Method and device for evaluating automatic parking capability and electronic equipment

Abstract

The invention discloses an automatic parking function evaluation method and device and electronic equipment. The method comprises the steps that a virtual vehicle is controlled to be parked in a target parking space indicated by each test case in a test case list in sequence based on a to-be-evaluated automatic parking function to obtain parking data; wherein the parking data indicates a parking track when the virtual vehicle is parked in the target parking space indicated by each test case, the test case list is associated with a first group of scene elements, and the first group of scene elements are determined according to scene elements affecting parking when the to-be-evaluated automatic parking function fails to run in a real scene; the specifications of at least one scene element in the first group of scene elements associated with any two test cases in the test case list are different; and generating an evaluation result of the automatic parking function according to the parking data. The scheme can be applied to the field of evaluation of the automatic parking function of the intelligent vehicle, the evaluation result can be quickly obtained, large-scale generalization is not needed, and the test period of the automatic parking function can be shortened.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving, and more specifically, to a method, device and electronic device for evaluating automatic parking capability. Background Art

[0002] With the advancement of intelligent driving technology, more and more car models are equipped with intelligent driving technology. As a function with a high penetration rate in intelligent driving technology, automatic parking has gradually penetrated from high-end models to mid- and low-end models, and the number of models equipped with automatic parking has increased significantly. At the same time, the automatic driving function is constantly iterating and updating, and the speed of software version iteration is greatly increasing. Under this development trend, how to quickly evaluate the adaptation of new software versions in different models has become an urgent problem to be solved. Summary of the invention

[0003] The present application provides an automatic parking function evaluation method, device and electronic device, which can quickly evaluate the adaptability of new software versions in different vehicle models and shorten the test cycle of the automatic parking function.

[0004] In a first aspect, a method for evaluating an automatic parking function is provided, the method comprising: controlling a virtual vehicle to park in a target parking space indicated by each test case in a first test case list in turn based on the automatic parking function to be evaluated, and obtaining first parking data; wherein the first parking data indicates a parking trajectory of the virtual vehicle when parking in the target parking space indicated by each test case, the first test case list is associated with a first group of scene elements, the first group of scene elements is determined according to scene elements that affect parking when the automatic parking function to be evaluated fails to run in a real scene, and the specifications of at least one scene element in the first group of scene elements associated with any two test cases in the first test case list are different; generating a first evaluation result according to the first parking data, the first evaluation result indicating at least one of the following: whether a process of the virtual vehicle parking in the target parking space indicated by the test case in the first test case list is successful, the performance boundary of the automatic parking function to be evaluated in the first group of scene elements, and the distribution of the test cases corresponding to parking failures in the first test case list.

[0005] In the above technical solution, the automatic parking function is evaluated based on the factors that affect parking when the automatic parking function fails to operate in real scenarios. The evaluation results can be quickly obtained with limited test scenarios, without the need for large-scale generalization, which helps to shorten the test cycle of the automatic parking function. In addition, for the test process of the automatic parking function, only a small amount of real vehicle test data is required, and more accurate evaluation results can be obtained through simulation testing in the later stage, which can improve the safety of the automatic parking function test process (such as avoiding the use of real vehicle testing to cause collision scenarios), thereby helping to save the manpower and material resources required for the automatic parking function test.

[0006] In combination with the first aspect, in certain implementations of the first aspect, the virtual vehicle is optimized based on chassis function test results of a real vehicle, the chassis function test results are obtained by running the chassis function to be evaluated of the real vehicle in a target scenario, and the target scenario is associated with scenario elements that affect the chassis function when the automatic parking function to be evaluated is running in the real scenario.

[0007] In the above technical solution, optimizing the virtual vehicle through chassis function test results helps to improve the accuracy of the evaluation results of the automatic parking function.

[0008] In combination with the first aspect, in certain implementations of the first aspect, the chassis function to be evaluated is associated with the automatic parking function to be evaluated.

[0009] In the above technical solution, the chassis function test result is obtained by using the chassis function to be evaluated associated with the automatic parking function to be evaluated, which helps to further improve the accuracy of the evaluation result of the automatic parking function.

[0010] In combination with the first aspect, in certain implementations of the first aspect, the first group of scene elements includes a first type of obstacles, a first type of parking spaces, and a first type of parking methods, and the specifications of at least one scene element include the width of the target parking space and / or the width of the road, and the road is the road on which the virtual vehicle travels during the parking process.

[0011] In the above technical solution, the test scenario is constructed based on obstacles, parking space types and parking methods that appear frequently in parking failure scenarios, which helps to achieve a rapid evaluation of the automatic parking function and improve the problem detection rate of the automatic parking function.

[0012] In combination with the first aspect, in certain implementations of the first aspect, generating a first evaluation result based on the first parking data includes: filling a first matrix table according to the first parking data to obtain the first evaluation result, each cell of the first matrix table represents a test case in the first test case list; when the parking data corresponding to the first test case in the first test case list indicates that the virtual vehicle has been parked in the target parking space, the cell corresponding to the first test case is set to a first value; or, when the parking data corresponding to the first test case indicates that the virtual vehicle has not been parked in the target parking space, the cell corresponding to the first test case is set to a second value.

[0013] In the above technical solution, the evaluation results of the automatic parking function under a single test case are represented based on a matrix table, which helps users to more intuitively determine the parking capability boundary of the automatic parking function to be evaluated under the current test scenario (or the current group of scenario elements), the test results of a single test case, and the distribution of test cases corresponding to parking failures in the matrix table and other information.

[0014] In combination with the first aspect, in certain implementations of the first aspect, the method also includes: when the virtual vehicle fails to park in the first target parking space indicated by the second test case in the first test case list, setting a first type of value for the cell corresponding to the second test case according to the reason for the parking failure, and the first type of value is different from the category of the first value and the second value; wherein the reason for the parking failure includes at least one of the following: the first target parking space is not released, a collision occurs during the parking process, there is a collision risk greater than a risk threshold during the parking process, there is a speed of the virtual vehicle greater than a speed threshold during the parking process, there is an acceleration during deceleration greater than an acceleration threshold during the parking process, and the automatic parking function to be evaluated is stuck.

[0015] In the above technical solution, the evaluation results of the automatic parking function under a single test case are represented based on a matrix table, which helps users to more intuitively determine the scenarios and / or reasons that lead to parking failures, and facilitates users to make targeted improvements to the automatic parking function.

