Vehicle testing method and device, computer equipment, readable storage medium and program product

By correlating the calculation of multiple evaluation indicators in the autonomous driving scenario, the problem of insufficient correlation calculation of scene elements in the prior art is solved, and the accuracy of performance evaluation of autonomous driving scenarios and the accuracy of vehicle testing is improved.

CN119086091AActive Publication Date: 2024-12-06FAW JIEFANG AUTOMOTIVE CO

Patent Information

Application Number
CN202411103528.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-13
Publication Date
2024-12-06
Estimated Expiration
2044-08-13

AI Technical Summary

Technical Problem

In the existing autonomous driving scenario complexity calculation scheme, the scene elements are not considered sufficiently, and the different scene elements cannot be effectively correlated and calculated, resulting in inaccurate evaluation.

Method used

By obtaining the current weather information, road information, number of traffic sign categories and dynamic information of traffic participants in the autonomous driving scenario, multiple evaluation indicators are calculated separately, and the target evaluation indicators are calculated based on these indicators and corresponding weight values ​​to evaluate the scenario pair Vehicle testing performance.

Benefits of technology

A more accurate evaluation of the performance of autonomous driving scenarios has been achieved, and the accuracy and efficiency of vehicle testing have been improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119086091A_ABST
    Figure CN119086091A_ABST
Patent Text Reader

Abstract

The invention relates to a vehicle testing method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring current weather information, current road information, current category number of traffic signs and current dynamic information of all traffic participants of an automatic driving scene in a current frame; obtaining a first evaluation index, a second evaluation index, a third evaluation index and a fourth evaluation index of the automatic driving scene based on the current weather information, the current road information, the current category number and the current dynamic information; obtaining a target evaluation index of the automatic driving scene based on the evaluation indexes and the weight value corresponding to each evaluation index; and testing the target vehicle in the automatic driving scene based on the target evaluation index. According to the method provided by the invention, the vehicle can be tested more accurately.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a vehicle testing method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] Testing based on autonomous driving scenarios is the main method for evaluating the safety and intelligence level of autonomous driving systems. The quality of autonomous driving scenarios will directly affect the effectiveness and efficiency of autonomous driving tests. Scenarios of different complexity can effectively evaluate the intelligence level of intelligent driving systems. Currently, there are many evaluation indicators for simulation test scenarios. As one of the important indicators, scene complexity currently has no unified calculation standard. In the existing scene complexity calculation scheme, scene elements are not fully considered, and different scene elements are not correlated for calculation. Summary of the invention

[0003] Based on this, it is necessary to provide a vehicle testing method, device, computer equipment, computer-readable storage medium and computer program product that can perform correlation calculations on all scene elements in order to address the above technical problems.

[0004] In a first aspect, the present application provides a vehicle testing method, the method comprising:

[0005] Obtain the current weather information, current road information, current number of traffic sign categories, and current dynamic information of all traffic participants in the current frame of the autonomous driving scene;

[0006] Respectively obtaining a first evaluation index, a second evaluation index, a third evaluation index, and a fourth evaluation index of the autonomous driving scenario based on the current weather information, the current road information, the current number of categories, and the current dynamic information;

[0007] Based on the first evaluation index, the second evaluation index, the third evaluation index, the fourth evaluation index and the corresponding weight value of each evaluation index, obtaining a target evaluation index for the autonomous driving scenario, wherein the target evaluation index is used to evaluate the test performance of the autonomous driving scenario on the vehicle;

[0008] Based on the target evaluation index, a target vehicle is tested in the autonomous driving scenario.

[0009] In one embodiment, the current weather information includes current light intensity, current visibility, current temperature, current humidity, current rainfall, and current snowfall; and obtaining the first evaluation index of the autonomous driving scenario based on the current weather information includes:

[0010] Get the optimum light intensity, preset maximum visibility, optimum temperature, optimum humidity, preset maximum snowfall and preset maximum rainfall;

[0011] Obtaining a first difference between the current light intensity and the optimum light intensity, a second difference between the preset maximum visibility and the current visibility, a third difference between the optimum temperature and the current temperature, and a fourth difference between the optimum humidity and the current humidity, and obtaining a larger value between the second difference and 0;

[0012] Based on the ratio between the first difference and the optimum light intensity, the ratio between the larger value and the preset maximum visibility, the ratio between the third difference and the optimum temperature, the ratio between the fourth difference and the optimum humidity, the ratio between the current rainfall and the preset maximum rainfall, and the ratio between the current snowfall and the preset maximum snowfall, a first evaluation index of the autonomous driving scenario is obtained.

