Autonomous driving vehicle performance testing method, device, electronic device and storage medium

Abstract

The present disclosure provides a method, device, electronic device, storage medium and program product for testing the performance of an autonomous driving vehicle, which relates to the field of artificial intelligence technology, and in particular to the field of autonomous driving technology. The specific implementation scheme is: determining test driving behavior data about the autonomous driving vehicle, the test driving behavior data corresponding to a predetermined test point on a predetermined driving trajectory; and determining the performance test result of the autonomous driving vehicle based on the test driving behavior data and a benchmark driving behavior data set, the benchmark driving behavior data set including verified benchmark driving behavior data, and the benchmark driving behavior data corresponding to the predetermined test point.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, in particular to the field of autonomous driving technology, and specifically to methods, devices, electronic devices, storage media, and program products for testing the performance of autonomous driving vehicles. Background Art

[0002] Autonomous vehicles can sense the surrounding environment through sensing components such as sensors and obtain surrounding environment data. The surrounding environment data is combined with map navigation data to make driving decisions through calculations. Finally, the autonomous driving of the autonomous vehicle is completed according to the driving decision through the control and execution system.

[0003] The autonomous driving performance of autonomous vehicles in terms of perception, calculation, and decision-making is an important consideration for the widespread use of autonomous vehicles. Summary of the invention

[0004] The present disclosure provides a method, device, electronic device, storage medium and program product for testing the performance of an autonomous driving vehicle.

[0005] According to one aspect of the present disclosure, a method for testing the performance of an autonomous driving vehicle is provided, comprising: determining test driving behavior data about the autonomous driving vehicle, wherein the test driving behavior data corresponds to predetermined test points on a predetermined driving trajectory; and determining a performance test result of the autonomous driving vehicle based on the test driving behavior data and a baseline driving behavior data set, wherein the baseline driving behavior data set includes calibrated baseline driving behavior data, and the baseline driving behavior data corresponds to the predetermined test points.

[0006] According to another aspect of the present disclosure, an autonomous driving vehicle performance testing device is provided, comprising: a first determination module, used to determine test driving behavior data about the autonomous driving vehicle, wherein the test driving behavior data corresponds to a predetermined test point on a predetermined driving trajectory; and a second determination module, used to determine a performance test result of the autonomous driving vehicle based on the test driving behavior data and a benchmark driving behavior data set, wherein the benchmark driving behavior data set includes calibrated benchmark driving behavior data, and the benchmark driving behavior data corresponds to the predetermined test point.

[0007] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a method as disclosed in the present disclosure.

[0008] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method of the present disclosure.

[0009] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program implements the method of the present disclosure when executed by a processor.

[0010] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0012] Figure 1 An exemplary system architecture to which the method and device for testing the performance of an autonomous driving vehicle according to an embodiment of the present disclosure can be applied is schematically shown;

[0013] Figure 2 A flowchart of a method for testing the performance of an autonomous driving vehicle according to an embodiment of the present disclosure is schematically shown;

[0014] Figure 3 A schematic diagram of determining benchmark driving behavior data according to an embodiment of the present disclosure is schematically shown;

[0015] Figure 4 A schematic diagram of determining benchmark driving behavior data according to an embodiment of the present disclosure is schematically shown;

[0016] Figure 5 A flowchart of a method for testing the performance of an autonomous driving vehicle according to another embodiment of the present disclosure is schematically shown;

[0017] Figure 6 A schematic diagram schematically shows a method for determining a performance test result according to another embodiment of the present disclosure;

[0018] Figure 7 A block diagram schematically shows an autonomous driving vehicle performance testing device according to an embodiment of the present disclosure; and

[0019] Figure 8 A block diagram of an electronic device suitable for implementing a method for testing the performance of an autonomous driving vehicle according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0020] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0021] The present disclosure provides a method, device, electronic device, storage medium and program product for testing the performance of an autonomous driving vehicle.

[0022] According to an embodiment of the present disclosure, a method for testing the performance of an autonomous driving vehicle is provided, which may include: determining test driving behavior data about the autonomous driving vehicle. The test driving behavior data corresponds to a predetermined test point on a predetermined driving trajectory. Based on the test driving behavior data and a baseline driving behavior data set, a performance test result of the autonomous driving vehicle is determined. The baseline driving behavior data set may include verified baseline driving behavior data, and the baseline driving behavior data corresponds to the predetermined test point.

[0023] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision, disclosure and application of user personal information involved comply with the provisions of relevant laws and regulations, take necessary confidentiality measures, and do not violate public order and good morals.

[0024] In the technical solution of the present disclosure, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0025] Figure 1 An exemplary system architecture to which the method and apparatus for testing the performance of an autonomous driving vehicle can be applied according to an embodiment of the present disclosure is schematically illustrated.

[0026] It should be noted that Figure 1 The examples shown are only examples of system architectures to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but do not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios. For example, in another embodiment, an exemplary system architecture to which the autonomous driving vehicle performance test method and apparatus can be applied may include a terminal device, but the terminal device may implement the autonomous driving vehicle performance test method and apparatus provided by the embodiments of the present disclosure without interacting with a server.

[0027] like Figure 1As shown, the system architecture 100 according to this embodiment may include an autonomous driving vehicle 101, a network 102, and a server 103. The network 102 is used to provide a medium for a communication link between the autonomous driving vehicle 101 and the server 103. The network 102 may include various connection types, such as wired and / or wireless communication links, and the like.

[0028] A user may use the autonomous vehicle 101 to interact with the server 103 via the network 102 to receive or send messages, etc.

[0029] The autonomous driving vehicle 101 may be implemented as any type of vehicle, including a sports car, a passenger car, a multi-purpose vehicle, an electric vehicle, or a truck, etc. (for example only).

[0030] The autonomous driving vehicle 101 may have a memory and a processor. The memory may be used to store program instructions that can be executed by the processor. In addition, the memory may also store a navigation application. In combination with vehicle position information obtained by a navigation positioning device mounted on the autonomous driving vehicle 101, for example, the navigation application may also be configured to determine a predetermined driving trajectory.

[0031] The autonomous driving vehicle 101 may also be equipped with environmental sensors and state sensors. The environmental sensors may include one or more of image sensors, radar sensors, ultrasonic sensors, and laser sensors. The environmental sensors may be configured to collect environmental data around the autonomous driving vehicle 101. The state sensors may include one or more of acceleration sensors, inertial measurement units, speed sensors, pressure sensors, and direction sensors. The state sensors may be configured to collect state data of the autonomous driving vehicle 101 itself.

[0032] The server 103 may be a server that provides various services, such as a background management server (only as an example) that provides support for the data transmitted by the environmental sensors and state sensors of the autonomous driving vehicle 101. The background management server may analyze the received data and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the autonomous driving vehicle 101.

