Automatic driving evaluation method and device, electronic equipment and storage medium

Abstract

The invention provides an automatic driving evaluation method and device, electronic equipment and a storage medium, and the method is applied to a cloud end, and comprises the steps: obtaining a preset driving scene and preset sensing data, and receiving vehicle information data uploaded by a vehicle end; based on the vehicle information data and a preset driving scene, evaluating and outputting simulation perception data through a simulation vehicle of preset simulation software; determining a first evaluation result based on the simulation perception data, preset perception data and a first preset condition; if the first evaluation result is unqualified, based on the vehicle information data, receiving real perception data which is uploaded by the vehicle end and is evaluated in a real driving scene through a real vehicle and is output; determining a second evaluation result based on the real sensing data, the preset sensing data and a second preset condition; and if the second evaluation result is qualified, the preset automatic driving algorithm is sent to the vehicle end, so that the safety of the automatic driving algorithm is improved, and the sense of security and experience of the user are improved.

Description

Technical Field

[0001] This application belongs to the field of autonomous driving technology, and particularly relates to a method, device, electronic device and storage medium for evaluating autonomous driving. Background Art

[0002] Currently, the evaluation method for autonomous driving mainly uses simulation software to set up multiple driving environment scenarios and directly evaluate the vehicle's perception ability until the requirements are met. However, this evaluation method lacks consideration of various information of the vehicle itself and real driving scenarios during evaluation, resulting in the situation where the vehicle's perception cannot meet the requirements in the same driving environment scenario.

[0003] The existing technology has the problem that when evaluating autonomous driving, insufficient consideration of the vehicle's own information and real driving scenarios leads to the vehicle's perception not meeting the requirements. Summary of the Invention

[0004] The embodiments of this application provide a method, device, electronic device and storage medium for evaluating autonomous driving, which can solve the problem that insufficient consideration of the vehicle's own information and real driving scenarios leads to the vehicle's perception not meeting the requirements when evaluating autonomous driving.

[0005] In a first aspect, the embodiments of this application provide a method for evaluating autonomous driving, which is applied to the cloud and includes:

[0006] Obtain a preset driving scenario and preset perception data, and receive vehicle information data uploaded by the vehicle terminal;

[0007] Based on the vehicle information data and the preset driving scenario, use a simulated vehicle of preset simulation software to evaluate a preset autonomous driving algorithm and output simulation perception data corresponding to the vehicle information data;

[0008] Based on the simulation perception data, the preset perception data and a first preset condition, determine a first evaluation result of the preset autonomous driving algorithm;

[0009] If the first evaluation result is unqualified, based on the vehicle information data, receive real perception data corresponding to the vehicle information data uploaded by the vehicle terminal through a real vehicle in a real driving scenario for evaluating the preset autonomous driving algorithm;

[0010] Based on the real perception data, the preset perception data and a second preset condition, determine a second evaluation result of the preset autonomous driving algorithm;

[0011] If the second evaluation result is qualified, send the preset autonomous driving algorithm to the vehicle terminal.

[0012] In one embodiment, the preset autonomous driving algorithm includes a single-function autonomous driving algorithm, multiple-function autonomous driving algorithms, and an integrated-function autonomous driving algorithm;

[0013] Based on the vehicle information data and the preset driving scenario, the preset simulation software's simulated vehicle evaluates the preset autonomous driving algorithm and outputs simulation perception data corresponding to the vehicle information data, including:

[0014] Based on the vehicle information data and the preset driving scenario, the preset simulation software's simulated vehicle evaluates the single-function autonomous driving algorithm and outputs first simulation perception data corresponding to the vehicle information data;

[0015] Based on the vehicle information data and the preset driving scenario, the preset simulation software's simulated vehicle evaluates the multiple-function autonomous driving algorithms and outputs second simulation perception data corresponding to the vehicle information data;

[0016] Based on the vehicle information data and the preset driving scenario, the preset simulation software's simulated vehicle evaluates the integrated-function autonomous driving algorithm and outputs third simulation perception data corresponding to the vehicle information data.

[0017] In one embodiment, the vehicle information data includes at least one of vehicle gear, vehicle speed, vehicle acceleration, steering wheel angle, and vehicle driving state. The multiple-function autonomous driving algorithms include obstacle avoidance autonomous driving, and the preset driving scenario includes lane lines, road edges, simulated obstacles, and traffic indication information;

[0018] Based on the vehicle information data and the preset driving scenario, the preset simulation software's simulated vehicle evaluates the multiple-function autonomous driving algorithms and outputs second simulation perception data corresponding to the vehicle information data, including:

[0019] Based on the simulated obstacles and the lane lines, the preset simulation software uses the principal component analysis method to extract the first label feature of the simulated obstacles, the second label feature of the lane lines, and the third label feature of the simulated vehicle;

[0020] Based on the first label feature, the second label feature, the third label feature, and the traffic indication information, the preset simulation software controls the simulated vehicle to avoid the simulated obstacles using the vehicle gear, the vehicle speed, the vehicle acceleration, the steering wheel angle, and the vehicle driving state;

[0021] Based on the result of the simulated vehicle avoiding the simulated obstacles, the preset simulation software outputs the second simulation perception data of the simulated vehicle corresponding to the vehicle information data.

[0022] In one embodiment, the first preset condition includes that the qualification rate of the simulation perception data compared to the preset perception data is greater than or equal to a first qualification rate threshold, and / or the computing power resource index meets the preset requirements;

[0023] Determining a first evaluation result of the preset autonomous driving algorithm based on the simulation perception data, the preset perception data, and the first preset condition includes:

[0024] If the qualification rate of the simulation perception data compared to the preset perception data is greater than or equal to the first qualification rate threshold, and / or the computing power resource index meets the preset requirements, determine that the first evaluation result of the preset autonomous driving algorithm is qualified; if the qualification rate of the simulation perception data compared to the preset perception data is less than the first qualification rate threshold, and / or the computing power resource index does not meet the preset requirements, determine that the first evaluation result of the preset autonomous driving algorithm is unqualified.

