Vehicle control method and device and storage medium

Abstract

The invention discloses a vehicle control method and device and a storage medium, and relates to the technical field of vehicles, the vehicle control method is applied to a vehicle end, and the method comprises the following steps: sending current address information and target address information to a cloud end, so that the cloud end carries out path planning according to the current address information and the target address information, a vehicle control signal is fed back; and when the vehicle control signal is received within a preset time, performing automatic driving control on the vehicle according to the vehicle control signal. The technology of wireless communication, vehicle-road cooperation, cloud computing and the like is fully utilized, a sensor sensing system is uniformly planned to a road section, a decision planning function is fused and arranged at the cloud end, sharing of a sensing sensor and a computing unit is achieved, and the problem that popularization of driverless automobiles is seriously hindered due to the high cost of the sensor and the computing unit is solved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a vehicle control method, device and storage medium. Background Art

[0002] End-to-end autonomous driving is an important direction for the development of autonomous driving systems and is regarded as the mainstream technical route to achieve fully autonomous driving. By integrating the functions of modules such as perception, decision-making, and control into a unified framework, it can directly realize the processing from perception to control, eliminating the loss in information transmission, and can greatly improve the data processing efficiency of smart cars, thereby improving the system response speed. The end-to-end autonomous driving system needs to process a large amount of sensor data, which places extremely high demands on computing power. The model deployed on the vehicle needs to perform complex reasoning calculations in real time, requiring the vehicle end to have corresponding high-performance computing hardware, which greatly increases the cost of the vehicle. In turn, it is possible to choose to transfer the perception, decision-making and planning capabilities to the road section and transportation end to reduce the investment in vehicle costs. The most beneficial application scenarios of this method include urban / inter-city buses, logistics vehicles, mining quarrying and transportation vehicles, and park distribution vehicles. Therefore, how to solve the high cost of sensors and computing units has seriously hindered the popularization of driverless cars and has become an urgent problem to be solved. Summary of the invention

[0003] The main purpose of this application is to provide a vehicle control method, device and storage medium, aiming to solve the technical problem that the high cost of sensors and computing units seriously hinders the popularization of driverless cars.

[0004] To achieve the above objectives, the present application proposes a vehicle control method, which is applied to a vehicle side and includes: Sending the current address information and the target address information to the cloud, so that the cloud performs path planning according to the current address information and the target address information, and feeds back a vehicle control signal; When the vehicle control signal is received within a preset time, the vehicle is automatically driven and controlled according to the vehicle control signal.

[0005] In one embodiment, before the step of sending the current address information and the target address information to the cloud, the method further includes: Sending the vehicle identification code to the cloud, so that the cloud can establish a communication connection according to the vehicle identification code and feedback the communication connection status; When the communication connection state is a successful connection state, controlling the vehicle to perform a self-check to determine the vehicle self-check state; When the vehicle self-check state is a normal vehicle state, the target address information input by the user is obtained.

[0006] In one embodiment, the method further comprises: When there is a target vehicle failure, obtain the current lateral distance sent by the road test equipment; Perform parking path planning according to the current lateral distance to obtain a target parking path and generate parking warning information; The parking warning information is broadcasted, and the vehicle is controlled to park according to the target parking path.

[0007] To achieve the above objectives, the present application proposes a vehicle control method, which is applied in the cloud and includes: Path planning is performed based on the current address information, target address information, and preset driving map sent by the vehicle to obtain the vehicle driving path; Generate a corresponding vehicle control signal according to the vehicle driving path, and send the vehicle control signal to the vehicle end; A device connection state is determined by communicating with a target road test device corresponding to the vehicle driving path, and the device connection state is sent to the target road test device, where the device connection state is used to wake up the target road test device.

[0008] In one embodiment, path planning is performed based on the current address information, target address information, and a preset driving map sent by the vehicle end to obtain multiple planned driving paths; Multiple planned driving paths are screened according to a preset path screening strategy to obtain a vehicle driving path.

[0009] In one embodiment, when there is a target communication failure, a vehicle control signal is sent to the road test device end; Determine multiple corresponding response devices according to the vehicle location information and the preset device coverage; The device response signal is sent to a plurality of response devices, so that the response devices send the vehicle control signal to the vehicle end.

[0010] To achieve the above object, the present application proposes a vehicle control method, which is applied to a road test device, and the method includes: When receiving the device connection status sent by the cloud, obtain the current device status; When the current device state is a device sleep state, the device sleep state is switched to a device wake-up state.

[0011] In one embodiment, the method further comprises: Obtain vehicle control signals sent from the cloud when there is a target communication failure; The vehicle control signal is sent to the vehicle end so that the vehicle end performs automatic driving control of the vehicle according to the vehicle control signal.

[0012] In addition, to achieve the above-mentioned purpose, the present application also proposes a vehicle control device, the vehicle control device comprising: A sending module, used to send current address information and target address information to the cloud, so that the cloud performs path planning according to the current address information and the target address information, and feeds back a vehicle control signal; The control module is used to control the vehicle automatically according to the vehicle control signal when the vehicle control signal is received within a preset time.

[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes a vehicle control device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the vehicle control method described above.

[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the vehicle control method described above are implemented.

[0015] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the vehicle control method described above are implemented.