[0016] In combination with the first aspect, in certain implementations of the first aspect, the method also includes: controlling the virtual vehicle to repeatedly park in the target parking space indicated by each test case in the second test case list based on the automatic parking function to be evaluated, to obtain second parking data, wherein the number of repetitions is a preset number, and the first test case list includes the second test case list; filling a second matrix table according to the second parking data to generate a second evaluation result, wherein the value of each cell of the second matrix table represents the number of successful parkings corresponding to a test case in the second test case list.

[0017] In the above technical solution, the evaluation results of the repeated execution of the test cases based on the automatic parking function are represented based on a matrix table, which helps the user to intuitively determine the stability of the automatic parking function and facilitates the user to make targeted improvements to the automatic parking function.

[0018] In a second aspect, an automatic parking function evaluation device is provided, the device comprising: a processing unit, used to control a virtual vehicle to park in a target parking space indicated by each test case in a first test case list in turn based on the automatic parking function to be evaluated, to obtain first parking data; wherein the first parking data indicates a parking trajectory of the virtual vehicle when parking in the target parking space indicated by each test case, the first test case list is associated with a first group of scene elements, the first group of scene elements is determined according to the scene elements that affect parking when the automatic parking function to be evaluated fails to run in a real scene, and the specifications of at least one scene element in the first group of scene elements associated with any two test cases in the first test case list are different; a generating unit, used to generate a first evaluation result according to the first parking data, the first evaluation result indicating at least one of the following: whether the process of the virtual vehicle parking in the target parking space indicated by the test case in the first test case list is successful, the performance boundary of the automatic parking function to be evaluated in the first group of scene elements, and the distribution of the test cases corresponding to the parking failure in the first test case list.

[0019] In combination with the second aspect, in certain implementations of the second aspect, the virtual vehicle is optimized based on the chassis function test results of the real vehicle, the chassis function test results are obtained by running the chassis function to be evaluated of the real vehicle in a target scenario, and the target scenario is associated with scene elements that affect the chassis function when the automatic parking function to be evaluated is running in the real scenario.

[0020] In conjunction with the second aspect, in certain implementations of the second aspect, the chassis function to be evaluated is associated with the automatic parking function to be evaluated.

[0021] In combination with the second aspect, in certain implementations of the second aspect, the first group of scene elements includes a first type of obstacles, a first type of parking space, and a first type of parking method, and the specifications of at least one scene element include the width of the target parking space and / or the width of the road, and the road is the road on which the virtual vehicle travels during the parking process.

[0022] In combination with the second aspect, in certain implementations of the second aspect, the generating unit is used to: fill in a first matrix table according to the first parking data to obtain a first evaluation result, each cell of the first matrix table representing a test case in the first test case list; when the parking data corresponding to the first test case in the first test case list indicates that the virtual vehicle has been parked in the target parking space, the cell corresponding to the first test case is set to a first value; or, when the parking data corresponding to the first test case indicates that the virtual vehicle has not been parked in the target parking space, the cell corresponding to the first test case is set to a second value.

[0023] In combination with the second aspect, in certain implementations of the second aspect, the generating unit is further used for: when the virtual vehicle fails to park in the first target parking space indicated by the second test case in the first test case list, setting a first type of value for the cell corresponding to the second test case according to the reason for the parking failure, and the first type of value is different from the category of the first value and the second value; wherein the reason for the parking failure includes at least one of the following: the first target parking space is not released, a collision occurs during the parking process, there is a collision risk greater than a risk threshold during the parking process, there is a speed of the virtual vehicle greater than a speed threshold during the parking process, there is an acceleration during deceleration greater than an acceleration threshold during the parking process, and the automatic parking function to be evaluated is stuck.

[0024] In combination with the second aspect, in certain implementations of the second aspect, the processing unit is further used to: control the virtual vehicle to repeatedly park in the target parking space indicated by each test case in the second test case list based on the automatic parking function to be evaluated, and obtain second parking data, wherein the number of repetitions is a preset number, and the first test case list includes the second test case list; the generation unit is further used to: fill in the second matrix table according to the second parking data to generate a second evaluation result, and the value of each cell of the second matrix table represents the number of successful parking corresponding to a test case in the second test case list.

[0025] In a third aspect, an automatic parking function evaluation device is provided, the device comprising: a memory for storing a computer program; and a processor for executing the computer program stored in the memory, so that the device executes the method in any possible implementation of the first aspect.

[0026] In a fourth aspect, an electronic device is provided, which includes a device as in any possible implementation of the second aspect or the third aspect.

[0027] In combination with the fourth aspect, in certain implementations of the fourth aspect, the intelligent driving device is a vehicle.

[0028] In a fifth aspect, a computer program product is provided, the computer program product comprising: a computer program code, when the computer program code is run on a computer, the computer executes the method in any possible implementation of the first aspect.

[0029] It should be noted that the above-mentioned computer program code may be stored in whole or in part on a first storage medium, wherein the first storage medium may be packaged together with the processor or may be packaged separately from the processor.

[0030] In a sixth aspect, a computer-readable medium is provided, wherein the computer-readable medium stores instructions, and when the instructions are executed by a processor, the processor implements the method in any possible implementation manner of the first aspect.

[0031] In a seventh aspect, a chip is provided, the chip comprising a circuit, the circuit being used to execute the method in any possible implementation manner of the first aspect above. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 is a schematic block diagram of an automatic parking capability evaluation system provided in an embodiment of the present application;

[0033] Figure 2 is a schematic flow chart of an automatic parking capability evaluation method provided in an embodiment of the present application;

[0034] Figure 3 is a schematic diagram of generating a test case provided by an embodiment of the present application;

[0035] Figure 4 This is a schematic diagram of a test scenario provided in an embodiment of the present application;

[0036] Figure 5 is another schematic flow chart of the automatic parking capability evaluation method provided in the embodiment of the present application;

[0037] Figure 6 is another schematic flow chart of the automatic parking capability evaluation method provided in the embodiment of the present application;

[0038] Figure 7 is another schematic flow chart of the automatic parking capability evaluation method provided in the embodiment of the present application;

[0039] Figure 8 is a schematic diagram of an evaluation result of the automatic parking capability provided in an embodiment of the present application;

[0040] Fig. 9 is another schematic diagram of the evaluation result of the automatic parking capability provided in the embodiment of the present application;

[0041] Fig.10 is another schematic flow chart of the automatic parking capability evaluation method provided in the embodiment of the present application;

[0042] Fig.11 is a schematic block diagram of an automatic parking capability evaluation device provided in an embodiment of the present application;

[0043] Fig.12 This is another schematic block diagram of the automatic parking capability evaluation device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0044] The technical solutions in the embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0045] Figure 1 is a schematic block diagram of an automatic parking capability evaluation system provided in an embodiment of the present application. Figure 1 As shown, the system includes an automatic parking capability evaluation device 100 and an intelligent driving device, wherein the automatic parking function to be tested is installed in the intelligent driving device.

