Traffic light estimation

Among other things, we describe techniques for traffic light estimation using range sensors. A planning circuit of a vehicle traveling on a first drivable region that forms an intersection with a second drivable region receives information sensed by a range sensor of the vehicle. The information represents a movement state of an object through the intersection. A traffic signal at the intersection controls movement of objects through the intersection. The planning circuit determines a state of the traffic signal at the intersection based, in part, on the received information. A control circuit controls an operation of the vehicle based, in part, on the state of the traffic signal at the intersection ...

AUTOMATICALLY PERCEIVING TRAVEL SIGNALS

Among other things, one or more travel signals are identified by analyzing one or more images and data from sensors, classifying candidate travel signals into zero, one or more true and relevant travel signals, and estimating a signal state of the classified travel signals. 1. An apparatus comprising:(a) an image processor configured to receive an image derived from signals of a sensor and to apply signal processing to the image to identify a representation of a travel signal in the image,(b) a classifier configured to receive information from the image processor that identifies the representation of the travel signal and to classify the representation of the travel signal,(c) an estimator configured to estimate a signal state of the travel signal, and(d) an output module to generate an alert or control a maneuver of the vehicle or both based on the estimated signal state.2. The apparatus of claim 1 , in which the classifiers configured to classify the representation of the travel signal as a true travel signal or not a true travel signal.3. The apparatus of claim 1 , in which the image processor is configured to analyze pixels of the image based on saturation or lightness or both.4. The apparatus of claim 1 , in which the image processor is configured to determine edges based on pixels and to generate a shape based on the edges.5. The apparatus of claim 4 , in which the image processor is configured to identify the representation of the travel signal based on one or more of the following criteria: edges claim 4 , shapes claim 4 , convexity claim 4 , sizes claim 4 , and solidness.6. The apparatus of claim 1 , in which the image processor identifies the representation of the travel signal based on matching characteristics of the representation of the travel signal to predefined criteria.7. The apparatus of claim 6 , in which the image processor identifies the representation of the travel signal based on modeling the predefined criteria probabilistically.8. The ...

TRAFFIC LIGHT ESTIMATION

Among other things, we describe techniques for traffic light estimation using range sensors. A planning circuit of a vehicle traveling on a first drivable region that forms an intersection with a second drivable region receives information sensed by a range sensor of the vehicle. The information represents a movement state of an object through the intersection. A traffic signal at the intersection controls movement of objects through the intersection. The planning circuit determines a state of the traffic signal at the intersection based, in part, on the received information. A control circuit controls an operation of the vehicle based, in part, on the state of the traffic signal at the intersection

Automatically perceiving travel signals

Among other things, one or more travel signals are identified by analyzing one or more images and data from sensors, classifying candidate travel signals into zero, one or more true and relevant travel signals, and estimating a signal state of the classified travel signals.

TRAFFIC LIGHT ESTIMATION

Among other things, we describe techniques for traffic light estimation using range sensors. A planning circuit of a vehicle traveling on a first drivable region that forms an intersection with a second drivable region receives information sensed by a range sensor of the vehicle. The information represents a movement state of an object through the intersection. A traffic signal at the intersection controls movement of objects through the intersection. The planning circuit determines a state of the traffic signal at the intersection based, in part, on the received information. A control circuit controls an operation of the vehicle based, in part, on the state of the traffic signal at the intersection ...

Automatically perceiving travel signals

Among other things, one or more travel signals are identified by analyzing one or more images and data from sensors, classifying candidate travel signals into zero, one or more true and relevant travel signals, and estimating a signal state of the classified travel signals.

Traffic light estimation

Among other things, we describe techniques for traffic light estimation using range sensors. A planning circuit of a vehicle traveling on a first drivable region that forms an intersection with a second drivable region receives information sensed by a range sensor of the vehicle. The information represents a movement state of an object through the intersection. A traffic signal at the intersection controls movement of objects through the intersection. The planning circuit determines a state of the traffic signal at the intersection based, in part, on the received information. A control circuit controls an operation of the vehicle based, in part, on the state of the traffic signal at the intersection.

Traffic light estimation

Among other things, we describe techniques for traffic light estimation using range sensors. A planning circuit of a vehicle traveling on a first drivable region that forms an intersection with a second drivable region receives information sensed by a range sensor of the vehicle. The information represents a movement state of an object through the intersection. A traffic signal at the intersection controls movement of objects through the intersection. The planning circuit determines a state of the traffic signal at the intersection based, in part, on the received information. A control circuit controls an operation of the vehicle based, in part, on the state of the traffic signal at the intersection.