[0016] This application sends the current address information and the target address information to the cloud, so that the cloud performs path planning according to the current address information and the target address information, and feeds back the vehicle control signal; when the vehicle control signal is received within a preset time, the vehicle is controlled to be driven automatically according to the vehicle control signal. By making full use of technologies such as wireless communication, vehicle-road collaboration and cloud computing, the sensor perception system is uniformly planned to the road section, and the integrated decision-making and planning functions are arranged in the cloud, so that the perception sensors and computing units can be shared, solving the problem that the high cost of sensors and computing units seriously hinders the popularization of driverless cars. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0019] Figure 1 A flow chart of a vehicle control method embodiment 1 of the present application applied to a vehicle side; Figure 2 A schematic diagram of the overall architecture of the vehicle-road-cloud integrated ecological system provided in Embodiment 1 of the vehicle control method applied to the vehicle side of the present application; Figure 3 A schematic diagram of an OBU-CSU communication process provided in Embodiment 1 of the vehicle control method of the present application applied to a vehicle side; Figure 4 A schematic diagram of a vehicle temporarily pulling over to park provided in Embodiment 1 of the vehicle control method of the present application applied to a vehicle side; Figure 5 A flow chart of the first embodiment of the vehicle control method applied to the cloud of the present application; Figure 6 A schematic diagram of the approximate road center distance provided in Embodiment 1 of the vehicle control method applied to the cloud of the present application; Figure 7 A schematic diagram of the heading angle provided in the first embodiment of the vehicle control method applied to the cloud of the present application; Figure 8 A schematic diagram of the management of the RSU by the CSU provided in the first embodiment of the vehicle control method applied to the cloud of the present application; Fig. 9 A schematic diagram of CSU management of OBU and RSU provided in Embodiment 1 of the vehicle control method applied to the cloud of the present application; Fig.10 A flowchart diagram of a vehicle control method embodiment 1 of the present application applied to a road test device; Fig.11 A schematic diagram of the connection between OBU and RSU provided in Embodiment 1 of the vehicle control method applied to the road test equipment side of the present application; Fig.12 A schematic diagram of a simplified process of a vehicle control method provided in Embodiment 1 of the present application applied to a vehicle side; Fig.13 This is a schematic diagram of the module structure of the vehicle control device according to an embodiment of the present application; Fig.14 Schematic diagram of the device structure of the hardware operating environment involved in the vehicle control method in the embodiment of the present application.

[0020] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0021] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0022] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0023] The main solution of the embodiment of the present application is: sending the current address information and the target address information to the cloud, so that the cloud performs path planning according to the current address information and the target address information, and feeds back the vehicle control signal; when the vehicle control signal is received within a preset time, the vehicle is automatically driven according to the vehicle control signal.

[0024] End-to-end autonomous driving is an important direction for the development of autonomous driving systems and is regarded as the mainstream technical route to achieve fully autonomous driving. By integrating the functions of modules such as perception, decision-making, and control into a unified framework, it can directly realize the processing from perception to control, eliminating the loss in information transmission, and can greatly improve the data processing efficiency of smart cars, thereby improving the system response speed. The end-to-end autonomous driving system needs to process a large amount of sensor data, which places extremely high demands on computing power. The model deployed on the vehicle needs to perform complex reasoning calculations in real time, requiring the vehicle end to have corresponding high-performance computing hardware, which greatly increases the cost of the vehicle. In turn, it is possible to choose to transfer the perception, decision-making and planning capabilities to the road section and transportation end to reduce the investment in vehicle costs. The most beneficial application scenarios of this method include urban / inter-city buses, logistics vehicles, mining quarrying and transportation vehicles, and park distribution vehicles. Therefore, how to solve the high cost of sensors and computing units has seriously hindered the popularization of driverless cars and has become an urgent problem to be solved.

[0025] This application sends the current address information and the target address information to the cloud, so that the cloud performs path planning according to the current address information and the target address information, and feeds back the vehicle control signal; when the vehicle control signal is received within a preset time, the vehicle is controlled to be driven automatically according to the vehicle control signal. By making full use of technologies such as wireless communication, vehicle-road collaboration and cloud computing, the sensor perception system is uniformly planned to the road section, and the integrated decision-making and planning functions are arranged in the cloud, so that the perception sensors and computing units can be shared, solving the problem that the high cost of sensors and computing units seriously hinders the popularization of driverless cars.

[0026] Based on this, the embodiment of the present application provides a vehicle control method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the vehicle control method of the present application applied to the vehicle side.

[0027] In this embodiment, the vehicle control method includes steps S10 to S20: Step S10, sending the current address information and the target address information to the cloud, so that the cloud performs path planning according to the current address information and the target address information, and feeds back a vehicle control signal; It should be noted that if Figure 2 As shown, the new ecological system based on vehicle-road-cloud integration in this embodiment is mainly composed of three parts: unmanned vehicle (vehicle side), road side intelligent infrastructure (Road Side Unit, referred to as RSU, i.e. road side equipment side) and cloud computing processing platform (Central Service Unit, referred to as CSU, also referred to as central service unit, i.e. cloud). The unmanned vehicle includes a positioning module, an on-board network communication terminal (On Board Unit, referred to as OBU, also referred to as on-board unit) and a wire-controlled chassis. The positioning module is used to obtain the vehicle's position information and driving posture information and send it to the on-board network communication terminal. The OBU is used for data exchange between unmanned vehicles and other vehicles, road side intelligent infrastructure and CSU, and can control the wire-controlled chassis through the CAN bus. The wire-controlled chassis refers to the vehicle drive, gear, brake, steering, parking and necessary indicator lights that can be controlled through the CAN bus, and the vehicle can give correct and timely status feedback. RSU includes radar, camera, road traffic signs, traffic lights and communication module. Radar and camera are used to sense the road traffic environment information within a certain range of the RSU and send the sensed information to the communication module. Road traffic signs refer to speed limit or warning signs used to remind drivers of non-connected vehicles in mixed traffic flow. Traffic lights are used to remind drivers of non-connected vehicles in mixed traffic flow. The communication module is used to exchange data with vehicles and CSU within the communication range. CSU includes information storage module, information processing module and communication module. The information storage module is used to record and save the road traffic environment information uploaded by RSU and the status information uploaded by the vehicle. The information processing module is used to plan the global and local driving paths of unmanned vehicles in mixed traffic flow and to build a mathematical model to dynamically update the road traffic environment information recorded in the information storage module. The communication module is used to exchange data with RSU and unmanned vehicles.