[0046] More specifically, the intelligent driving device may include a perception system, a planning module, a control module and an execution module. Among them, the perception system may include several sensors for sensing information about the environment around the intelligent driving device. For example, the perception system may include a positioning system, and the positioning system may be a global positioning system (GPS), or a Beidou system or other positioning systems. For another example, the perception system may also include one or more of an inertial measurement unit (IMU), a laser radar, a millimeter wave radar, an ultrasonic radar and a camera device. During the automatic parking process, the perception system is used to collect the surrounding environment information of the intelligent driving device, the planning module is used to plan the parking path according to the information collected by the perception system, and the control module calculates the corresponding lateral control amount and / or longitudinal control amount according to the planned parking path, and outputs the above control amount to the execution module. When the execution module executes the control amount, the intelligent driving device is controlled to travel according to the planned parking path. In some possible implementations, the execution module may include chassis control systems such as steering control and power control in the intelligent driving device.

[0047] The intelligent driving device involved in the embodiments of the present application can be a vehicle in a broad sense, which can be a means of transportation (such as commercial vehicles, passenger cars, motorcycles, flying cars, trains, etc.), industrial vehicles (such as forklifts, trailers, tractors, etc.), engineering vehicles (such as excavators, bulldozers, cranes, etc.), agricultural equipment (such as mowers, harvesters, etc.), amusement equipment, toy vehicles, etc. The embodiments of the present application do not specifically limit the type of vehicle. In addition, the intelligent driving device involved in the present application can be a real intelligent driving device, or it can also be a virtual intelligent driving device. The following is an example of an intelligent driving device as a vehicle.

[0048] The automatic parking capability evaluation device 100 includes a test scenario construction module 110 , a test execution module 120 and a result evaluation module 130 .

[0049] The automatic parking capability evaluation device 100 is used to evaluate the automatic parking function of a vehicle.

[0050] Automatic parking (AP) refers to the automatic parking of the vehicle, that is, the automatic driving system can semi-automatically or fully automatically help the user to park the vehicle into the parking space. In the embodiment of the present application, automatic parking may include automatic parking assist (APA), remote parking assist (RPA) and automatic valet parking (AVP). For APA, the driver does not need to operate the steering wheel, but the driver is still required to operate the intelligent driving device to monitor the status of the intelligent driving device in real time; for RPA, the driver can use a terminal (such as a mobile phone) to remotely park the intelligent driving device outside the intelligent driving device; for AVP, the intelligent driving device can complete parking without a driver.

[0051] After the tester configures the simulation environment according to the vehicle model equipped with the parking function to be evaluated and loads the parking function to be evaluated, the test scenario construction module 110 constructs the test scenario of the automatic parking function according to the information recorded by the automatic parking function, wherein the information recorded by the parking function includes relevant information of the scenario that causes parking failure, including but not limited to obstacle type, parking space type, parking method, parking space width, road width, and the road is a road used for driving during the parking process of the vehicle, and can be a road between the edge of the parking space and the road boundary. Exemplarily, the test scenario construction module 110 can fully combine the obstacle type, parking space type, and parking method to obtain multiple test scenarios. For example, if there are m types of obstacle types, n types of parking spaces, and k parking methods, the test scenario construction module 110 can construct K test scenarios, where K is the product of m, n, and k, wherein m, n, and k are all integers greater than or equal to 1. Further, for one of the K test scenarios, changing the parking space width and / or the road width can construct multiple test cases. That is to say, the obstacle types, parking space types and parking methods of multiple test cases corresponding to a test scenario are the same, and the parking space widths and / or road widths of any two test cases in the multiple test cases are different. Exemplarily, obstacle types may include but are not limited to: static obstacles such as vehicles, pillars, high shoulders, walls, etc., and dynamic obstacles such as pedestrians, etc.; parking space types include but are not limited to vertical parking spaces, horizontal parking spaces, and inclined parking spaces; parking methods include but are not limited to the rear of the vehicle entering the parking space first (hereinafter referred to as rear entry), the front of the vehicle entering the parking space first (hereinafter referred to as head entry), the front of the vehicle parking out of the parking space first and driving forward (hereinafter referred to as head out forward), the front of the vehicle parking out of the parking space first and driving to the left (hereinafter referred to as head out left), the front of the vehicle parking out of the parking space first and driving to the right (hereinafter referred to as head out right), the rear of the vehicle parking out of the parking space first and driving forward (hereinafter referred to as rear out forward), the rear of the vehicle parking out of the parking space first and driving to the left (hereinafter referred to as rear out left), and the rear of the vehicle parking out of the parking space first and driving to the right (hereinafter referred to as rear out right). Furthermore, the test execution module 120 executes the test case, i.e., controls the virtual vehicle to park in the target parking space indicated by the test case based on the parking function to be evaluated, wherein the virtual vehicle can be understood as a model equipped with the automatic parking function to be tested. The result evaluation module 130 is used to evaluate the test case running results and output the simulation test results, wherein the simulation test results include at least one of the following: the test result of a single test case, the boundary of the automatic parking function, and the stability of the automatic parking function.

[0052] It should be understood that the above system is only an example, and in actual applications, the modules in the above system may be added or deleted according to actual needs. For example, the test execution module 120 and the result evaluation module 130 may be combined into one module.

[0053] The above introduces the evaluation system of the automatic parking function provided by the present application. The following describes in detail the evaluation method of the automatic parking function provided by the present application.

[0054] Figure 2 FIG. 1 shows an exemplary flow chart of an automatic parking function evaluation method provided by an embodiment of the present application. For example, the method may be Figure 1 The automatic parking capability evaluation device 100 is shown to be executed. Figure 2 The illustrated method may include S210 to S230 .

[0055] S210, constructing an automatic parking test scenario.

[0056] For example, S210 may be Figure 1 Specifically, according to the parking failure scenario recorded during the vehicle parking process, at least one of the obstacle type, parking space type, and parking method that caused the parking failure is determined. Figure 3 As shown, the obstacle type, parking space type, and parking method are fully combined to obtain the test scenario. For example, the obstacle types in the parking failure scenario recorded by the vehicle include vehicle, pillar, high shoulder, and wall, the parking space type in the parking failure scenario includes oblique train space, and the parking methods in the parking failure scenario include tail-in and tail-out to the left. Then the test scenarios obtained by the full combination include 8, namely: vehicle-oblique train space-tail-in, vehicle-oblique train space-tail-out to the left, pillar-oblique train space-tail-in, pillar-oblique train space-tail-out to the left, high shoulder-oblique train space-tail-in, high shoulder-oblique train space-tail-out to the left, wall-oblique train space-tail-in, wall-oblique train space-tail-out to the left.