[0025] In one embodiment, the preset autonomous driving algorithm includes a single-function autonomous driving algorithm, multiple-function autonomous driving algorithms, and an integrated-function autonomous driving algorithm;

[0026] Receiving, based on the vehicle information data, the true perception data corresponding to the vehicle information data uploaded by the vehicle terminal through a real vehicle in a real driving scenario for evaluating the preset autonomous driving algorithm includes:

[0027] Receiving, based on the vehicle information data, the first true perception data corresponding to the vehicle information data uploaded by the vehicle terminal through a real vehicle in a real driving scenario for evaluating the single-function autonomous driving algorithm;

[0028] Receiving, based on the vehicle information data, the second true perception data corresponding to the vehicle information data uploaded by the vehicle terminal through a real vehicle in a real driving scenario for evaluating the multiple-function autonomous driving algorithms;

[0029] Receiving, based on the vehicle information data, the third true perception data corresponding to the vehicle information data uploaded by the vehicle terminal through a real vehicle in a real driving scenario for evaluating the integrated-function autonomous driving algorithm.

[0030] In one embodiment, the vehicle information data includes at least one of vehicle gear, vehicle speed, vehicle acceleration, steering wheel angle, and vehicle driving state, the preset autonomous driving algorithm includes multiple-function autonomous driving algorithms, the multiple-function autonomous driving algorithms include obstacle avoidance autonomous driving, and the real driving scenario includes lane lines, road edges, real obstacles, and traffic indication information;

[0031] Based on the vehicle information data, receiving the second real perception data corresponding to the vehicle information data uploaded by the vehicle terminal through the real vehicle evaluating the multiple functional autonomous driving algorithms in a real driving scenario, including:

[0032] Based on the real obstacles, the lane lines, and the traffic indication information, the real vehicle uses the vehicle gear, the vehicle speed, the vehicle acceleration, the steering wheel angle, and the vehicle driving state to avoid the real obstacles;

[0033] Receiving the second real perception data of the real vehicle uploaded by the vehicle terminal, where the second real perception data is the perception data corresponding to the vehicle information data based on the result of the real vehicle avoiding the real obstacles.

[0034] In one embodiment, the second preset condition includes that the qualified rate of the real perception data compared to the preset perception data is greater than or equal to a second qualified rate threshold, and / or the computing power resource index meets the preset requirements;

[0035] Based on the real perception data, the preset perception data, and the second preset condition, determining the second evaluation result of the preset autonomous driving algorithm, including:

[0036] If the qualified rate of the real perception data compared to the preset perception data is greater than or equal to the first qualified rate threshold, and / or the computing power resource index meets the preset requirements, determining that the second evaluation result of the preset autonomous driving algorithm is qualified; if the qualified rate of the real perception data compared to the preset perception data is less than the second qualified rate threshold, and / or the computing power resource index does not meet the preset requirements, determining that the second evaluation result of the preset autonomous driving algorithm is unqualified.

[0037] In a second aspect, an embodiment of the present application provides an evaluation device for autonomous driving, which is applied to the cloud and includes:

[0038] An acquisition module, configured to acquire a preset driving scenario and preset perception data, and receive vehicle information data uploaded by the vehicle terminal;

[0039] A first evaluation module, configured to evaluate a preset autonomous driving algorithm through a simulated vehicle of preset simulation software based on the vehicle information data and the preset driving scenario, and output simulation perception data corresponding to the vehicle information data;

[0040] A first determination module, configured to determine a first evaluation result of the preset autonomous driving algorithm based on the simulation perception data, the preset perception data, and a first preset condition;

[0041] A second evaluation module, configured to, if the first evaluation result is unqualified, based on the vehicle information data, receive the real perception data corresponding to the vehicle information data uploaded by the vehicle terminal through evaluating the preset autonomous driving algorithm by a real vehicle in a real driving scenario;

[0042] A second determination module, configured to determine a second evaluation result of the preset autonomous driving algorithm based on the real perception data, the preset perception data, and a second preset condition;

[0043] A sending module, configured to, if the second evaluation result is qualified, send the preset autonomous driving algorithm to the vehicle terminal.

[0044] In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method described in any item of the above first aspect is implemented.

[0045] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, where when the computer program is executed by a processor, the method described in any item of the above first aspect is implemented.

[0046] In a fifth aspect, an embodiment of the present application provides a computer program product, which when running on an electronic device causes the terminal device to execute the method described in any item of the above first aspect.

[0047] It can be understood that the beneficial effects of the above second to fifth aspects can refer to the relevant descriptions in the above first aspect and will not be elaborated here.

[0048] The beneficial effects of the embodiments of the present application compared with the prior art are:

[0049] The evaluation method of autonomous driving of this application is applied to the cloud. By obtaining a preset driving scenario and preset perception data, and receiving vehicle information data uploaded by the vehicle terminal; based on the vehicle information data and the preset driving scenario, the preset autonomous driving algorithm is evaluated through a simulated vehicle of a preset simulation software to output simulation perception data corresponding to the vehicle information data; based on the simulation perception data, the preset perception data, and a first preset condition, a first evaluation result of the preset autonomous driving algorithm is determined; if the first evaluation result is unqualified, based on the vehicle information data, the vehicle terminal is received to upload real perception data corresponding to the vehicle information data obtained by evaluating the preset autonomous driving algorithm with a real vehicle in a real driving scenario; based on the real perception data, the preset perception data, and a second preset condition, a second evaluation result of the preset autonomous driving algorithm is determined; if the second evaluation result is qualified, the preset autonomous driving algorithm is sent to the vehicle terminal. Since the vehicle information data is used in the preset driving scenario of the simulation software to obtain the simulation vehicle to output the corresponding simulation perception data, it is possible to obtain the simulation perception data corresponding to multiple vehicle information data in the same preset driving scenario, expanding the adaptability of the simulation perception data evaluation. For the unqualified simulation perception data, the vehicle information data is used in the real driving scenario to obtain the real vehicle to output the corresponding real perception data, and then multiple real perception data are evaluated, so as to ensure that the preset autonomous driving algorithm outputs qualified real perception data in the case of multiple vehicle information data in the same driving scenario. Through the two evaluations of the autonomous driving algorithm, the safety of the autonomous driving algorithm in multiple driving scenarios and multiple vehicle information data is improved, and the sense of security and experience of users are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0051] Figure 1 It is a flowchart of the evaluation method of autonomous driving provided by an embodiment of the present application;