[0028] It can be understood that this embodiment is illustrated by taking an unmanned vehicle (vehicle end) as the execution subject, such as an on-board network communication terminal (OBU). The current address information refers to the location information of the unmanned vehicle at the current moment, the target address information refers to the address information of the destination that the user needs to reach, and the vehicle control signal refers to the signal that controls the vehicle to achieve end-to-end automated driving.

[0029] In the specific implementation, after the vehicle establishes a communication connection with the cloud, the current location information of the unmanned vehicle and the address information of the destination required by the user are sent to the cloud, and the cloud then performs path planning and feeds back signals to control the vehicle to achieve end-to-end automated driving.

[0030] In a feasible implementation manner, step S10 may include steps A11 to A13: Step A11, sending the vehicle identification code to the cloud, so that the cloud can establish a communication connection according to the vehicle identification code and feedback the communication connection status; It should be noted that the vehicle identification code refers to the Vehicle Identification Number (VIN), a unique code consisting of 17 digits and numbers, which is used to identify the car, and the communication connection status refers to the communication connection status between the vehicle and the cloud.

[0031] In a specific implementation, in order to establish a communication connection with the cloud, the unmanned vehicle sends the vehicle VIN to the cloud, and the cloud authenticates the communication connection of the vehicle VIN and feeds back the communication connection status between the vehicle and the cloud to the unmanned vehicle.

[0032] Step A12, when the communication connection state is a connection success state, controlling the vehicle to perform a self-check to determine the vehicle self-check state; It can be understood that the vehicle self-check status refers to the self-check result of whether the vehicle has any fault.

[0033] In the specific implementation, when the communication connection status is a successful connection status, it indicates that the vehicle can communicate with the cloud, and then the vehicle enters the self-test mode to check whether the vehicle systems are working normally and whether the connection between OBU and CSU is stable (whether the communication quality is good) to determine the vehicle self-test status.

[0034] Step A13, when the vehicle self-check state is a normal vehicle state, obtaining the target address information input by the user.

[0035] In a specific implementation, when the vehicle self-check state is a normal vehicle state, it indicates that each system of the vehicle is working normally and the connection between the OBU and the CSU is stable, thereby obtaining the address information of the destination required by the user.

[0036] It should be noted that if Figure 3As shown, the vehicle's unmanned driving mode is started, the OBU applies to establish a connection with the CSU, and sends the user's unique identity ID / password to the CSU. The CSU matches the information uploaded by the OBU with the database. After the match is successful, the CSU creates the user's session (a temporary data structure or object created by the server to track the user status) and sends a successful access signal to the OBU. After the connection is successful, the vehicle enters the self-test mode to check whether the vehicle systems are working normally and whether the connection between the OBU and the CSU is stable (whether the communication quality is good). After the self-test is completed, the user is reminded to enter the destination address. After the user enters the address and confirms it, the OBU sends the vehicle's basic status information and driving status information to the CSU.

[0037] Step S20, when the vehicle control signal is received within a preset time, the vehicle is automatically driven and controlled according to the vehicle control signal.

[0038] It can be understood that the preset time refers to a preset control information receiving duration.

[0039] In a specific implementation, when a vehicle control signal is received within a preset control information reception time, it indicates that there is no communication failure, and then the vehicle is automatically driven according to the signal that controls the vehicle to achieve end-to-end automated driving.

[0040] In a feasible implementation manner, the vehicle control method further includes steps S11 to S13: Step S11, when there is a target vehicle failure, obtaining the current lateral distance sent by the road test device; It can be understood that the target vehicle failure includes control system failure, sensor failure, communication terminal failure, power system failure, etc. The current lateral distance refers to the lateral distance between the vehicle and the roadside.

[0041] In the specific implementation, when the vehicle has a control system failure, sensor failure, communication terminal failure, power system failure, etc., it indicates that the vehicle needs to be stopped, and then the lateral distance of the vehicle from the roadside, that is, the current lateral distance, is obtained through the road test equipment.

[0042] Step S12, performing parking path planning according to the current lateral distance, obtaining a target parking path, and generating parking warning information; It can be understood that the target parking path refers to the path for controlling the vehicle to park by the side of the road, and the parking warning information refers to the warning information used to remind other vehicles to drive safely.

[0043] In the specific implementation, the path planning for the vehicle to pull over is carried out according to the lateral distance between the vehicle and the roadside, and then the path for controlling the vehicle to pull over, that is, the target parking path, is obtained, and warning information is generated to remind other vehicles to drive safely to avoid collision with the vehicle behind that is about to pass through the section of road.

[0044] Step S13, broadcasting the parking warning information, and controlling the vehicle to park according to the target parking path.

[0045] In specific implementation, warning information is broadcasted to remind other vehicles to drive safely, and the vehicle is parked according to the path for controlling the vehicle to pull over.