[0033] It should be noted that the autonomous driving vehicle performance test method provided in the embodiment of the present disclosure can generally be performed by the autonomous driving vehicle 101. Accordingly, the autonomous driving vehicle performance test device provided in the embodiment of the present disclosure can also be set in the autonomous driving vehicle 101.

[0034] Alternatively, the autonomous driving vehicle performance testing method provided in the embodiment of the present disclosure may also be executed by the server 103. Accordingly, the autonomous driving vehicle performance testing device provided in the embodiment of the present disclosure may also be arranged in the server 103. The autonomous driving vehicle performance testing method provided in the embodiment of the present disclosure may also be executed by a server or server cluster that is different from the server 103 and can communicate with the autonomous driving vehicle 101 and / or the server 103. Accordingly, the autonomous driving vehicle performance testing device provided in the embodiment of the present disclosure may also be arranged in a server or server cluster that is different from the server 103 and can communicate with the autonomous driving vehicle 101 and / or the server 103.

[0035] It should be understood that Figure 1 The number of autonomous driving vehicles, networks, and servers in the embodiment is only for illustration purposes. Any number of terminal devices, networks, and servers may be provided as required.

[0036] It should be noted that the sequence numbers of the operations in the following method are only used as representations of the operations for the purpose of description, and should not be regarded as representing the execution order of the operations. Unless explicitly stated, the method does not need to be executed completely in the order shown.

[0037] Figure 2 A flowchart of an autonomous driving vehicle performance testing method according to an embodiment of the present disclosure is schematically shown.

[0038] like Figure 2 As shown, the method includes operations S210 to S220.

[0039] In operation S210, test driving behavior data about the autonomous driving vehicle is determined, wherein the test driving behavior data corresponds to a predetermined test point on a predetermined driving trajectory.

[0040] In operation S220 , a performance test result of the autonomous driving vehicle is determined based on the test driving behavior data and the baseline driving behavior data set.

[0041] According to an embodiment of the present disclosure, the reference driving behavior data set may include calibrated reference driving behavior data, and the reference driving behavior data corresponds to a predetermined test point.

[0042] According to an embodiment of the present disclosure, the benchmark driving behavior data in the benchmark driving behavior data set may be obtained by collecting verified driving behavior data of the autonomous driving vehicle during the autonomous driving process, but is not limited thereto, and may also be obtained by collecting verified driving behavior data of the driver during the driving of the autonomous driving vehicle. As long as it is verified benchmark driving behavior data, it can be used as reference data to evaluate the autonomous driving performance of the autonomous driving vehicle.

[0043] According to an embodiment of the present disclosure, each benchmark driving behavior data may represent driving behavior data collected during a round of driving along a predetermined driving trajectory and may be used as a reference.

[0044] According to an embodiment of the present disclosure, the predetermined driving trajectory may refer to a planned trajectory virtually formed based on information such as the actual driving road and the road surrounding environment, etc. For example, it may be a virtual driving trajectory for navigation determined based on the topology around the vehicle in a navigation application.

[0045] According to an embodiment of the present disclosure, the predetermined test point may be at least one track point on the predetermined driving track, for example, the predetermined test point may include multiple track points. The multiple predetermined test points may be track points divided according to the same distance interval on the predetermined driving track, but are not limited thereto, and the multiple predetermined test points may also be track points divided according to different distance intervals on the predetermined driving track according to actual conditions.

[0046] According to the embodiments of the present disclosure, the number of multiple predetermined test points is not limited. If the number of predetermined test points is small, the data volume of the determined baseline driving behavior data and the test driving behavior data is small, resulting in a small amount of calculation, and the accuracy of the corresponding autonomous driving vehicle performance test results is reduced. Conversely, if the number of predetermined test points is large, the data volume of the determined baseline driving behavior data and the test driving behavior data is large, resulting in a large amount of calculation, and the accuracy of the corresponding autonomous driving vehicle performance test results is improved. The number of predetermined test points can be set according to actual conditions.

[0047] According to an embodiment of the present disclosure, the test driving behavior data may match the number of predetermined test points, for example, multiple test driving behavior data may be collected. The multiple test driving behavior data may be actual driving behavior data collected based on the position information of multiple predetermined test points during the driving of the autonomous driving vehicle along the predetermined driving trajectory.

[0048] According to an embodiment of the present disclosure, the test driving behavior data corresponds to a predetermined test point on a predetermined driving trajectory, which may mean that the position information of the actual driving trajectory point corresponding to the test driving behavior data may be the same as the position information of the predetermined test point. However, it is not limited to this. The test driving behavior data corresponds to a predetermined test point on a predetermined driving trajectory, which may mean that the position information of the actual driving trajectory point corresponding to the test driving behavior data may correspond to the position information of the predetermined test point. The position information of the actual driving trajectory point may correspond to the position information of the predetermined test point, which may mean that the position coordinate information of the actual driving trajectory point A in the driving direction is the same as the position coordinate information of the predetermined test point B corresponding to the actual driving trajectory point A in the driving direction, while the position coordinate information of the actual driving trajectory point A in the direction perpendicular to the driving direction and the position coordinate information of the predetermined test point B in the direction perpendicular to the driving direction may be different.

[0049] For example, the driving direction is the Y-axis direction in the two-dimensional coordinate system, the position coordinate information of the driving trajectory point A can be (X_A, Y), and the position coordinate information of the predetermined test point B can be (X_B, Y). The driving trajectory point A and the predetermined test point B have the same coordinate point on the Y axis, and the coordinate points X_A and X_B are different on the X axis. In this case, it can also be considered that the test driving behavior data corresponding to the driving trajectory point A is in a corresponding relationship with the predetermined test point B.

[0050] According to the embodiments of the present disclosure, based on the above-mentioned matching method, the benchmark driving behavior data corresponding to the predetermined test point can also be determined. Then, the benchmark driving behavior data corresponding to the test driving behavior data can be determined based on the predetermined test point on the predetermined driving trajectory. In this way, the performance test results of the autonomous driving vehicle can be determined based on the test driving behavior data and the benchmark driving behavior data set.

[0051] According to an embodiment of the present disclosure, by utilizing predetermined test points on a predetermined driving trajectory, the test driving behavior data can be matched with the baseline driving behavior data, thereby automatically and objectively evaluating the autonomous driving performance of the autonomous driving vehicle during actual driving.