[0052] Figure 2 It is a flowchart of the preset simulation software outputting simulation perception data corresponding to the vehicle information data provided by an embodiment of the present application;

[0053] Figure 3 It is a flowchart of the preset simulation software outputting second simulation perception data corresponding to the vehicle information data provided by an embodiment of the present application;

[0054] Figure 4It is a schematic flowchart of receiving real perception data corresponding to vehicle information data uploaded by the vehicle terminal provided by an embodiment of the present application;

[0055] Figure 5 It is a schematic flowchart of receiving second real perception data corresponding to vehicle information data uploaded by the vehicle terminal provided by another embodiment of the present application;

[0056] Figure 6 It is a schematic structural diagram of an evaluation device for autonomous driving provided by an embodiment of the present application. Detailed implementation manners

[0057] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system architectures and technologies are presented in order to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0058] It should be understood that when used in the specification and appended claims of the present application, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0059] It should also be understood that the term "and / or" as used in the specification and appended claims of the present application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0060] In addition, in the description of the specification and appended claims of the present application, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0061] The reference to "an embodiment" or "some embodiments" etc. described in the specification of the present application means that a specific feature, structure, or characteristic described in conjunction with the embodiment is included in one or more embodiments of the present application. Thus, the statements "in an embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "comprising", "including", "having", and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0062] Currently, the evaluation method for autonomous driving mainly uses simulation software to set up multiple driving environment scenarios and directly evaluate the vehicle's perception ability until the requirements are met. However, this evaluation method lacks consideration of various information of the vehicle itself and real driving scenarios during the evaluation, resulting in situations where the vehicle's perception cannot meet the requirements in the same driving environment scenario.

[0063] In this embodiment, the evaluation system for autonomous driving includes a cloud end and a vehicle end. The autonomous driving algorithm is deployed at the vehicle end. The cloud end includes a simulation evaluation device and a human-computer interaction display device. The vehicle end uploads various vehicle information data of the self-vehicle to the simulation evaluation device at the cloud end. The simulation evaluation device at the cloud end conducts simulations and evaluates the output simulation perception data. The simulation evaluation device at the cloud end also receives the real perception data corresponding to the vehicle information data output from the evaluation of the preset autonomous driving algorithm by a real vehicle in a real driving scenario, and evaluates the received real perception data, and sends the autonomous driving algorithm with a qualified evaluation result to the vehicle end.

[0064] Among them, the vehicle end uses the 4G / 5G wireless network as a carrier to send requests of the Hypertext Transfer Protocol (HTTP), and uploads various vehicle information data of the self-vehicle to the vehicle information database at the cloud end through a web server. The real perception data of the real vehicle is uploaded to the video database at the cloud end through the File Transfer Protocol (FTP). The communication data between the cloud end and the vehicle end and the evaluation data of the autonomous driving algorithm are stored in the log database. The preset driving scenario is stored in the map data at the cloud end. The human-computer interaction display device at the cloud end is used to display various evaluation information of the autonomous driving algorithm evaluation, and to conduct route scheduling when evaluating with a real vehicle in a real driving scenario and communicate when an abnormality occurs during the evaluation.

[0065] The evaluation method for autonomous driving in this embodiment includes obtaining a preset driving scenario and preset perception data, and receiving vehicle information data uploaded from the vehicle terminal; based on the vehicle information data and the preset driving scenario, evaluating the preset autonomous driving algorithm through a simulated vehicle of a preset simulation software to output simulation perception data corresponding to the vehicle information data; based on the simulation perception data, the preset perception data, and a first preset condition, determining a first evaluation result of the preset autonomous driving algorithm; if the first evaluation result is unqualified, based on the vehicle information data, receiving real perception data corresponding to the vehicle information data output by the real vehicle in the real driving scenario for evaluating the preset autonomous driving algorithm from the vehicle terminal; based on the real perception data, the preset perception data, and a second preset condition, determining a second evaluation result of the preset autonomous driving algorithm; if the second evaluation result is qualified, sending the preset autonomous driving algorithm to the vehicle terminal. Since the vehicle information data is used in the preset driving scenario of the simulation software to obtain the simulation vehicle to output corresponding simulation perception data, multiple simulation perception data corresponding to multiple vehicle information data can be obtained in the same preset driving scenario, expanding the adaptability of the simulation perception data evaluation. For the unqualified simulation perception data, the vehicle information data is used in the real driving scenario to obtain the real vehicle to output corresponding real perception data, and then the multiple real perception data are evaluated, so as to ensure that the real perception data output by the autonomous driving algorithm is qualified in the case of multiple vehicle information data in the same driving scenario. Through the two evaluations of the autonomous driving algorithm, the safety of the autonomous driving algorithm in multiple driving scenarios and multiple vehicle information data is improved, and the sense of security and experience of users are enhanced.

[0066] The technical solution of the present application will be described below through specific embodiments.

