihood of ice or snow on a roadway proximate a vehicle;receiving data from a plurality of vehicle sensors;analyzing the received data to identify ice or snow on the roadway; and adjusting vehicle operations; and', 'reporting the ice or snow condition to a shared database., 'responsive to identification of ice or snow on the roadway2. The method of claim 1 , further comprising fusing the data received from the plurality of vehicle sensors.3. The method of claim 1 , wherein analyzing the received data to identify ice or snow on the roadway includes:determining a current height of the roadway surface;comparing the current height of the roadway surface to a previously recorded height of the roadway surface; anddetermining that ice or snow is present on the roadway if the current height of the roadway surface is greater than the previously recorded height of the roadway surface.4. The method of claim 1 , wherein analyzing the received data to identify ice or snow on the roadway includes:determining a current reflectivity of the roadway surface;comparing the current reflectivity of the roadway surface to a previously recorded reflectivity of the roadway surface; anddetermining that ice or snow is present on the roadway if the current reflectivity of the roadway surface is greater than the previously recorded reflectivity of the roadway surface.5. ...

Подробнее
Номер записи: 114
22-03-2018 дата публикации

METAL BRIDGE DETECTION SYSTEMS AND METHODS

Номер: US20180081057A1
Автор: Banvait Harpreetsingh, Kadetotad Sneha, Micks Ashley Elizabeth, Myers Scott Vincent
Принадлежит:

Example metal bridge detection systems and methods are described. In one implementation, a method receives LIDAR data from a LIDAR system mounted to a vehicle and receives camera data from a camera system mounted to the vehicle. The method analyzes the received LIDAR data and the camera data to identify a metal bridge proximate the vehicle. If a metal bridge is identified, the method adjusts vehicle operations to improve vehicle control as it drives across the metal bridge. 1. A method comprising:receiving LIDAR data from a LIDAR system mounted to a vehicle;receiving camera data from a camera system mounted to the vehicle;analyzing the received LIDAR data and the camera data to identify a metal bridge proximate the vehicle; andresponsive to identifying a metal bridge proximate the vehicle, adjusting vehicle operations to improve vehicle control as it drives across the metal bridge.2. The method of claim 1 , further comprising activating a metal bridge detection system responsive to receiving weather data indicating a likelihood of ice or snow proximate the vehicle.3. The method of claim 1 , further comprising receiving navigational information that indicates the existence of a bridge ahead of the vehicle.4. The method of claim 1 , further comprising reporting the existence of the metal bridge to a shared database.5. The method of claim 4 , wherein reporting the existence of the metal bridge to a shared database includes reporting a geographic location associated with the metal bridge.6. The method of claim 1 , wherein adjusting vehicle operations includes:determining the vehicle's longitudinal slip; andresponsive to determining a non-zero longitudinal slip, reducing the speed of the vehicle until the longitudinal slip is zero.7. The method of claim 1 , wherein the metal bridge is a metal grate bridge.8. The method of claim 7 , wherein at least a portion of the metal grate bridge includes a metal road surface that has apertures therethrough.9. The method of claim 7 , ...

Подробнее
Номер записи: 115
28-03-2019 дата публикации

Lane Boundary Detection Data Generation In Virtual Environment

Номер: US20190096128A1
Автор: Kadetotad Sneha, Micks Ashley Elizabeth, Nallapa Venkatapathi Raju, Nariyambut Murali Vidya, Reiff Brielle
Принадлежит:

A method and an apparatus pertaining to generating training data. The method may include executing a simulation process. The simulation process may include traversing one or more virtual sensors over a virtual driving environment defining a plurality of lane markings or virtual objects that are each sensible by the one or more virtual sensors. During the traversing, each of the one or more virtual sensors may be moved with respect to the virtual driving environment as dictated by a vehicle-dynamic model modeling motion of a vehicle driving on a virtual road surface of the virtual driving environment while carrying the one or more virtual sensors. Virtual sensor data characterizing the virtual driving environment may be recorded. The virtual sensor data may correspond to what an actual sensor would produce in a real-world environment that is similar or substantially matching the virtual driving environment. 1. A method , comprising:generating, by a processor via a computer simulation, a virtual driving environment;positioning, by the processor via the computer simulation, one or more virtual sensors within the virtual driving environment, the one or more virtual sensors modeled by the computer simulation and not comprising any physical component;traversing, by the processor via the computer simulation, the one or more virtual sensors within the virtual driving environment; andadjusting, by the processor according to a set of bias parameters via the computer simulation, the data to account for a weather condition, a time of a day having different lighting conditions, sensor aging and vehicle aging.2. The method of claim 1 , wherein the virtual driving environment comprises a virtual road surface having one or more driving lanes.3. The method of claim 2 , wherein the virtual road surface further comprises a plurality of lane markings corresponding to the one or more driving lanes claim 2 , each of the plurality of lane markings sensible by the one or more virtual ...