[0057] like Figure 4 The schematic diagram of a test scenario is shown, the target parking space is the target parking space of the self-vehicle when the automatic parking function to be tested is running, the obstacles on both sides of the target parking space can be the same type or different types, and the size of the self-vehicle can be determined according to the vehicle model to be tested, for example, the size of the self-vehicle can be 4.93m and 1.94m in length and width respectively, or the size of the self-vehicle can also be other sizes. Further, multiple scene specifications can be set for each test scene to obtain multiple test cases. Among them, the scene specifications can include parking space width and / or road width. Exemplarily, the scene specification range such as the range of parking space width and the range of road width can be determined according to the size of the vehicle to be tested. Exemplarily, the range of parking space width can be 2.1 meters (meter, m) to 4m, the range of road width can be 3 meters to unlimited, and the change step of scene specifications can be 5 centimeters (centimeter, cm). Among them, unlimited can be understood as the road width that the vehicle can travel on during the parking process is infinite.

[0058] It should be understood that the numerical values ​​of the above scenario specification ranges and step sizes are only examples, and other ranges and step sizes may be used in actual implementation.

[0059] S220, executing simulation test.

[0060] For example, S220 may be composed of Figure 1 The test execution module 120 shown is executed, that is, the test case is run. Exemplarily, running the test case may include: running all test cases, that is, for each test scenario, running multiple test cases corresponding to it, until the test cases corresponding to all test scenarios are run; and / or, each test case is repeated for a preset number of times, which can be 10 times, or can also be another number. Exemplarily, running the test case includes: controlling the virtual vehicle to park in the target parking space indicated by the test case based on the parking function to be evaluated. A more detailed method for running the test case will be combined with Figure 5 and Figure 6 Expand Description.

[0061] S230, evaluating the test results.

[0062] For example, S230 may be Figure 1 The result evaluation module 130 is shown as an example. A more specific result evaluation method will be combined with Figures 7 to 9 Expand Description.

[0063] The automatic parking function evaluation method provided in the embodiment of the present application can quickly evaluate the automatic parking function in a limited test scenario based on a small amount of real vehicle data. In addition, the execution of the simulation test, data analysis and test result generation can all be completed automatically, which helps save manpower.

[0064] Figure 5 Another exemplary flow chart of the method for evaluating the automatic parking function provided in the embodiment of the present application is shown. Figure 5 It can be regarded as an expanded description of S220 in the above embodiment. Specifically, Figure 5 The illustrated method may include S221 to S229.

[0065] S221, start the simulation environment.

[0066] S222, select and load a test case from a test case list corresponding to the target test scenario.

[0067] Exemplarily, the target test scenario may include a test scenario constructed in S210, and the test case list may include multiple test cases corresponding to the target test scenario.

[0068] S223, determine the target parking space.

[0069] Exemplarily, the position of the target parking space indicated by the test case is determined.

[0070] S224, determining whether the target parking space is released.

[0071] Exemplarily, the target parking space being released indicates that the target parking space can be used for parking, otherwise it indicates that the target parking space is not available for parking.

[0072] Specifically, if the target parking space is not released, execute S227; otherwise, execute S225.

[0073] S225, determining whether the target parking function is released.

[0074] Exemplarily, the target parking function may be a parking function to be evaluated.

[0075] Specifically, if the target parking capability has not been released, execute S227; otherwise, execute S226.

[0076] S226, simulating and executing the parking process.

[0077] Exemplarily, the virtual vehicle is controlled to park in the target parking space indicated by the test case based on the target parking function. The target parking function can be implemented by the planning module, the control module and the execution module of the virtual vehicle. Parking in the target parking space includes: parking in the target parking space, and / or parking out of the target parking space.

[0078] S227, output the test results.

[0079] In one example, the test result includes parking data generated during the process of the virtual vehicle parking in the target parking space, and the parking data may include a parking trajectory of the virtual vehicle. It should be understood that the parking trajectory indicates the parking path of the virtual vehicle and the driving speed of the virtual vehicle in the path. In another example, the test result may indicate that the target parking space is not released.

[0080] S228, vehicle status reset.

[0081] For example, the specific process of resetting the vehicle status can be as follows: Figure 6 As shown, including S2281 to S2283:

[0082] S2281, moving the virtual vehicle to a target area, where the distance between the target area and the target parking space is greater than or equal to a distance threshold.

[0083] Exemplarily, the distance threshold may be 20 m, or 25 m, or other values.

[0084] S2282, controlling the virtual vehicle to stay in the target area for a preset time period.

[0085] Exemplarily, the preset duration may be 10 seconds, or 5 seconds, or other durations.

[0086] S2283, controlling the virtual vehicle to exit the parking state.

[0087] Exemplarily, the virtual vehicle is controlled to accelerate for a period of time (eg, 5 seconds) and then decelerate and stop to exit the parking state.

[0088] S229, determining whether the test case list has been executed.

[0089] Exemplarily, when all test cases corresponding to the target test scenario are executed, it is determined that the test case list is executed.

[0090] Specifically, if the test case list is executed, it is determined that the simulation test for the target test scenario is executed; otherwise, execute S222.

[0091] Figure 7 Another exemplary flow chart of the method for evaluating the automatic parking function provided in the embodiment of the present application is shown. Figure 7 It can be regarded as an expanded description of S230 in the above embodiment. In some implementations, Figure 7 The method shown can be Figure 5 The S227 shown is then executed. Specifically, Figure 7 The illustrated method may include S231 to S238.

[0092] S231, obtaining the test result of the test case.

[0093] Exemplarily, the test result of the test case may include the test result outputted in S227 .

[0094] S232, determining whether the target parking space is released.

[0095] Specifically, if the target parking space is not released, it is determined that the parking has failed, and the reason for the parking failure is "the target parking space is not released"; otherwise, execute S233.

[0096] S233, determining whether the vehicle is parked in the target parking space.

[0097] Specifically, if the vehicle is parked in the target parking space, execute S234; otherwise, execute S236.

[0098] S234, determining whether there is no collision during the parking process and whether the collision risk is less than or equal to a risk threshold.

[0099] For example, the collision risk may be quantified into at least two levels based on the distance between the obstacle and the vehicle, and the speed of the vehicle and / or the obstacle. For example, the at least two levels may include level 1 and level 2. If the collision risk corresponding to level 1 is less than the collision risk corresponding to level 2, the risk threshold may be level 1.

