用于显示屏幕面板的交通智慧出行预约图形用户界面

Collaborative loading and transporting system and method for unmanned transportation of mine

The invention discloses a cooperative loading and transporting system and method for mine unmanned transportation, and belongs to the technical field of intelligent mine mining. Comprising a carrying equipment remote control subsystem, a vehicle-mounted automatic driving subsystem, a vehicle-ground wireless communication system, an unmanned mine car and an unmanned forklift. The system has the advantages that the remote driving technology is more mature, the system complexity and cost are lower, and the system is more suitable for fine loading operation; one person operates a plurality of vehicles, so that the labor cost is saved; switching between an automatic driving mode and a remote driving mode can be achieved, switching of manipulated equipment can be achieved when remote driving is activated, working modes and equipment are flexibly selected, and operation tasks are safe and efficient; a path planning module and modes of augmented reality visualization, panoramic images and the like ...

AGV number static decision-making method

The invention discloses an AGV number static decision-making method. Firstly, a scene working time domain is divided into a plurality of sub-domains, then all tasks generated in a single sub-domain are divided into a plurality of task groups according to a certain criterion, and by estimating execution time consumption of all the tasks in a single group and cooperating with energy consumption, speed and task execution sequence constraints of the AGVs, the static number of the AGVs needed for executing all the tasks in the group is estimated and calculated. On the premise that the influence of dynamic factors on AGV number adjustment is not considered, the system decides the corresponding number of AGVs to circularly execute operation on all tasks in the corresponding task group according to an estimation result until the tasks in the group are all completed. Based on the characteristics of large task quantity, complex task demand, uncertain task generation time and the like of the operation ...

Control method for linkage of vehicle road and central control dispatching system

The invention provides a control method for linkage of a vehicle road and a central control scheduling system, and the method comprises the steps: collecting the state data and reservation order data of a vehicle in real time through the central control scheduling system, carrying out the matching of an order and the vehicle through the central control scheduling system, and controlling the order receiving of the vehicle through setting a maximization function. Reasonable scheduling of vehicles can be realized, the vehicle utilization rate is improved, and the operation cost is saved.

Underwater dynamic target state prediction method and device based on T-S fuzzy

The invention discloses an underwater dynamic target state prediction method and device based on T-S fuzzy, and the method comprises the steps: collecting an input variable, used for T-S fuzzy reasoning, of an underwater dynamic target at a t-1 moment, and carrying out the extended Kalman filtering at the t-1 moment through a fused underwater dynamic target motion model represented by a formula (6), in the formula, Xt and Xt-1 represent state vectors of the underwater dynamic target at the t moment and the t-1 moment respectively, u represents a process noise vector of an input variable, Yt represents an output vector of a motion model at the t moment, Amix and Bmix are a state transition matrix and an input matrix respectively, and t = t + 1; c represents a preset relation matrix of the output vector Yt and the state vector Xt. According to the method, the state of the underwater dynamic target is predicted more accurately, and the requirements of an underwater dynamic target tracking ...

Soil parameter estimation method and device based on ground mechanical characteristics of tracked vehicle

The invention discloses a soil parameter estimation method and device based on tracked vehicle ground mechanical characteristics, and the method comprises the steps: S10, collecting the pose information Pobs of a tracked vehicle in a preset time period [(j-N) * T, t], and obtaining an observation information sequence; the left side track slip rate al, the right side track slip rate ar and the slip angle alpha of the tracked vehicle are obtained, and then the traction force F of a single side track of the tracked vehicle is obtained; and S30, according to the left side track slip rate al, the right side track slip rate ar and the slip angle alpha of the tracked vehicle, a cohesion parameter c, an internal friction angle phi and a shear modulus k are obtained. The soil parameters estimated by the method are high in accuracy.

Intelligent vehicle global optimal trajectory planning method and system based on dynamic planning

The invention discloses an intelligent vehicle global optimal trajectory planning method and system based on dynamic planning, and the method comprises the steps: 1, converting a road environment in map information from a Cartesian coordinate system to a Frenet coordinate system according to the map information, vehicle chassis parameter information and starting point and terminal point pose information, carrying out the discretization of a state space, and carrying out the calculation of the state space; establishing a first optimal control problem model according to the trajectory planning task, and solving an optimal control problem by adopting a dynamic planning method to obtain a path point sequence of a global optimal path; and 2, state space discretization is performed according to the path point sequence and the kinetic parameter information of the vehicle, a second optimal control problem model is established by referring to a trajectory planning task, the optimal control problem ...