[0052] According to an embodiment of the present disclosure, before performing operation S210, the autonomous driving vehicle performance test method may further include the following operations. For example, at least one initial baseline driving behavior data subset may be obtained, and each initial baseline driving behavior data subset may include initial baseline driving behavior data obtained by driving the autonomous driving vehicle along a predetermined driving trajectory for one round. The initial baseline driving behavior data may correspond to a predetermined test point. The initial baseline driving trajectory of the driver driving the autonomous driving vehicle may be determined based on the initial baseline driving behavior data. However, it is not limited to this. The initial baseline driving behavior data subset may include initial baseline driving behavior data corresponding to the predetermined test point and other initial driving behavior data about the driver driving the autonomous driving vehicle. Other initial driving behavior data corresponds to other driving trajectory points on the predetermined driving trajectory except the predetermined test point. The initial baseline driving trajectory of the driver driving the autonomous driving vehicle may be determined based on the initial base accurate driving behavior data in the initial baseline driving behavior data subset and other initial driving behavior data.

[0053] According to an embodiment of the present disclosure, compared with determining the initial baseline driving trajectory of the driver driving the autonomous driving vehicle based on the initial base accurate driving behavior data in the initial baseline driving behavior data subset, determining the initial baseline driving trajectory of the driver driving the autonomous driving vehicle based on the initial base accurate driving behavior data in the initial baseline driving behavior data subset and other initial driving behavior data uses more driving behavior data, thereby making the determined initial baseline driving trajectory closer to the actual driving trajectory.

[0054] According to an embodiment of the present disclosure, it is possible to determine whether the initial reference driving behavior data meets the normal driving behavior standard based on the degree of approximation between the initial reference driving trajectory and the predetermined driving trajectory. For example, the driver drives according to the predetermined driving trajectory to obtain a first initial reference driving behavior data subset. Based on the first initial reference driving behavior data subset, the first initial reference driving trajectory is determined. If the degree of approximation between the first initial reference driving trajectory and the predetermined driving trajectory is high, it means that the first initial reference driving behavior data about the driver driving the automatic driving vehicle in the first initial reference driving behavior data subset corresponding to the first reference driving trajectory meets the normal driving behavior standard. On the contrary, if the degree of deviation between the first initial reference driving trajectory and the predetermined driving trajectory is high, it means that the first initial reference driving behavior data about the driver driving the automatic driving vehicle in the first initial reference driving behavior data subset corresponding to the first initial reference driving trajectory has an abnormal phenomenon and does not meet the normal driving behavior standard. The initial reference driving behavior data that does not meet the normal driving behavior standard can be deleted. The initial reference driving behavior data that meets the normal driving behavior standard is used as the benchmark driving behavior data, and the initial reference driving behavior data subset corresponding to the benchmark driving behavior data is used as the benchmark driving behavior data subset in the benchmark driving behavior data set.

[0055] Figure 3 A schematic diagram of determining benchmark driving behavior data according to an embodiment of the present disclosure is schematically shown.

[0056] like Figure 3 As shown, the first initial reference driving trajectory 310 can be determined by the first initial reference driving behavior data subset, and the second initial reference driving trajectory 320 can be determined by the second initial reference driving behavior data subset. The first initial reference driving trajectory 310 and the second initial reference driving trajectory 320 are respectively compared with the predetermined driving trajectory 330, and whether there is an abnormality in the first initial reference driving behavior data and the second initial reference driving behavior data is determined by the comparison result.

[0057] According to an embodiment of the present disclosure, it may be determined whether the initial reference driving behavior data corresponding to the initial reference driving trajectory is abnormal by a predetermined verification threshold.

[0058] like Figure 3As shown, any track point S_310A on the first initial reference driving track 310 can be selected, and a track point S_330A corresponding to the track point S_310A on the first initial reference driving track can be determined on the predetermined driving track 330. When it is determined that the lateral spacing between the track point S_310A and the track point S_330A is less than or equal to the predetermined verification threshold, it is determined that the degree of approximation between the track point S_310A and the track point S_330A is high, and the first initial reference driving behavior data is normal. Similarly, the track point S_320A on the second initial reference driving track 320 also corresponds to the track point S_330A on the predetermined driving track 330. When it is determined that the lateral spacing W between the track point S_320A and the track point S_330A is greater than the predetermined verification threshold, it can be determined that the degree of approximation between the track point S_320A and the track point S_330A is low, and the second initial reference driving behavior data is abnormal.

[0059] According to an embodiment of the present disclosure, any track point on the predetermined driving track can be compared with a track point on the initial reference driving track corresponding to the track point to determine whether the initial reference driving behavior data is abnormal. However, it is not limited to this. It is also possible to determine whether the initial reference driving behavior data is abnormal based on comparing multiple track points on the predetermined driving track with multiple track points on the initial reference driving track corresponding to the track points one by one.

[0060] For example, a plurality of trajectory points on the predetermined driving trajectory may be used to determine the degree of closeness between the predetermined driving trajectory and the initial reference driving trajectory. When the number of trajectory points that characterize a high degree of closeness between the two trajectories is greater than a predetermined number threshold, the initial reference driving behavior data may be determined to be normal. Conversely, when the number of trajectory points that characterize a high degree of closeness between the two trajectories is less than or equal to a predetermined number threshold, the initial reference driving behavior data may be determined to be abnormal.

[0061] like Figure 3As described above, it is possible to determine whether the first initial reference driving behavior data is abnormal based on the track points S_330A, S_330B, S_330C, S_330D, S_330E, and S_330F on the predetermined driving track 330. For example, based on the track points S_330A, S_330B, S_330C, S_330D, S_330E, and S_330F, and the six track points on the first initial reference driving track corresponding to the six track points, the lateral spacing between the six track points in the predetermined driving track and the six track points on the first initial reference driving track is determined. For example, the lateral spacing corresponding to the track point S_330A, the lateral spacing corresponding to the track point S_330B, the lateral spacing corresponding to the track point S_330C, the lateral spacing corresponding to the track point S_330D, the lateral spacing corresponding to the track point S_330E, and the lateral spacing corresponding to the track point S_330F. The number of track points whose lateral spacing is greater than or equal to the predetermined verification threshold is determined by 6 lateral spacings. In the case where the number of track points whose lateral spacing is greater than or equal to the predetermined verification threshold is greater than or equal to the predetermined number threshold, it is determined that the degree of approximation between the first initial reference driving trajectory 310 and the predetermined driving trajectory 330 is high. If the degree of approximation between the first initial reference driving trajectory 320 and the predetermined driving trajectory 330 is high, it is determined that the first initial reference driving behavior data is normal. Similarly, if the degree of approximation between the second initial reference driving trajectory 320 and the predetermined driving trajectory 330 is low, it is determined that the second initial reference driving behavior data is abnormal and should be discarded.

[0062] According to an embodiment of the present disclosure, before executing an operation to determine the performance test results of an autonomous driving vehicle based on the test driving behavior data and the baseline driving behavior data set, a subset of the collected initial baseline driving behavior data is preliminarily screened so that abnormal initial baseline driving behavior data is deleted to avoid contamination of data that does not meet normal driving behavior standards, and the verification operation of the initial baseline driving behavior data is completed, thereby improving the accuracy of the performance test results.