[0100] Specifically, if there is no collision during the parking process and the collision risk is less than or equal to the risk threshold, S235 is executed; otherwise, it is determined that the parking has failed, and the reason for the parking failure is "a collision occurs during the parking process or the collision risk is greater than the risk threshold".

[0101] S235, determining whether the speed during parking does not exceed a speed threshold, and whether the acceleration during deceleration does not exceed an acceleration threshold.

[0102] For example, the speed threshold may be 5 kilometers per hour (kph), or may be other values. It is understood that the acceleration during the deceleration process is a negative value, and the acceleration not exceeding the acceleration threshold may be understood as the absolute value of the acceleration during the deceleration process being less than or equal to the acceleration threshold, wherein the acceleration threshold may be 20 m / s 2 , or other values.

[0103] Specifically, if the speed during parking does not exceed the speed threshold and the acceleration during deceleration does not exceed the acceleration threshold, parking is determined to be successful; otherwise, parking is determined to have failed, and the cause of the parking failure is determined to be "speeding during parking" and / or "parking in progress" according to the specific situation.

[0104] S236, determining whether the parking function is stuck.

[0105] Exemplarily, if the parking function is stuck, it is determined that parking has failed; otherwise, S234 is executed.

[0106] It should be understood that Figure 7 The process shown is only for illustrative purposes. In actual implementation, S232 to S235 may also be executed synchronously.

[0107] Figure 8 A schematic diagram showing the evaluation results obtained by running the autonomous driving function provided by an embodiment of the present application under a target test scenario. Figure 8 In the table shown, each row represents the road width, each column represents the parking space width of the target parking space, and each cell at the cross intersection of a row and a column represents a test case. It can be understood that Figure 8All cells in the table shown correspond to the same obstacle type, parking space type, and parking method. More specifically, a cell value of "0" indicates that the virtual vehicle has not parked in the target parking space indicated by the test case, and a cell value of "1" indicates that the virtual vehicle has parked in the target parking space indicated by the test case. During the simulation, even if the virtual vehicle parks in the target parking space, it may encounter situations that affect parking safety during the parking process; or there are many reasons why the virtual vehicle does not park in the parking space. Therefore, Figure 8 The table shown uses different colors to indicate situations that affect parking safety during parking and / or reasons for not parking in a parking space. For example, color 1 may indicate that the target parking space is not released, color 2 may indicate that a collision occurs during parking or the collision risk is higher than a threshold, and color 3 may indicate that the parking function is stuck.

[0108] It should be understood that Figure 8 The representation shown is only for illustrative purposes. In actual implementation, other forms may be used to represent the execution results of the test case. For example, a cell color of color 1 indicates that the virtual vehicle has not been parked in the target parking space indicated by the test case, and a cell color of color 2 indicates that the virtual vehicle has been parked in the target parking space indicated by the test case. Furthermore, different numerical values ​​are used to indicate situations that affect parking safety during the parking process and / or the reasons for not parking in the parking space. For another example, a cell value of "0" indicates that the virtual vehicle has not been parked in the target parking space indicated by the test case, and a cell value of "1" indicates that the virtual vehicle has been parked in the target parking space indicated by the test case. Furthermore, setting "0" or "1" to different colors indicates situations that affect parking safety during the parking process or the reasons for not parking in the parking space.

[0109] Fig. 9 Figure 1 shows a schematic diagram of the evaluation results obtained by repeatedly executing the test case. Fig. 9 In the table shown, each row represents the road width, each column represents the parking space width of the target parking space, and the cell at the cross-shaped difference of each row and column represents a test case. Taking each test case repeated 10 times as an example, when the cell value is any one from "0" to "10", it represents the number of times the virtual vehicle successfully parks at the target parking space indicated by the test case. When the cell value is " / ", it indicates that the target parking space indicated by the test case has not been released.

[0110] In some implementations, the virtual vehicle in the above embodiment can be generated according to the vehicle configuration parameters set by the user. In some implementations, the vehicle configuration parameters can be determined according to the chassis function test results of the real vehicle. Among them, the chassis function test results can be obtained by testing different chassis functions to be tested in different chassis test scenarios, and the chassis test scenarios can be constructed according to the information recorded by the automatic parking function, wherein the information recorded by the automatic parking function may include chassis-related information that affects the parking function, including but not limited to road surface material, road surface state, road slope, wheel block, speed bump, vehicle tire pressure, and vehicle load. Exemplarily, the road surface material includes but is not limited to cement, asphalt, epoxy floor, ecological floor tile, gravel road; the road surface state includes but is not limited to dry, slippery, snow, and ice. The chassis function to be tested can be determined according to the requirements of the automatic parking function, or it can also be determined according to user feedback. Exemplarily, the chassis function to be tested may include but is not limited to: starting, braking, gear switching, speed change (acceleration or deceleration), and steering.

[0111] Fig.10 FIG. 1 is a schematic flow chart of an automatic parking function evaluation method provided by an embodiment of the present application. The method may be performed by Figure 1 The method 1000 may include:

[0112] S1010, controlling a virtual vehicle to park in a target parking space indicated by each test case in a first test case list in turn based on the automatic parking function to be evaluated, and obtaining first parking data.

[0113] Among them, the first parking data indicates the parking trajectory of the virtual vehicle when it parks in the target parking space indicated by each test case, the first test case list is associated with the first group of scene elements, the first group of scene elements is determined according to the scene elements that affect parking when the automatic parking function to be evaluated fails to operate in the real scene, and the specifications of at least one scene element in the first group of scene elements associated with any two test cases in the first test case list are different.

[0114] Exemplarily, the first group of scene elements constitutes a test scene, which can be one of the test scenes obtained by full combination in S210. The first test case list can be a list consisting of multiple test cases obtained by setting multiple scene specifications for the above test scene. The specific implementation method of controlling the virtual vehicle to park in a target parking space indicated by a test case based on the automatic parking function to be evaluated to obtain test data can refer to the description in S221 to S227, which will not be repeated here.

[0115] In some implementations, the first group of scene elements includes a first type of obstacles, a first type of parking spaces, and a first type of parking methods, and the specifications of at least one scene element include the width of the target parking space and / or the width of the road, where the road is the road on which the virtual vehicle travels during the parking process.

[0116] Exemplarily, the first type of obstacle may be an obstacle that appears more frequently in parking failure scenarios, such as one or more of a vehicle, a pillar, a high shoulder, and a wall.

[0117] S1020, generating a first evaluation result based on the first parking data, the first evaluation result indicating at least one of the following: whether a process of the virtual vehicle parking at a target parking space indicated by a test case in a first test case list is successful, a performance boundary of the automatic parking function to be evaluated in a first group of scene elements, and a distribution of test cases corresponding to parking failures in the first test case list.