Taxi scheduling method and system based on multiple vehicle types and empty vehicle rebalance

The invention discloses a taxi scheduling method based on multiple vehicle types and empty vehicle rebalance, and the method comprises the steps: S1, obtaining the riding request information of a passenger and the real-time state of a vehicle, and carrying out the distribution of a vehicle in an empty state at intervals; s2, defining a decision network according to the riding request information and the real-time state of the vehicle; s3, defining a vehicle maximization revenue function in the decision network; s4, further defining constraint conditions in the decision network; and S5, scheduling the vehicles based on the vehicle maximization revenue function and the constraint condition. According to the invention, through distribution of multiple types of vehicles and rebalance scheduling of empty vehicles, the requirements of passengers can be met while the vehicle using efficiency is improved, the travel experience of the passengers is improved, and the driving cost of the taxis is ...

Visual SLAM (Simultaneous Localization and Mapping) system and method for autonomous vehicle

The invention discloses a visual SLAM (Simultaneous Localization and Mapping) system and method for an autonomous vehicle. The system comprises an image preprocessing module, a multi-target tracking module, a visual odometer module, an object state updating module and a rear-end optimization module. The method comprises the following steps: S1, preprocessing an image through an instance segmentation network; s2, judging the dynamic state and the static state of the object; s3, estimating the pose of the initial camera; s4, removing the dynamic object; and S5, executing an optimization strategy on the image key frame. The method has the beneficial effects that in a visual image, efficient dynamic object filtering can be realized, mapping ghosts are effectively reduced, the accuracy and robustness of positioning are improved, and the applicability of an automatic driving vehicle in a dynamic environment can be improved.

Multi-vehicle operation scheduling method, system and equipment for deep sea mine collection vehicles and medium

The invention discloses a multi-car operation scheduling method, system and device for deep sea mine cars and a medium. The method comprises the steps that the distance and the relative angle between a mining ship and the mass center position of each sub mineral exploitation area are calculated; taking the mining ship as the center of a circle, performing fan-shaped division on a mining area, and constructing an operation area division optimization problem of the mining cars by taking the minimum total operation time of all the mining cars as a target; solving the optimization problem to obtain a fan-shaped region corresponding to each mine car set; generating a task execution sequence table of the mine cars according to the sub-mineral exploitation areas covered by the fan-shaped areas corresponding to the mine cars and the corresponding relative angles of the sub-mineral exploitation areas; and each mine car is controlled to operate according to the corresponding task execution sequence ...

Intelligent real-time scheduling method and device for oil-electricity mixed truck in strip mine

The invention discloses an intelligent real-time scheduling method and device for an oil-electricity hybrid truck in a strip mine, and the method comprises the steps: receiving a truck scheduling application which comprises an empty truck scheduling application and a heavy truck scheduling application; carrying out empty vehicle optimal scheduling calculation on the truck set which sends the empty vehicle scheduling application; judging whether the residual energy quantity of each truck can complete the whole cycle of the empty truck scheduling and the next link of heavy truck scheduling or not, and if the truck set meets the energy quantity requirement, generating a scheduling instruction to be executed by the truck; if not, forming a new truck set by the trucks meeting the energy quantity requirement; forming a dispatching truck set for trucks which do not meet the energy quantity requirement, and instructing to charge energy; and establishing a total objective function for the truck ...

Combined navigation positioning method, device and system based on asynchronous differential positioning technology

The invention discloses a combined navigation positioning method, device and system based on an asynchronous differential positioning technology, and the method comprises the steps: employing an asynchronous RTK technology, carrying out the double-difference processing based on the observation data received by a user side at the current moment and the observation data received by a reference station at the historical moment, and obtaining a double-difference observation value; according to the received INS data, calculating to obtain an INS navigation positioning result of a user side and a predicted double-difference distance based on asynchronization; and calculating according to the double-difference observation value and the predicted double-difference distance to obtain information, performing Kalman filtering estimation, and compensating a navigation positioning result of the INS of the user side to obtain a non-synchronous RTK and INS combined navigation positioning result of the ...