Trajectory planning of vehicles using route information

Among other things, techniques are described for improving the trajectory estimates for an object in an environment. The technique includes receiving, by at least one processor, information indicating a presence of an object operating in an environment; determining, by the at least one processor, a trajectory of the object, the trajectory including at least a position, a speed, and a direction of travel of the object; determining, by the at least one processor, an expected route of the object, wherein the expected route is pre-planned and includes an expected future position of the object at a future time; comparing the trajectory of the object to the expected route of the object; and in accordance with the comparison that the trajectory of the object is consistent with the expected route of the object, updating the trajectory of the object based on the expected route of the object.

AUTOMATICALLY PERCEIVING TRAVEL SIGNALS

Among other things, one or more travel signals are identified by analyzing one or more images and data from sensors, classifying candidate travel signals into zero, one or more true and relevant travel signals, and estimating a signal state of the classified travel signals.

AUTOMATICALLY PERCEIVING TRAVEL SIGNALS

Among other things, one or more travel signals are identified by analyzing one or more images and data from sensors, classifying candidate travel signals into zero, one or more true and relevant travel signals, and estimating a signal state of the classified travel signals. 1. A method comprising:(a) causing a vehicle to drive autonomously on a road,(b) automatically detecting a travel signal and estimating a signal state of the travel signal, and(c) automatically controlling a maneuver of the vehicle based on the signal state.2. The method of claim 1 , in which the detecting the travel signal comprises identifying claim 1 , in an image derived from signals of a sensor claim 1 , a representation of the travel signal.3. The method of claim 1 , in which the identifying the representation of the travel signal comprises analyzing pixels of the image based on saturation or lightness or both.4. The method of claim 1 , in which the identifying the representation of the travel signal comprises determining edges based on pixels and generating a shape based on the edges.5. The method of claim 4 , in which the identifying the representation of the travel signal is based on one or more of the following criteria: edges claim 4 , shapes claim 4 , convexity claim 4 , sizes claim 4 , and solidness.6. The method of claim 1 , in which the identifying the representation of the travel signal is based on matching characteristics of the representation of the travel signal to predefined criteria.7. The method of claim 6 , in which the identifying the representation of the travel signal is based on modeling the predefined criteria by probabilistic distributions and inferring probabilistic scores.8. The method of claim 1 , in which the detecting the travel signal comprises determining a correspondence between the representation of the travel signal and a true travel signal.9. The method of claim 1 , in which the determining the correspondence is based on one or more of the following: a ...

Automatically perceiving travel signals

Among other things, one or more travel signals are identified by analyzing one or more images and data from sensors, classifying candidate travel signals into zero, one or more true and relevant travel signals, and estimating a signal state of the classified travel signals.

AUTOMATICALLY PERCEIVING TRAVEL SIGNALS

Among other things, one or more travel signals are identified by analyzing one or more images and data from sensors, classifying candidate travel signals into zero, one or more true and relevant travel signals, and estimating a signal state of the classified travel signals. 1. (canceled)2. A method comprising:causing a vehicle to drive autonomously on a road; identifying, in an image derived from signals of a sensor, a representation of the travel signal, the identifying being based on matching characteristics of the representation of the travel signal to predefined criteria;', 'estimating a signal state of the travel signal, the estimating comprising:', 'evaluating, use one or more sensors corresponding to the vehicle, a flow of traffic in a neighborhood proximate to the vehicle, and', 'determining, using the flow of traffic, the signal state of the travel signal; and, 'automatically detecting a travel signal, comprisingautomatically controlling a maneuver of the vehicle based on the signal state.3. The method of claim 2 , in which the identifying the representation of the travel signal further comprises analyzing pixels of the image based on saturation or lightness or both.4. The method of claim 2 , in which the identifying the representation of the travel signal further comprises determining edges based on pixels and generating a shape based on the edges.5. The method of claim 4 , in which the identifying the representation of the travel signal is based on one or more of the following criteria: edges claim 4 , shapes claim 4 , convexity claim 4 , sizes claim 4 , or solidness.6. The method of claim 2 , in which the identifying the representation of the travel signal is further based on matching characteristics of the representation of the travel signal to predefined criteria claim 2 , wherein the predefined criteria is modeled by probabilistic distributions and inferring probabilistic scores.7. The method of claim 2 , in which the estimating the signal state ...