Подробнее
Номер записи: 116
19-04-2018 дата публикации

Roadway-Crossing-Anomaly Detection System and Method

Номер: US20180105009A1
Автор: Ashley Elizabeth Micks, Harpreetsingh Banvait, Scott Vincent Myers, Sneha Kadetotad
Принадлежит: FORD GLOBAL TECHNOLOGIES LLC

A method for improving the safety and comfort of a vehicle driving over a railroad track, cattle guard, or the like. The method may include receiving, by a computer system, one or more inputs corresponding to one or more forward looking sensors. The computer system may also receive data characterizing a motion of the vehicle. The computer system may estimate, based on the one or more inputs and the data, a motion of a vehicle with respect to a railroad track, cattle guard, or the like extending across a road ahead of the vehicle. Accordingly, the computer system may change a suspension setting, steering setting, or the like of the vehicle to more safely or comfortably drive over the railroad track, cattle guard, or the like.

Подробнее
Номер записи: 117
24-05-2018 дата публикации

SINKHOLE DETECTION SYSTEMS AND METHODS

Номер: US20180143631A1
Автор: Banvait Harpreetsingh, Gurghian Alexandru Mihai, Mahmoudieh Parsa, Micks Ashley Elizabeth, Myers Scott Vincent
Принадлежит:

Example sinkhole detection systems and methods are described. In one implementation, a method receives data from multiple sensors mounted to a vehicle and analyzes the received data to identify a sinkhole in a roadway ahead of the vehicle. If a sinkhole is identified, the method adjusts vehicle operations and reports the sinkhole to a shared database and/or another vehicle. 1. A method comprising:receiving data from a plurality of sensors mounted to a vehicle;analyzing, using one or more processors, the received data to identify a sinkhole in a roadway ahead of the vehicle; and adjusting vehicle operations; and', 'reporting the sinkhole to at least one of a shared database and another vehicle., 'responsive to identification of a sinkhole in the roadway2. The method of claim 1 , wherein the plurality of sensors include one or more of a Lidar sensor claim 1 , a radar sensor claim 1 , and a camera.3. The method of claim 1 , further comprising fusing the data received from the plurality of vehicle sensors.4. The method of claim 1 , wherein analyzing the received data to identify a sinkhole in the roadway includes detecting an area in the roadway that does not return Lidar ground plane points.5. The method of claim 1 , wherein analyzing the received data to identify a sinkhole in the roadway includes detecting an area in data from a camera that does not indicate a roadway surface.6. The method of claim 1 , wherein analyzing the received data to identify a sinkhole in the roadway includes detecting a sudden descent of another vehicle on the roadway.7. The method of claim 1 , wherein analyzing the received data to identify a sinkhole in the roadway includes detecting a sudden rise of a back of another vehicle on the roadway.8. The method of claim 1 , wherein analyzing the received data to identify a sinkhole in the roadway includes:receiving elevation data associated with the roadway ahead of the vehicle;determining an expected elevation of a second vehicle on the roadway ...

Подробнее
Номер записи: 118
21-06-2018 дата публикации

Automatic Vehicle Leak Detection

Номер: US20180173961A1
Автор: Banvait Harpreetsingh, JAIN Jinesh J., Jales Costa Bruno Sielly, Micks Ashley Elizabeth
Принадлежит:

A vehicle controller receives images from a camera upon arrival and upon departure. A location of the vehicle may be tracked and images captured by the camera may be tagged with a location. A departure image may be compared to an arrival image captured closest to the same location as the arrival image. A residual image based on a difference between the arrival and departure images is evaluated for anomalies. Attributes of the anomaly such as texture, color, and the like are determined and the anomaly is classified based on the attributes. If the classification indicates an automotive fluid, then an alert is generated. 1. A method comprising , by a vehicle controller:receiving an arrival image from a camera during parking at a parking location;receiving a departure image from the camera during departure from the parking location;identifying an anomaly according to an evaluation of the arrival image and the departure image; anddetermining that the anomaly indicates a fluid leak.2. The method of claim 1 , wherein identifying the anomaly according to the evaluation of the arrival image and the departure image comprises:generating a residual image according to a difference between the arrival image and the departure image; andidentifying the anomaly according to analysis of the residual image.3. The method of claim 2 , wherein identifying the anomaly according to the evaluation of the arrival image and the departure image comprises:performing image stabilization on a first output of the camera to obtain the arrival image; andperforming image stabilization on a second output of the camera to obtain the departure image.4. The method of claim 1 , wherein determining that the anomaly indicates the fluid leak comprises performing texture analysis of the anomaly.5. The method of claim 4 , wherein determining that the anomaly indicates the fluid leak comprises classifying a result of the texture analysis of the anomaly.6. The method of claim 1 , wherein identifying the anomaly ...