[0063] According to an embodiment of the present disclosure, the driver's baseline driving behavior data is used to evaluate the test driving behavior data, thereby obtaining the performance test results of the autonomous driving vehicle. The performance test results can also show the intelligence and flexibility of the autonomous driving vehicle. In addition, by using the above-mentioned method of determining the subset of baseline driving behavior data, it can be ensured that the baseline driving behavior data set can reflect the driving level of excellent drivers, thereby improving the accuracy and authenticity of the performance test results.

[0064] According to an embodiment of the present disclosure, when a driver drives an autonomous driving vehicle based on a predetermined driving trajectory, the driving behavior data of the autonomous driving vehicle is generally collected in real time in chronological order to obtain benchmark driving behavior data. For example, the benchmark driving behavior data includes benchmark driving behavior data corresponding to a predetermined test point, and other driving behavior data on the predetermined driving trajectory except for the predetermined test point. The benchmark driving trajectory can be determined based on the benchmark driving behavior data.

[0065] Figure 4 A schematic diagram of determining benchmark driving behavior data according to an embodiment of the present disclosure is schematically shown.

[0066] like Figure 4 As shown, based on the predetermined test point S_410A, the predetermined test point S_410B, and the predetermined test point S_410C of the predetermined driving trajectory point 410, the initial reference driving trajectory point position S_420A, the initial reference driving trajectory point position S_420B, and the initial reference driving trajectory point position S_420C corresponding to the predetermined test point S_410A, the predetermined test point S_410B, and the predetermined test point S_410C can be determined from the initial reference driving trajectory 420. Based on the initial reference driving trajectory point position, a plurality of initial reference driving behavior data corresponding to the plurality of predetermined test points are determined from the plurality of initial reference driving behavior data and the plurality of other driving behavior data.

[0067] According to an embodiment of the present disclosure, determining a plurality of test driving behavior data about an autonomous driving vehicle may also include the following operations. For example, in a case where the autonomous driving vehicle is driving based on a predetermined driving trajectory, a plurality of initial test driving behavior data of the autonomous driving vehicle are collected. Based on the plurality of initial test driving behavior data, a test driving trajectory of the autonomous driving vehicle is determined. Based on a predetermined test point of the predetermined driving trajectory, a target test position corresponding to the predetermined test point is determined from the test driving trajectory of the autonomous driving vehicle. Based on the target test position, the test driving behavior data is determined from the plurality of initial test driving behavior data.

[0068] According to an embodiment of the present disclosure, the target test position corresponding to the predetermined test point may refer to that the position coordinate information of the predetermined test point is exactly the same as the position coordinate information of the target test position, but is not limited to this. It may also refer to that the position coordinate information of the predetermined test point in the driving direction is the same as the position coordinate information of the target test position in the driving direction, while the position coordinate information of the predetermined test point in the direction perpendicular to the driving direction and the position coordinate information of the target test position in the direction perpendicular to the driving direction may be different.

[0069] According to an embodiment of the present disclosure, the predetermined driving trajectory can be used to match the benchmark driving behavior data and the test driving behavior data. Then, the performance test result is obtained based on the benchmark driving behavior data and the test driving behavior data. Before performing operations S210 and S220, an operation of determining the predetermined driving trajectory can be performed.

[0070] Figure 5 A flowchart of a method for testing the performance of an autonomous driving vehicle according to another embodiment of the present disclosure is schematically shown.

[0071] like Figure 5 As shown, the method includes operations S510 to S550.

[0072] In operation S510 , a target trajectory point of a predetermined driving trajectory is determined.

[0073] According to an embodiment of the present disclosure, the target trajectory point may include one or more of a starting point, an end point, and an intermediate point of a predetermined driving trajectory.

[0074] In operation S520, a predetermined driving trajectory is generated based on the target trajectory point.

[0075] According to an embodiment of the present disclosure, a predetermined driving trajectory can be generated based on at least one target trajectory point, but is not limited to this. The predetermined driving trajectory can also be generated based on map information, such as a drivable road trajectory in the map information, combined with at least one target trajectory point.

[0076] According to an embodiment of the present disclosure, a predetermined driving trajectory is generated by using at least one target trajectory point and map information. The predetermined driving trajectory can be a trajectory marked in the map. Multiple predetermined test points can be marked in an automatic manner, and the predetermined driving trajectory can be used to navigate the autonomous driving vehicle on the motor vehicle lane, thereby avoiding planning the predetermined driving trajectory on the non-motor vehicle lane.

[0077] In operation S530 , a predetermined test point on a predetermined driving track is determined.

[0078] In operation S540, it is determined whether a predetermined test point is generated. In the case where it is determined that the predetermined test point is generated, operation S550 may be performed. In the case where it is determined that the predetermined test point is not generated, operations S520 to S540 are repeatedly performed until the predetermined test point is generated.

[0079] In operation S550 , initial baseline driving behavior data of the autonomous driving vehicle is collected.

[0080] According to the embodiments of the present disclosure, the autonomous driving performance testing method provided by the implementation of the present disclosure can ensure that the planning of the predetermined driving trajectory and the predetermined test points has been completed before the initial baseline driving behavior data is collected, thereby ensuring that the corresponding initial baseline driving behavior data can be matched according to the predetermined test points.

[0081] According to an embodiment of the present disclosure, before determining the test driving behavior data about the autonomous driving vehicle, the autonomous driving vehicle performance testing method may also perform the following operations.

[0082] For example, a target trajectory point of a predetermined driving trajectory is determined. Based on the target trajectory point, a predetermined driving trajectory is generated. A predetermined test point on the predetermined driving trajectory is determined. It is determined whether to generate the predetermined test point. In the case where it is determined that the predetermined test point is generated, an operation of collecting initial test driving behavior data of the autonomous driving vehicle can be performed. In the case where it is determined that the predetermined test point is not generated, the operations of generating a predetermined driving trajectory based on the target trajectory point, determining a predetermined test point on the predetermined driving trajectory, and determining whether to generate the predetermined test point are repeatedly performed until the predetermined test point is generated.

[0083] According to the embodiments of the present disclosure, the automatic driving performance testing method provided by the implementation of the present disclosure can ensure that the planning of the predetermined driving trajectory and the predetermined test points has been completed before collecting the test driving behavior data, thereby ensuring that the corresponding test driving behavior data can be matched according to the predetermined test points.

[0084] According to an embodiment of the present disclosure, the test driving behavior data may include a plurality of test driving behavior sub-data of different performance indicators.