AUTOMATICALLY PERCEIVING TRAVEL SIGNALS

Among other things, one or more travel signals are identified by analyzing one or more images and data from sensors, classifying candidate travel signals into zero, one or more true and relevant travel signals, and estimating a signal state of the classified travel signals. 1. A method comprising:(a) identifying, in an image derived from signals of a sensor, a representation of a travel signal,(b) determining a correspondence between the representation of the travel signal and a true travel signal, and(c) estimating a signal state of the true travel signal.2. The method of claim 1 , comprising identifying in the image a representation of another travel signal and determining that the representation of the other travel signal corresponds to a true travel signal.3. The method of claim 1 , in which the identifying the representation of the travel signal comprises analyzing pixels of the image based on saturation or lightness or both.4. The method of claim 1 , in which the identifying the representation of the travel signal comprises determining edges based on pixels and generating a shape based on the edges.5. The method of claim 1 , in which the identifying the representation of the travel signal is based on one or more of the following criteria: edges claim 1 , shapes claim 1 , convexity claim 1 , sizes claim 1 , and solidness.6. The method of claim 1 , in which the identifying the representation of the travel signal is based on matching characteristics of the representation of the travel signal to predefined criteria.7. The method of claim 6 , in which the identifying the representation of the travel signal is based on modeling the predefined criteria probabilistically.8. The method of claim 1 , in which the determining the correspondence is based on one or more of the following: a previously identified travel signal claim 1 , travel signal shapes claim 1 , travel signal colors claim 1 , travel signal positions claim 1 , travel signal configurations claim 1 , road ...

Automatically perceiving travel signals

Among other things, one or more travel signals are identified by analyzing one or more images and data from sensors, classifying candidate travel signals into zero, one or more true and relevant travel signals, and estimating a signal state of the classified travel signals.

TRAJECTORY PLANNING OF VEHICLES USING ROUTE INFORMATION

Among other things, techniques are described for improving the trajectory estimates for an object in an environment. The technique includes receiving, by at least one processor, information indicating a presence of an object operating in an environment; determining, by the at least one processor, a trajectory of the object, the trajectory including at least a position, a speed, and a direction of travel of the object; determining, by the at least one processor, an expected route of the object, wherein the expected route is pre-planned and includes an expected future position of the object at a future time; comparing the trajectory of the object to the expected route of the object; and in accordance with the comparison that the trajectory of the object is consistent with the expected route of the object, updating the trajectory of the object based on the expected route of the object. 1. A method comprising:receiving, by at least one processor, information indicating a presence of an object operating in an environment;determining, by the at least one processor, a trajectory of the object, the trajectory including at least a position, a speed, and a direction of travel of the object;determining, by the at least one processor, an expected route of the object, wherein the expected route is pre-planned and includes an expected future position of the object at a future time;comparing the trajectory of the object to the expected route of the object; andin accordance with the comparison that the trajectory of the object is consistent with the expected route of the object, updating the trajectory of the object based on the expected route of the object.2. The method of claim 1 , wherein determining the expected route of the object includes receiving route information from a server.3. The method of claim 1 , wherein the determination of the expected route is based on received route information from a transceiver or a mobile device associated with the object.4. The method of ...

AUTOMATICALLY PERCEIVING TRAVEL SIGNALS

Among other things, one or more travel signals are identified by analyzing one or more images and data from sensors, classifying candidate travel signals into zero, one or more true and relevant travel signals, and estimating a signal state of the classified travel signals.

DISTRIBUTED VEHICLE BODY SENSORS FOR EVENT DETECTION

Systems and techniques are described for event detection. A described system includes a vehicle body containing body regions, sensors, processor, and memory. The sensors can include at least one sensor positioned about at least one body region of the body regions. The at least one body region can be associated with a region event type. The memory can store instructions thereon that, when executed by the processor, cause the processor to perform operations which can include obtaining data associated with at least one sensor measurement from the at least one sensor, determining that the at least one sensor measurement is associated with the region event type, and determining that an event associated with the region event type occurred based on determining that the at least one sensor measurement is associated with the region event type and that the at least one body region is associated with the region event type.

Autonomous vehicle operation using acoustic modalities

Techniques for autonomous vehicle operation using acoustic modalities include using one or more acoustic sensors of a vehicle to receive acoustic waves from one or more objects. The acoustic waves have multiple wavelengths. The acoustic waves are clustered into one or more acoustic clusters based on the plurality of wavelengths. A particular acoustic cluster of the one or more acoustic clusters is selected based on signal processing of the one or more acoustic clusters. A particular object is associated with the particular acoustic cluster. An acoustic fingerprint of the particular object is generated based on the particular acoustic cluster. Characteristics of the particular object are determined based on the acoustic fingerprint of the particular object. A control circuit of the vehicle is used to operate the vehicle to avoid a collision with the particular object based on the characteristics of the particular object.