[0118] Exemplarily, the process of the virtual vehicle parking at the target parking space indicated by the test case in the first test case list can be understood as the virtual vehicle parking in the target parking space, and none of the following situations occurs during the parking process: a collision occurs, the collision risk is greater than the collision threshold, the speed exceeds the speed threshold, the acceleration exceeds the acceleration threshold during deceleration, and the deviation between the parking posture and the preset posture is greater than the preset threshold. Wherein, the deviation between the parking posture and the preset posture can be characterized by the angle and / or position between the two postures. When the angle between the two postures is greater than the angle threshold and / or the distance between the center points of the two postures is greater than the preset distance, it is determined that the deviation between the parking posture and the preset posture is greater than the preset threshold. The process of the virtual vehicle parking at the target parking space indicated by the test case in the first test case list fails to be understood as: the virtual vehicle does not park in the target parking space; or, the virtual vehicle parks in the target parking space, but one or more of the following situations occur: a collision occurs, the collision risk is greater than the collision threshold, the speed exceeds the speed threshold, the acceleration exceeds the acceleration threshold during deceleration, and the deviation between the parking posture and the preset posture is greater than the preset threshold.

[0119] The performance boundary of the automatic parking function to be evaluated in the first group of scene elements may indicate: in which scene specifications of the first group of scene elements the automatic parking function to be evaluated can successfully park.

[0120] In some implementations, generating a first evaluation result according to the first parking data includes: filling a first matrix table according to the first parking data to obtain the first evaluation result, each cell of the first matrix table represents a test case in the first test case list; when the parking data corresponding to the first test case in the first test case list indicates that the virtual vehicle has been parked in the target parking space, the cell corresponding to the first test case is set to a first value; or, when the parking data corresponding to the first test case indicates that the virtual vehicle has not been parked in the target parking space, the cell corresponding to the first test case is set to a second value. The rows and columns of the first matrix table represent the width of the target parking space and the width of the road, respectively, and the cell at the cross intersection of each row and column of the first matrix table represents a test case in the first test case list.

[0121] In some implementations, when a virtual vehicle fails to park in a first target parking space indicated by a second test case in a first test case list, a first type of value is set for a cell corresponding to the second test case according to the reason for the parking failure, and the first type of value is different from the first value and the second value; wherein the reason for the parking failure includes at least one of the following: the first target parking space is not released, a collision occurs during parking, a collision risk is greater than a risk threshold during parking, a speed of the virtual vehicle is greater than a speed threshold during parking, an acceleration during deceleration is greater than an acceleration threshold during parking, and the automatic parking function to be evaluated is stuck.

[0122] Exemplarily, the first test case and the second test case may be the same test case, or may be different test cases.

[0123] For example, the first evaluation result may be as follows: Figure 8 As shown in the table in. More specifically, the first value and the second value can be numbers with different values, and the first type of values ​​can be different colors of the cell. Alternatively, the first value and the second value can be numbers with different values, and the first type of values ​​can be different colors of the numbers in the cell. Alternatively, the first value and the second value can be different colors of the cell, and the first type of values ​​can be different numbers in the cell.

[0124] In some implementations, the method further includes: controlling the virtual vehicle to repeatedly park in the target parking space indicated by each test case in the second test case list based on the automatic parking function to be evaluated, to obtain second parking data, wherein the number of repetitions is a preset number, and the first test case list includes the second test case list; filling a second matrix table according to the second parking data to generate a second evaluation result, wherein the value of each cell of the second matrix table represents the number of successful parkings corresponding to a test case in the second test case list.

[0125] Exemplarily, the second evaluation result may be as follows: Fig. 9As shown in the table.

[0126] In some implementations, the virtual vehicle is optimized based on the chassis function test results of the real vehicle, the chassis function test results are obtained by running the chassis function to be evaluated of the real vehicle in the target scene, and the target scene is associated with the scene elements that affect the chassis function when the automatic parking function to be evaluated runs in the real scene. Exemplarily, the target scene may include any of the following scene elements: road surface material, road surface state, road slope, wheel block, speed bump, vehicle tire pressure, and vehicle load.

[0127] In some implementations, the chassis function to be evaluated is associated with the automatic parking function to be evaluated. Exemplarily, the chassis function to be evaluated may include any of the following: starting, braking, gear switching, speed change (acceleration or deceleration), and steering.

[0128] The automatic parking function evaluation method provided in the embodiment of the present application can quickly obtain evaluation results with limited test scenarios, without the need for large-scale generalization, which helps to shorten the test cycle of the automatic parking function. In addition, for the test process of the automatic parking function, only a small amount of real vehicle test data is required, and a relatively accurate evaluation result can be obtained through simulation testing in the later stage, which can improve the safety of the automatic parking function test process (such as avoiding the scenario of collision when using real vehicle testing), thereby helping to save the manpower and material resources required for the automatic parking function test.

[0129] In the various embodiments of the present application, unless otherwise specified or logically conflicting, the terms and / or descriptions between the various embodiments are consistent and can be referenced to each other, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0130] Combined with the above Figures 1 to 10 The automatic parking capability evaluation method provided by the embodiment of the present application is described in detail. Fig.11 and Fig.12 The automatic parking capability evaluation device provided in the embodiment of the present application is described in detail. It should be understood that the description of the automatic parking capability evaluation device embodiment corresponds to the description of the method embodiment, so the contents not described in detail can be referred to the method embodiment above, and for the sake of brevity, they will not be repeated here.

[0131] Fig.11 A schematic block diagram of an automatic parking capability evaluation device 2000 provided in an embodiment of the present application is shown. The device 2000 may include a Figure 2 , Figure 5 , Figure 6 , Figure 7 , Fig.10 Furthermore, each unit in the device 2000 is used to implement Figure 2 , Figure 5 , Figure 6 , Figure 7 , Fig.10 The corresponding process of the method embodiment in FIG.

[0132] Specifically, the device 2000 includes a processing unit 2010 and a generating unit 2020, wherein the device 2000 is applied to Fig.10 In the method shown, the processing unit 2010 is used to: control the virtual vehicle to park in the target parking space indicated by each test case in the first test case list based on the automatic parking function to be evaluated, and obtain the first parking data. The first parking data indicates the parking trajectory of the virtual vehicle when parking in the target parking space indicated by each test case, the first test case list is associated with the first group of scene elements, the first group of scene elements is determined according to the scene elements that affect parking when the automatic parking function to be evaluated fails to run in the real scene, and the specifications of at least one scene element in the first group of scene elements associated with any two test cases in the first test case list are different. The generation unit 2020 is used to: generate a first evaluation result based on the first parking data, and the first evaluation result indicates at least one of the following: whether the process of the virtual vehicle parking in the target parking space indicated by the test case in the first test case list is successful, the performance boundary of the automatic parking function to be evaluated in the first group of scene elements, and the distribution of the test cases corresponding to the parking failure in the first test case list.