[0067] In the first aspect, as Figure 1 shown, this embodiment provides an evaluation method for autonomous driving, which is applied to the cloud and includes:

[0068] S100, obtaining a preset driving scenario and preset perception data, and receiving vehicle information data uploaded from the vehicle terminal.

[0069] In one embodiment, the vehicle information data includes at least one of vehicle gear, vehicle speed, vehicle acceleration, steering wheel angle, and vehicle driving state. The preset driving scenario includes lane lines, road edges, simulated obstacles, and traffic indication information. The perception data represents the perception data obtained by multiple sensors, and the perception data includes first point cloud data obtained by a lidar, second point cloud data obtained by a millimeter wave radar, picture data and / or video data obtained by a camera, and positioning information obtained by a positioning module. The positioning information includes vehicle coordinates and vehicle pose.

[0070] In one embodiment, preset driving scenarios and preset perception data are obtained, vehicle information data uploaded by the vehicle terminal is received, and simulation of an autonomous driving algorithm can be performed based on the vehicle information data and the preset driving scenarios.

[0071] S200. Based on the vehicle information data and the preset driving scenarios, the preset autonomous driving algorithm is evaluated by a simulated vehicle of a preset simulation software to output simulation perception data corresponding to the vehicle information data.

[0072] In one embodiment, the preset autonomous driving algorithms include single-function autonomous driving algorithms, multi-function autonomous driving algorithms, and integrated-function autonomous driving algorithms, so that corresponding autonomous driving algorithms can be called when the vehicle is in various driving scenarios, and corresponding autonomous driving control decisions can be made to improve the safety and experience of users.

[0073] In one embodiment, the simulation software includes SCANeR, CarSim, Prescan, CARLA, or Logsim. In this embodiment, the simulation software is Logsim.

[0074] In one embodiment, the single-function autonomous driving algorithms include at least one of lane line recognition, curb recognition, traffic light recognition, pedestrian recognition, vehicle recognition, building recognition, other object recognition, sunny day recognition, cloudy day recognition, rainy day recognition, other weather recognition, daytime recognition, nighttime recognition, driving along the center of the lane line, driving at a preset distance from the curb, driving while avoiding pedestrians, driving while avoiding vehicles, driving while avoiding buildings, driving while avoiding other objects, driving on a sunny day, driving on a cloudy day, driving on a rainy day, driving in other weather, driving during the day, and driving at night;

[0075] In one embodiment, the multi-function autonomous driving algorithms include at least one of obstacle avoidance autonomous driving, driving while adapting to various traffic conditions, driving while adapting to the weather, driving automatically on various roads, and driving automatically during the day and at night. The obstacles include pedestrians, vehicles, buildings, and other objects.

[0076] In one embodiment, the integrated-function autonomous driving represents autonomous driving when all the autonomous driving algorithms are turned on.

[0077] In one embodiment, as Figure 2 shown, based on the vehicle information data and the preset driving scenarios, the preset autonomous driving algorithm is evaluated by a simulated vehicle of a preset simulation software to output simulation perception data corresponding to the vehicle information data, including:

[0078] S210. Based on the vehicle information data and the preset driving scenarios, the single-function autonomous driving algorithm is evaluated by a simulated vehicle of a preset simulation software to output first simulation perception data corresponding to the vehicle information data.

[0079] In one embodiment, based on vehicle information data and a preset driving scenario, a simulated vehicle of a preset simulation software evaluates a single-function autonomous driving algorithm, and outputs first simulation perception data corresponding to the vehicle information data, so as to evaluate each single function of the autonomous driving algorithm of the vehicle in various driving scenarios, and construct the decision-making ability of the autonomous driving algorithm in a single scenario.

[0080] S220, based on vehicle information data and a preset driving scenario, a simulated vehicle of a preset simulation software evaluates a multi-function autonomous driving algorithm, and outputs second simulation perception data corresponding to the vehicle information data.

[0081] In one embodiment, based on vehicle information data and a preset driving scenario, a simulated vehicle of a preset simulation software evaluates a multi-function autonomous driving algorithm, and outputs second simulation perception data corresponding to the vehicle information data, so as to comprehensively evaluate multiple single functions of the autonomous driving algorithm of the vehicle in various driving scenarios, and realize the decision-making ability of the autonomous driving algorithm in multiple driving scenarios.

[0082] In one embodiment, as Figure 3 shown, based on vehicle information data and a preset driving scenario, a simulated vehicle of a preset simulation software evaluates a multi-function autonomous driving algorithm, and outputs second simulation perception data corresponding to the vehicle information data, including:

[0083] S221, based on simulated obstacles and lane lines, the preset simulation software uses the principal component analysis method to extract the first label feature of the simulated obstacles, the second label feature of the lane lines, and the third label feature of the simulated vehicle.

[0084] In one embodiment, based on simulated obstacles and lane lines, the preset simulation software uses the Gaussian mixture method (Generalized Method of Moment, GMM) to cluster the simulated obstacles, lane lines, and simulated vehicle respectively, and then uses the principal component analysis method (Principal Component Analysis, PCA) to extract the first label feature of the simulated obstacles, the second label feature of the lane lines, and the third label feature of the simulated vehicle, which improves the speed of extracting the label features of the simulated obstacles, lane lines, and simulated vehicle from the driving scenario.

[0085] S222, based on the first label feature, the second label feature, the third label feature, and traffic indication information, the preset simulation software controls the simulated vehicle to avoid the simulated obstacles by using the vehicle gear, vehicle speed, vehicle acceleration, steering wheel angle, and vehicle driving state.

[0086] In one embodiment, avoiding a simulated obstacle includes continuing to drive while avoiding the simulated obstacle, making an emergency stop before the simulated obstacle, or following the simulated obstacle and continuing to drive.