Multi-agent reinforcement learning Internet of Vehicles calculation unloading method

The invention discloses a multi-agent reinforcement learning Internet of Vehicles calculation unloading method. The method comprises the following steps: S1, constructing a system model; s2, constructing a communication model; s3, constructing a task and calculation model; s4, constructing an energy consumption model; step S5, constructing an optimization model and establishing a Markov decision process; s6, performing neural network training on the optimization model by using an MADDPG algorithm; and step S7, deploying the trained network to each agent. According to the invention, the service vehicle and the MEC server in the Internet of Vehicles system are also used as agents in reinforcement learning to make a decision of resource allocation, and each agent obtains the own strategy network by using a multi-agent reinforcement learning mode; and each agent can quickly output own action according to the current local information without excessive communication, can cope with a quickly ...

Multi-scene crowd counting method and device based on multi-modal fusion

The invention discloses a multi-modal fusion-based multi-scene crowd counting method and device. The method comprises the following steps of: shooting paired pictures by using paired infrared thermal imagers and visible light cameras; calculating a real crowd density map of each picture to obtain a data set; training a crowd counting network by using the data set; wherein the crowd counting network comprises a front-end network for fusing the infrared image and the visible light image to obtain a fused image, and a rear-end network for obtaining a crowd density map based on the fused image; the step of training the crowd counting network through the data set comprises the steps that a fusion loss function corresponding to the front-end network, a crowd counting loss function corresponding to the rear-end network and a joint training loss function jointly corresponding to the front-end network and the rear-end network are set, and when the loss functions converge, corresponding parameters ...

Unmanned heavy-duty vehicle for surface mine and path tracking control method and device of unmanned heavy-duty vehicle

The invention discloses a surface mine unmanned heavy-load vehicle and a path tracking control method and device thereof, and the method comprises the following steps: a forward path tracking step: controlling the path tracking control of the surface mine heavy-load vehicle when the surface mine heavy-load vehicle moves forward by using a new Stanley controller according to preset path information and vehicle state information, the new Stanley controller considers the time lag characteristic of a vehicle steering gear, the vehicle size and the forward running speed; and a retreating path tracking step: a new rear wheel feedback controller is used for controlling path tracking control during retreating of the heavy-duty vehicle of the surface mine, and the new rear wheel feedback controller considers the time lag characteristic of a vehicle steering gear, the vehicle size and the retreating running speed. According to the invention, path tracking control during forward and backward movement ...

Structured road vehicle trajectory planning method and system based on reinforcement learning

The invention discloses a structured road vehicle trajectory planning method based on reinforcement learning, and the trajectory planning method based on reinforcement learning improves the safety of trajectory planning by constructing a driving risk field and incorporating a risk index into an optimization function. The initial trajectory is solved through the intelligent agent, so that the calculation efficiency of trajectory planning in a time-space domain is improved; and trajectory optimization is performed based on the trajectory initial solution through the trajectory optimization model, so that the optimality and feasibility of the generated trajectory are ensured.

Crawler sliding parameter real-time estimation method and system based on sliding-mode observer

The invention discloses a real-time estimation method and system for sliding parameters of a crawler based on a sliding-mode observer, and the method comprises the steps: judging the driving working condition to which the vehicle state at the current moment belongs according to the real-time yaw angle of the crawler and a flag bit corresponding to the driving working condition of the crawler at the previous moment, and outputting the corresponding flag bit; if the flag bit corresponding to the current vehicle driving working condition is inconsistent with the flag bit corresponding to the vehicle driving working condition at the previous moment, driving working condition switching occurs, an observation value resetting strategy is executed, and a reset tracked vehicle sliding parameter estimated value at the previous moment is output; and carrying out real-time estimation on the sliding parameters of the crawler at the current moment. According to the method, the sliding parameters of the ...