[0133] In some implementations, the virtual vehicle is optimized based on chassis function test results of a real vehicle, the chassis function test results are obtained by running the chassis function to be evaluated of the real vehicle in a target scenario, and the target scenario is associated with scenario elements that affect the chassis function when the automatic parking function to be evaluated is running in the real scenario.

[0134] In some implementations, the chassis function to be evaluated is associated with the automatic parking function to be evaluated.

[0135] In some implementations, the first group of scene elements includes a first type of obstacles, a first type of parking spaces, and a first type of parking methods, and the specifications of at least one scene element include the width of the target parking space and / or the width of the road, where the road is the road on which the virtual vehicle travels during the parking process.

[0136] In some implementations, the generation unit 2020 is used to: fill in a first matrix table according to the first parking data to obtain a first evaluation result, each cell of the first matrix table represents a test case in the first test case list; when the parking data corresponding to the first test case in the first test case list indicates that the virtual vehicle has been parked in the target parking space, the cell corresponding to the first test case is set to a first value; or, when the parking data corresponding to the first test case indicates that the virtual vehicle has not been parked in the target parking space, the cell corresponding to the first test case is set to a second value.

[0137] In some implementations, the generation unit 220 is also used to: when the virtual vehicle fails to park in the first target parking space indicated by the second test case in the first test case list, set a first type of value for the cell corresponding to the second test case according to the reason for the parking failure, and the first type of value is different from the category of the first value and the second value; wherein the reason for the parking failure includes at least one of the following: the first target parking space is not released, a collision occurs during the parking process, there is a collision risk greater than a risk threshold during the parking process, there is a speed of the virtual vehicle greater than a speed threshold during the parking process, there is an acceleration during deceleration greater than an acceleration threshold during the parking process, and the automatic parking function to be evaluated is stuck.

[0138] In some implementations, the processing unit 2010 is also used to: control the virtual vehicle to repeatedly park in the target parking space indicated by each test case in the second test case list based on the automatic parking function to be evaluated, and obtain second parking data, wherein the number of repetitions is a preset number of times, and the first test case list includes the second test case list; the generation unit 2020 is also used to: fill in the second matrix table according to the second parking data to generate a second evaluation result, and the value of each cell of the second matrix table represents the number of successful parking corresponding to a test case in the second test case list.

[0139] Exemplarily, the processing unit 2010 and the generating unit 2020 may be arranged in Figure 1 In the system shown in FIG. 1 , more specifically, the processing unit 2010 may include Figure 1 The test execution module 120 shown may also include a test scenario construction module 110, and the generation unit 2020 may include a result evaluation module 130. Exemplarily, the operations performed by the processing unit 2010 and the generation unit 2020 may be performed by one processor, or may be performed by different processors. In a specific implementation process, the one or more processors may be set in an electronic device, such as a computer or other electronic device.

[0140] In the specific implementation process, all or part of the units in the above device can be integrated together, or can be implemented independently. In one implementation, these units are integrated together and implemented in the form of a system-on-a-chip (SoC).

[0141] Fig.12 It is a schematic block diagram of an automatic parking capability evaluation device provided in an embodiment of the present application. Fig.12 The device 2100 shown may include: a processor 2110, a transceiver 2120, and a memory 2130. The processor 2110, the transceiver 2120, and the memory 2130 are connected via an internal connection path, the memory 2130 is used to store instructions, and the processor 2110 is used to execute the instructions stored in the memory 2130 to implement the methods in the above embodiments. Optionally, the memory 2130 may be coupled to the processor 2110 via an interface, or may be integrated with the processor 2110.

[0142] It should be noted that the transceiver 2120 may include but is not limited to a transceiver device such as an input / output interface to achieve communication between the device 2100 and other devices or a communication network.

[0143] The memory 2130 may be a read only memory (ROM), a static storage device, a dynamic storage device or a random access memory (RAM).

[0144] The transceiver 2120 uses a transceiver device such as but not limited to a transceiver to implement communication between the device 2100 and other devices or a communication network to receive / send data / information used to implement the methods in the above embodiments.

[0145] An embodiment of the present application also provides an electronic device, which is an intelligent driving device including the above-mentioned device 2000, or the above-mentioned device 2100.

[0146] An embodiment of the present application further provides a computer program product, which includes a computer program code. When the computer program code runs on a computer, the computer implements the methods in the above embodiments of the present application.

[0147] An embodiment of the present application further provides a computer-readable storage medium, which stores computer instructions. When the computer instructions are executed on a computer, the computer implements the methods in the above embodiments of the present application.

[0148] An embodiment of the present application also provides a chip, including a circuit, for executing the methods in the above embodiments of the present application.

[0149] In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software. The method disclosed in conjunction with the embodiment of the present application can be directly embodied as a hardware processor for execution, or a combination of hardware and software modules in a processor for execution. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or a power-on erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in conjunction with its hardware. To avoid repetition, it is not described in detail here.

[0150] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0151] In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is a kind of association relationship that describes associated objects, indicating that three relationships can exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In this application, "at least one" means one or more, and "multiple" means two or more. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0152] The prefixes such as "first" and "second" used in the embodiments of the present application are only used to distinguish different description objects, and have no limiting effect on the position, order, priority, quantity or content of the described objects. The use of prefixes such as ordinal numbers used to distinguish description objects in the embodiments of the present application does not constitute a limitation on the described objects. For the statement of the described objects, please refer to the description in the context of the claims or embodiments, and the use of such prefixes should not constitute an unnecessary limitation.

[0153] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0154] In the various embodiments of the present application, unless otherwise specified or logically conflicting, the terms and / or descriptions between the various embodiments are consistent and can be referenced to each other, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0155] 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 may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0156] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0157] 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.

