Method and device for constructing a test scenario library for autonomous driving functions

Abstract

The application relates to the technical field of automatic driving, in particular to a test scene library construction method and device for automatic driving functions, wherein the method comprises the following steps: obtaining at least one target test case of the automatic driving function; establishing a target logical scene corresponding to each target test case according to the at least one target test case, splitting the target logical scene to obtain at least one static logical scene and at least one dynamic logical scene, and obtaining a static template scene and a dynamic template scene according to the at least one static logical scene and the at least one dynamic logical scene respectively; generating a plurality of scene files according to the number of the target test cases, the static template scene, the dynamic template scene and the element value range in the static logical scene and the dynamic logical scene; and constructing a test scene library for the automatic function by using the plurality of scene files. Therefore, the problems of low verification efficiency, high cost, large repetitive workload and high error rate of manual test scene construction caused by real vehicle data collection and scene generation are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, in particular to a method and device for constructing a test scenario library of automatic driving functions. BACKGROUND

[0002] With the increasing iteration speed of automatic driving technology, it is crucial to adopt a more efficient testing method to promote the technology from the research and development stage to mass production. Since simulation testing has the advantages of short cycle, low cost, rich test scenarios, high safety, etc., it is usually used to verify software functions before entering the real vehicle testing and verification stage.

[0003] However, the effectiveness of using real vehicle data collection and scene mining technology to generate scenarios in real vehicle testing and verification still needs to be verified, and it cannot be directly applied to the software development process. The ROD and SE modules of the VTD software are manually built, which is inefficient and has a high error rate. SUMMARY

[0004] The present application provides a method and device for constructing a test scenario library of automatic driving functions to solve the problems of low efficiency and high cost of using real vehicle data collection to generate scenarios for software function verification, and the high error rate and large amount of repetitive work of manually building test scenarios in related technologies.

[0005] The first aspect of the present application provides a method for constructing a test scenario library of automatic driving functions, comprising the following steps: obtaining at least one target test case of automatic driving functions; establishing a target logical scenario corresponding to each target test case according to the at least one target test case, splitting the target logical scenario to obtain at least one static logical scenario and at least one dynamic logical scenario, and obtaining a static template scenario and a dynamic template scenario according to the at least one static logical scenario and the at least one dynamic logical scenario, respectively; generating a plurality of scene files according to the number of the target test cases, the static template scenario, the dynamic template scenario, and the element value range in the static logical scenario and the dynamic logical scenario; and constructing a test scenario library of the automatic functions using the plurality of scene files.

[0006] According to the above technical means, the embodiments of the present application can establish corresponding static logical scenarios and dynamic logical scenarios through target test cases, generate a plurality of scene files using a plurality of static template scenarios and dynamic logical template scenarios, and establish a test scenario library, without using real vehicle data collection and scene mining technology to generate scenarios, thereby improving the effectiveness of the scenarios and reducing the cost of scenario construction.

[0007] Optionally, obtaining the static template scene and the dynamic template scene according to the at least one static logic scene and the at least one dynamic logic scene respectively comprises: classifying elements of the at least one static logic scene and the at least one dynamic logic scene according to a preset classification strategy respectively to obtain element classification results, and integrating the element classification results to obtain classified elements of the static logic scene and classified elements of the dynamic logic scene; performing scene building on the classified elements of the static logic scene by using a ROD module of a preset VTD software to obtain the static template scene; and performing scene building on the classified elements of the dynamic logic scene by using a SE module of the preset VTD software to obtain the dynamic template scene.

[0008] According to the technical means, the static template scene and the dynamic template scene are built by using the ROD and SE modules of the VTD software, so that the workload and error rate of manual building are reduced, and the scene test efficiency is improved.

[0009] Optionally, generating the plurality of scene files according to the number of the target test case, the static template scene, the dynamic template scene, and the element values of the static logic scene and the dynamic logic scene comprises: writing the number of the target test case, names of the static template scene and the dynamic template scene, and element value ranges in the static logic scene and the dynamic logic scene into a preset file to generate a scene design document, wherein the names of the static template scene and the dynamic template scene are respectively named according to the classified elements; reading the scene design document by using a preset script, and traversing the static logic scene and the dynamic logic scene in the element value ranges to generate the plurality of scene files.

