Testing method, device and computer equipment for autonomous driving mapping results

Abstract

The present invention discloses a test method, device and computer equipment for the results of autonomous driving mapping, wherein the method comprises: obtaining test scene data and video data of a vehicle driving in a test scene; constructing a mapping result file through mapping software according to the test scene data; obtaining a mapping result true value file according to the video data and the mapping result file; and testing the stability of the mapping result and / or the iterative validity of the mapping software based on the mapping result true value file. Thus, the mapping result test can be independently performed from two aspects: the stability of the mapping result and the iterative validity of the mapping software, so that the mapping problem can be discovered as early as possible.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a method, device and computer equipment for testing autonomous driving mapping results. Background Art

[0002] With the widespread application of autonomous driving equipment in closed and semi-closed parks, the requirements for the accuracy of autonomous driving mapping results are becoming increasingly higher. However, there are currently few separate tests on mapping results, and most of them are integrated into system testing. As a result, mapping problems cannot be discovered early, which in turn greatly increases software quality costs. Summary of the invention

[0003] The present invention aims to solve at least one of the technical problems in the related art to a certain extent. To this end, the first object of the present invention is to propose a method for testing the results of autonomous driving mapping, which can test the results of mapping from two aspects: the stability of the mapping results and the effectiveness of the iteration of the mapping software, so as to discover the problems of mapping as early as possible.

[0004] The second objective of the present invention is to provide a testing device for autonomous driving mapping results.

[0005] A third object of the present invention is to provide a computer device.

[0006] To achieve the above-mentioned objectives, an embodiment of the first aspect of the present invention proposes a testing method for autonomous driving mapping results, comprising the following steps: obtaining test scene data and video data of a vehicle traveling in a test scene; constructing a mapping result file through mapping software based on the test scene data; obtaining a mapping result true value file based on the video data and the mapping result file; and testing the stability of the mapping result and / or the iterative validity of the mapping software based on the mapping result true value file.

[0007] According to the test method of the autonomous driving mapping result of the embodiment of the present invention, the test scene data and video data of the vehicle driving in the test scene are obtained, and the mapping result file is constructed by the mapping software according to the test scene data, and the mapping result true value file is obtained according to the obtained video data and mapping result file, and the stability of the mapping result and / or the validity of the mapping software iteration are tested based on the mapping result true value file. In this way, the mapping result test can be independently performed from two aspects: the stability of the mapping result and the validity of the mapping software iteration, so that the mapping problem can be discovered as early as possible.

[0008] According to one embodiment of the present invention, a mapping result file is constructed by mapping software according to test scenario data, including: generating a bag package based on the test scenario data; starting a positioning node by the mapping software and playing the bag package to construct a mapping result file.

[0009] According to an embodiment of the present invention, during the process of constructing the mapping result file, the mapping result file is also displayed in real time.

[0010] According to one embodiment of the present invention, obtaining a true mapping result file based on video data and a mapping result file includes: matching and differential analysis of the mapping result file and the video data; if the difference between the mapping result file and the video data is less than or equal to a preset threshold, determining that the mapping result file is a true mapping result file; if the difference between the mapping result file and the video data is greater than the preset threshold, adjusting the mapping software until the difference between the mapping result file and the video data is less than or equal to the preset threshold.

[0011] According to one embodiment of the present invention, the difference between the mapping result file and the video data is less than or equal to a preset threshold, including: the position and shape variables of each object in the mapping result file and the position and shape variables of the corresponding object in the video data are both less than or equal to the preset threshold.

[0012] According to one embodiment of the present invention, the stability of a mapping result is tested based on a mapping result true value file, including: constructing a mapping result file multiple times through mapping software according to test scenario data to obtain multiple mapping result files; and determining the stability of the mapping result by comparing and analyzing the multiple mapping result files with the mapping result true value file.

[0013] According to one embodiment of the present invention, the validity of the iteration of the mapping software is tested based on the mapping result true value file, including: constructing a mapping result file through the iterative software of the mapping software according to the test scenario data to obtain a mapping result iteration file; and determining the validity of the iteration of the mapping software by comparing and analyzing the mapping result iteration file and the mapping result true value file.

[0014] According to one embodiment of the present invention, the iterative software of the mapping software includes the optimization software and the repair software of the mapping software.