Подробнее
Номер записи: 119
12-07-2018 дата публикации

Generating Training Data for Automatic Vehicle Leak Detection

Номер: US20180197048A1
Автор: Banvait Harpreetsingh, JAIN Jinesh J., Jales Costa Bruno Sielly, Micks Ashley Elizabeth
Принадлежит:

A vehicle controller receives images from a camera upon arrival and upon departure. A location of the vehicle may be tracked and images captured by the camera may be tagged with a location. A departure image may be compared to an arrival image captured closest to the same location as the arrival image. A residual image based on a difference between the arrival and departure images is evaluated for anomalies. Attributes of the anomaly such as texture, color, and the like are determined and the anomaly is classified based on the attributes. If the classification indicates an automotive fluid, then an alert is generated. A machine learning algorithm for generating classifications from image data may be trained using arrival and departure images obtained by rendering of a three-dimensional model or by adding simulated fluid leaks to two-dimensional images. 1. A method comprising , by a computer system:generating a plurality of training data sets, each including an arrival image having a parking position in its field of view, a departure image corresponding the arrival image, and a classification of the departure image, a portion of the training data sets including departure images having simulated fluid spills; andtraining a machine learning model according to the training data sets to identify fluid leaks.2. The method of claim 1 , wherein generating the plurality of training data sets comprises claim 1 , for each training data set:defining a three-dimensional model of a parking scenario for the each training data set; andrendering the arrival image of the each training data set from the three-dimensional model from a point of view of a camera mounted to a vehicle in the parking scenario.3. The method of claim 2 , wherein generating the training data sets comprises claim 2 , for each training data set of the portion of the training data sets:adding a fluid spill model to the three dimensional model of the parking scenario for the each training data set to obtain a ...

Подробнее
Номер записи: 120
29-07-2021 дата публикации

Vehicle neural network training

Номер: US20210229680A1
Автор: Ashley Elizabeth Micks, Punarjay Chakravarty
Принадлежит: FORD GLOBAL TECHNOLOGIES LLC

A computer, including a processor and a memory, the memory including instructions to be executed by the processor to determine six degree of freedom (DoF) data for a first object in a first video image and generate a synthetic video image corresponding to the first video image including a synthetic object and a synthetic object label based on the six DoF data. The instructions can include further instructions to train a generative adversarial network (GAN) based on a paired first video image and a synthetic video image to generate a modified synthetic image and train a deep neural network to locate the synthetic object in the modified synthetic video image based on the synthetic object. The instructions can include further instructions to download the trained deep neural network to a computing device in a vehicle.

Подробнее
Номер записи: 121
21-07-2016 дата публикации

VIRTUAL AUTONOMOUS RESPONSE TESTBED

Номер: US20160210383A1
Автор: Alaniz Arthur, Banvait Harpreetsingh, JAIN Jinesh J., Kadetotad Sneha, Micks Ashley Elizabeth, Nariyambut Murali Vidya
Принадлежит: FORD GLOBAL TECHNOLOGIES, LLC

A computing device includes a processing circuit and a data storage medium, and is programmed to receive a user input representing a vehicle control action associated with operating a virtual vehicle in a virtual environment, virtually navigate the virtual vehicle through the virtual environment according to the vehicle control action, collect virtual sensor data, and process the virtual sensor data collected. 1. A computing device comprising a processing circuit and a data storage medium , wherein the computing device is programmed to:receive a user input representing a vehicle control action associated with operating a virtual vehicle in a virtual environment;virtually navigate the virtual vehicle through the virtual environment according to the vehicle control action;collect virtual sensor data; andprocess the virtual sensor data collected.2. The computing device of claim 1 , wherein the computing device is programmed to generate the virtual sensor data based at least in part on the virtual navigation of the virtual vehicle through the virtual environment.3. The computing device of claim 1 , wherein the computing device is programmed to generate calibration data from the virtual sensor data claim 1 , wherein the calibration data is uploaded to an autonomous vehicle.4. The computing device of claim 1 , wherein the computing device is programmed to virtually navigate the virtual vehicle through the virtual environment in real time.5. The computing device of claim 4 , wherein the virtual sensors are based at least in part on autonomous driving sensors incorporated into an autonomous vehicle.6. The computing device of claim 1 , wherein the vehicle control action includes controlling at least one of a virtual throttle system claim 1 , a virtual brake system claim 1 , and a virtual steering system.7. The computing device of claim 1 , wherein generating the virtual environment includes generating the virtual environment with random testing parameters.8. The computing ...