[0046] It should be noted that if Figure 4 As shown, in order to further ensure the driving safety of unmanned vehicles, the vehicle adds a safety redundant braking mechanism. When a special accident occurs, the OBU can control the wire-controlled chassis to pull over. To achieve this function, the OBU needs to obtain the lateral distance of the vehicle from the roadside at that moment. Therefore, the roadside intelligent infrastructure can monitor this information in real time through its sensors, and then forward the control signal of the CSU to the OBU. When the communication terminal or other uncontrollable failures occur, the OBU plans the vehicle's driving path to the roadside and controls the vehicle to pull over. Before executing the pull-over task, the hazard warning lights are turned on and broadcast to the outside to avoid collision with the vehicle behind that is about to pass through the section.

[0047] In this embodiment, when there is a target vehicle failure, the current lateral distance sent by the road test device is obtained; parking path planning is performed according to the current lateral distance to obtain the target parking path, and parking warning information is generated; the parking warning information is broadcast, and the vehicle is controlled to park according to the target parking path. By adding a safety redundant braking mechanism, when a special accident occurs, the side parking task is performed and the hazard warning lights are turned on and broadcasted to the outside to avoid collision with the vehicle behind that is about to pass through the road section.

[0048] This embodiment sends the current address information and the target address information to the cloud, so that the cloud performs path planning according to the current address information and the target address information, and feeds back the vehicle control signal; when the vehicle control signal is received within a preset time, the vehicle is automatically driven according to the vehicle control signal. By making full use of wireless communication, vehicle-road collaboration, cloud computing and other technologies, the sensor perception system is uniformly planned to the road section, and the integrated decision-making and planning functions are arranged in the cloud, and the perception sensors and computing units are shared, which solves the problem that the high cost of sensors and computing units seriously hinders the popularization of driverless cars.

[0049] Based on the first embodiment of the present application applied to the vehicle side, in the first embodiment of the present application applied to the cloud side, the same or similar contents as those of the above-mentioned embodiment 1 applied to the vehicle side can be referred to the above introduction, and will not be repeated later. Figure 5 , the vehicle control method further includes steps S21 to S23: Step S21, performing path planning according to the current address information, target address information and preset driving map sent by the vehicle end to obtain the vehicle driving path; It can be understood that this embodiment is illustrated by taking the cloud computing processing platform (CSU, cloud) as the execution entity, the preset driving map refers to a pre-set intelligent driving map applied to the automatic driving system, and the vehicle driving path refers to the optimal vehicle automatic driving path.

[0050] In the specific implementation, path planning is performed based on the pre-set intelligent driving map applied to the automatic driving system, combined with the current location information of the unmanned vehicle and the address information of the user's required destination, to obtain the optimal vehicle automatic driving path, that is, the vehicle driving path.

[0051] In a feasible implementation, step S21 may include steps A211 to A212: Step A211, performing route planning according to the current address information, the target address information and the preset driving map sent by the vehicle end, and obtaining multiple planned driving routes; It is understandable that the planned driving route refers to the path from the current address to the target address planned in the cloud.

[0052] In a specific implementation, path planning is performed based on a pre-set intelligent driving map applied to an autonomous driving system, combined with the current location information of the unmanned vehicle and the address information of the destination required by the user, to obtain multiple planned driving paths, wherein the vehicle driving time and driving road conditions corresponding to the planned driving paths are different.

[0053] Step A212, screening multiple planned driving paths according to a preset path screening strategy to obtain a vehicle driving path.

[0054] It can be understood that the preset path screening strategy refers to a preset strategy for screening the optimal path, wherein the optimal path generally has two types, namely the path with the shortest driving distance and the path with the shortest driving time.

[0055] In a specific implementation, this embodiment selects the optimal path based on the path with the shortest driving time, that is, the driving times corresponding to multiple planned paths are screened to determine the path with the shortest driving time, and then obtain the vehicle driving path.

[0056] It should be noted that this embodiment completes the design of the end-to-end behavior decision system by solving the path constraints. The path constraints mainly include the lateral position constraint of the road center distance and the longitudinal heading constraint of the heading angle. The distance constraint of the vehicle from the road center is simplified to the height of a triangle with the current position of the vehicle as the vertex and the two nearest waypoints as the base. The schematic diagram of the approximate road center distance is shown in Figure 6 The target waypoint is , is the last target waypoint, is the next target waypoint, is the current position of the vehicle, then the distance between the vehicle and the center of the road is solved as follows:

[0057]

[0058] In the formula, The vehicle's current position O points to the waypoint. , The vector of It is the area of ​​the triangle with the vehicle's current position as the vertex and the two nearest waypoints as the base. is the vector from the previous waypoint to the current waypoint, is the approximate road center distance of the vehicle from the center of the road.

[0059] When the vehicle is in lane keeping, the lateral position constraint requires that the vehicle cannot cross the lane line unless it is an accident. The lateral position constraint solution process is as follows:

[0060]

[0061] In the formula, Due to distance restrictions, is the lane width, is the body width, is the lateral velocity of the vehicle, The decision-making time is long (determined by the system's hardware performance and model algorithm).

[0062] During the driving process, the vehicle must not only meet the lateral position constraint of the vehicle position, but also meet the longitudinal heading constraint of the vehicle heading angle. The heading angle represents the heading deviation between the current heading of the vehicle and the desired heading of the vehicle, such as Figure 7 As shown. Among them, is the current target waypoint, is the target heading vector, containing axis, The two-dimensional axis component represents the direction vector from the vehicle center point to the current target waypoint; is the vehicle's current heading vector, which also contains axis, The two-dimensional component of the axis represents the direction vector of the vehicle, and the longitudinal heading constraint solution process is as follows:

[0063]

[0064]

[0065] In the formula, is the coordinate of the vehicle's current position in the map coordinate system, are the coordinates of the target waypoint in the map coordinate system. is the heading angle, indicating the target heading vector and the vehicle's current heading vector The heading deviation, For the heading deflection angle limit, the longitudinal heading constraint needs to satisfy the heading deflection angle cannot exceed the maximum deflection angle limit.