[0087] In one embodiment, based on the first tag feature, the second tag feature, the third tag feature, and traffic indication information, a preset simulation software plans a route for avoiding a simulated obstacle and controls the simulated vehicle to avoid the simulated obstacle by using the vehicle gear, vehicle speed, vehicle acceleration, steering wheel angle, and vehicle driving state. Since there are multiple routes and multiple processing methods for avoiding the obstacle, the simulated vehicle will respectively use any combination of vehicle gear, vehicle speed, vehicle acceleration, steering wheel angle, and vehicle driving state to avoid the obstacle, so as to be able to evaluate the simulation results of avoiding obstacles of multiple vehicle information data in the same preset driving scenario.

[0088] S223. Based on the result of the simulated vehicle avoiding the simulated obstacle, the preset simulation software outputs second simulation perception data corresponding to the vehicle information data of the simulated vehicle.

[0089] In one embodiment, based on the result of the simulated vehicle avoiding the simulated obstacle, the preset simulation software outputs second simulation perception data corresponding to the vehicle information data of the simulated vehicle. Since the preset simulation software uses the vehicle information data in the preset driving scenario to obtain the simulation perception data output by the simulated vehicle corresponding to the vehicle information data, it is possible to obtain the second simulation perception data corresponding to multiple vehicle information data output in the same preset driving scenario, expanding the adaptability of the evaluation of the simulation perception data.

[0090] S230. Based on the vehicle information data and the preset driving scenario, the preset simulation software evaluates the integrated function autonomous driving algorithm through the simulated vehicle and outputs third simulation perception data corresponding to the vehicle information data.

[0091] In one embodiment, the preset simulation software uses the vehicle information data to control the simulated vehicle to evaluate the integrated function autonomous driving algorithm in the preset driving scenario, and then outputs the third simulation perception data corresponding to the vehicle information data, so as to be able to obtain the third simulation perception data corresponding to multiple vehicle information data of the integrated function autonomous driving algorithm output in the same preset driving scenario, further expanding the adaptability of the evaluation of the simulation perception data.

[0092] S300. Based on the simulation perception data, the preset perception data, and the first preset condition, determine the first evaluation result of the preset autonomous driving algorithm.

[0093] In one embodiment, the first preset condition includes that the pass rate of the simulation perception data compared to the preset perception data is greater than or equal to the first pass rate threshold, and / or the computing power resource index meets the preset requirements. The first preset condition takes into account both the vehicle-end hardware and the conditions of the vehicle-end autonomous driving algorithm software.

[0094] In one embodiment, the computing power resource index includes the proportion of the processor occupied by the autonomous driving algorithm, the proportion of the memory occupied by the autonomous driving algorithm, and the time for the autonomous driving algorithm to complete decision-making. The preset requirements include that the proportion of the processor occupied by a single-function autonomous driving algorithm is less than or equal to 10%, the proportion of the memory occupied by a single-function autonomous driving algorithm is less than or equal to 10%, the proportion of the processor occupied by multiple-function / integrated-function autonomous driving algorithms is less than or equal to 90%, the proportion of the memory occupied by multiple-function / integrated-function autonomous driving algorithms is less than or equal to 90%, and the time for the autonomous driving algorithm to complete decision-making is less than or equal to 50 milliseconds.

[0095] In one embodiment, based on the simulation perception data, the preset perception data, and the first preset condition, determining the first evaluation result of the preset autonomous driving algorithm includes:

[0096] If the pass rate of the simulation perception data compared to the preset perception data is greater than or equal to the first pass rate threshold, and / or the computing power resource index meets the preset requirements, determine that the first evaluation result of the preset autonomous driving algorithm is qualified; if the pass rate of the simulation perception data compared to the preset perception data is less than the first pass rate threshold, and / or the computing power resource index does not meet the preset requirements, determine that the first evaluation result of the preset autonomous driving algorithm is unqualified. Screen the evaluation items of qualified and unqualified autonomous driving algorithms through the first evaluation result, thereby accelerating the evaluation speed of the autonomous driving algorithm, improving the evaluation efficiency of the autonomous driving algorithm, and reducing the evaluation cost of the autonomous driving algorithm.

[0097] In one embodiment, the value range of the first pass rate threshold is greater than or equal to 80%.

[0098] In one embodiment, the autonomous driving algorithm is obstacle avoidance autonomous driving, and the obstacles are multiple obstacles. If the qualification rate of the simulation perception data compared to the preset perception data is greater than or equal to 80%, that is, the obstacle avoidance autonomous driving has identified and avoided more than 80% of the obstacles, or more than 80% of the evaluation times of the evaluated obstacle avoidance times have identified and avoided the obstacles, and / or the computing power resource index meets the preset requirements, that is, the proportion of multiple functional autonomous driving algorithms occupying the processor is less than or equal to 90%, the proportion of multiple functional autonomous driving algorithms occupying the memory is less than or equal to 90%, and the time for the obstacle avoidance autonomous driving to complete the decision is less than or equal to 50 milliseconds, it is determined that the first evaluation result of the obstacle avoidance autonomous driving is qualified; if the qualification rate of the simulation perception data compared to the preset perception data is less than 80%, that is, the obstacle avoidance autonomous driving has identified and avoided less than 80% of the obstacles, or less than 80% of the evaluation times of the evaluated obstacle avoidance times have identified and avoided the obstacles, and / or the computing power resource index does not meet the preset requirements, that is, the proportion of multiple functional autonomous driving algorithms occupying the processor is greater than 90%, the proportion of multiple functional autonomous driving algorithms occupying the memory is greater than 90%, and the time for the obstacle avoidance autonomous driving to complete the decision is greater than 50 milliseconds, it is determined that the first evaluation result of the preset autonomous driving algorithm is unqualified, thereby accelerating the evaluation speed of the autonomous driving algorithm, improving the evaluation efficiency of the autonomous driving algorithm, and reducing the evaluation cost of the autonomous driving algorithm.