[0013] In one embodiment, the current road information includes a current road type, a current number of lanes, a current road slope, and a current road curvature; and obtaining a second evaluation index of the autonomous driving scenario based on the current road information includes:

[0014] Obtaining an identifier corresponding to each road type, a preset maximum number of lanes, a preset maximum road slope, and a preset maximum road curvature;

[0015] Based on the identifier corresponding to the current road type, the maximum value between the current number of lanes and the preset maximum number of lanes, the minimum value between the current road slope and the preset maximum road slope, and the minimum value between the current road curvature and the preset maximum road curvature, a second evaluation index of the autonomous driving scenario is obtained.

[0016] In one embodiment, obtaining a third evaluation index of the autonomous driving scenario based on the current number of categories includes:

[0017] Obtaining the total number of preset categories of the traffic sign;

[0018] Based on the ratio between the current number of categories and the total number of preset categories, a third evaluation index of the autonomous driving scenario is obtained.

[0019] In one embodiment, the current dynamic information includes a current position, a current speed, a current direction, profile information, and a type; and obtaining a fourth evaluation index of the autonomous driving scene based on the current dynamic information includes:

[0020] Obtaining remaining traffic participants except the target vehicle from among all the traffic participants, and determining traffic participants among the remaining traffic participants that have a reachable path with the target vehicle as target traffic participants;

[0021] For each target traffic participant, based on the current position, the current speed, the current orientation, the profile information and the type, obtain the current time distance, the current occlusion relationship, the current shortest distance and the current orientation relationship between the target vehicle and the target traffic participant;

[0022] Based on the current time distance, the current occlusion relationship, the current shortest distance, the current orientation relationship and the type of the target traffic participant, a fourth evaluation index of the autonomous driving scenario is obtained.

[0023] In one embodiment, for each target traffic participant, based on the current position, the current speed, the current orientation, the profile information and the type, obtaining the current time distance, the current occlusion relationship, the current shortest distance and the current orientation relationship between the target vehicle and the target traffic participant includes:

[0024] Obtaining a speed difference between a current speed of the target vehicle and a current speed of the target traffic participant, and determining a ratio between the speed difference and a total mileage of a minimum achievable path as the current time distance;

[0025] Based on the current position, current orientation, contour information and type of the target vehicle, and the current position, current orientation, contour information and type of the target traffic participant, obtaining a current occlusion relationship between the target vehicle and the target traffic participant;

[0026] Based on the current position of the target vehicle and the current position of the target traffic participant, obtaining the current shortest distance between the target vehicle and the target traffic participant;

[0027] Based on the current orientation and current position of the target vehicle and the current position of the target traffic participant, a current orientation relationship between the target vehicle and the target traffic participant is acquired.

[0028] In a second aspect, the present application further provides a vehicle testing device, the device comprising:

[0029] A first acquisition module is used to acquire current weather information, current road information, current number of categories of traffic signs, and current dynamic information of all traffic participants in the autonomous driving scene in the current frame;

[0030] A second acquisition module is used to acquire a first evaluation index, a second evaluation index, a third evaluation index and a fourth evaluation index of the autonomous driving scene based on the current weather information, the current road information, the current number of categories and the current dynamic information respectively;

[0031] A third acquisition module, configured to acquire a target evaluation index for the autonomous driving scenario based on the first evaluation index, the second evaluation index, the third evaluation index, the fourth evaluation index, and a weight value corresponding to each evaluation index, wherein the target evaluation index is used to evaluate the test performance of the autonomous driving scenario on the vehicle;

[0032] A testing module is used to test the target vehicle in the autonomous driving scenario based on the target evaluation index.

[0033] In a third aspect, the present application further provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method in any one of the above embodiments when executing the computer program.

[0034] In a fourth aspect, the present application further provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method in any one of the above embodiments are implemented.

[0035] In a fifth aspect, the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the method in any one of the above embodiments are implemented.