Подробнее
Номер записи: 122
19-07-2018 дата публикации

Generating Simulated Sensor Data For Training And Validation Of Detection Models

Номер: US20180203445A1
Автор: Gerardo Castro Marcos Paul, JAIN Jinesh J., Kadetotad Sneha, Liu Dongran, Micks Ashley Elizabeth, Nariyambut Murali Vidya
Принадлежит:

A scenario is defined that including models of vehicles and a typical driving environment. A model of a subject vehicle is added to the scenario and sensor locations are defined on the subject vehicle. Perception of the scenario by sensors at the sensor locations is simulated to obtain simulated sensor outputs. The simulated sensor outputs are annotated to indicate the location of obstacles in the scenario. The annotated sensor outputs may then be used to validate a statistical model or to train a machine learning model. The simulates sensor outputs may be modeled with sufficient detail to include sensor noise or may include artificially added noise to simulate real world conditions. 1. A method comprising , by a computer system:simulating perception of a 3D model by one or more sensors to obtain one or more sensor outputs such that the one or more sensor outputs simulate sensor noise;annotating the one or more sensor outputs according to locations of obstacles in the 3D model; andat least one of training and testing a model according to the one or more sensor outputs and the annotations.2. The method of claim 1 , wherein the one or more sensors are defined with respect to model of a subject vehicle;wherein the one or more sensors are defined by one or more camera locations; andwherein simulating perception of the 3D model by the one or more sensors comprises simulating detection of images of the 3D model from the one or more camera locations.3. The method of claim 1 , wherein the one or more sensors are defined with respect to a model of a subject vehicle;wherein the one or more sensors are defined by a RADAR (radio detection and ranging) sensor location; andwherein simulating perception of the 3D model by the one or more sensors comprises simulating a RADAR sensor output according to perception of the 3D model from the RADAR sensor location.4. The method of claim 1 , wherein the one or more sensors are defined with respect to a model of a subject vehicle;wherein ...

Подробнее
Номер записи: 123
26-07-2018 дата публикации

Training An Automatic Traffic Light Detection Model Using Simulated Images

Номер: US20180211120A1
Автор: Goh Madeline J., Micks Ashley Elizabeth, Moosaei Maryam, Nariyambut Murali Vidya, SMITH Simon Murtha
Принадлежит:

A scenario is defined that including models of vehicles and a typical driving environment as well as a traffic light having a state (red, green, amber). A model of a subject vehicle is added to the scenario and camera location is defined on the subject vehicle. Perception of the scenario by a camera is simulated to obtain an image. The image is annotated with a location and state of the traffic light. Various annotated images may be generated for difference scenarios, including scenarios lacking a traffic light or having traffic lights that do not govern the subject vehicle. A machine learning model is then trained using the annotated images to identify the location and state of traffic lights that govern the subject vehicle. 1. A method comprising , by a computer system:simulating perception of a 3D model having a traffic light model as a light source to obtain an image;annotating the image with a location and state of the traffic light model to obtain an annotated image; andtraining a model according to the annotated image.2. The method of claim 1 , wherein the 3D model includes a plurality of other light sources.3. The method of claim 1 , wherein the state of the traffic light model is one of red claim 1 , amber claim 1 , and green.4. The method of claim 1 , wherein simulating perception of the 3D model comprises simulating perception of the 3D model having one or more components of the 3D model in motion to obtain a plurality of images including the image;wherein annotating the image with the location and state of the traffic light model to obtain the annotated image comprises annotating the plurality of images with the state of the traffic light model to obtain a plurality of annotated images; andwherein training the model according to the annotated image comprises training the model according to the plurality of annotated images.5. The method of claim 1 , wherein training the model according to the annotated image comprises training a machine learning ...

Подробнее
Номер записи: 124
23-08-2018 дата публикации

Autonomous Driving At Intersections Based On Perception Data

Номер: US20180239361A1
Автор: Banvait Harpreetsingh, JAIN Jinesh J., Micks Ashley Elizabeth, Reiff Brielle
Принадлежит:

Systems, methods, and devices for predicting a driver's intention and future movements of a proximal vehicle, whether an automated vehicle or a human driven vehicle, are disclosed herein. A system for predicting future movements of a vehicle includes an intersection component, a camera system, a boundary component, and a prediction component. The intersection component is configured to determine that a parent vehicle is near an intersection. The camera system is configured to capture an image of the proximal vehicle. The boundary component is configured to identify a sub-portion of the image containing a turn signal indicator on the proximal vehicle. The prediction component is configured to predict future movement of the proximal vehicle through the intersection based on a state of the turn signal indicator. 120-. (canceled)21. A system comprising:an intersection component configured to determine that a parent vehicle is near an intersection;a camera system configured to capture an image of a proximal vehicle;a boundary component configured to identify a sub-portion of the image containing a turn signal indicator on the proximal vehicle;a turn signal component configured to process image data in the sub-portion of the image to determine the state of the turn signal indicator; anda prediction component configured to predict future movement of the proximal vehicle through the intersection based on a state of the turn signal indicator.22. The system of claim 21 , further comprising a previous state component configured to determine one or more previous states of the proximal vehicle based on wireless communications indicating the one or more previous states of the proximal vehicle claim 21 , wherein the prediction component is configured to predict future movements of the proximal vehicle based on the one or more previous states of the proximal vehicle.23. The system of claim 22 , wherein the wireless communication comprises one or more of a vehicle-to-vehicle (V2V) ...