Claims

1. A method for evaluating an automatic parking function, characterized in that: include: Controlling the virtual vehicle to park in the target parking space indicated by each test case in the first test case list in turn based on the automatic parking function to be evaluated, to obtain first parking data; wherein the first parking data indicates a parking trajectory of the virtual vehicle when parking in the target parking space indicated by each test case, the first test case list is associated with a first group of scene elements, the first group of scene elements is determined according to scene elements that affect parking when the automatic parking function to be evaluated fails to run in a real scene, and the specifications of at least one scene element in the first group of scene elements associated with any two test cases in the first test case list are different; A first evaluation result is generated based on the first parking data, and the first evaluation result indicates at least one of the following: whether a process of the virtual vehicle parking at a target parking space indicated by a test case in the first test case list is successful, a performance boundary of the automatic parking function to be evaluated in the first group of scene elements, and a distribution of test cases corresponding to parking failures in the first test case list.

2. The method according to claim 1, characterized in that The virtual vehicle is optimized according to chassis function test results of a real vehicle, and the chassis function test results are obtained by running the chassis function to be evaluated of the real vehicle in a target scenario, and the target scenario is associated with scenario elements that affect the chassis function when the automatic parking function to be evaluated is running in a real scenario.

3. The method according to claim 2, characterized in that The chassis function to be evaluated is associated with the automatic parking function to be evaluated.

4. The method according to any one of claims 1 to 3, characterized in that The first group of scene elements includes a first type of obstacles, a first type of parking spaces and a first type of parking methods. The specifications of at least one scene element include a width of a target parking space and / or a width of a road, and the road is a road on which the virtual vehicle travels during parking.

5. The method according to any one of claims 1 to 4, characterized in that The generating a first evaluation result according to the first parking data includes: Filling a first matrix table according to the first parking data to obtain the first evaluation result, wherein each cell of the first matrix table represents a test case in the first test case list; When the parking data corresponding to the first test case in the first test case list indicates that the virtual vehicle has been parked in the target parking space, the cell corresponding to the first test case is set to a first value; or, when the parking data corresponding to the first test case indicates that the virtual vehicle has not been parked in the target parking space, the cell corresponding to the first test case is set to a second value.

6. The method according to claim 5, characterized in that The method further comprises: When the virtual vehicle fails to park in the first target parking space indicated by the second test case in the first test case list, a first type of value is set for the cell corresponding to the second test case according to the reason for the parking failure, and the first type of value is different from the first value and the second value; Among them, the reasons for the parking failure include at least one of the following: the first target parking space is not released, a collision occurs during the parking process, there is a collision risk greater than a risk threshold during the parking process, there is a speed of the virtual vehicle greater than a speed threshold during the parking process, there is an acceleration during deceleration greater than an acceleration threshold during the parking process, and the automatic parking function to be evaluated is stuck.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: controlling the virtual vehicle to repeatedly park in a target parking space indicated by each test case in a second test case list based on the automatic parking function to be evaluated, to obtain second parking data, wherein the first test case list includes the second test case list; A second evaluation result is generated by filling a second matrix table according to the second parking data, wherein a value of each cell of the second matrix table represents the number of successful parkings corresponding to a test case in the second test case list.

8. An evaluation device for an automatic parking function, characterized in that: include: a processing unit, configured to control the virtual vehicle to park in a target parking space indicated by each test case in the first test case list in turn based on the automatic parking function to be evaluated, so as to obtain first parking data; wherein the first parking data indicates a parking trajectory of the virtual vehicle when parking in the target parking space indicated by each test case, the first test case list is associated with a first group of scene elements, the first group of scene elements is determined according to scene elements that affect parking when the automatic parking function to be evaluated fails to run in a real scene, and the specifications of at least one scene element in the first group of scene elements associated with any two test cases in the first test case list are different; a generating unit, configured to generate a first evaluation result according to the first parking data, wherein the first evaluation result indicates at least one of the following: whether a process of the virtual vehicle parking at a target parking space indicated by a test case in the first test case list is successful, a performance boundary of the automatic parking function to be evaluated in the first group of scene elements, and a distribution of test cases corresponding to parking failures in the first test case list.

9. The device according to claim 8, characterized in that The virtual vehicle is optimized according to chassis function test results of a real vehicle, and the chassis function test results are obtained by running the chassis function to be evaluated of the real vehicle in a target scenario, and the target scenario is associated with scenario elements that affect the chassis function when the automatic parking function to be evaluated is running in a real scenario.

10. The device according to claim 9, characterized in that The chassis function to be evaluated is associated with the automatic parking function to be evaluated.

11. The device according to any one of claims 8 to 10, characterized in that The first group of scene elements includes a first type of obstacles, a first type of parking spaces and a first type of parking methods. The specifications of at least one scene element include a width of a target parking space and / or a width of a road, and the road is a road on which the virtual vehicle travels during parking.

12. The device according to any one of claims 8 to 11, characterized in that The generating unit is used for: Filling a first matrix table according to the first parking data to obtain the first evaluation result, wherein each cell of the first matrix table represents a test case in the first test case list; When the parking data corresponding to the first test case in the first test case list indicates that the virtual vehicle has been parked in the target parking space, the cell corresponding to the first test case is set to a first value; or, when the parking data corresponding to the first test case indicates that the virtual vehicle has not been parked in the target parking space, the cell corresponding to the first test case is set to a second value.

13. The device according to claim 11, characterized in that The generating unit is further configured to: When the virtual vehicle fails to park in the first target parking space indicated by the second test case in the first test case list, a first type of value is set for the cell corresponding to the second test case according to the reason for the parking failure, and the first type of value is different from the first value and the second value; Among them, the reasons for the parking failure include at least one of the following: the first target parking space is not released, a collision occurs during the parking process, there is a collision risk greater than a risk threshold during the parking process, there is a speed of the virtual vehicle greater than a speed threshold during the parking process, there is an acceleration during deceleration greater than an acceleration threshold during the parking process, and the automatic parking function to be evaluated is stuck.

14. The device according to any one of claims 8 to 13, characterized in that The processing unit is also used for: controlling the virtual vehicle to repeatedly park in a target parking space indicated by each test case in a second test case list based on the automatic parking function to be evaluated, to obtain second parking data, wherein the first test case list includes the second test case list; The generating unit is further used to fill a second matrix table according to the second parking data to generate a second evaluation result, wherein the value of each cell of the second matrix table represents the number of successful parking corresponding to a test case in the second test case list.

15. An evaluation device for an automatic parking function, characterized in that: include: Memory for storing computer programs; A processor, configured to execute the computer program stored in the memory, so that the apparatus performs the method according to any one of claims 1 to 7.

16. An electronic device, characterized in that: The electronic device comprises the apparatus according to any one of claims 8 to 15.

17. A computer-readable storage medium, characterized in that: Instructions are stored thereon, and when the instructions are executed by a processor, the processor implements the method according to any one of claims 1 to 7.

18. A chip, characterized in that: The chip comprises a circuit for executing the method according to any one of claims 1 to 7.

Images