[0099] S400. If the first evaluation result is unqualified, based on the vehicle information data, receive the real perception data corresponding to the vehicle information data uploaded by the vehicle terminal through the real vehicle evaluating the preset autonomous driving algorithm in the real driving scenario.

[0100] In one embodiment, if the first evaluation result is unqualified, based on the vehicle information data, receive the real perception data corresponding to the vehicle information data uploaded by the vehicle terminal through the real vehicle evaluating the preset autonomous driving algorithm in the real driving scenario, so that after the simulation perception data evaluation is unqualified, the real vehicle evaluates the preset autonomous driving algorithm in the real driving scenario and outputs the real perception data corresponding to the vehicle information data, thereby making up for the deficiency of the simulation and further improving the safety and experience of the autonomous driving algorithm.

[0101] In one embodiment, as Figure 4 shown, based on the vehicle information data, receiving the real perception data corresponding to the vehicle information data uploaded by the vehicle terminal through the real vehicle evaluating the preset autonomous driving algorithm in the real driving scenario includes:

[0102] S410. Based on the vehicle information data, receive the first real perception data corresponding to the vehicle information data uploaded by the vehicle terminal through the real vehicle evaluating a single functional autonomous driving algorithm in the real driving scenario.

[0103] S420, based on the vehicle information data, receive the second real perception data corresponding to the vehicle information data uploaded by the vehicle end, which is the evaluation output of multiple functional autonomous driving algorithms by a real vehicle in a real driving scenario.

[0104] In one embodiment, the real driving scenario includes lane lines, curbs, real obstacles, and traffic indication information.

[0105] In one embodiment, as Figure 5 shown, based on the vehicle information data, receive the second real perception data corresponding to the vehicle information data uploaded by the vehicle end, which is the evaluation output of multiple functional autonomous driving algorithms by a real vehicle in a real driving scenario, including:

[0106] S421, based on real obstacles, lane lines, and traffic indication information, the real vehicle uses the vehicle gear, vehicle speed, vehicle acceleration, steering wheel angle, and vehicle driving state to avoid real obstacles.

[0107] S422, receive the second real perception data of the real vehicle uploaded by the vehicle end, and the second real perception data is the perception data corresponding to the vehicle information data based on the result of the real vehicle avoiding real obstacles.

[0108] It can be understood that the real vehicle uses multiple vehicle information data to evaluate and avoid real obstacles in a real driving scenario, which is closer to the actual operation of the hardware and software of the real vehicle, can find the deficiencies in the simulation evaluation of avoiding obstacles, further improve the autonomous driving algorithm, and further improve the safety and experience of the autonomous driving algorithm.

[0109] S430, based on the vehicle information data, receive the third real perception data corresponding to the vehicle information data uploaded by the vehicle end, which is the evaluation output of the integrated functional autonomous driving algorithm by a real vehicle in a real driving scenario.

[0110] S500, based on the real perception data, preset perception data, and second preset condition, determine the second evaluation result of the preset autonomous driving algorithm.

[0111] In one embodiment, the second preset condition includes that the qualified rate of the real perception data compared to the preset perception data is greater than or equal to the second qualified rate threshold, and / or the computing power resource index meets the preset requirements.

[0112] In one embodiment, the value range of the second qualified rate threshold is greater than or equal to 70%.

[0113] In one embodiment, the determination of the second evaluation result of the preset autonomous driving algorithm based on the real perception data, preset perception data, and second preset condition includes:

[0114] If the pass rate of the real perception data compared to the preset perception data is greater than or equal to 70%, that is, the obstacle avoidance automatic driving recognizes and avoids more than 70% of the obstacles, or more than 70% of the evaluation times of the evaluated obstacle avoidance times recognize and avoid the obstacles, and / or the computing power resource index meets the preset requirements, that is, the proportion of multiple functional automatic driving algorithms occupying the processor is less than or equal to 90%, the proportion of multiple functional automatic driving algorithms occupying the memory is less than or equal to 90%, and the time for the obstacle avoidance automatic driving to complete the decision is less than or equal to 50 milliseconds, determine that the second evaluation result of the preset automatic driving algorithm is qualified; if the pass rate of the real perception data compared to the preset perception data is less than 70%, that is, the obstacle avoidance automatic driving recognizes and avoids less than 70% of the obstacles, or less than 70% of the evaluation times of the evaluated obstacle avoidance times recognize and avoid the obstacles, and / or the computing power resource index does not meet the preset requirements, that is, the proportion of multiple functional automatic driving algorithms occupying the processor is greater than 90%, the proportion of multiple functional automatic driving algorithms occupying the memory is greater than 90%, and the time for the obstacle avoidance automatic driving to complete the decision is greater than 50 milliseconds, determine that the second evaluation result of the preset automatic driving algorithm is unqualified.

[0115] S600, if the second evaluation result is qualified, send the preset automatic driving algorithm to the vehicle end.

[0116] In one embodiment, if the second evaluation result is qualified, send the preset automatic driving algorithm to the vehicle end, thereby improving the safety and experience of the user.

[0117] In one embodiment, if the first evaluation result is qualified, send the preset automatic driving algorithm to the vehicle end, or if both the first evaluation result and the second evaluation result are qualified, send the preset automatic driving algorithm to the vehicle end, thereby improving the safety and experience of the user.