[0036] The above-mentioned vehicle testing method, device, computer equipment, computer-readable storage medium and computer program product obtain the current weather information, current road information, current number of categories of traffic signs, and current dynamic information of all traffic participants in the current frame of the autonomous driving scene; obtain the first evaluation index, the second evaluation index, the third evaluation index and the fourth evaluation index of the autonomous driving scene based on the current weather information, the current road information, the current number of categories and the current dynamic information respectively; obtain the target evaluation index of the autonomous driving scene based on the first evaluation index, the second evaluation index, the third evaluation index, the fourth evaluation index and the corresponding weight value of each evaluation index, and the target evaluation index is used to evaluate the test performance of the autonomous driving scene for testing the vehicle; based on the target evaluation index, the target vehicle is tested in the autonomous driving scene. The method provided by the present application takes into account all possible scene elements in the autonomous driving scene, and associates and calculates these scene elements to obtain the target evaluation index, so that the target evaluation index obtained can more accurately evaluate the performance of the autonomous driving scene, thereby conducting a more accurate test on the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 A schematic diagram of a vehicle testing method according to an embodiment of the present invention;

[0039] Figure 2 Schematic diagram of a flow chart of a method for obtaining a first evaluation index in an embodiment;

[0040] Figure 3 A flow chart of a vehicle testing method in another embodiment;

[0041] Figure 4 is a structural block diagram of a vehicle testing device in one embodiment;

[0042] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0044] In one embodiment, Figure 1 As shown, a vehicle testing method is provided. This embodiment uses the method applied to a terminal as an example for illustration. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0045] S102: Obtain current weather information, current road information, current number of categories of traffic signs, and current dynamic information of all traffic participants in the autonomous driving scene in the current frame.

[0046] First, the original data of the autonomous driving scene is obtained, and then the current weather data, current road information, current number of categories of traffic signs, and current dynamic information of all traffic participants in the original data are arranged in ascending order according to the order of timestamps. After the arranged data are matched with the fields in the simulation scene proto, they are written into different channels (storage buffer area, responsible for storing events) frame by frame for storage.

[0047] S104. Obtain a first evaluation index, a second evaluation index, a third evaluation index, and a fourth evaluation index of the autonomous driving scenario based on the current weather information, the current road information, the current number of categories, and the current dynamic information, respectively.

[0048] Among them, each evaluation indicator is used to evaluate the influence of the corresponding scene elements of the autonomous driving scene on the vehicle test.

[0049] S106. Based on the first evaluation index, the second evaluation index, the third evaluation index, the fourth evaluation index and the corresponding weight value of each evaluation index, obtain the target evaluation index of the autonomous driving scenario, and the target evaluation index is used to evaluate the test performance of the autonomous driving scenario on the vehicle.

[0050] Among them, the target evaluation index can be determined by the following formula:

[0051]

[0052] In the formula, C is the target evaluation index, is the first evaluation index, is the corresponding weight value of the first evaluation index, is the second evaluation index, is the corresponding weight value of the second evaluation index, is the third evaluation index, is the corresponding weight value of the third evaluation index, is the fourth evaluation index, is the corresponding weight value of the fourth evaluation index.

[0053] When the autonomous driving scene is an urban scene, in order to increase the impact of obstacle vehicles and intersections on the target evaluation index, K 2 and K 4 The value is 0.35, k 1 Take 0.1, k 3 The weight value is 0.2. When the autonomous driving scenario is other scenarios, the weight value may also take other values, which is not specifically limited in the embodiments of the present application.

[0054] S108. Testing the target vehicle in the autonomous driving scenario based on the target evaluation index.

[0055] Among them, when the target evaluation index is greater than the preset index, it means that the overall performance of the current autonomous driving scenario is good and it can be used as a scenario for testing the target vehicle; when the target evaluation index is less than the preset index, it means that the overall performance of the current autonomous driving scenario is poor and the result of vehicle testing in this scenario will not be accurate enough. Therefore, this scenario will not be used as a test scenario for the target vehicle.

[0056] You can use dimensions such as mean, maximum, median, and longest subsequence to mark scenes. These indicators can also be used in the scene library to quickly filter and organize scenes to improve scene maintenance efficiency.

[0057] In the above vehicle testing method, the current weather information, current road information, current number of categories of traffic signs, and current dynamic information of all traffic participants in the current frame of the autonomous driving scene are obtained; based on the current weather information, current road information, current number of categories and current dynamic information, the first evaluation index, the second evaluation index, the third evaluation index and the fourth evaluation index of the autonomous driving scene are obtained; based on the first evaluation index, the second evaluation index, the third evaluation index, the fourth evaluation index and the corresponding weight value of each evaluation index, the target evaluation index of the autonomous driving scene is obtained, and the target evaluation index is used to evaluate the test performance of the autonomous driving scene for testing the vehicle; based on the target evaluation index, the target vehicle is tested in the autonomous driving scene. The method provided by the present application takes into account all possible scene elements in the autonomous driving scene, and associates and calculates these scene elements to obtain the target evaluation index, so that the target evaluation index obtained can more accurately evaluate the performance of the autonomous driving scene, thereby conducting more accurate testing of the vehicle.