[0066] The vehicle driving scene can be divided into the following driving scenarios. First, determine whether it is an intersection scene or a non-intersection scene. The intersection scene is divided into three scenes: straight, left turn, and right turn. The non-intersection scene is divided into straight, left lane change (including left turn on a curve), and right lane change (including right turn on a curve). According to the vehicle positioning and global path planning waypoint information, the waypoint closest to the vehicle is obtained. The road curvature is accurately calculated through a mathematical model using multiple waypoints to identify straight roads and turning roads. The waypoint direction vector is used to further identify the direction of left turn and right turn on a curve, thereby constructing a scene recognition module.

[0067] The calculation of road curvature can be solved by fitting the current curvature circle. The general equation of a circle in space can be written as:

[0068] In the formula, As parameters, is the coordinate point on the circle, and the standard equation of the sphere can be obtained by deformation transformation:

[0069] The coordinates of the three nearest waypoints of the vehicle are selected , Substituting the three waypoints into the available parameters Homogeneous linear equations.

[0070]

[0071] Since equation (10) is not a square matrix, the parameters of the equation group cannot be directly solved. Therefore, three waypoints are used to determine the coplanar equation, which is:

[0072] Substituting the three waypoints into equation (11), the parameters of the coplanar equation can be solved: , because the center It is also on the plane, so the simultaneous equation (9) substitutes the center of the circle into equation (11), which is

[0073] Combining equations (10) and (12), we can solve the equation system parameters: , so the coordinates of the center of the curvature circle ( and radius for:

[0074] The road curvature for:

[0075] A straight road can be regarded as a circle with an infinite radius, and its ideal road curvature is (According to the highway route design specification document of the industry standard of the People's Republic of China, the maximum radius of a highway circular curve should not exceed 10,000m. The current scene is considered to be a straight road), and the curves are divided into left curves and right curves. The left and right directions can be represented by two direction vectors on the plane formed by the three waypoints. , The solution process is as follows:

[0076]

[0077] In formula (16), It is the vector product of two direction vectors, and the direction is perpendicular to the plane formed by the two direction vectors. According to the left-hand rule of the map, The positive and negative values ​​represent the rotation direction of the two direction vectors:

[0078] In the formula, It is a direction sign, that is, the direction of vehicle travel. 1 represents a left turn, and 1 represents a right turn. Through the scene recognition module, the driving task is divided into different driving scene sections.

[0079] The selection strategy of the vehicle agent currently includes the following four situations: ① Non-intersection straight driving, left turn on curve, and right turn on curve scenarios, corresponding to the lane keeping agent, numbered Agent 1; ② intersection straight driving scenario, corresponding to the intersection straight driving agent, numbered Agent 2; ③ intersection left turn scenario, corresponding to the intersection left turn agent, numbered Agent 3; ④ intersection right turn scenario, corresponding to the intersection right turn agent, numbered Agent 4. Based on the action space designed in the agent action space design, and taking into account the difficulty of model training and vehicle safety conditions, the action space regulations for vehicle agent training are shown in Table 1.

[0080] Table 1:

[0081] Among them, only the lane keeping agent Agent1 can have the throttle control amount of 0.4, 0.5, and 0.6, while the throttle control amount of other vehicle agents is 0.5, and the brake control amount is 0.0. This setting can ensure the action accessibility of the task and prevent the agent from learning the strategy of frequent acceleration and deceleration. The steering wheel control amount is specially designed for different vehicle agents. The lane keeping agent needs to realize lane keeping in non-intersection scenarios (straight driving, left turn on curve, right turn on curve), so a control amount is set from -0.5 to 0.5 every 0.1, and a total of 11 discrete values ​​can be selected; the straight-moving vehicle agent at the intersection hardly needs too much fluctuation in the steering wheel value, so a control amount is set from -0.2 to 0.2 every 0.1, and a total of 5 discrete values ​​can be selected; the left-turning vehicle agent at the intersection mainly realizes the left-turn function at the intersection, so a control amount is set from -0.5 to 0.2 every 0.1, and a total of 8 discrete values ​​can be selected; the right-turning vehicle agent at the intersection realizes the right-turn function at the intersection, so a control amount is set from -0.2 to 0.5 every 0.1, and a total of 8 discrete values ​​can be selected.

[0082] Before using the intelligent agent library, you need to use the set action space in advance to train the end-to-end behavior decision-making intelligent agent for common scenarios through deep reinforcement learning and store it in the intelligent agent library. When in use, the smart car uses the scene recognition module to identify the current driving scene of the smart car in real time, and then selects the appropriate vehicle intelligent agent from the established vehicle intelligent agent library according to the selection strategy to make the behavior decision of the smart car, realizing the end-to-end decision-making driving of the smart car in common scenarios.

[0083] Step S22, generating a corresponding vehicle control signal according to the vehicle driving path, and sending the vehicle control signal to the vehicle end; It can be understood that a corresponding signal for controlling the automatic driving of the vehicle is generated based on the optimal path obtained by screening and sent to the vehicle end.

[0084] Step S23, determining a device connection state by communicating with a target road test device corresponding to the vehicle driving path, and sending the device connection state to the target road test device, wherein the device connection state is used to wake up the target road test device.

[0085] In a specific implementation, a communication connection is established with the target road test device corresponding to the vehicle's driving path, and then the communication connection status between the roadside device and the cloud is determined, and then the communication connection status between the roadside device and the cloud is sent to each road test device to wake up the corresponding road test device.