Annular underwater robot and control method thereof

The invention discloses an annular underwater robot and a control method thereof.The annular underwater robot comprises an annular robot body, the hollow part of the robot body is a water guide groove, and a plurality of propellers and a plurality of steering engines are arranged in the water guide groove. According to different operation modes, different control strategies are used, and the stealth, maneuverability and cruising ability are improved by adopting the annular underwater robot provided by the invention.

High-adaptability multi-sensor weighted fusion SLAM system and method

The invention discloses a high-adaptability multi-sensor weighted fusion SLAM system and method, and belongs to the technical field of data processing. The system comprises a data preprocessing module, a tight coupling front-end module and a mapping module. According to the multi-sensor fusion SLAM system provided by the invention, the advantages of a plurality of sensors are utilized to make up the respective defects, a weight distribution strategy is provided, weight distribution is implemented according to initialization detection, degradation detection and vehicle slip detection, weighted joint optimization is performed, the effect of nonlinear optimization is improved, the adaptability to the environment is high, and the method is suitable for large-scale popularization and application. The method can cope with the problems of laser radar degradation environment, vehicle slippage working condition, instability in the initial stage of mapping and the like, and is stable in positioning ...

Manufacturing method of aluminum alloy mold and aluminum alloy mold

The invention discloses a manufacturing method of an aluminum alloy mold and the aluminum alloy mold, in the manufacturing method of the aluminum alloy mold, the aluminum alloy mold is produced by an aluminum casting process, the aluminum alloy mold is used for producing an automobile composite material part, and the automobile composite material part is an exterior part or an interior part. The automobile composite material part is used for verifying modeling or verifying functions of a sample automobile, and the automobile composite material part is produced in the following mode that the surface of the aluminum alloy mold is covered with a composite material, and the composite material is taken down from the aluminum alloy mold after being naturally air-dried and solidified.

Emergency connection scheduling system and method of intelligent network connection bus

The invention discloses an emergency connection scheduling system and method for an intelligent network connection bus, and belongs to the technical field of intelligent bus emergency scheduling. The system comprises a scheduling platform and a vehicle-mounted system which is in communication connection with the scheduling platform and is installed on a vehicle, and the scheduling platform comprises a first information interaction device, a line map, a state monitoring device, an information processor and a storage device; the vehicle-mounted system comprises a second information interaction device, a positioning device, a vehicle-mounted display screen and a sensor. The method has the following beneficial effects that the vehicle resource utilization rate is improved; the overall cost is reduced by improving the passenger carrying rate of the bus, and intelligent network connection bus dispatching of various types of buses is achieved. Normal standby of vehicles of different types in each ...

Multi-line laser radar positioning method and system based on dynamic obstacle removal

The invention discloses a multi-line laser radar positioning method based on dynamic obstacle removal. The method comprises the following steps: collecting a global laser point cloud; detecting and filtering dynamic point clouds; extracting feature points and acquiring a speedometer pose; correcting the pose based on loopback detection; establishing a global high-precision point cloud map of the filtered dynamic point cloud; driving again to collect the point cloud; extracting feature points of the current frame and establishing a sliding window local map; solving the initial pose of the current frame relative to the local map; projecting the feature points of the current frame to a local map; eliminating the dynamic point cloud of the local map; and correcting the initial pose through global map matching so as to obtain accurate positioning. The multi-line laser radar positioning method has the beneficial effects that the laser positioning precision and robustness can be improved through ...

Sensor structure multiplexing design method and device, computer equipment and storage medium

The invention discloses a sensor structure multiplexing design method and device, computer equipment and a storage medium, and the method comprises the steps: evaluating each function according to function complexity, calling frequency and estimated configuration cost, and determining a function design sequence; constructing a sensor configuration design optimization model for balancing perception performance and system cost, and solving based on various multi-objective optimization algorithms; traversing all functions according to function design sorting based on sensor structure multiplexing; and carrying out redundancy elimination on the sensor configuration scheme. On the premise that multiple function detection requirements are met at the same time, the number of sensors can be reduced, the utilization rate of sensor hardware resources is improved, redundant waste in design is reduced, and the design cost is saved.