Подробнее
Номер записи: 125
21-12-2017 дата публикации

Training Algorithm For Collision Avoidance Using Auditory Data

Номер: US20170364776A1
Автор: Banvait Harpreetsingh, Han Kyu Jeong, JAIN Jinesh J., Micks Ashley Elizabeth
Принадлежит:

A machine learning model is trained by defining a scenario including models of vehicles and a typical driving environment. A model of a subject vehicle is added to the scenario and sensor locations are defined on the subject vehicle. A perception of the scenario by sensors at the sensor locations is simulated. The scenario further includes a model of a parked vehicle with its engine running. The location of the parked vehicle and the simulated outputs of the sensors perceiving the scenario are input to a machine learning algorithm that trains a model to detect the location of the parked vehicle based on the sensor outputs. A vehicle controller then incorporates the machine learning model and estimates the presence and/or location of a parked vehicle with its engine running based on actual sensor outputs input to the machine learning model. 1. A method comprising:defining, by a computer system, a three dimensional (3D) model;simulating, by the computer system, two or more sensor outputs from sound from a parked vehicle with its engine running incident on two or more sensor locations of a subject vehicle in the 3D model; andtraining, by the computer system, a machine-learning model using a location of the parked vehicle in the 3D model and the two or more sensor outputs.2. The method of claim 1 , further comprising:defining on the subject vehicle one or more camera locations;simulating detection of images at the one or more camera locations; andtraining the machine-learning model using both the images and the two or more sensor outputs.3. The method of further comprising:defining on the subject vehicle a RADAR sensor location;simulating a RADAR sensor output according to the 3D model; andtraining the machine learning model using all of the images, the RADAR sensor output, and the two or more sensor outputs.4. The method of claim 3 , further comprising:defining on the subject vehicle a LIDAR sensor location;simulating a sequence of point clouds detected from the LIDAR ...

Подробнее
Номер записи: 126
28-11-2019 дата публикации

Predicting Vehicle Movements Based on Driver Body Language

Номер: US20190362168A1
Автор: Ashley Elizabeth Micks, Brielle Reiff, Harpreetsingh Banvait, Jinesh J. Jain
Принадлежит: FORD GLOBAL TECHNOLOGIES LLC

Systems, methods, and devices for predicting driver intent and future movements of a human driven vehicles are disclosed herein. A computer implemented method includes receiving an image of a proximal vehicle in a region near a vehicle. The method includes determining a region of the image that contains a driver of the proximal vehicle, wherein determining the region comprises determining based on a location of one or more windows of the proximal vehicle. The method includes processing image data only in the region of the image that contains the driver of the proximal vehicle to detect a driver's body language.

Подробнее
Номер записи: 127
20-07-2016 дата публикации

Virtual autonomous response testbed.

Номер: MX2016000873A
Автор: Arthur Alaniz, Ashley Elizabeth Micks, Harpreetsingh Banvait, Jinesh J Jain, Sneha Kadetotad, Vidya Nariyambut murali
Принадлежит: Ford Global Tech Llc

Un dispositivo de computación incluye un circuito de procesamiento y un medio de almacenamiento de datos, y está programado para recibir la entrada de un usuario que representa una acción de control del vehículo asociada con operar un vehículo virtual en un entorno virtual, navegar virtualmente con el vehículo virtual a través del entorno virtual de acuerdo con la acción de control del vehículo, recolectar datos de sensores virtuales, y procesar los datos recolectados por sensores virtuales.

Подробнее
Номер записи: 128
30-08-2017 дата публикации

Virtual sensor data generation for wheel stop detection

Номер: GB2547745A
Автор: Banvait Harpreetsingh, Elizabeth Micks Ashley, Raju Nallapa Venkatapathi, Vincent Myers Scott
Принадлежит: FORD GLOBAL TECHNOLOGIES LLC

Virtual sensor data is generated for training and testing models or algorithms to detect objects or obstacles, such as wheel stops or parking barriers. A method for generating virtual sensor data includes simulating a three-dimensional (3D) environment comprising one or more objects. The method includes generating virtual sensor data for a plurality of positions of one or more sensors within the 3D environment. The method includes determining virtual ground truth corresponding to each of the plurality of positions, wherein the ground truth includes information about at least one object within the virtual sensor data. The method also includes storing and associating the virtual sensor data and the virtual ground truth. Alternatively the method may include simulated conditions corresponding to each of the plurality of positions.

Подробнее
Номер записи: 129
24-09-2019 дата публикации

Predicting vehicle movements based on driver body language

Номер: US10423847B2
Автор: Ashley Elizabeth Micks, Brielle Reiff, Harpreetsingh Banvait, Jinesh J Jain
Принадлежит: FORD GLOBAL TECHNOLOGIES LLC

Systems, methods, and devices for predicting driver intent and future movements of a human driven vehicles are disclosed herein. A computer implemented method includes receiving an image of a proximal vehicle in a region near a vehicle. The method includes determining a region of the image that contains a driver of the proximal vehicle, wherein determining the region comprises determining based on a location of one or more windows of the proximal vehicle. The method includes processing image data only in the region of the image that contains the driver of the proximal vehicle to detect a driver's body language.