[0086] It should be noted that if Figure 8 As shown, in this embodiment, the CSU plans the global path of the vehicle based on the current location information and destination address of the unmanned vehicle. This solution performs path planning through end-to-end deep learning. The CSU selects the optimal driving path based on the planned path. The CSU selects all RSUs covered by the information set path based on the total set of path information and wakes them up. Usually, after the RSU is built, it establishes a connection with the CSU. First, the CSU sends its unique identity ID / password. The CSU matches the received RSU information with the database. After the match is successful, the CSU creates a session for the RSU and sends a successful access signal to the RSU. Under normal circumstances, in order to reduce the energy consumption of the system and increase the service life of the system, when there is no unmanned vehicle passing through the section, the roadside intelligent infrastructure of the section is usually in a dormant state. When an unmanned vehicle passes through the section, the RSU of the section is awakened, and the RSU uploads real-time traffic environment information within its perception range. First, select the path information set that fully covers the roadside intelligent infrastructure If there is no path with full coverage of roadside intelligent infrastructure, the CSU controls the vehicle through remote driving to the area covered by the roadside intelligent infrastructure and then returns to the unmanned driving mode to perform subsequent driving tasks.

[0087] In a feasible implementation manner, the vehicle control method further includes steps S201 to S203: Step S201, when there is a target communication failure, sending a vehicle control signal to the road test equipment end; It can be understood that the target communication failure refers to the communication failure between the vehicle and the cloud.

[0088] In a specific implementation, when there is a communication failure between the vehicle and the cloud, it means that the vehicle cannot receive the control signal sent by the cloud, and then the cloud sends the vehicle control signal to the road test equipment.

[0089] Step S202, determining a plurality of corresponding response devices according to the vehicle location information and the preset device coverage; It can be understood that the vehicle location information refers to the real-time location information of the vehicle, the preset equipment coverage range refers to the communication range of the pre-set roadside equipment, and 1000 meters is taken as an example in this embodiment. The responding device refers to all roadside equipment that needs to be responded to within the preset equipment coverage range.

[0090] In a specific implementation, the roadside equipment is screened according to the real-time position information of the vehicle and the communication range of the preset roadside equipment, and then all the corresponding roadside equipment that needs to respond is determined.

[0091] Step S203, sending a device response signal to a plurality of response devices, so that the response devices send a vehicle control signal to the vehicle end.

[0092] In a specific implementation, the device response signal refers to a signal for controlling the roadside device to send a control instruction. The signal for controlling the roadside device to send a control instruction is sent to all road test devices that need to respond, so that the road test device forwards the vehicle control signal sent from the cloud to the vehicle end.

[0093] It should be noted that if Fig. 9 As shown in the figure, when the vehicle is executing the control signal sent by the RSU, since the communication distance of the RSU is no more than 1000 meters, the OBU will soon leave the coverage of a certain RSU during the driving process. In order to avoid the loss of control signals in a short time due to the frequent switching of the RSU connected to the OBU, the method provided by this scheme is that the CSU will send the control signal to several RSUs that the vehicle will pass through in the driving path. The above RSUs continuously broadcast the control signal sent by the CSU. Therefore, during the entire driving process, the OBU can receive the control signal sent by the CSU. When the vehicle leaves the RSU, the CSU can identify it according to the position of the vehicle, and then control the RSU to stop sending the control signal. If no other unmanned vehicle passes through the RSU, a sleep signal is sent to it to reduce the energy consumption of the system and increase the service life of the system.

[0094] In this embodiment, when there is a target communication failure, a vehicle control signal is sent to the road test device end; multiple corresponding response devices are determined according to the vehicle location information and the preset device coverage range; and a device response signal is sent to multiple response devices, so that the response device sends the vehicle control signal to the vehicle end. By adding a communication redundancy mechanism, when the vehicle does not receive the control signal sent by the cloud, the vehicle is controlled according to the control signal sent by the roadside device, avoiding the delay or loss of the control signal due to the fluctuation of the wireless communication signal, which in turn causes the unmanned vehicle to lose control and collide.

[0095] This embodiment obtains the vehicle's driving path by performing path planning based on the current address information, target address information, and preset driving map sent by the vehicle end; generates a corresponding vehicle control signal based on the vehicle's driving path, and sends the vehicle control signal to the vehicle end; determines the device connection status by communicating with the target road test device corresponding to the vehicle's driving path, and sends the device connection status to the target road test device, and the device connection status is used to wake up the target road test device. By planning the vehicle's global path based on the current location information and destination address of the unmanned vehicle, and waking up all roadside devices covered by the path, end-to-end automated driving control of the vehicle is achieved.

[0096] Based on the first embodiment of the present application applied to the vehicle side and / or the first embodiment of the present application applied to the cloud side, in the first embodiment of the present application applied to the road test device side, the same or similar contents as those in the above-mentioned embodiment 1 applied to the vehicle side and / or the embodiment 1 applied to the cloud side can be referred to the above introduction and will not be repeated later. Fig.10 , the vehicle control method further includes steps S31-S32: Step S31, upon receiving the device connection status sent by the cloud, obtaining the current device status; It can be understood that this embodiment is illustrated by taking the roadside intelligent infrastructure (RSU, road test equipment end) as the execution subject, and the current equipment state refers to the state of the current roadside equipment, including the awake state and the sleep state.

[0097] In a specific implementation, when the communication connection status between the roadside device and the cloud is received from the cloud, it indicates that the roadside device needs to be woken up, and then the current status of the roadside device is obtained.

[0098] Step S32: when the current device state is the device sleep state, switch the device sleep state to the device wake-up state.

[0099] In a specific implementation, when the current device state is the device sleep state, it indicates that the roadside device is in the sleep state and needs to be awakened, and then the sleep state of the roadside device is switched to the awake state to complete the awakening control of the roadside device.