[0058] In some embodiments, Figure 2 As shown, the current weather information includes the current light intensity, the current visibility, the current temperature, the current humidity, the current rainfall and the current snowfall; based on the current weather information, the first evaluation index of the autonomous driving scene is obtained, including:

[0059] S202, obtaining an optimum light intensity, a preset maximum visibility, an optimum temperature, an optimum humidity, a preset maximum snowfall, and a preset maximum rainfall.

[0060] S204, obtaining a first difference between the current light intensity and the optimum light intensity, a second difference between the preset maximum visibility and the current visibility, a third difference between the optimum temperature and the current temperature, and a fourth difference between the optimum humidity and the current humidity, and obtaining a larger value between the second difference and 0.

[0061] S206. Based on the ratio between the first difference and the optimum light intensity, the ratio between the larger value and the preset maximum visibility, the ratio between the third difference and the optimum temperature, the ratio between the fourth difference and the optimum humidity, the ratio between the current rainfall and the preset maximum rainfall, and the ratio between the current snowfall and the preset maximum snowfall, obtain a first evaluation index for the autonomous driving scenario.

[0062] The determination process of the first evaluation index is as follows:

[0063]

[0064] Where, L i is the current light intensity, L s is the most suitable light intensity, V max is the preset maximum visibility, V i is the current visibility, T s is the optimum temperature, T i is the current temperature, H s is the optimum humidity, H i is the current humidity, R i is the current rainfall, R max is the preset maximum rainfall, S i is the current snowfall, S max The preset maximum snowfall amount.

[0065] In this embodiment, the first evaluation index is determined based on weather information in multiple dimensions, so that the subsequent evaluation of the performance of the autonomous driving scenario based on the first evaluation index is more accurate, thereby making the test process of the target vehicle more accurate.

[0066] In some embodiments, the current road information includes the current road type, the current number of lanes, the current road slope and the current road curvature; based on the current road information, a second evaluation index of the autonomous driving scene is obtained, including: obtaining an identifier corresponding to each road type, a preset maximum number of lanes, a preset maximum road slope and a preset maximum road curvature; based on the identifier corresponding to the current road type, the maximum value between the current number of lanes and the preset maximum number of lanes, the minimum value between the current road slope and the preset maximum road slope, and the minimum value between the current road curvature and the preset maximum road curvature, a second evaluation index of the autonomous driving scene is obtained.

[0067] Among them, road types include straight roads, ramps, bridges, tunnels and intersections. The identifier of a straight road is 0, and the identifiers of other road types are 1.

[0068] The determination process of the second evaluation index is as follows:

[0069]

[0070] In the formula, is the identifier of the current road type, R c is the current number of lanes, R max The maximum number of lanes is preset, for example, R max is 5, R slope is the current road slope, The maximum road slope is preset. For urban roads and highways, the road slope is generally 7-12%. Take 10%, R rate is the current road curvature, To preset the maximum road curvature, for urban roads and highways, the road curvature is generally 0.002-0.01. Take 0.01.

[0071] In this embodiment, the second evaluation index is determined based on a variety of road information, so that the subsequent evaluation of the performance of the autonomous driving scenario based on the second evaluation index is more accurate, thereby making the test process of the target vehicle more accurate.

[0072] In some embodiments, based on the current number of categories, a third evaluation index of the autonomous driving scenario is obtained, including: obtaining the total number of preset categories of traffic signs; based on the ratio between the current number of categories and the total number of preset categories, obtaining the third evaluation index of the autonomous driving scenario.

[0073] Among them, the categories of traffic signs may include regulatory signs, warning signs, direction signs, tourist area signs, work area signs, auxiliary signs and special signs, and the total number of preset categories may be 7.

[0074] The determination process of the third evaluation index is as follows:

[0075]

[0076] In the formula, S c is the current category number, S max The total number of preset categories.

[0077] In this embodiment, the third evaluation index is determined based on the current number of categories and the total number of preset categories, so that the subsequent evaluation of the performance of the autonomous driving scenario based on the third evaluation index is more accurate, thereby making the test process of the target vehicle more accurate.