[0085] For example, at least one of the multiple test driving behavior sub-data of different performance indicators may include one or more of the test driving behavior sub-data related to the efficiency indicator, the test driving behavior sub-data related to the comfort indicator, and the test driving behavior sub-data related to the safety indicator. However, it is not limited to this. The test driving behavior sub-data may also include the test driving behavior sub-data related to the trip rationality indicator, and the test driving behavior sub-data related to the traffic rules indicator, etc.

[0086] According to an embodiment of the present disclosure, the test driving behavior sub-data related to the high efficiency index may include driving behavior data related to driving efficiency, such as 1 / average speed, but is not limited to this and may also include other driving behavior data related to driving efficiency, which will not be repeated here.

[0087] According to an embodiment of the present disclosure, the test driving behavior sub-data related to the comfort index may include lateral acceleration, longitudinal acceleration, average speed, lateral acceleration change rate, longitudinal acceleration change rate, etc., but is not limited to this. It may also include other driving behavior data related to the comfort index, which will not be repeated here.

[0088] According to an embodiment of the present disclosure, the test driving behavior sub-data related to safety indicators may include the safe distance from surrounding obstacles, steering wheel angle, etc., but is not limited to this. It may also include other driving behavior data related to safety indicators, which will not be repeated here.

[0089] According to the embodiments of the present disclosure, the autonomous driving vehicle performance testing method includes test driving behavior sub-data related to efficiency indicators, test driving behavior sub-data related to comfort indicators, and test driving behavior sub-data related to safety indicators. It can realize autonomous driving performance evaluation of different multi-dimensional indicators such as safety, efficiency, comfort, etc. in a single scenario, which is more targeted and comprehensive.

[0090] According to an embodiment of the present disclosure, for operation S220, determining the performance test result of the autonomous driving vehicle based on the test driving behavior data and the benchmark driving behavior data set may include: determining the performance test sub-results of each of the plurality of test driving behavior sub-data of the test driving behavior data based on the benchmark driving behavior data set. Determining the performance test result of the test driving behavior data based on the performance test sub-results of each of the plurality of test driving behavior sub-data.

[0091] For example, the plurality of test driving behavior sub-data of the test driving behavior data may include data such as average speed and safety distance of surrounding obstacles. Based on the benchmark driving behavior data set, the performance test sub-result for the average speed and the performance test sub-result for the safety distance of surrounding obstacles may be determined. The performance test result of the test driving behavior data may be determined based on the performance test sub-result for the average speed and the performance test sub-result for the safety distance of surrounding obstacles.

[0092] According to an embodiment of the present disclosure, determining the performance test result of the test driving behavior data based on the performance test sub-results of each of the multiple test driving behavior sub-data may include: performing weighted summation on the multiple test driving behavior sub-data to obtain the performance test result of the test driving behavior data. However, it is not limited to this. Alternatively, the performance test sub-results of each of the multiple test driving behavior sub-data may be directly averaged to obtain the performance test result of the test driving behavior data.

[0093] According to an embodiment of the present disclosure, a baseline driving behavior data set may include multiple baseline driving behavior data subsets. Multiple baseline driving behavior data subsets may be data obtained by multiple drivers driving an autonomous driving vehicle along a predetermined driving trajectory. However, it is not limited to this. Multiple baseline driving behavior data subsets may also be data obtained by a driver driving an autonomous driving vehicle for multiple rounds along a predetermined driving trajectory. As long as the baseline driving behavior data set is determined based on a sufficient number of baseline driving behavior data subsets, it will suffice.

[0094] According to an embodiment of the present disclosure, a plurality of predetermined test points may be set on the predetermined driving trajectory, for example, a predetermined test point S1, a predetermined test point S2, a predetermined test point S3, and a predetermined test point S4. A plurality of test driving behavior data corresponding one-to-one to a plurality of predetermined test points may include test driving behavior data T1, test driving behavior data T2, test driving behavior data T3, and test driving behavior data T4. A benchmark driving behavior data set includes a plurality of benchmark driving behavior data subsets, each of which may include a plurality of benchmark driving behavior data corresponding one-to-one to a plurality of predetermined test points. For example, a benchmark driving behavior data set may include 2 benchmark driving behavior data subsets. A first benchmark driving behavior data subset may include benchmark driving behavior data R1_C1, benchmark driving behavior data R1_C2, benchmark driving behavior data R1_C3, and benchmark driving behavior data R1_C4. A second benchmark driving behavior data subset may include benchmark driving behavior data R2_C1, benchmark driving behavior data R2_C2, benchmark driving behavior data R2_C3, and benchmark driving behavior data R2_C4. The more predetermined test points are set for the test driving behavior data, the more test driving behavior data and benchmark driving behavior data corresponding one-to-one to the predetermined test points are, and the higher the accuracy of the performance test results of the autonomous driving vehicle is.

[0095] According to an embodiment of the present disclosure, for each predetermined test point, the test driving behavior data corresponding to the predetermined test point may include multiple test driving behavior sub-data of different performance indicators. For each predetermined test point, the benchmark driving behavior data corresponding to the predetermined test point may include multiple benchmark driving behavior sub-data of different performance indicators.

[0096] According to an embodiment of the present disclosure, when determining the performance test sub-results of each of a plurality of test driving behavior sub-data, for example, when determining the performance test sub-results of each of the test driving behavior data T1, a target test position in the test driving trajectory corresponding to the test driving behavior data T1 can be determined for the test driving behavior data T1. Based on the target test position, a target predetermined test point in the predetermined driving trajectory corresponding to the target test position is determined. Based on the target predetermined test point, a target reference position in the reference driving trajectory corresponding to the target predetermined test point is determined. Based on the target reference position, a plurality of target reference driving behavior sub-data in a reference driving behavior data set are determined. Based on the plurality of target reference driving behavior sub-data and the test driving behavior sub-data, the performance test sub-results of the test driving behavior sub-data are determined.

[0097] For example, for the test driving behavior sub-data T1_D1 in the test driving behavior data T1, the target predetermined test point S1 can be determined based on the position information in the test driving behavior sub-data T1_D1, that is, the target test position. Based on the target predetermined test point S1, the target reference position of the reference driving trajectory is determined. Based on the target reference position, multiple benchmark driving behavior sub-data with the same performance indicator type as the test driving behavior sub-data T1_D1 are determined. For example, the benchmark driving behavior sub-data R1_C1_D1 in the benchmark driving behavior data R1_C1 and the benchmark driving behavior sub-data R2_C1_D1 in the benchmark driving behavior data R2_C1. The performance test sub-result of the test driving behavior sub-data T1_D1 can be determined based on the benchmark driving behavior sub-data R1_C1_D1 and the benchmark driving behavior sub-data R2_C1_D1. Similarly, the performance test sub-results of other test driving behavior sub-data in the test driving behavior data T1 can be obtained. The performance test result is determined based on multiple performance test sub-results corresponding one-to-one to multiple test driving behavior sub-data.