[0010] According to the technical means, the number of the target test case, the names of the static template scene and the dynamic template scene, and the element value ranges in the static logic scene and the dynamic logic scene are written into a preset file to generate a specific scene design document, so that the scene test efficiency is improved.

[0011] Optionally, establishing the target logic scene corresponding to each target test case according to the at least one target test case comprises: identifying a scene description and a scene sketch of the each target test case; and establishing the target logic scene corresponding to the each target test case by using the scene description and the scene sketch of the each target test case.

[0012] According to the technical means, the target logic scene is established according to the scene description and the scene sketch of the target test case, so that the efficiency of establishing the test scene is improved, and the cost of building the scene test is reduced.

[0013] The second aspect embodiment of the application provides a test scene library construction device of an automatic driving function, comprising: an acquisition module configured to acquire at least one target test case of the automatic driving function; a splitting module configured to establish a target logical scene corresponding to each target test case according to the at least one target test case, split the target logical scene to obtain at least one static logical scene and at least one dynamic logical scene, and obtain a static template scene and a dynamic template scene according to the at least one static logical scene and the at least one dynamic logical scene respectively; and a construction module configured to generate a plurality of scene files according to a number of the target test case, the static template scene, the dynamic template scene, and a value range of elements in the static logical scene and the dynamic logical scene, and construct a test scene library of the automatic function by using the plurality of scene files.

[0014] Optionally, the splitting module is further configured to: classify elements of the at least one static logical scene and the at least one dynamic logical scene according to a preset classification strategy to obtain element classification results, and integrate the element classification results to obtain classified elements of the static logical scene and the dynamic logical scene; perform scene building on the classified elements of the static logical scene by using an ROD module of a preset VTD software to obtain the static template scene; and perform scene building on the classified elements of the dynamic logical scene by using an SE module of the preset VTD software to obtain the dynamic template scene.

[0015] Optionally, the construction module is further configured to: write the number of the target test case, a name of the static template scene, a name of the dynamic template scene, and the value range of the elements in the static logical scene and the dynamic logical scene into a preset file to generate a scene design document, wherein the name of the static template scene and the name of the dynamic template scene are named according to the classified elements respectively; read the scene design document by using a preset script, and traverse the static logical scene and the dynamic logical scene within the value range of the elements to generate the plurality of scene files.

[0016] Optionally, the construction module is further configured to: identify a scene description and a scene sketch of each target test case; and establish the target logical scene corresponding to each target test case by using the scene description and the scene sketch of each target test case.

[0017] The third aspect embodiment of the application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the program to implement the test scene library construction method of the automatic driving function as described in the above embodiments.

[0018] The fourth aspect of the present application provides a computer readable storage medium, which stores a computer program. The program is executed by a processor to implement the test scenario library construction method of the automatic driving function as described in the above embodiments.

[0019] Therefore, the present application has at least the following beneficial effects:

[0020] (1) The embodiments of the present application can establish corresponding static logic scenarios and dynamic logic scenarios through target test cases, generate a plurality of scenario files by using a plurality of static template scenarios and dynamic logic template scenarios, and establish a test scenario library, without using real vehicle data collection and scene mining technology to generate scenarios, thereby improving the effectiveness of the scenarios and reducing the cost of scenario building.

[0021] (2) The embodiments of the present application establish static template scenarios and dynamic template scenarios through the ROD and SE modules of the VTD software, thereby reducing the workload and error rate of manual building and improving the scenario test efficiency.

[0022] (3) The embodiments of the present application write the number of the target test case, the name of the static template scenario, the name of the dynamic template scenario, and the element value range in the static logic scenario and the dynamic logic scenario into a preset file, thereby generating a specific scenario design document and improving the efficiency of scenario testing.

[0023] (4) The embodiments of the present application establish target logic scenarios according to the scenario description and the scenario schematic diagram of the target test case, which can improve the efficiency of establishing test scenarios and reduce the cost of building scenario tests.