[0078] In some embodiments, the current dynamic information includes the current position, current speed, current direction, contour information and type; based on the current dynamic information, a fourth evaluation index of the autonomous driving scenario is obtained, including: obtaining the remaining traffic participants except the target vehicle among all traffic participants, and determining the traffic participants among the remaining traffic participants who have a reachable path with the target vehicle as the target traffic participants; for each target traffic participant, based on the current position, current speed, current direction, contour information and type, obtaining the current time distance, current occlusion relationship, current shortest distance and current orientation relationship between the target vehicle and the target traffic participant; based on the current time distance, current occlusion relationship, current shortest distance, current orientation relationship and the type of the target traffic participant, a fourth evaluation index of the autonomous driving scenario is obtained.

[0079] Among them, the current position relationship may include the target traffic participant being directly in front of, in front of, behind, and directly behind the target vehicle; the type of the target traffic participant may be a pedestrian, a bicycle, a car, etc.

[0080] In this embodiment, the fourth evaluation index is determined based on a variety of dynamic information, so that the subsequent evaluation of the performance of the autonomous driving scenario based on the fourth evaluation index is more accurate, thereby making the test process of the target vehicle more accurate.

[0081] In some embodiments, for each target traffic participant, based on the current position, current speed, current orientation, contour information and type, the current time distance, current occlusion relationship, current shortest distance and current orientation relationship between the target vehicle and the target traffic participant are obtained, including: obtaining the speed difference between the current speed of the target vehicle and the current speed of the target traffic participant, and determining the ratio between the speed difference and the total mileage of the minimum reachable path as the current time distance; obtaining the current occlusion relationship between the target vehicle and the target traffic participant based on the current position, current orientation, contour information and type of the target vehicle, and the current position, current orientation, contour information and type of the target traffic participant; obtaining the current shortest distance between the target vehicle and the target traffic participant based on the current position of the target vehicle and the current position of the target traffic participant; obtaining the current orientation relationship between the target vehicle and the target traffic participant based on the current orientation and current position of the target vehicle, and the current position of the target traffic participant.

[0082] The determination process of the fourth evaluation index is as follows:

[0083]

[0084] Where V car is the current speed of the target vehicle, V obis the current speed of the target traffic participant, r_dis is the total mileage of the minimum accessible path, Area s Area is the volume of the target traffic participant blocked by other traffic participants with the target vehicle as the origin. all is the total volume of the target traffic participant, dis is the current shortest distance between the target vehicle and the target traffic participant, and F i is the current direction, Ob type is the category of the target traffic participant.

[0085] In this embodiment, by determining the current time distance, the current occlusion relationship, the current shortest distance and the current orientation relationship, the determined fourth evaluation index is made more accurate.

[0086] In one embodiment, another vehicle testing method is provided. The flowchart of the method is as follows: Figure 3 As shown, the method includes the following contents:

[0087] S1: Data access, converting csv and rosbag data into simulation scenario format;

[0088] S2: Simulation scenario complexity calculation;

[0089] S2.1: Computational weather complexity;

[0090] S2.2: Calculate road complexity;

[0091] S2.3: Calculate the complexity of transportation facilities;

[0092] S2.4: Calculate the complexity of traffic participants;

[0093] S2.5: Single complexity aggregation calculation;

[0094] S3: Associate the scenes in the scene library with the complexity of the calculation.

[0095] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0096] Based on the same inventive concept, the embodiment of the present application also provides a vehicle testing device for implementing the vehicle testing method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more vehicle testing device embodiments provided below can refer to the limitations on the vehicle testing method above, and will not be repeated here.

[0097] In an exemplary embodiment, Figure 4 As shown, a vehicle testing device 400 is provided, comprising: a first acquisition module 401, a second acquisition module 402, a third acquisition module 403 and a testing module 404, wherein:

[0098] The first acquisition module 401 is used to obtain the current weather information, current road information, current number of categories of traffic signs, and current dynamic information of all traffic participants in the automatic driving scene in the current frame.

[0099] The second acquisition module 402 is used to obtain the first evaluation index, the second evaluation index, the third evaluation index and the fourth evaluation index of the autonomous driving scenario based on the current weather information, the current road information, the current number of categories and the current dynamic information, respectively.

[0100] The third acquisition module 403 is used to acquire the target evaluation index of the autonomous driving scenario based on the first evaluation index, the second evaluation index, the third evaluation index, the fourth evaluation index and the corresponding weight value of each evaluation index, wherein the target evaluation index is used to evaluate the test performance of the autonomous driving scenario on the vehicle.

[0101] The testing module 404 is used to test the target vehicle in the autonomous driving scenario based on the target evaluation index.