[0098] According to other embodiments of the present disclosure, when determining the performance test sub-results of each of a plurality of test driving behavior sub-data, calculations can also be performed based on the order of a plurality of predetermined test points in a predetermined driving trajectory. For example, for a target predetermined test point in a predetermined driving trajectory, a target test position and a target reference position corresponding to the target predetermined test point can be determined from the test driving trajectory and the reference driving trajectory, respectively. Test driving behavior sub-data are determined based on the target test position, and a plurality of target reference driving behavior sub-data having the same performance index as the test driving behavior sub-data are determined based on the target reference position. Based on the plurality of target reference driving behavior sub-data and the test driving behavior sub-data, performance test sub-results of the test driving behavior sub-data are determined.

[0099] According to an embodiment of the present disclosure, a benchmark condition that meets a predetermined standard can be determined based on multiple target benchmark driving behavior sub-data. The performance test sub-result is determined using the benchmark condition that meets the predetermined standard. For example, in the case where the test driving behavior sub-data meets the benchmark condition, the first evaluation value is used as the performance test sub-result of the test driving behavior sub-data. In the case where the test driving behavior sub-data does not meet the benchmark condition, a second evaluation value is determined based on the multiple target benchmark driving behavior sub-data and the test driving behavior sub-data, and the second data is used as the performance test sub-result of the test driving behavior sub-data.

[0100] According to an exemplary embodiment of the present disclosure, based on a plurality of baseline driving behavior sub-data, it can be determined that the baseline driving behavior eventually tends to be consistent, and the obtained baseline driving behavior sub-data obeys a normal distribution. A baseline condition that meets a predetermined standard can be determined based on a sufficient amount of baseline driving behavior sub-data. For example, the baseline condition may include a baseline threshold value, and the baseline threshold value may include, for example, a value greater than or equal to a minimum value among the plurality of baseline driving behavior sub-data, and less than a maximum value among the plurality of baseline driving behavior sub-data.

[0101] According to an embodiment of the present disclosure, the test driving behavior sub-data satisfying the benchmark condition may refer to: the test driving behavior sub-data is greater than or equal to the minimum value among multiple benchmark driving behavior sub-data, and is less than the maximum value among multiple benchmark driving behavior sub-data. In this case, the first evaluation value, such as score 1, can be used as the performance test sub-result. The test driving behavior sub-data not satisfying the benchmark condition may refer to: the test driving behavior sub-data is less than the minimum value among multiple benchmark driving behavior sub-data, or the test driving behavior sub-data is greater than the maximum value among multiple benchmark driving behavior sub-data. In this case, a second evaluation value can be determined based on multiple target benchmark driving behavior sub-data and the test driving behavior sub-data, and the second evaluation value can be used as the performance test sub-result of the test driving behavior sub-data.

[0102] Figure 6 A schematic diagram of determining performance test results according to another embodiment of the present disclosure is schematically shown.

[0103] like Figure 6As shown, taking the driving behavior sub-data of longitudinal acceleration as an example, the circular points are used to represent the target benchmark driving behavior sub-data, and the triangular points are used to represent the test driving behavior sub-data. When driving to a distance of 400 meters from the starting point, the longitudinal driving degree value 611 of the test driving behavior sub-data meets the benchmark condition, for example, it is greater than the minimum longitudinal driving degree value 612 of the target benchmark driving behavior sub-data, and less than the maximum longitudinal acceleration value 613 of the target benchmark driving behavior sub-data, then the performance test sub-result of the test driving behavior sub-data for longitudinal acceleration can be the first evaluation value, score 1. Similarly, it can be determined based on the above calculation method that the performance test sub-result of the test driving behavior sub-data for lateral safe driving distance at a distance of 400 meters from the starting point can be the second evaluation value, score 0.8. Weights can be configured for the performance test sub-result of the test driving behavior sub-data for longitudinal acceleration and the performance test sub-result of the test driving behavior sub-data for lateral safe driving distance, respectively, and the weighted sum is used to determine the performance test result of the test driving behavior data at a distance of 400 meters from the starting point.

[0104] According to an embodiment of the present disclosure, a plurality of predetermined test points may be set in the predetermined driving trajectory, and the performance test results of the plurality of test driving behavior data corresponding to the plurality of predetermined test points may be weighted to obtain the performance test result of the entire test driving trajectory.

[0105] like Figure 6 As shown, when the vehicle is traveling to a distance of 800 meters from the starting point, the longitudinal driving degree value 621 of the test driving behavior sub-data does not meet the benchmark condition, for example, it is less than the minimum longitudinal acceleration value 622 of the target benchmark driving behavior sub-data, then the performance test sub-result of the test driving behavior sub-data for longitudinal acceleration can be the second evaluation value, with a score of 0.6. Similarly, based on the above calculation method, it can be determined that the performance test sub-result of the test driving behavior sub-data for the lateral safe driving distance at a distance of 800 meters from the starting point can be the second evaluation value, with a score of 0.7. Weights can be configured for the performance test sub-result of the test driving behavior sub-data for longitudinal acceleration and the performance test sub-result of the test driving behavior sub-data for the lateral safe driving distance, respectively, and the performance test result of the test driving behavior data at a distance of 800 meters from the starting point is determined by weighted summation.

[0106] According to an embodiment of the present disclosure, the performance test result of the entire test driving trajectory can be obtained based on the average of the performance test result of the test driving behavior data at a distance of 800 meters from the starting point and the performance test result of the test driving behavior data at a distance of 400 meters from the starting point.

[0107] According to an embodiment of the present disclosure, the second evaluation value may be determined according to formula (1).

[0108]

[0109] in, score represents the second evaluation value of the test driving behavior sub-data; μ represents the expected value of the normal distribution determined by multiple target benchmark driving behavior sub-data; σ represents the standard deviation of the normal distribution determined by multiple target benchmark driving behavior sub-data; x represents the test driving behavior sub-data; minx represents the minimum value in the target benchmark driving behavior sub-data that meets the benchmark conditions.

[0110] According to the embodiments of the present disclosure, the autonomous driving vehicle performance test method provided by the present disclosure can be applied to high-frequency scenarios of autonomous driving of autonomous driving vehicles, such as starting and encountering a stationary vehicle ahead, U-turn scenarios, left turn scenarios, right turn scenarios, bypassing obstacles scenarios, and cut-in scenarios, thereby effectively improving the autonomous driving evaluation performance of the autonomous driving vehicle. In addition, the autonomous driving vehicle performance test results can be used to improve the autonomous driving strategy and make the autonomous driving vehicle more intelligent.

[0111] Figure 7 A block diagram of an autonomous driving vehicle performance testing device according to an embodiment of the present disclosure is schematically shown.