[0100] In a feasible implementation manner, the vehicle control method further includes steps S301-S302: Step S301, when there is a target communication failure, obtaining a vehicle control signal sent by the cloud; It is understandable that when there is a communication failure between the vehicle and the cloud, it means that the vehicle control information needs to be forwarded through the roadside equipment to obtain the vehicle control signal sent by the cloud.

[0101] Step S302, sending the vehicle control signal to the vehicle end, so that the vehicle end performs automatic driving control of the vehicle according to the vehicle control signal.

[0102] In a specific implementation, the roadside equipment sends the vehicle control signal sent from the cloud to the vehicle side to ensure that the vehicle side performs automatic driving control according to the vehicle control signal.

[0103] It should be noted that if Fig.11 As shown in the figure, CSU sends control signals to OBU to control the unmanned vehicle. In order to avoid delay or loss of control signals due to fluctuations in wireless communication signals, which may lead to loss of control and collision of the unmanned vehicle, the control signals of CSU can also be forwarded to OBU through RSU. To ensure the communication security of the entire communication link, the connection between OBU and RSU is controlled by CSU as a whole. After the path planning is completed, CSU numbers the IP addresses or other unique identifiers of the RSUs on the path in the order in which the vehicles pass, and then forms an RSU information set. Sent to OBU, when Uu communication is normal, execute the received CSU control signal, when a certain time If the control signal from the CSU is not received, the control signal sent by the RSU is executed.

[0104] In this embodiment, when there is a target communication failure, the vehicle control signal sent by the cloud is obtained; the vehicle control signal is sent to the vehicle end, so that the vehicle end performs automatic driving control on the vehicle according to the vehicle control signal. In the above manner, unmanned vehicle traffic accidents caused by network communication quality are avoided, and control is sent by using two communication methods: Uu wireless communication (a technology that allows direct communication between user equipment (UE)) and PC5 wireless communication (used to support direct communication between vehicles and other vehicles, pedestrians, and infrastructure), adding a communication safety redundancy mechanism and providing a corresponding network switching method.

[0105] This embodiment obtains the current device state when receiving the device connection state sent by the cloud; when the current device state is the device sleep state, the device sleep state is switched to the device wake-up state. Through the communication connection mechanism between the roadside intelligent infrastructure and the decision-making and planning cloud platform, the roadside intelligent infrastructure is awakened to realize end-to-end automated driving control of the vehicle.

[0106] For example, in order to help understand the implementation process of the vehicle control method obtained by combining this embodiment with the above-mentioned embodiment 1, please refer to Fig.12 , Fig.12A brief flow chart of a vehicle control method is provided, specifically: when an unmanned vehicle is started, a vehicle-mounted network communication terminal establishes a connection with a decision-making and planning cloud platform, and then the vehicle system self-check is completed, the user enters the destination address and confirms it, and then the vehicle driving path is planned and the optimal driving path is selected through the decision-making cloud platform, and a control signal is sent down to control the unmanned vehicle to perform the driving task. When the cellular network signal fluctuates, the control signal forwarded by the roadside intelligent infrastructure is received, and when there is no fault in the vehicle system, the remaining driving task is performed.

[0107] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the vehicle control method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0108] This application also provides a vehicle control device, please refer to Fig.13 The vehicle control device is applied to a vehicle end, and the device comprises: The sending module 10 is used to send the current address information and the target address information to the cloud, so that the cloud performs path planning according to the current address information and the target address information, and feeds back the vehicle control signal; The control module 20 is used to control the vehicle automatically according to the vehicle control signal when the vehicle control signal is received within a preset time.

[0109] Optionally, the sending module 10 is further used for: Sending the vehicle identification code to the cloud, so that the cloud can establish a communication connection according to the vehicle identification code and feedback the communication connection status; When the communication connection state is a successful connection state, controlling the vehicle to perform a self-check to determine the vehicle self-check state; When the vehicle self-check state is a normal vehicle state, the target address information input by the user is obtained.

[0110] Optionally, the control module 20 is further used for: When there is a target vehicle failure, obtain the current lateral distance sent by the road test equipment; Perform parking path planning according to the current lateral distance to obtain a target parking path and generate parking warning information; The parking warning information is broadcasted, and the vehicle is controlled to park according to the target parking path.

[0111] The present application also provides a vehicle control device, which is applied to the cloud and includes: The planning module is used to plan the route according to the current address information, target address information and preset driving map sent by the vehicle end, and obtain the vehicle driving route; A generating module, used for generating a corresponding vehicle control signal according to the vehicle driving path, and sending the vehicle control signal to the vehicle end; The generating module is further used to determine a device connection state by communicating with a target road test device corresponding to the vehicle driving path, and send the device connection state to the target road test device, wherein the device connection state is used to wake up the target road test device.

[0112] Optionally, the planning module is further used to: Path planning is performed based on the current address information, target address information, and preset driving map sent by the vehicle end to obtain multiple planned driving paths; Multiple planned driving paths are screened according to a preset path screening strategy to obtain a vehicle driving path.

[0113] Optionally, the planning module is further used to: When there is a target communication failure, a vehicle control signal is sent to the road test equipment end; Determine multiple corresponding response devices according to the vehicle location information and the preset device coverage; The device response signal is sent to a plurality of response devices, so that the response devices send the vehicle control signal to the vehicle end.

[0114] The present application also provides a vehicle control device, which is applied to a roadside device, and includes: The acquisition module is used to obtain the current device status when receiving the device connection status sent by the cloud; The switching module is used to switch the device sleep state to the device awake state when the current device state is the device sleep state.