[0102] In some embodiments, the current weather information includes current light intensity, current visibility, current temperature, current humidity, current rainfall and current snowfall; the second acquisition module 402 is also used to obtain the optimum light intensity, preset maximum visibility, optimum temperature, optimum humidity, preset maximum snowfall and preset maximum rainfall; obtain a first difference between the current light intensity and the optimum light intensity, a second difference between the preset maximum visibility and the current visibility, a third difference between the optimum temperature and the current temperature, and a fourth difference between the optimum humidity and the current humidity, and obtain a larger value between the second difference and 0; based on the ratio between the first difference and the optimum light intensity, the ratio between the larger value and the preset maximum visibility, the ratio between the third difference and the optimum temperature, the ratio between the fourth difference and the optimum humidity, the ratio between the current rainfall and the preset maximum rainfall, and the ratio between the current snowfall and the preset maximum snowfall, obtain the first evaluation index of the autonomous driving scene.

[0103] In some embodiments, the current road information includes the current road type, the current number of lanes, the current road slope and the current road curvature; the second acquisition module 402 is also used to obtain the corresponding identifier of each road type, the preset maximum number of lanes, the preset maximum road slope and the preset maximum road curvature; based on the identifier corresponding to the current road type, the maximum value between the current number of lanes and the preset maximum number of lanes, the minimum value between the current road slope and the preset maximum road slope, and the minimum value between the current road curvature and the preset maximum road curvature, the second evaluation index of the autonomous driving scenario is obtained.

[0104] In some embodiments, the second acquisition module 402 is further used to obtain the total number of preset categories of the traffic sign; and obtain a third evaluation index of the autonomous driving scenario based on the ratio between the current number of categories and the total number of preset categories.

[0105] In some embodiments, the current dynamic information includes current position, current speed, current direction, profile information and type; the second acquisition module 402 includes:

[0106] The first acquisition unit is used to acquire the remaining traffic participants except the target vehicle from among all the traffic participants, and determine the traffic participants among the remaining traffic participants who have a reachable path with the target vehicle as target traffic participants.

[0107] A second acquisition unit is used to acquire, for each target traffic participant, a current time distance, a current occlusion relationship, a current shortest distance, and a current orientation relationship between the target vehicle and the target traffic participant based on the current position, the current speed, the current orientation, the profile information, and the type;

[0108] The third acquisition unit is used to acquire a fourth evaluation index of the autonomous driving scenario based on the current time distance, the current occlusion relationship, the current shortest distance, the current orientation relationship and the type of the target traffic participant.

[0109] In some embodiments, the second acquisition unit is also used to obtain the speed difference between the current speed of the target vehicle and the current speed of the target traffic participant, and determine the ratio of the speed difference to the total mileage of the minimum reachable path as the current time distance; based on the current position, current orientation, contour information and type of the target vehicle, and the current position, current orientation, contour information and type of the target traffic participant, obtain the current occlusion relationship between the target vehicle and the target traffic participant; based on the current position of the target vehicle and the current position of the target traffic participant, obtain the current shortest distance between the target vehicle and the target traffic participant; based on the current orientation and current position of the target vehicle, and the current position of the target traffic participant, obtain the current orientation relationship between the target vehicle and the target traffic participant.

[0110] Each module in the above vehicle testing device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.

[0111] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 5As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, a near field communication (NFC) or other technologies. When the computer program is executed by the processor, a vehicle testing method is implemented.

[0112] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0113] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the following steps when executing the computer program: obtaining current weather information, current road information, current number of categories of traffic signs, and current dynamic information of all traffic participants of an autonomous driving scene in a current frame; obtaining a first evaluation index, a second evaluation index, a third evaluation index, and a fourth evaluation index of the autonomous driving scene based on the current weather information, the current road information, the current number of categories, and the current dynamic information, respectively; obtaining a target evaluation index of the autonomous driving scene based on the first evaluation index, the second evaluation index, the third evaluation index, the fourth evaluation index, and the corresponding weight value of each evaluation index, wherein the target evaluation index is used to evaluate the test performance of the autonomous driving scene on a vehicle; and testing a target vehicle in the autonomous driving scene based on the target evaluation index.