[0015] To achieve the above-mentioned purpose, the second aspect of the present invention proposes a testing device for autonomous driving mapping results, including: a data acquisition module, used to acquire test scene data and video data of a vehicle traveling in a test scene; a construction module, used to construct a mapping result file through mapping software according to the test scene data; a file acquisition module, used to acquire a mapping result true value file according to the video data and the mapping result file; a verification module, used to test the stability of the mapping result and / or the iterative validity of the mapping software based on the mapping result true value file.

[0016] According to the test device for the result of autonomous driving mapping of the embodiment of the present invention, the test scene data and video data of the vehicle driving in the test scene are obtained through the data acquisition module, and the mapping result file is constructed through the mapping software according to the test scene data through the construction module, and the mapping result true value file is obtained according to the obtained video data and the mapping result file through the file acquisition module, and the stability of the mapping result and / or the validity of the mapping software iteration are tested based on the mapping result true value file through the verification module. Thus, the mapping result test can be independently performed from two aspects: the stability of the mapping result and the validity of the mapping software iteration, so that the mapping problem can be discovered as early as possible.

[0017] To achieve the above-mentioned purpose, the third aspect of the present invention proposes a computer device, including a memory and a processor, the memory storing a computer program, and the processor implementing the steps of the testing method for the autonomous driving mapping results as described in any one of the first aspect embodiments when executing the computer program.

[0018] According to the computer device of an embodiment of the present invention, through the above-mentioned testing method of autonomous driving mapping results, it is possible to independently test the mapping results from two aspects: the stability of the mapping results and the effectiveness of the iteration of the mapping software, so that mapping problems can be discovered as early as possible.

[0019] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a flowchart of a method for testing an autonomous driving mapping result according to an embodiment of the present invention;

[0021] Figure 2 A flowchart of constructing a mapping result file according to an embodiment of the present invention;

[0022] Figure 3 A flowchart of obtaining a true value file of a mapping result according to video data and a mapping result file according to an embodiment of the present invention;

[0023] Figure 4 A flowchart of testing the stability of a mapping result based on a true value file of the mapping result according to an embodiment of the present invention;

[0024] Figure 5 A flowchart of testing the iterative validity of mapping software based on a mapping result true value file according to an embodiment of the present invention;

[0025] Figure 6 A schematic diagram of the structure of a testing device for autonomous driving mapping results according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0027] The following describes the method, device and computer equipment for testing the autonomous driving mapping results proposed in the embodiments of the present invention with reference to the accompanying drawings.

[0028] Figure 1 FIG. 1 is a flow chart of a method for testing an autonomous driving mapping result according to an embodiment of the present invention. Figure 1 As shown, the test method of the autonomous driving mapping result includes the following steps:

[0029] Step S101, acquiring test scene data and video data of a vehicle traveling in a test scene.

[0030] Specifically, in the selected test scenario, the vehicle can be controlled in a manual or automatic driving mode to travel at a certain speed in the test scenario, and the vehicle-mounted lidar, millimeter-wave radar, GNSS equipment required for positioning, IMU equipment and other various sensors are used as perception sources to collect data for the test scene to obtain test scene data; at the same time, the surround-view camera carried by the vehicle is used to collect video data of the test scene in real time during the vehicle's driving.

[0031] Step S102: construct a mapping result file using mapping software according to the test scene data.

[0032] In some embodiments, a mapping result file is constructed through mapping software according to the test scenario data, including: generating a bag package based on the test scenario data; starting a positioning node through the mapping software and playing the bag package to construct a mapping result file.

[0033] Specifically, after obtaining the test scene data, a corresponding bag package can be generated according to the test scene data, and then the bag package can be input into the mapping software for mapping. When mapping, first start the positioning node. The positioning node (blind node) is a type of movable node that can be moved arbitrarily within the area surrounded by the reference node. Then, the content in the bag package is played in the mapping software for mapping, and after the mapping is completed, the mapping result file is saved. Optionally, during the mapping process, the mapping effect can also be viewed in real time, such as starting the rviz software to view the mapping results generated according to the bag package in real time.

[0034] Further, as a specific example, refer to Figure 2 As shown, constructing a mapping result file may include the following steps:

[0035] Step S201, start the positioning node, that is, when using the mapping software to build a map, start the corresponding movable node to ensure that the vehicle can move freely within the area surrounded by the positioning node (reference node).

[0036] Step S202, play the test scene data bag package, that is, convert the test scene data into the form of a bag package, and play the bag package during the mapping process to perform mapping. The bag package can be set according to actual needs. For example, the bag package may include / tpcansensor, / scan_top, / scan_bottom, etc., which is not limited here.