[0115] Optionally, the acquisition module is further used to: Obtain vehicle control signals sent from the cloud when there is a target communication failure; The vehicle control signal is sent to the vehicle end so that the vehicle end performs automatic driving control of the vehicle according to the vehicle control signal.

[0116] The vehicle control device provided by the present application adopts the vehicle control method in the above embodiment, which can solve the technical problem that the high cost of sensors and computing units seriously hinders the popularization of driverless cars. Compared with the prior art, the beneficial effects of the vehicle control device provided by the present application are the same as the beneficial effects of the vehicle control method provided by the above embodiment, and the other technical features in the vehicle control device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0117] The present application provides a vehicle control device, which includes: at least one processor; and a memory that is communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the vehicle control method in the above-mentioned embodiment one.

[0118] Reference below Fig.14 , which shows a schematic diagram of the structure of a vehicle control device suitable for implementing an embodiment of the present application. The vehicle control device in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig.14 The vehicle control device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0119] like Fig.14 As shown, the vehicle control device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the vehicle control device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the vehicle control device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a vehicle control device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0120] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0121] The vehicle control device provided by the present application adopts the vehicle control method in the above embodiment, which can solve the technical problem that the high cost of sensors and computing units seriously hinders the popularization of driverless cars. Compared with the prior art, the beneficial effects of the vehicle control device provided by the present application are the same as the beneficial effects of the vehicle control method provided by the above embodiment, and the other technical features in the vehicle control device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0122] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0123] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0124] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the vehicle control method in the above-mentioned embodiment.

[0125] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0126] The computer-readable storage medium may be included in the vehicle control device; or may exist independently without being assembled into the vehicle control device.

[0127] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the vehicle control device, the vehicle control device: sends current address information and target address information to the cloud, so that the cloud performs path planning according to the current address information and the target address information, and feeds back a vehicle control signal; when the vehicle control signal is received within a preset time, the vehicle is automatically driven according to the vehicle control signal.

[0128] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0129] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0130] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0131] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned vehicle control method, and can solve the technical problem that the high cost of sensors and computing units seriously hinders the popularization of driverless cars. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the vehicle control method provided in the above-mentioned embodiment, and will not be repeated here.

[0132] The present application also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the steps of the vehicle control method as described above are implemented.

[0133] The computer program product provided by the present application can solve the technical problem that the high cost of sensors and computing units seriously hinders the popularization of driverless cars. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the vehicle control method provided by the above embodiment, which will not be repeated here.

[0134] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A vehicle control method, characterized in that: The vehicle control method is applied to a vehicle side, and the method comprises: Sending the current address information and the target address information to the cloud, so that the cloud performs path planning according to the current address information and the target address information, and feeds back a vehicle control signal; When the vehicle control signal is received within a preset time, the vehicle is automatically driven and controlled according to the vehicle control signal.

2. The method according to claim 1, characterized in that Before the step of sending the current address information and the target address information to the cloud, the method further includes: Sending the vehicle identification code to the cloud, so that the cloud can establish a communication connection according to the vehicle identification code and feedback the communication connection status; When the communication connection state is a successful connection state, controlling the vehicle to perform a self-check to determine the vehicle self-check state; When the vehicle self-check state is a normal vehicle state, the target address information input by the user is obtained.

3. The method according to claim 1, characterized in that The method further comprises: When there is a target vehicle failure, obtain the current lateral distance sent by the road test equipment; Perform parking path planning according to the current lateral distance to obtain a target parking path and generate parking warning information; The parking warning information is broadcasted, and the vehicle is controlled to park according to the target parking path.

4. A vehicle control method, characterized in that: The vehicle control method is applied to the cloud, and the method includes: Path planning is performed based on the current address information, target address information, and preset driving map sent by the vehicle to obtain the vehicle driving path; Generate a corresponding vehicle control signal according to the vehicle driving path, and send the vehicle control signal to the vehicle end; A device connection state is determined by communicating with a target road test device corresponding to the vehicle driving path, and the device connection state is sent to the target road test device, where the device connection state is used to wake up the target road test device.

5. The method according to claim 4, characterized in that The step of performing path planning according to the current address information, the target address information and the preset driving map sent by the vehicle end to obtain the vehicle driving path includes: Path planning is performed based on the current address information, target address information, and preset driving map sent by the vehicle end to obtain multiple planned driving paths; Multiple planned driving paths are screened according to a preset path screening strategy to obtain a vehicle driving path.

6. The method according to claim 4, characterized in that The method further comprises: When there is a target communication failure, a vehicle control signal is sent to the road test equipment end; Determine multiple corresponding response devices according to the vehicle location information and the preset device coverage; The device response signal is sent to a plurality of response devices, so that the response devices send the vehicle control signal to the vehicle end.

7. A vehicle control method, characterized in that: The vehicle control method is applied to a road test device, and the method includes: When receiving the device connection status sent by the cloud, obtain the current device status; When the current device state is a device sleep state, the device sleep state is switched to a device wake-up state.

8. The method according to claim 7, characterized in that The method further comprises: Obtain vehicle control signals sent from the cloud when there is a target communication failure; The vehicle control signal is sent to the vehicle end so that the vehicle end performs automatic driving control of the vehicle according to the vehicle control signal.

9. A vehicle control device, characterized in that: The device comprises: A sending module, used to send current address information and target address information to the cloud, so that the cloud performs path planning according to the current address information and the target address information, and feeds back a vehicle control signal; The control module is used to control the vehicle automatically according to the vehicle control signal when the vehicle control signal is received within a preset time.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the vehicle control method according to any one of claims 1 to 8 are implemented.

Images