Подробнее
Номер записи: 130
14-03-2018 дата публикации

Using virtual data to test and train parking space detection systems

Номер: GB2553654A
Автор: Banvait Harpreetsingh, Elizabeth Micks Ashley, Gyumyeong Joh Peter, J Jain Jinesh, Kadetotad Sneha, Nariyambut Murali Vidya
Принадлежит: FORD GLOBAL TECHNOLOGIES LLC

Creating a virtual environment 200 including one or more virtual parking spaces 242A-F and a virtual vehicle 201 with a virtual radar system 217, the virtual radar system generating virtual radar data 212, classifying virtual parking spaces as occupied or unoccupied based on virtual radar data 203, determining the accuracy of the classifications 228. The parking spaces may be classified using a parking space classification algorithm 202, such as a neural network. The accuracy results may be used to update or generate training feedback for the parking space classification algorithm which may then be ported to a real vehicle. The virtual environment may be a three-dimensional (3D) virtual parking lot created from simulation data 206. The accuracy of the classifications may be determined by comparing them to ground truth data 207. The virtual parking spaces may be defined by virtual space markings 214A-241H. Testing/training the algorithm using simulated virtual data may be quicker and cheaper than real world testing/training.

Подробнее
Номер записи: 131
12-01-2018 дата публикации

Heads up display for observing vehicle perception activity.

Номер: MX2017009139A
Автор: Ahmad Mohamed, Banvait Harpreetsingh, Elizabeth Micks Ashley, Nagraj Rao Nikhil
Принадлежит: Ford Global Tech Llc

La presente invención se extiende a métodos, sistemas y productos de programas informáticos para una pantalla superpuesta para observar la actividad de percepción de un vehículo. A medida que se opera el vehículo, un ocupante puede ver los objetos fuera del vehículo a través del parabrisas. Los sensores del vehículo también detectan los objetos fuera del vehículo. Un sistema de proyección del vehículo puede proyectar una pantalla superpuesta para los objetos detectados sobre el parabrisas. La pantalla superpuesta puede alinearse con el punto de vista de un conductor de manera que los objetos gráficos proyectados en un parabrisas se superpongan con los objetos correspondientes vistos a través del parabrisas. En sí, un conductor (por ejemplo, un ingeniero de pruebas) es capaz de visualizar el resultado del algoritmo (por ejemplo, resultado del algoritmo de percepción) sin tener que quitar la vista del camino mientras conduce. Por consiguiente, las características de asistencia al piloto de pruebas y de conducción autónoma son más seguras y más eficientes. La pantalla superpuesta también puede utilizarse para asistir al conductor.

Подробнее
Номер записи: 132
14-06-2017 дата публикации

Predicting vehicle movements based on driver body language

Номер: GB2545321A
Автор: Banvait Harpreetsingh, Elizabeth Micks Ashley, J Jain Jinesh, Reiff Brielle
Принадлежит: FORD GLOBAL TECHNOLOGIES LLC

A system for predicting future movements of another vehicle includes, in the own vehicle, a camera system, a boundary component, a body language component, and a prediction component. The camera system captures an image of another vehicle behind the own vehicle. The boundary component identifies a sub-portion of the image corresponding to an area where a driver of the other vehicle is located. The body language component detects the driver's body language such as head orientation, eye gaze direction, changes in eye gaze direction, or gestures such as a raised hand and fingers or waved hand. The prediction component predicts future motion of the other vehicle by correlating the driver's body language with a library of corresponding likely maneuvers. The other vehicle may be located in the image, and the sub-portion can be identified on the basis of its windows.

Подробнее
Номер записи: 133
01-09-2020 дата публикации

Rear camera lane detection

Номер: US10762358B2
Автор: Alexandro Walsh, Alexandru Mihai Gurghian, Ashley Elizabeth Micks, Scott Vincent Myers
Принадлежит: FORD GLOBAL TECHNOLOGIES LLC

A method for determining lane information includes receiving perception data from at least two sensors, the at least two sensors including a rear facing camera of a vehicle. The method includes determining, based on the perception data, a number of lanes on a roadway within a field of view captured by the perception data using a neural network. The method includes providing an indication of the number of lanes to an automated driving system or driving assistance system.

Подробнее
Номер записи: 134
22-03-2018 дата публикации

Drive history parking barrier alert.