[0037] Step S203, start rviz and check the mapping effect, that is, during the mapping process, use the rviz software to view the image effect formed under this bag in real time, so that you can see whether there is a problem with the mapping result in the mapping stage and change the mapping algorithm in time.

[0038] Step S204, determine whether the map is successfully built, if the map is successfully built, execute step S205; if the map is not successfully built, return to step S201 and start again.

[0039] Step S205, save the mapping result file, that is, the map file, the file type can be *.png, *.yaml, *.pgm, etc.

[0040] Step S103, obtaining a true value file of a mapping result according to the video data and the mapping result file.

[0041] In some embodiments, obtaining a true mapping result file based on video data and a mapping result file includes: matching and differential analysis of the mapping result file and the video data; if the difference between the mapping result file and the video data is less than or equal to a preset threshold, determining that the mapping result file is a true mapping result file; if the difference between the mapping result file and the video data is greater than a preset threshold, adjusting the mapping software until the difference between the mapping result file and the video data is less than or equal to the preset threshold.

[0042] That is to say, after obtaining the mapping result file, it is compared and analyzed with the video data of the test scene, that is, compared and analyzed with the actual scene to determine whether the mapping result file is consistent with the actual scene. If it is consistent, the mapping result file is used as the mapping result true value file. If it is not consistent, the mapping algorithm of the mapping software is adjusted according to the inconsistency between the mapping result file and the actual scene, until the mapping result file is consistent with the actual scene, and the mapping result file at this time is used as the mapping result true value file. Among them, when judging whether the mapping result file is consistent with the actual scene, the mapping result file and the video data can be matched and differentially analyzed. If the difference is small, it is considered that the mapping result file is consistent with the actual scene. Otherwise, it is considered that the mapping result file is inconsistent with the actual scene.

[0043] Furthermore, the difference between the mapping result file and the video data is less than or equal to a preset threshold, including: the position and shape variable of each object in the mapping result file and the position and shape variable of the corresponding object in the video data are both less than or equal to the preset threshold.

[0044] Specifically, when judging whether the mapping result file is consistent with the actual scene, the mapping result file can be firstly subjected to feature analysis to determine the various objects in the mapping result file, and the corresponding objects can be obtained from the video data of the actual scene. Then, the differences between the objects in the mapping result file and the corresponding objects in the video data can be compared, such as comparing the positions of the objects and the differences in the shape variables, etc., and whether the mapping result file is consistent with the actual scene can be determined based on the differences in the positions and shape variables.

[0045] As a specific example, the various objects in the mapping result file may be buildings, walls, and other objects. If the positions of the buildings, walls, and other objects are consistent with the positions in the actual scene, that is, the positions are accurate without obvious differences, and the buildings, walls, and other objects have no obvious mutations, and the buildings, walls, and other objects have no obvious deformations, then it means that the mapping result file is consistent with the actual scene, otherwise, the mapping result file is inconsistent with the actual scene.

[0046] Further, as a specific example, refer to Figure 3 As shown, obtaining the true value file of the mapping result may include the following steps:

[0047] Step S301, collecting test scene data and video data.

[0048] Specifically, various sensors can be used as perception sources to collect test scene data for the test scene, while the surround-view camera installed in the vehicle can be used to collect video data of the test scene during the vehicle driving process in real time.

[0049] Step S302, start the project and start drawing.

[0050] Specifically, the test scene data can be input into the mapping software in the form of a bag package, and the mapping software plays the content in the bag package to construct a mapping result file.

[0051] Step S303, saving the mapping result file.

[0052] Specifically, after the map is successfully built, the map result file is saved.

[0053] Step S304, compare the mapping result file and the video data to see if they are consistent. If they are consistent, execute step S306; otherwise, execute step S305.

[0054] Specifically, the difference between each object in the mapping result file and the corresponding object in the video data can be compared to determine whether the difference is small. If so, step S306 is executed; otherwise, step S305 is executed.

[0055] Step S305, modify the problem and save the project.

[0056] Specifically, if the mapping result file is inconsistent with the video data, the mapping algorithm is modified according to the inconsistency, and the project is saved, and then the project is started again to start mapping.

[0057] Step S306: Use the mapping result file as a true value file of the mapping result.

[0058] Specifically, if the mapping result file is consistent with the video data, it means that the current mapping algorithm is reasonable. In this case, the mapping result file is used as the true value file of the mapping result.

[0059] It can be seen from the above examples that the true value file of the mapping result obtained through video data and mapping result files can more accurately simulate the actual test scenario and provide higher quality autonomous driving mapping results.