[0112] like Figure 7 As shown, the autonomous driving vehicle performance testing device 700 may include a first determination module 710 and a second determination module 720 .

[0113] The first determination module 710 is used to determine test driving behavior data about the autonomous driving vehicle, wherein the test driving behavior data corresponds to a predetermined test point on a predetermined driving trajectory.

[0114] The second determination module 720 is used to determine the performance test results of the autonomous driving vehicle based on the test driving behavior data and the benchmark driving behavior data set.

[0115] According to an embodiment of the present disclosure, the reference driving behavior data set includes calibrated reference driving behavior data, and the reference driving behavior data corresponds to a predetermined test point.

[0116] According to an embodiment of the present disclosure, the autonomous driving vehicle performance testing device may further include an acquisition module, a third determination module, and a fourth determination module.

[0117] An acquisition module is used to acquire at least one initial baseline driving behavior data subset, wherein the initial baseline driving behavior data subset in the at least one initial baseline driving behavior data subset includes initial baseline driving behavior data about a driver driving an autonomous driving vehicle.

[0118] The third determination module is used to determine, for each initial benchmark driving behavior data subset in at least one initial benchmark driving behavior data subset, an initial benchmark driving trajectory of the driver driving the automatic driving vehicle based on the initial benchmark driving behavior data.

[0119] The fourth determination module is used to determine at least one baseline driving behavior data subset from at least one initial baseline driving behavior data subset based on the initial baseline driving trajectory and the predetermined driving trajectory, and use the at least one baseline driving behavior data subset as the baseline driving behavior data set.

[0120] According to an embodiment of the present disclosure, the first determination module may include a collection submodule, a first determination submodule, a second determination submodule, and a third determination submodule.

[0121] The collection submodule is used to collect multiple initial test driving behavior data of the autonomous driving vehicle when the autonomous driving vehicle is driving based on a predetermined driving trajectory.

[0122] The first determination submodule is used to determine a test driving trajectory of the autonomous driving vehicle based on a plurality of initial test driving behavior data.

[0123] The second determination submodule is used to determine a target test position corresponding to a predetermined test point from the test driving trajectory of the autonomous driving vehicle based on the predetermined test point of the predetermined driving trajectory.

[0124] The third determination submodule is used to determine the test driving behavior data from the plurality of initial test driving behavior data based on the target test location.

[0125] According to an embodiment of the present disclosure, the test driving behavior data includes a plurality of test driving behavior sub-data of different performance indicators.

[0126] According to an embodiment of the present disclosure, the second determining module may include a fourth determining submodule and a fifth determining submodule.

[0127] The fourth determination submodule is used to determine the performance test sub-results of each of the plurality of test driving behavior sub-data of the test driving behavior data based on the reference driving behavior data set.

[0128] The fifth determination submodule is used to determine the performance test result based on the performance test sub-results of each of the multiple test driving behavior sub-data.

[0129] According to an embodiment of the present disclosure, a baseline driving behavior data set includes multiple baseline driving behavior data subsets, each of the multiple baseline driving behavior data subsets includes baseline driving behavior data, and the baseline driving behavior data includes multiple baseline driving behavior sub-data of different performance indicators.

[0130] According to an embodiment of the present disclosure, the fourth determining submodule may include a first determining unit and a second determining unit.

[0131] The first determination unit is used to determine, for each test driving behavior sub-data in the multiple test driving behavior sub-data, a plurality of target baseline driving behavior sub-data corresponding to the target predetermined test point from the baseline driving behavior data set, wherein the performance indicators of the multiple target baseline driving behavior sub-data are the same as those of the test driving behavior sub-data.

[0132] The second determining unit is configured to determine a performance test sub-result of the driving behavior sub-data based on the plurality of target benchmark driving behavior sub-data and the test driving behavior sub-data.

[0133] According to an embodiment of the present disclosure, the second determining unit may include a first determining subunit, a second determining subunit, and a third determining subunit.

[0134] The first determination subunit is used to determine a reference condition that meets a predetermined standard based on a plurality of target reference driving behavior sub-data.

[0135] The second determining subunit is used to use the first evaluation value as a performance test sub-result of the test driving behavior sub-data when the test driving behavior sub-data meets the benchmark condition.

[0136] The third determination subunit is used to determine a second evaluation value based on multiple target benchmark driving behavior sub-data and initial driving behavior sub-data when the test driving behavior sub-data does not meet the benchmark conditions, and use the second evaluation value as a performance test sub-result of the test driving behavior sub-data.

[0137] According to an embodiment of the present disclosure, the autonomous driving vehicle performance testing device may further include, before the first determination module: a trajectory point determination module, a generation module, and a test point determination module.

[0138] The trajectory point determination module is used to determine the target trajectory point of the predetermined driving trajectory.

[0139] The generation module is used to generate a predetermined driving trajectory based on the target trajectory point.

[0140] The test point determination module is used to determine a predetermined test point on a predetermined driving trajectory.

[0141] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0142] According to an embodiment of the present disclosure, an electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a method as in the embodiment of the present disclosure.

[0143] According to an embodiment of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to execute a method as described in an embodiment of the present disclosure.

[0144] According to an embodiment of the present disclosure, a computer program product includes a computer program, and when the computer program is executed by a processor, the method according to the embodiment of the present disclosure is implemented.

[0145] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0146] like Figure 8 As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0147] A number of components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0148] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as the autonomous driving vehicle performance test method. For example, in some embodiments, the autonomous driving vehicle performance test method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the autonomous driving vehicle performance test method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the autonomous driving vehicle performance test method in any other appropriate manner (e.g., by means of firmware).

[0149] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0150] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0151] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0152] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0153] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0154] A computer system may include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises through computer programs running on respective computers and having a client-server relationship to each other. The server may be a cloud server, a server in a distributed system, or a server combined with a blockchain.