[0118] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution is prior or posterior, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0119] The beneficial effects of the embodiments of the present application compared with the prior art are:

[0120] The evaluation method for autonomous driving in this embodiment is applied to the cloud. By obtaining a preset driving scenario and preset perception data, and receiving vehicle information data uploaded from the vehicle terminal; based on the vehicle information data and the preset driving scenario, using the simulated vehicle of the preset simulation software to evaluate the preset autonomous driving algorithm and output simulation perception data corresponding to the vehicle information data; based on the simulation perception data, the preset perception data and the first preset condition, determining the first evaluation result of the preset autonomous driving algorithm; if the first evaluation result is unqualified, based on the vehicle information data, receiving the real perception data corresponding to the vehicle information data uploaded from the vehicle terminal by the real vehicle in the real driving scenario for evaluating the preset autonomous driving algorithm; based on the real perception data, the preset perception data and the second preset condition, determining the second evaluation result of the preset autonomous driving algorithm; if the second evaluation result is qualified, sending the preset autonomous driving algorithm to the vehicle terminal. Since the vehicle information data is used in the preset driving scenario of the simulation software to obtain the simulated vehicle to output the corresponding simulation perception data, it is possible to obtain the simulation perception data corresponding to multiple vehicle information data in the same preset driving scenario, expanding the adaptability of the simulation perception data evaluation. For the unqualified simulation perception data, the vehicle information data is used in the real driving scenario to obtain the real vehicle to output the corresponding real perception data, and then the multiple real perception data are evaluated, so as to ensure that the autonomous driving algorithm outputs qualified real perception data in the case of multiple vehicle information data in the same driving scenario. Through the two evaluations of the autonomous driving algorithm, the safety of the autonomous driving algorithm in multiple driving scenarios and multiple vehicle information data is improved, and the sense of security and experience of users are improved.

[0121] In a second aspect, as Figure 6 shown, this embodiment provides an evaluation device 100 for autonomous driving, which is applied to the cloud and includes:

[0122] An acquisition module 110, configured to acquire a preset driving scenario and preset perception data, and receive vehicle information data uploaded from the vehicle terminal.

[0123] A first evaluation module 120, configured to, based on the vehicle information data and the preset driving scenario, use the simulated vehicle of the preset simulation software to evaluate the preset autonomous driving algorithm and output simulation perception data corresponding to the vehicle information data.

[0124] A first determination module 130, configured to determine the first evaluation result of the preset autonomous driving algorithm based on the simulation perception data, the preset perception data, and the first preset condition.

[0125] A second evaluation module 140, configured to, if the first evaluation result is unqualified, based on the vehicle information data, receive the real perception data corresponding to the vehicle information data uploaded from the vehicle terminal by the real vehicle in the real driving scenario for evaluating the preset autonomous driving algorithm.

[0126] A second determination module 150, configured to determine a second evaluation result of a preset autonomous driving algorithm based on real perception data, preset perception data, and a second preset condition.

[0127] A sending module 160, configured to send the preset autonomous driving algorithm to a vehicle terminal if the second evaluation result is qualified.

[0128] It should be noted that for the information interaction, execution process, etc. between the above-mentioned modules / units, since they are based on the same concept as the method embodiment of the present application, their specific functions and the technical effects brought thereby can be specifically referred to in the method embodiment part, and will not be elaborated herein.

[0129] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiment and will not be elaborated herein.

[0130] In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method described in any item of the above first aspect is implemented.

[0131] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the method described in any item of the above first aspect is implemented.

[0132] In a fifth aspect, an embodiment of the present application provides a computer program product, and when the computer program product runs on an electronic device, the terminal device is enabled to execute the method described in any item of the above first aspect.

[0133] It can be understood that the beneficial effects of the above second aspect to fifth aspect can be referred to the relevant descriptions in the above first aspect, and will not be elaborated herein.

[0134] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-described embodiment methods of this application, a computer program can be used to instruct the relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc.

[0135] The computer-readable medium can at least include: any entity or device that can carry the computer program code to the photographing device / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk, or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0136] In the above embodiments, the descriptions of the respective embodiments have their own focuses. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0137] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0138] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0139] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included within the protection scope of the present application.

Claims

1. A method for evaluating autonomous driving, characterized in that, Applied to the cloud, including: Obtain preset driving scenarios and preset perception data, and receive vehicle information data uploaded by the vehicle terminal; Based on the vehicle information data and the preset driving scenario, use the simulated vehicle of the preset simulation software to evaluate the preset autonomous driving algorithm and output simulation perception data corresponding to the vehicle information data; Based on the simulation perception data, the preset perception data and the first preset condition, determine the first evaluation result of the preset autonomous driving algorithm; If the first evaluation result is unqualified, based on the vehicle information data, receive the real perception data corresponding to the vehicle information data output by evaluating the preset autonomous driving algorithm by the real vehicle in the real driving scenario uploaded by the vehicle terminal; Based on the real perception data, the preset perception data and the second preset condition, determine the second evaluation result of the preset autonomous driving algorithm; If the second evaluation result is qualified, send the preset autonomous driving algorithm to the vehicle terminal.

2. The method according to claim 1, characterized in that, The preset autonomous driving algorithm includes a single-function autonomous driving algorithm, multiple-function autonomous driving algorithms, and an integrated-function autonomous driving algorithm; Based on the vehicle information data and the preset driving scenario, using the simulated vehicle of the preset simulation software to evaluate the preset autonomous driving algorithm and output simulation perception data corresponding to the vehicle information data, including: Based on the vehicle information data and the preset driving scenario, use the simulated vehicle of the preset simulation software to evaluate the single-function autonomous driving algorithm and output the first simulation perception data corresponding to the vehicle information data; Based on the vehicle information data and the preset driving scenario, use the simulated vehicle of the preset simulation software to evaluate the multiple-function autonomous driving algorithms and output the second simulation perception data corresponding to the vehicle information data; Based on the vehicle information data and the preset driving scenario, use the simulated vehicle of the preset simulation software to evaluate the integrated-function autonomous driving algorithm and output the third simulation perception data corresponding to the vehicle information data.