[0060] Step S104: testing the stability of the mapping results and / or the iterative validity of the mapping software based on the true value file of the mapping results.

[0061] In some embodiments, the stability of the mapping results is tested based on the mapping result true value file, including: constructing the mapping result file multiple times through the mapping software according to the test scenario data to obtain multiple mapping result files; and determining the stability of the mapping results by comparing and analyzing the multiple mapping result files with the mapping result true value file.

[0062] Specifically, due to the characteristics of the mapping algorithm, even if the same test scenario data is used for mapping, the mapping result files generated multiple times by the same version of the mapping software may be inconsistent. Therefore, in this application, after obtaining the true value file of the mapping result, the stability of the mapping result of the same version of the mapping software can be tested according to the true value file of the mapping result to obtain the test result of the stability of the mapping result. Specifically, according to the same test scenario data as that for generating the true value file of the mapping, the mapping result file can be constructed multiple times by the same version of the mapping software to obtain multiple mapping result files, and then the multiple mapping result files can be compared with the true value file of the mapping result one by one to determine the number of the multiple mapping result files that are consistent with the true value file of the mapping result, and the stability of the mapping result of the version of the mapping software is determined based on the number, wherein the more the number of the multiple mapping result files that are consistent with the true value file of the mapping result, the more stable the mapping result of the mapping software.

[0063] Further, as a specific example, refer to Figure 4 As shown, testing the stability of the mapping result may include the following steps:

[0064] Step S401, running the same version of mapping software.

[0065] Step S402, play the test scene data bag.

[0066] Step S403, determine whether the map is successfully built, if the map is successfully built, execute step S404; if the map is not successfully built, return to step S402 and replay the test scene data bag.

[0067] Step S404, saving the mapping result file.

[0068] Step S405, input the true value file of the mapping result.

[0069] Step S406: Use Python script to automatically compare the two to see if they are consistent. If they are consistent, execute step S408; if they are inconsistent, execute step S407.

[0070] Step S407, record the results and provide feedback.

[0071] Step S408, record the result, and return to step S401 to re-build the map until the number of map building times reaches the preset number N times.

[0072] That is to say, use Python script to automatically compare the generated mapping result file and the mapping result true value file. If the two are consistent, the test passes, otherwise the test fails. When the test fails, the problem can be recorded and fed back to the relevant personnel, and a stability test report can be generated. In addition, the relevant personnel can also modify the mapping algorithm based on the problems recorded in the test report to improve the stability of the mapping results, so that each mapping result is consistent or has a small difference. In addition, different stability test goals can be set according to the different stages of mapping software development, and the stability test report can be used to check whether the goal is achieved to assist developers in the development of mapping software, thereby improving development efficiency.

[0073] Therefore, by comparing the mapping result files generated multiple times by the mapping software with the true value files of the mapping results, the stability test of the mapping software can be implemented, and problems with the mapping results can be discovered in a timely manner based on the test results.

[0074] In some embodiments, testing the validity of the mapping software iteration based on the mapping result true value file includes: constructing the mapping result file through the mapping software iteration software according to the test scenario data to obtain the mapping result iteration file; and determining the validity of the mapping software iteration by comparing and analyzing the mapping result iteration file and the mapping result true value file. The mapping software iteration software includes the mapping software optimization software and repair software.

[0075] Specifically, in this application, after obtaining the true value file of the mapping result, the validity of the iteration of the mapping software can also be tested based on the true value file of the mapping result. Specifically, the mapping result file can be constructed by the iterative software of the mapping software (such as optimization software and repair software) based on the same test scenario data as that for generating the true value file of the mapping result. The file is called the iterative file of the mapping result, and then the iterative file of the mapping result is compared with the true value file of the mapping result. Through the comparison results, it can be quickly checked whether the problems of the iterative software have been fixed or whether there are new problems, etc.

[0076] Further, as a specific example, refer to Figure 5 As shown, testing the iterative effectiveness of the mapping software may include the following steps:

[0077] Step S501, running iterative software.

[0078] Step S502, play the test scene data bag.

[0079] Step S503, determine whether the map is successfully built, if the map is successfully built, execute step S504; if the map is not successfully built, return to step S502 and replay the test scene data bag.

[0080] Step S504, saving the mapping result file.

[0081] Step S505, input the true value file of the mapping result.

[0082] Step S506: Use Python script to automatically compare the two to see if they are consistent. If they are consistent, the test passes and the test ends; if they are inconsistent, execute step S507.

[0083] Step S507, record the results and provide feedback.