Man-machine multi-node collaborative semantic laser SLAM system and method

The invention discloses a man-machine multi-node collaborative semantic laser SLAM (Simultaneous Localization and Mapping) method. The method comprises the following steps: step 1, setting a node end, a collaborative end and a server end; 2, collecting point cloud data, extracting semantic information, and constructing a local semantic map; step 3, the server performs semantic feature matching, and generates a map fusion matrix according to the pose and semantic information; 4, fusing each local semantic map through the map fusion matrix, and establishing a global map; 5, transmitting the global map to the node end and the cooperation end; 6, the node end extracts the features again to correct the global map pose; and step 7, the cooperation end collects the geometric truth value of the map area and uploads the geometric truth value to the server end to assist in optimizing the global map. The method has the beneficial effects that the collaborative global map is constructed according to ...

V2X task unloading matching method and system fusing collaborative filtering and feedback

The invention discloses a V2X task unloading matching method and system fusing collaborative filtering and feedback. The method comprises the following steps: receiving a user task request; querying a historical request list according to the user task request; whether a historical request record exists in the current communication area range of the user or not is judged; if the user does not have the historical request record, a recommended matching result is generated for the user through a V2X task unloading matching cold start model; if the user has the historical request record, generating a recommended matching result for the user by fusing a collaborative filtering algorithm and an unloading matching recommendation model fed back by the user; and outputting a recommended matching result, obtaining feedback information of the user on the current matching result, and updating the historical request list. Through fusion of collaborative filtering and feedback, the matching problem between ...

Parking trajectory planning method and device for four-wheel independent steering vehicle

The invention discloses a parking track planning method and device for a four-wheel independent steering vehicle, and the method comprises the steps: S1, obtaining a grid map of a vehicle initial position, a target parking position and a parking scene, taking the target parking position as a search starting point, taking the vehicle initial position as an end point, carrying out the global path planning through an improved mixed A * algorithm, and obtaining a parking track; obtaining an original global path; the improved mixed A * algorithm comprises a sub-node expansion step, and the sub-node expansion step adopts a preset sub-node expansion mode corresponding to a vehicle movement mode; and S2, segmenting the original global path by taking a mode switching node on the original global path as an end point, and performing path optimization and speed planning on each segment of path to obtain an optimized global trajectory. The flexibility of the four-wheel independent steering vehicle can ...

Road fault early warning method and system based on vehicle-road cooperation

The invention discloses a road fault early warning method and system based on vehicle-road cooperation, and the method comprises the steps: carrying out the real-time detection of a road condition, and outputting a detection result; recognizing the type of the road fault according to the detection result, and outputting a road fault recognition result; the road fault recognition result is sent to a vehicle end on the road in a wireless communication mode, and is displayed or/and warned at the vehicle end; and the road fault identification result is displayed through the display screen or/and the central control system broadcasts the vehicles on the road. According to the method, the dangerous position in the road can be accurately identified, and the driver behind the faulty road is informed of the dangerous information in an early warning manner, so that the collision loss is reduced to the maximum extent, and the operation safety of the system is improved.

Sonar image database augmentation device and method based on cyclic generative adversarial network

The invention discloses a sonar image database augmentation device and method based on a cyclic generative adversarial network. The device comprises an original data acquisition hardware module; an original data acquisition software module; the sonar image preprocessing module is provided with a histogram equalization unit; a contour clustering and pixel filling unit; a large and small slicing unit and an image screening unit; and the sonar image synthesis module is provided with a discrete cosine transform cyclic generative adversarial network, a loss function described in the following formula is preset in the discrete cosine transform cyclic generative adversarial network, and the discrete cosine transform cyclic generative adversarial network is used for performing training constraint in the process of training the real sonar image and the remote sensing image to perform adversarial generation of the sonar image. According to the method, the sonar image which is good in quality and ...

Flexible bus scheduling method and system

The invention provides a flexible bus scheduling method and system which are different from a traditional parking mode, passengers autonomously upload bus taking requirements, a control terminal schedules buses according to the bus taking requirements, and in the scheduling process, it is guaranteed that the passengers arrive at own terminal stations within 15 minutes within 5 kilometers and arrive within 30 minutes within the distance larger than 5 kilometers; and the bus can be stopped without entering the station for the station where the bus taking demand is not submitted, so that the single-trip operation time of the bus is greatly shortened, and the operation efficiency and the taking experience of passengers can be improved.