[0114] In one embodiment, the obtaining of the first evaluation index of the autonomous driving scene based on the current weather information implemented by the processor when executing a computer program includes: obtaining an optimum light intensity, a preset maximum visibility, an optimum temperature, an optimum humidity, a preset maximum snowfall, and a preset maximum rainfall; obtaining a first difference between the current light intensity and the optimum light intensity, a second difference between the preset maximum visibility and the current visibility, a third difference between the optimum temperature and the current temperature, and a fourth difference between the optimum humidity and the current humidity, and obtaining a larger value between the second difference and 0; obtaining the first evaluation index of the autonomous driving scene based on the ratio between the first difference and the optimum light intensity, the ratio between the larger value and the preset maximum visibility, the ratio between the third difference and the optimum temperature, the ratio between the fourth difference and the optimum humidity, the ratio between the current rainfall and the preset maximum rainfall, and the ratio between the current snowfall and the preset maximum snowfall.

[0115] In one embodiment, the obtaining of the second evaluation index of the autonomous driving scenario based on the current road information implemented when the processor executes a computer program includes: obtaining an identifier corresponding to each road type, a preset maximum number of lanes, a preset maximum road slope, and a preset maximum road curvature; obtaining the second evaluation index of the autonomous driving scenario based on the identifier corresponding to the current road type, the maximum value between the current number of lanes and the preset maximum number of lanes, the minimum value between the current road slope and the preset maximum road slope, and the minimum value between the current road curvature and the preset maximum road curvature.

[0116] In one embodiment, the processor executes a computer program to obtain a third evaluation index of the autonomous driving scenario based on the current number of categories, including: obtaining the total number of preset categories of the traffic signs; and obtaining the third evaluation index of the autonomous driving scenario based on the ratio between the current number of categories and the total number of preset categories.

[0117] In one embodiment, the obtaining of the fourth evaluation index of the autonomous driving scenario based on the current dynamic information implemented by the processor when executing a computer program includes: obtaining the remaining traffic participants except the target vehicle among all the traffic participants, and determining the traffic participants among the remaining traffic participants who have a reachable path with the target vehicle as target traffic participants; for each target traffic participant, obtaining the current time distance, current occlusion relationship, current shortest distance and current orientation relationship between the target vehicle and the target traffic participant based on the current position, the current speed, the current orientation, the contour information and the type; obtaining the fourth evaluation index of the autonomous driving scenario based on the current time distance, the current occlusion relationship, the current shortest distance, the current orientation relationship and the type of the target traffic participant.

[0118] In one embodiment, the processor executes a computer program to obtain, for each target traffic participant, a current headway, a current occlusion relationship, a current shortest distance, and a current orientation relationship between the target vehicle and the target traffic participant based on the current position, the current speed, the current orientation, the contour information, and the type, including: obtaining a speed difference between a current speed of the target vehicle and a current speed of the target traffic participant, and determining a ratio between the speed difference and the total mileage of a minimum reachable path as the current headway; obtaining a current occlusion relationship between the target vehicle and the target traffic participant based on the current position, current orientation, contour information, and type of the target vehicle, and the current position, current orientation, contour information, and type of the target traffic participant; obtaining a current shortest distance between the target vehicle and the target traffic participant based on the current position of the target vehicle and the current position of the target traffic participant; and obtaining a current orientation relationship between the target vehicle and the target traffic participant based on the current orientation and current position of the target vehicle and the current position of the target traffic participant.

[0119] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0120] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0121] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0122] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0123] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0124] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A vehicle testing method, characterized in that: The method comprises: Obtain the current weather information, current road information, current number of traffic sign categories, and current dynamic information of all traffic participants in the current frame of the autonomous driving scene; Respectively obtaining a first evaluation index, a second evaluation index, a third evaluation index, and a fourth evaluation index of the autonomous driving scenario based on the current weather information, the current road information, the current number of categories, and the current dynamic information; Based on the first evaluation index, the second evaluation index, the third evaluation index, the fourth evaluation index and the corresponding weight value of each evaluation index, obtaining a target evaluation index for the autonomous driving scenario, wherein the target evaluation index is used to evaluate the test performance of the autonomous driving scenario on the vehicle; Based on the target evaluation index, a target vehicle is tested in the autonomous driving scenario.

2. The method according to claim 1, characterized in that: The current weather information includes current light intensity, current visibility, current temperature, current humidity, current rainfall, and current snowfall; and obtaining the first evaluation index of the autonomous driving scenario based on the current weather information includes: Get the optimum light intensity, preset maximum visibility, optimum temperature, optimum humidity, preset maximum snowfall and preset maximum rainfall; Obtaining a first difference between the current light intensity and the optimum light intensity, a second difference between the preset maximum visibility and the current visibility, a third difference between the optimum temperature and the current temperature, and a fourth difference between the optimum humidity and the current humidity, and obtaining a larger value between the second difference and 0; Based on the ratio between the first difference and the optimum light intensity, the ratio between the larger value and the preset maximum visibility, the ratio between the third difference and the optimum temperature, the ratio between the fourth difference and the optimum humidity, the ratio between the current rainfall and the preset maximum rainfall, and the ratio between the current snowfall and the preset maximum snowfall, a first evaluation index of the autonomous driving scenario is obtained.