3. The method according to claim 2, characterized in that, The vehicle information data includes at least one of vehicle gear, vehicle speed, vehicle acceleration, steering wheel angle, and vehicle driving state. The multiple-function autonomous driving algorithms include obstacle avoidance autonomous driving. The preset driving scenario includes lane lines, road edges, simulated obstacles, and traffic indication information; Based on the vehicle information data and the preset driving scenario, using the simulated vehicle of the preset simulation software to evaluate the multiple-function autonomous driving algorithms and output the second simulation perception data corresponding to the vehicle information data, including: Based on the simulated obstacles and the lane lines, the preset simulation software uses the principal component analysis method to extract the first label feature of the simulated obstacles, the second label feature of the lane lines, and the third label feature of the simulated vehicle; Based on the first tag feature, the second tag feature, the third tag feature, and the traffic indication information, the preset simulation software controls the simulated vehicle to avoid the simulated obstacle by using the vehicle gear, the vehicle speed, the vehicle acceleration, the steering wheel angle, and the vehicle driving state; Based on the result of the simulated vehicle avoiding the simulated obstacle, the preset simulation software outputs the second simulation perception data corresponding to the vehicle information data of the simulated vehicle.

4. The method according to claim 1, characterized in that, The first preset condition includes that the qualified rate of the simulation perception data compared with the preset perception data is greater than or equal to the first qualified rate threshold, and / or the computing power resource index meets the preset requirements; Determining the first evaluation result of the preset autonomous driving algorithm based on the simulation perception data, the preset perception data, and the first preset condition includes: If the qualified rate of the simulation perception data compared with the preset perception data is greater than or equal to the first qualified rate threshold, and / or the computing power resource index meets the preset requirements, determine that the first evaluation result of the preset autonomous driving algorithm is qualified; if the qualified rate of the simulation perception data compared with the preset perception data is less than the first qualified rate threshold, and / or the computing power resource index does not meet the preset requirements, determine that the first evaluation result of the preset autonomous driving algorithm is unqualified.

5. The method according to claim 1, characterized in that, The preset autonomous driving algorithm includes a single-function autonomous driving algorithm, multiple-function autonomous driving algorithms, and an integrated-function autonomous driving algorithm; Receiving, based on the vehicle information data, the real perception data corresponding to the vehicle information data uploaded by the vehicle terminal through a real vehicle in a real driving scenario for evaluating the preset autonomous driving algorithm, includes: Receiving, based on the vehicle information data, the first real perception data corresponding to the vehicle information data uploaded by the vehicle terminal through a real vehicle in a real driving scenario for evaluating the single-function autonomous driving algorithm; Receiving, based on the vehicle information data, the second real perception data corresponding to the vehicle information data uploaded by the vehicle terminal through a real vehicle in a real driving scenario for evaluating the multiple-function autonomous driving algorithms; Receiving, based on the vehicle information data, the third real perception data corresponding to the vehicle information data uploaded by the vehicle terminal through a real vehicle in a real driving scenario for evaluating the integrated-function autonomous driving algorithm.

6. The method according to claim 5, characterized in that, The vehicle information data includes at least one of vehicle gear, vehicle speed, vehicle acceleration, steering wheel angle, and vehicle driving state. The preset autonomous driving algorithm includes multiple-function autonomous driving algorithms. The multiple-function autonomous driving algorithms include obstacle avoidance autonomous driving. The real driving scenario includes lane lines, curbs, real obstacles, and traffic indication information; Receiving, based on the vehicle information data, the second real perception data corresponding to the vehicle information data uploaded by the vehicle terminal through a real vehicle in a real driving scenario for evaluating the multiple-function autonomous driving algorithms, includes: Based on the real obstacle, the lane line, and the traffic indication information, the real vehicle uses the vehicle gear, the vehicle speed, the vehicle acceleration, the steering wheel angle, and the vehicle driving state to avoid the real obstacle; Receiving the second real perception data of the real vehicle uploaded by the vehicle terminal, where the second real perception data is the perception data corresponding to the vehicle information data based on the result of the real vehicle avoiding the real obstacle.

7. The method according to claim 1, characterized in that, The second preset condition includes that the qualification rate of the real perception data compared to the preset perception data is greater than or equal to the second qualification rate threshold, and / or the computing power resource index meets the preset requirements; Determining the second evaluation result of the preset autonomous driving algorithm based on the real perception data, the preset perception data, and the second preset condition, including: If the qualification rate of the real perception data compared to the preset perception data is greater than or equal to the second qualification rate threshold, and / or the computing power resource index meets the preset requirements, determining that the second evaluation result of the preset autonomous driving algorithm is qualified; if the qualification rate of the real perception data compared to the preset perception data is less than the second qualification rate threshold, and / or the computing power resource index does not meet the preset requirements, determining that the second evaluation result of the preset autonomous driving algorithm is unqualified.

8. An apparatus for evaluating autonomous driving, characterized in that,Applied to the cloud, including: An acquisition module, configured to acquire a preset driving scenario and preset perception data, and receive vehicle information data uploaded by the vehicle terminal; A first evaluation module, configured to evaluate the preset autonomous driving algorithm through a simulated vehicle of a preset simulation software based on the vehicle information data and the preset driving scenario, and output simulation perception data corresponding to the vehicle information data; A first determination module, configured to determine the first evaluation result of the preset autonomous driving algorithm based on the simulation perception data, the preset perception data, and the first preset condition; A second evaluation module, configured to, if the first evaluation result is unqualified, based on the vehicle information data, receive the real perception data uploaded by the vehicle terminal through the real vehicle in the real driving scenario for evaluating the preset autonomous driving algorithm and output the real perception data corresponding to the vehicle information data; A second determination module, configured to determine the second evaluation result of the preset autonomous driving algorithm based on the real perception data, the preset perception data, and the second preset condition; A sending module, configured to, if the second evaluation result is qualified, send the preset autonomous driving algorithm to the vehicle terminal.

9. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the method according to any one of claims 1 to 7.

Images