[0084] Therefore, by comparing the iterative file of mapping results generated by the iterative software of the mapping software with the true value file of the mapping results, the iteration effect can be evaluated quickly and effectively, that is, the results of the iterative software algorithm optimization and the problem repair can be quickly and effectively verified, so as to timely discover whether the mapping problem has been repaired.

[0085] Furthermore, when the stability test of the above-mentioned mapping software and the effectiveness test of the mapping software iteration are combined, the two can timely discover problems with the mapping results, and at the same time improve the testing efficiency of the software iteration on the mapping effect, thereby improving the quality of the mapping result file, and providing a basic guarantee for subsequent autonomous driving control decision-making behaviors.

[0086] In summary, according to the path planning method of the smart car of the embodiment of the present invention, the test scene data and video data of the vehicle driving in the test scene are obtained, and the mapping result file is constructed by the mapping software according to the test scene data, and the mapping result true value file is obtained by combining the acquired video data and the mapping result file, and the stability of the mapping result and / or the validity of the mapping software iteration are tested based on the mapping result true value file. The mapping result test can be independently performed from two aspects: the stability of the mapping result and the validity of the mapping software iteration, so that the mapping problem can be discovered as early as possible.

[0087] Figure 6 FIG. 1 is a schematic diagram of a test device for autonomous driving mapping results according to an embodiment of the present invention. Figure 6 As shown, the testing device 100 for the autonomous driving mapping result includes: a data acquisition module 110, a construction module 120, a file acquisition module 130 and a verification module 140.

[0088] Among them, the data acquisition module 110 is used to obtain test scene data and video data of a vehicle traveling in a test scene; the construction module 120 is used to construct a mapping result file through a mapping software according to the test scene data; the file acquisition module 130 is used to obtain a mapping result true value file according to the video data and the mapping result file; the verification module 140 is used to test the stability of the mapping result and / or the iterative validity of the mapping software based on the mapping result true value file.

[0089] In some embodiments, the construction module 120 is specifically used to: generate a bag package based on the test scene data; start the positioning node through the mapping software and play the bag package to construct a mapping result file.

[0090] In some embodiments, the above-mentioned testing device for autonomous driving mapping results also includes: a display module (not specifically shown in the figure), which is used to display the mapping result file in real time during the process of constructing the mapping result file.

[0091] In some embodiments, the file acquisition module 130 is specifically used to: match and differentiate the mapping result file and the video data; if the difference between the mapping result file and the video data is less than or equal to a preset threshold, determine that the mapping result file is a true value file of the mapping result; if the difference between the mapping result file and the video data is greater than the preset threshold, adjust the mapping software until the difference between the mapping result file and the video data is less than or equal to the preset threshold.

[0092] In some embodiments, the file acquisition module 130 is further specifically used to: when the position and shape variables of each object in the mapping result file and the position and shape variables of the corresponding object in the video data are both less than or equal to a preset threshold, determine that the difference between the mapping result file and the video data is less than or equal to a preset threshold.

[0093] In some embodiments, the verification module 140 is specifically used to: construct a mapping result file multiple times through mapping software according to the test scenario data to obtain multiple mapping result files; and determine the stability of the mapping results by comparing and analyzing the multiple mapping result files and the mapping result true value files.

[0094] In some embodiments, the verification module 140 is specifically used to: construct a mapping result file through the iterative software of the mapping software according to the test scenario data to obtain a mapping result iteration file; and determine the validity of the mapping software iteration by comparing and analyzing the mapping result iteration file and the mapping result true value file.

[0095] In some embodiments, the iterative software of the mapping software includes optimization software and repair software of the mapping software.

[0096] It should be noted that for the description of the testing device for the autonomous driving mapping results in this application, please refer to the description of the testing method for the autonomous driving mapping results in this application, and the details will not be repeated here.

[0097] According to the test device for the result of autonomous driving mapping of the embodiment of the present invention, the test scene data and video data of the vehicle driving in the test scene are obtained through the data acquisition module, and the mapping result file is constructed through the mapping software according to the test scene data through the construction module, and the mapping result true value file is obtained according to the obtained video data and the mapping result file through the file acquisition module, and the stability of the mapping result and / or the validity of the mapping software iteration are tested based on the mapping result true value file through the verification module. Thus, the mapping result test can be independently performed from two aspects: the stability of the mapping result and the validity of the mapping software iteration, so that the mapping problem can be discovered as early as possible.

[0098] In addition, an embodiment of the present invention further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method for testing the results of autonomous driving mapping as described in any of the aforementioned embodiments are implemented.