Номер: MX2016012409A
Автор: Banvait Harpreetsingh, Elizabeth Micks Ashley, Raju Nallapa Venkatapathi, Scott Myers Vincent
Принадлежит: Ford Global Tech Llc

Un sistema de asistencia de conducción que incluye un componente de detección de conducción, un componente de presencia y un componente de notificación. El componente de detección de conducción está configurado para determinar si un vehículo o un conductor están saliendo o preparándose para salir de un sitio de estacionamiento. El componente de presencia está configurado para determinar, de una base de datos de historial de conducción, si un tope de estacionamiento está presente en la parte delantera o trasera del sitio de estacionamiento. El componente de notificación está configurado para proporcionar una indicación de que el tope de estacionamiento está presente a un conductor humano o un sistema de conducción automatizada del vehículo.

Подробнее
Номер записи: 135
02-05-2018 дата публикации

Predicting vehicle movements based on driver body language.

Номер: MX2016014391A
Автор: Banvait Harpreetsingh, Elizabeth Micks Ashley, J Jain Jinesh, Reiff Brielle
Принадлежит: Ford Global Tech Llc

Se divulgan en este documento sistemas, métodos y dispositivos para predecir la intención del conductor y los movimientos futuros de vehículos conducidos por un humano. Un sistema para predecir los movimientos futuros de un vehículo incluye un sistema de cámaras, un componente de límites, un componente del lenguaje corporal y un componente de predicción. El sistema de cámaras está configurado para capturar una imagen de un vehículo. El componente de límites está configurado para identificar una subporción de la imagen o correspondiente a un área donde un conductor de un vehículo está ubicado. El componente del lenguaje corporal configurado para detectar un lenguaje corporal de un conductor. El componente de predicción configurado para predecir el movimiento futuro del vehículo en base al lenguaje corporal del conductor detectado por el componente del lenguaje corporal.

Подробнее
Номер записи: 136
17-03-2017 дата публикации

Virtual, road-surface-perception test bed.

Номер: MX2016012108A
Автор: Blue Douglas, Elizabeth Micks Ashley, Raju Nallapa Venkatapathi, Saeger Martin
Принадлежит: Ford Global Tech Llc

Un método para probar el desempeño de uno o más algoritmos de detección de anomalías. El método puede incluir obtener datos del sensor emitidos por un sensor virtual que modela el comportamiento de un sensor de imagen. Los datos del sensor pueden corresponder a un momento en el que el sensor virtual detectó una anomalía virtual definida dentro de una superficie de la carretera virtual. Uno o más algoritmos pueden aplicarse a los datos del sensor para producir al menos una dimensión percibida de la anomalía virtual. Posteriormente, el desempeño del uno o más algoritmos puede cuantificarse mediante la comparación de la al menos una dimensión percibida con al menos una dimensión real de la anomalía virtual como se define en la superficie de la carretera virtual.

Подробнее
Номер записи: 137
26-09-2018 дата публикации

Training an automatic traffic light detection model using simulated images

Номер: GB2560805A
Автор: Elizabeth Micks Ashley, J Goh Madeline, Moosaei Maryam, Murtha Smith Simon, Nariyambut Murali Vidya
Принадлежит: FORD GLOBAL TECHNOLOGIES LLC

A method of training a model comprises simulating perception of a 3D model having a traffic light model as a light source to obtain an image, annotating the image with a location and state of the traffic light model to obtain an annotated image, and training a machine-learning algorithm according to the annotated image. The 3D model includes a plurality of other light sources, and the state of the traffic light model is one of red, amber and green. The model may be trained to identify a state and location of an actual traffic light in a camera output, and to output whether the traffic light applies to a vehicle processing camera processing camera outputs in the real world. The annotated image may be an annotated first image, and the method may further comprise reading a configuration file defining locations of one or more components, generating a second 3D model according to the configuration file, simulating perception of the second 3D model to obtain a second image, which is annotated in the same way as the first, and then training the model according to both annotated images.

Подробнее
Номер записи: 138
20-06-2018 дата публикации

Sinkhole detection systems and methods

Номер: GB2557457A
Автор: Banvait Harpreetsingh, Elizabeth Micks Ashley, Mahmoudieh Parsa, Mihai Gurghian Alexandru, Vincent Myers Scott
Принадлежит: FORD GLOBAL TECHNOLOGIES LLC

A sinkhole detection system and method are provided for a vehicle 302. Data received from vehicle mounted sensors (106, 108, 110 see fig 1) is analysed. When a sinkhole 304 is identified in a road ahead of the vehicle 302, vehicle operations are adjusted and the hole is reported to a shared database and/or to another vehicle. The response preferably includes stopping or manoeuvring around the sinkhole. Reporting may include vehicle to vehicle communication. Sensing may include the use of radar, LIDAR and a camera and may rely on detecting a change in elevation of a vehicle in front. The invention reduces the likelihood of accidents and potential injury.