3. The method according to claim 1, characterized in that The current road information includes a current road type, a current number of lanes, a current road slope, and a current road curvature; and obtaining a second evaluation index of the autonomous driving scenario based on the current road information includes: Obtaining an identifier corresponding to each road type, a preset maximum number of lanes, a preset maximum road slope, and a preset maximum road curvature; Based on the identifier corresponding to the current road type, the maximum value between the current number of lanes and the preset maximum number of lanes, the minimum value between the current road slope and the preset maximum road slope, and the minimum value between the current road curvature and the preset maximum road curvature, a second evaluation index of the autonomous driving scenario is obtained.

4. The method according to claim 1, characterized in that: The obtaining, based on the current number of categories, a third evaluation index of the autonomous driving scenario includes: Obtaining the total number of preset categories of the traffic sign; Based on the ratio between the current number of categories and the total number of preset categories, a third evaluation index of the autonomous driving scenario is obtained.

5. The method according to claim 1, characterized in that The current dynamic information includes a current position, a current speed, a current direction, profile information, and a type; and obtaining a fourth evaluation index of the autonomous driving scene based on the current dynamic information includes: Obtaining remaining traffic participants except the target vehicle from among all the traffic participants, and determining traffic participants among the remaining traffic participants that have a reachable path with the target vehicle as target traffic participants; For each target traffic participant, based on the current position, the current speed, the current orientation, the profile information and the type, obtain the current time distance, the current occlusion relationship, the current shortest distance and the current orientation relationship between the target vehicle and the target traffic participant; Based on the current time distance, the current occlusion relationship, the current shortest distance, the current orientation relationship and the type of the target traffic participant, a fourth evaluation index of the autonomous driving scenario is obtained.

6. The method according to claim 5, characterized in that The method of obtaining, for each target traffic participant, a current time distance, a current occlusion relationship, a current shortest distance, and a current orientation relationship between the target vehicle and the target traffic participant based on the current position, the current speed, the current orientation, the profile information, and the type, includes: Obtaining a speed difference between a current speed of the target vehicle and a current speed of the target traffic participant, and determining a ratio between the speed difference and a total mileage of a minimum achievable path as the current time distance; Based on the current position, current orientation, contour information and type of the target vehicle, and the current position, current orientation, contour information and type of the target traffic participant, obtaining a current occlusion relationship between the target vehicle and the target traffic participant; Based on the current position of the target vehicle and the current position of the target traffic participant, obtaining the current shortest distance between the target vehicle and the target traffic participant; Based on the current orientation and current position of the target vehicle and the current position of the target traffic participant, a current orientation relationship between the target vehicle and the target traffic participant is acquired.

7. A vehicle testing device, characterized in that: The device comprises: A first acquisition module is used to acquire current weather information, current road information, current number of categories of traffic signs, and current dynamic information of all traffic participants in the autonomous driving scene in the current frame; A second acquisition module is used to acquire a first evaluation index, a second evaluation index, a third evaluation index and a fourth evaluation index of the autonomous driving scene based on the current weather information, the current road information, the current number of categories and the current dynamic information respectively; A third acquisition module, configured to acquire a target evaluation index for the autonomous driving scenario based on the first evaluation index, the second evaluation index, the third evaluation index, the fourth evaluation index, and a weight value corresponding to each evaluation index, wherein the target evaluation index is used to evaluate the test performance of the autonomous driving scenario on the vehicle; A testing module is used to test the target vehicle in the autonomous driving scenario based on the target evaluation index.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Citation Information

Patent Citations

  • Testing method and device for driverless automobiles

    CN105954040A

  • Scene classification method and device for automatic driving vehicle road testing

    CN111178402A

  • Method and system for evaluating complexity of intelligent automobile test scene

    CN111651712A

  • Complexity-based automatic driving effective static scene construction method and system

    CN114820922A

  • Vehicle scene complexity determination method

    CN115376324A

Cited By

  • Evaluation method for automatic driving road passing regulation conformity test scene

    CN120236398A