[0155] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0156] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for testing the performance of an autonomous driving vehicle, comprising: Determining test driving behavior data about the autonomous driving vehicle, wherein the test driving behavior data corresponds to a predetermined test point on a predetermined driving trajectory; and Determining a performance test result of the autonomous driving vehicle based on the test driving behavior data and the baseline driving behavior data set, wherein the benchmark driving behavior data set includes verified benchmark driving behavior data, and the benchmark driving behavior data corresponds to the predetermined test point; The determining of the performance test result of the autonomous driving vehicle based on the test driving behavior data and the benchmark driving behavior data set includes: For the test driving behavior sub-data in the test driving behavior data, if the test driving behavior sub-data satisfies a benchmark condition that meets a predetermined standard, taking a first evaluation value as a performance test sub-result of the test driving behavior sub-data; In a case where the test driving behavior sub-data does not satisfy the benchmark condition, determining a second evaluation value based on a plurality of target benchmark driving behavior sub-data and the test driving behavior sub-data, and using the second evaluation value as a performance test sub-result of the test driving behavior sub-data; and determining the performance test result based on the performance test sub-results of each of the plurality of test driving behavior sub-data; The benchmark condition is determined based on a plurality of target benchmark driving behavior sub-data in the benchmark driving behavior data set, the test driving behavior sub-data and the plurality of target benchmark driving behavior sub-data correspond to the same test point and have the same performance index, and the plurality of target benchmark driving behavior sub-data obey a normal distribution; The second evaluation value is determined by the following formula: ； in, ; the second evaluation value representing the test driving behavior sub-data; represents an expected value of a normal distribution determined by a plurality of said target reference driving behavior sub-data; represents a standard deviation of a normal distribution determined by a plurality of said target reference driving behavior sub-data; represents the test driving behavior sub-data; Indicates the minimum value of the target benchmark driving behavior sub-data that meets the benchmark conditions.

2. The method according to claim 1, further comprising: Acquire at least one initial baseline driving behavior data subset, wherein the initial baseline driving behavior data subset in the at least one initial baseline driving behavior data subset includes initial baseline driving behavior data about a driver driving the autonomous driving vehicle; For each initial benchmark driving behavior data subset of the at least one initial benchmark driving behavior data subset, determining an initial benchmark driving trajectory of the driver driving the autonomous driving vehicle based on the initial benchmark driving behavior data; and Based on the initial reference driving trajectory and the predetermined driving trajectory, at least one reference driving behavior data subset is determined from the at least one initial reference driving behavior data subset, and the at least one reference driving behavior data subset is used as the reference driving behavior data subset.

3. The method according to claim 1, wherein: Determining the test driving behavior data about the autonomous driving vehicle includes: When the autonomous driving vehicle is driving based on the predetermined driving trajectory, collecting a plurality of initial test driving behavior data of the autonomous driving vehicle; Determining a test driving trajectory of the autonomous driving vehicle based on the plurality of initial test driving behavior data; Based on the predetermined test point of the predetermined driving trajectory, determining a target test position corresponding to the predetermined test point from the test driving trajectory of the autonomous driving vehicle; and The test driving behavior data is determined from the plurality of initial test driving behavior data based on the target test location.

4. The method according to claim 1 further comprises, before determining the test driving behavior data about the autonomous driving vehicle: Determining a target trajectory point of the predetermined driving trajectory; Based on the target trajectory point, generating the predetermined driving trajectory; and The predetermined test point on the predetermined driving trajectory is determined.

5. The method according to claim 1, wherein: At least one of the plurality of test driving behavior sub-data includes at least one of the following: Test driving behavior sub-data related to efficiency indicators, test driving behavior sub-data related to comfort indicators, and test driving behavior sub-data related to safety indicators.

6. An automatic driving vehicle performance testing device, comprising: a first determination module, configured to determine test driving behavior data about the autonomous driving vehicle, wherein the test driving behavior data corresponds to a predetermined test point on a predetermined driving trajectory; and A second determination module is configured to determine a performance test result of the autonomous driving vehicle based on the test driving behavior data and the benchmark driving behavior data set, wherein the benchmark driving behavior data set includes verified benchmark driving behavior data, and the benchmark driving behavior data corresponds to the predetermined test point; The determining of the performance test result of the autonomous driving vehicle based on the test driving behavior data and the benchmark driving behavior data set includes: For the test driving behavior sub-data in the test driving behavior data, if the test driving behavior sub-data satisfies a benchmark condition that meets a predetermined standard, taking a first evaluation value as a performance test sub-result of the test driving behavior sub-data; In a case where the test driving behavior sub-data does not satisfy the benchmark condition, determining a second evaluation value based on a plurality of target benchmark driving behavior sub-data and the test driving behavior sub-data, and using the second evaluation value as a performance test sub-result of the test driving behavior sub-data; and determining the performance test result based on the performance test sub-results of each of the plurality of test driving behavior sub-data; The benchmark condition is determined based on a plurality of target benchmark driving behavior sub-data in the benchmark driving behavior data set, the test driving behavior sub-data and the plurality of target benchmark driving behavior sub-data correspond to the same test point and have the same performance index, and the plurality of target benchmark driving behavior sub-data obey a normal distribution; The second evaluation value is determined by the following formula: ； in, ; the second evaluation value representing the test driving behavior sub-data; represents an expected value of a normal distribution determined by a plurality of said target reference driving behavior sub-data; represents a standard deviation of a normal distribution determined by a plurality of said target reference driving behavior sub-data; represents the test driving behavior sub-data; Indicates the minimum value of the target benchmark driving behavior sub-data that meets the benchmark conditions.

7. The apparatus according to claim 6, further comprising: an acquisition module, configured to acquire at least one initial benchmark driving behavior data subset, wherein the initial benchmark driving behavior data subset in the at least one initial benchmark driving behavior data subset includes initial benchmark driving behavior data about a driver driving the autonomous driving vehicle; a third determination module, configured to determine, for each initial benchmark driving behavior data subset in the at least one initial benchmark driving behavior data subset, an initial benchmark driving trajectory of the driver driving the automatic driving vehicle based on the initial benchmark driving behavior data; and The fourth determination module is used to determine at least one baseline driving behavior data subset from the at least one initial baseline driving behavior data subset based on the initial baseline driving trajectory and the predetermined driving trajectory, and use the at least one baseline driving behavior data subset as the baseline driving behavior data set.

8. The device according to claim 6, wherein: The first determining module comprises: a collection submodule, configured to collect a plurality of initial test driving behavior data of the autonomous driving vehicle when the autonomous driving vehicle is driving based on the predetermined driving trajectory; A first determination submodule, configured to determine a test driving trajectory of the autonomous driving vehicle based on the plurality of initial test driving behavior data; A second determination submodule is configured to determine, based on the predetermined test point of the predetermined driving trajectory, a target test position corresponding to the predetermined test point from the test driving trajectory of the autonomous driving vehicle; and The third determination submodule is configured to determine the test driving behavior data from the plurality of initial test driving behavior data based on the target test location.

9. The apparatus according to claim 6, further comprising, before the first determining module: A trajectory point determination module, used to determine a target trajectory point of the predetermined driving trajectory; A generating module, used for generating the predetermined driving trajectory based on the target trajectory point; as well as The test point determination module is used to determine the predetermined test point on the predetermined driving trajectory.

10. The device according to claim 6, wherein: At least one of the plurality of test driving behavior sub-data includes at least one of the following: Test driving behavior sub-data related to efficiency indicators, test driving behavior sub-data related to comfort indicators, and test driving behavior sub-data related to safety indicators.

11. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 5.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 5.

13. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 5.

Images