Подробнее
Номер записи: 139
12-09-2018 дата публикации

Generating simulated sensor data for training and validation of detection models

Номер: GB2560412A
Автор: Elizabeth Micks Ashley, J Jain Jinesh, Kadetotad Sneha, Liu Dongran, Nariyambut Murali Vidya, Paul Gerardo Castro Marcos
Принадлежит: FORD GLOBAL TECHNOLOGIES LLC

A method and system for generated simulated sensor data which includes simulation perception of a 3D model by one or more sensors to obtain one or more sensor outputs such that the one or more sensor outputs simulate sensor noise. The 3D model maybe a scenario 302 that includes models of vehicles and a typical driving environment where perception of the scenario by sensors at the sensor locations is simulated 306 to obtain simulated sensor outputs. The simulated sensor outputs are annotated 308 according to the location of obstacles in the 3D model. Annotating may include listing the actual locations and/or relative velocity of obstacles in a scenario, such as vehicles, pedestrians, signs, buildings etc. Locations and velocities may be included in the annotation relative to the position of the subject vehicle. The annotated sensor outputs may then be used 318 to validate a statistical model or to train a machine learning model 320. The simulated sensor outputs may be modelled with sufficient detail to include sensor noise or may include artificially added noise to simulate real world conditions.

Подробнее
Номер записи: 140
08-08-2024 дата публикации

Prädizieren von fahrzeugbewegungen anhand von fahrerkörpersprache

Номер: DE102016120507B4
Автор: Ashley Elizabeth Micks, Brielle Reiff, Harpreetsingh Banvait, Jinesh J. Jain
Принадлежит: FORD GLOBAL TECHNOLOGIES LLC

System, das umfasst:ein Kamerasystem, das ausgelegt ist, ein Bild eines proximalen Fahrzeugs aufzunehmen;eine Begrenzungskomponente, die ausgelegt ist, einen Teilabschnitt des Bildes zu identifizieren, der einem Bereich entspricht, in dem sich ein Fahrer des proximalen Fahrzeugs befindet,wobei die Begrenzungskomponente den Teilabschnitt des Bildes anhand einer Identifizierung eines oder mehrerer Fenster des proximalen Fahrzeugs identifiziert;eine Körpersprachenkomponente, die ausgelegt ist, eine Körpersprache eines Fahrers zu detektieren durch Verarbeiten von Bilddaten in dem Teilabschnitt des Bildes; undeine Prädiktionskomponente, die ausgelegt ist, eine zukünftige Bewegung des Fahrzeugs anhand der von der Körpersprachenkomponente detektierten Körpersprache des Fahrers zu prädizieren;wobei die Prädiktionskomponente ausgelegt ist, auf eine Datenbank oder ein Modell zuzugreifen, die bzw. das die von der Körpersprachenkomponente detektierte Körpersprache des Fahrers mit einer oder mehreren zukünftigen Fahrzeugbewegungen korreliert;wobei die Datenbank oder das Modell eine Geste mit einem aktuellen Fahrkontext korreliert, wobei der Fahrkontext ein Anhalten an einer Kreuzung, eine Annäherung an eine Kreuzung, Einfädeln in eine Fahrbahn, Verlassen einer Fahrbahn, Einfahren auf ein Parkplatzgelände oder Einparken in eine Parklücke, oder Verlassen eines Parkplatzgeländes oder einer Parklücke umfasst.

Подробнее
Номер записи: 141
22-08-2017 дата публикации

Virtual sensor data generation for wheel stop detection

Номер: US09740944B2
Автор: Ashley Elizabeth Micks, Harpreetsingh Banvait, Scott Vincent Myers, Venkatapathi Raju Nallapa
Принадлежит: FORD GLOBAL TECHNOLOGIES LLC

The disclosure relates to methods, systems, and apparatuses for virtual sensor data generation and more particularly relates to generation of virtual sensor data for training and testing models or algorithms to detect objects or obstacles, such as wheel stops or parking barriers. A method for generating virtual sensor data includes simulating a three-dimensional (3D) environment comprising one or more objects. The method includes generating virtual sensor data for a plurality of positions of one or more sensors within the 3D environment. The method includes determining virtual ground truth corresponding to each of the plurality of positions, wherein the ground truth includes information about at least one object within the virtual sensor data. The method also includes storing and associating the virtual sensor data and the virtual ground truth.

Подробнее
Номер записи: 142
01-08-2017 дата публикации

Parking obstruction locator and height estimator

Номер: US09718404B2
Автор: Ashley Elizabeth Micks, Harpreetsingh Banvait, Scott Vincent Myers, Venkatapathi Raju Nallapa
Принадлежит: FORD GLOBAL TECHNOLOGIES LLC

Systems, methods and apparatuses are disclosed for assessing whether a vehicle will make contact with an obstacle. The systems, methods, and apparatuses may include an obstacle sensing component configured to determine a location and a dimension of an obstacle, a vehicle sensing component configured to determine a height of a point of the vehicle relative to the ground, and a notification component configured to provide an indication of a presence of the obstacle to assist a human driver or an automated driving system in parking the vehicle without making contact with the obstacle.

Подробнее
Номер записи: 143