AUTONOMOUS VEHICLE OPERATION USING ACOUSTIC MODALITIES

Techniques for autonomous vehicle operation using acoustic modalities include using one or more acoustic sensors of a vehicle to receive acoustic waves from one or more objects. The acoustic waves have multiple wavelengths. The acoustic waves are clustered into one or more acoustic clusters based on the plurality of wavelengths. A particular acoustic cluster of the one or more acoustic clusters is selected based on signal processing of the one or more acoustic clusters. A particular object is associated with the particular acoustic cluster. An acoustic fingerprint of the particular object is generated based on the particular acoustic cluster. Characteristics of the particular object are determined based on the acoustic fingerprint of the particular object. A control circuit of the vehicle is used to operate the vehicle to avoid a collision with the particular object based on the characteristics of the particular object. 1. A method comprising:receiving, using one or more acoustic sensors of a vehicle, acoustic waves from one or more objects, wherein the acoustic waves have a plurality of wavelengths;clustering, using one or more processors of the vehicle, the acoustic waves into one or more acoustic clusters based on the plurality of wavelengths;selecting, using the one or more processors, a particular acoustic cluster of the one or more acoustic clusters based on signal processing of the one or more acoustic clusters;associating, using the one or more processors, a particular object of the one or more objects with the particular acoustic cluster;generating, using the one or more processors, an acoustic fingerprint of the particular object based on the particular acoustic cluster;determining, using the one or more processors, characteristics of the particular object based on the acoustic fingerprint of the particular object; andoperating, using a control circuit of the vehicle, the vehicle to avoid a collision with the particular object based on the characteristics ...

Trajectory planning of vehicles using route information

Thermal sensor data vehicle perception

Obtaining thermal sensor (thermal camera, infrared thermal sensor, thermal imaging) and non-thermal sensor (LiDAR, RADAR, camera, ultrasonic sensors) data, determining a perception parameter indicative of an object in the surrounding environment of the autonomous vehicle AV, and generating a trajectory based on the perception parameter. Perception parameter may indicate the state of the object (presence or potential obstacles). A reaction parameter may indicate an emergency reaction based on the thermal sensor data. The object may be an agent (other vehicles, animals, road users, pedestrians, cyclists). Perception parameter may include a feature (light, doorknob, window frame, window). Object may be a driving surface. Thermal sensor data may be a thermal reflection of the object. Object trajectory may be predicted. Representation of thermal sensor data may be overlaid onto a 3D reconstruction of the object for estimating the location of the object and the object trajectory.

Traffic light estimation

Distributed vehicle body sensors for event detection

Verteilte fahrzeugkarosseriesensoren zur ereignisdetektion

Systeme und Techniken zur Ereignisdetektion werden beschrieben. Ein beschriebenes System beinhaltet eine Fahrzeugkarosserie, die Karosseriegebiete, Sensoren, einen Prozessor und einen Speicher enthält. Die Sensoren können wenigstens einen Sensor beinhalten, der bei wenigstens einem Karosseriegebiet der Karosseriegebiete positioniert ist. Das wenigstens eine Karosseriegebiet kann mit einem Gebietsereignistyp assoziiert sein. Der Speicher kann Anweisungen darin speichern, die bei Ausführung durch den Prozessor den Prozessor zum Durchführen von Operationen veranlassen, die Folgendes beinhalten können: Erhalten von Daten, die mit wenigstens einer Sensormessung assoziiert sind, von dem wenigstens einen Sensor, Bestimmen, dass die wenigstens eine Sensormessung mit dem Gebietsereignistyp assoziiert ist, und Bestimmen, dass ein mit dem Gebietsereignistyp assoziiertes Ereignis stattgefunden hat, basierend auf Bestimmen, dass die wenigstens eine Sensormessung mit dem Gebietsereignistyp assoziiert ist und dass das wenigstens eine Karosseriegebiet mit dem Gebietsereignistyp assoziiert ist.

Traffic light estimation

Information is sensed by a range sensor (e.g. LiDAR or RADAR) on a vehicle (e.g. autonomous vehicle 100) traveling on a first drivable region 1302, 1316 that forms an intersection with a second drivable region 1304, 1306. Traffic signal 1318 controls the intersection. An onboard planning circuit uses the information to determine movement states of a first object on the first region and a second object 1328 on the second region - each movement state comprising a stationary or mobile state and a movement direction. The planning circuit determines a traffic signal state based on at least one of the movement states; determines a traffic delay at the intersection (e.g. from object speed profiles); and generates data for controlling an operation of the vehicle (e.g. stopping or travelling through the intersection) based on the traffic signal state and traffic delay. If the traffic signal permits the vehicle to proceed but the likelihood of the second object stopping is low, the vehicle may be controlled to travel through the intersection before or after the second object.