[0099] According to the computer device of an embodiment of the present invention, through the above-mentioned testing method of autonomous driving mapping results, it is possible to independently test the mapping results from two aspects: the stability of the mapping results and the effectiveness of the iteration of the mapping software, so that mapping problems can be discovered as early as possible.

[0100] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0101] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0102] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0103] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0104] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0105] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for testing the results of autonomous driving mapping, characterized in that: The following steps are involved: Acquire test scene data and video data of a vehicle driving in a test scene; According to the test scenario data, a mapping result file is constructed by using mapping software; Acquire a true value file of a mapping result according to the video data and the mapping result file; Testing the stability of the mapping results and the iterative validity of the mapping software based on the true value file of the mapping results; The stability of the mapping result is tested based on the true value file of the mapping result, including: According to the test scenario data, constructing a mapping result file multiple times by the mapping software to obtain multiple mapping result files; Determine the stability of the mapping result by comparing and analyzing the multiple mapping result files and the mapping result true value file, wherein determining the stability of the mapping result comprises: determining the number of the multiple mapping result files that are consistent with the mapping result true value file, and the more the number of the multiple mapping result files that are consistent with the mapping result true value file is, the more stable the mapping result of the mapping software is; The iterative validity of the mapping software is tested based on the true value file of the mapping result, including: According to the test scenario data, constructing a mapping result file by the iterative software of the mapping software to obtain a mapping result iteration file; Determine the validity of the iteration of the mapping software by comparing and analyzing the mapping result iteration file and the mapping result true value file; The obtaining of a true value file of a mapping result according to the video data and the mapping result file comprises: Matching and differentially analyzing the mapping result file and the video data; If the difference between the mapping result file and the video data is less than or equal to a preset threshold, determining that the mapping result file is the mapping result true value file; If the difference between the mapping result file and the video data is greater than the preset threshold, adjusting the mapping software until the difference between the mapping result file and the video data is less than or equal to the preset threshold; The difference between the mapping result file and the video data is less than or equal to the preset threshold, including: The position and shape of each object in the mapping result file and the position and shape of the corresponding object in the video data are both less than or equal to the preset threshold.

2. The method for testing the autonomous driving mapping result according to claim 1, characterized in that: The step of constructing a mapping result file using mapping software according to the test scenario data includes: Generate a bag based on the test scenario data; The positioning node is started through the mapping software and the bag package is played to construct the mapping result file.

3. The method for testing the autonomous driving mapping result according to claim 2, characterized in that: In the process of constructing the mapping result file, the mapping result file is also displayed in real time.

4. The method for testing the autonomous driving mapping result according to claim 1, characterized in that: The iterative software of the mapping software includes the optimization software and the repair software of the mapping software.

5. A testing device for autonomous driving mapping results, characterized in that: include: A data acquisition module, used to acquire test scene data and video data of a vehicle driving in a test scene; A construction module, used to construct a mapping result file through mapping software according to the test scenario data; A file acquisition module, used to acquire a true value file of a mapping result according to the video data and the mapping result file; A verification module, used to test the stability of the mapping results and the iterative validity of the mapping software based on the true value file of the mapping results; The verification module is specifically used to: construct a mapping result file multiple times through the mapping software according to the test scenario data to obtain multiple mapping result files; determine the stability of the mapping result by comparing and analyzing the multiple mapping result files and the mapping result true value file, wherein determining the stability of the mapping result includes: determining the number of the multiple mapping result files that are consistent with the mapping result true value file, and the more the number of the multiple mapping result files that are consistent with the mapping result true value file is, the more stable the mapping result of the mapping software is; The verification module is specifically used to: construct a mapping result file through the iterative software of the mapping software according to the test scenario data to obtain a mapping result iteration file; and determine the validity of the mapping software iteration by comparing and analyzing the mapping result iteration file and the mapping result true value file; The file acquisition module is specifically used to: match and differentially analyze the mapping result file and the video data; if the difference between the mapping result file and the video data is less than or equal to a preset threshold, determine that the mapping result file is a true value file of the mapping result; If the difference between the mapping result file and the video data is greater than a preset threshold, the mapping software is adjusted until the difference between the mapping result file and the video data is less than or equal to the preset threshold; when the position and shape variables of each object in the mapping result file and the position and shape variables of the corresponding object in the video data are both less than or equal to the preset threshold, it is determined that the difference between the mapping result file and the video data is less than or equal to the preset threshold.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

Images