[0024] Additional aspects and advantages of the present application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0025] The above and / or additional aspects and advantages of the present application will become apparent and be readily appreciated from the following description, including the appended drawings.

[0026] Figure 1 A flowchart of the test scenario library construction method of the automatic driving function according to the embodiments of the present application is provided;

[0027] Figure 2 A use case test scenario schematic diagram of the automatic on-ramp and off-ramp function according to the embodiments of the present application is provided;

[0028] Figure 3 A schematic diagram of static template classification according to the embodiments of the present application is provided;

[0029] Figure 4A dynamic template scene classification element schematic diagram provided according to an embodiment of the application;

[0030] Figure 5 A step schematic diagram of a test scene library construction method of an automatic driving function provided according to an embodiment of the application;

[0031] Figure 6 An example diagram of a test scene library construction device of an automatic driving function provided according to an embodiment of the application;

[0032] Figure 7 A structural schematic diagram of an electronic device provided according to an embodiment of the application. DETAILED DESCRIPTION

[0033] Embodiments of the application are described in detail below with reference to examples shown in the attached drawings, wherein the same or similar reference numerals represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary and are intended to explain the application, and cannot be understood as a limitation of the application.

[0034] With the increasing iteration speed of automatic driving technology, it is crucial to adopt a more efficient testing method to promote the related technology from the research and development stage to mass production. Since simulation testing has the advantages of short cycle, low cost, rich test scenarios, high safety, etc., it is usually used to verify the software function before entering the real vehicle test verification link.

[0035] Related technology 1 discloses a construction method of constructing an automatic driving test scene, specifically by collecting data through a real vehicle, and using a clustering method to classify scenes, extracting elements in each type of scene to obtain an element library, and counting the probability of each value of the sub-element corresponding to the scene category. According to the probability distribution of the value of each sub-element, a value is extracted from it as the position corresponding to the sub-element in the current scene, and then the value of each sub-element is combined to form an initial test scene, and the rationality of the initial test scene is analyzed manually, and unreasonable scenes are removed to generate a large number of test scenes. Although this patent can provide a method for generating a large number of test scenes, it needs to rely on a large amount of road data, and the cost is high. At the same time, this method needs to use mathematical analysis method to establish scene mining technology, and its effectiveness still needs to be further verified, and cannot be directly applied to the software development process.

[0036] The related technology 2 discloses a method for building a virtual test scene based on VTD (Virtual Test Drive, scene simulation software) software. First, the required parameter information in the built scene is determined, a static scene and a dynamic scene are built by using a ROD (Road Network Editor) module of the VTD software, then simulation is started to judge whether the built static and dynamic scenes reach a consistent test environment with an original scene, if consistent with the original scene, an XML file is saved and naming record and management are completed. A large number of test scenes need to be generated in the current intelligent driving software development process. However, the related technology 2 only describes a method for manually building a scene, which has certain limitations and cannot improve the efficiency of simulation testing.

[0037] The test scene library construction method and device for automatic driving function of the embodiment of the present application are described below with reference to the accompanying drawings. In view of the effectiveness of the scene generated by the real vehicle data collection and scene mining technology mentioned in the above background technology to be verified, the method cannot be directly applied to the software development process, the problem of low efficiency and high error rate of manually building the automatic driving simulation test scene by using the ROD and SE (Scenario Editor) modules of the VTD software, the present application provides a test scene library construction method for automatic driving function. In the method, the logical scene library is summed up by the target test case, the logical scene is classified and integrated, the scene template is built, and the specific scene design document is generated, so as to build the test scene library for automatic function. Thus, the problems of low efficiency and high cost of using the scene generated based on the real vehicle data collection for software function verification, and the problems of large repetitive workload and high error rate of manually building the test scene are solved.

[0038] Specifically, Figure 1 The flowchart of the test scene library construction method for automatic driving function provided by the embodiment of the present application is shown.

[0039] As Figure 1 shown, the test scene library construction method for automatic driving function includes the following steps:

[0040] In step S101, at least one target test case of automatic driving function is acquired.

[0041] Among them, the target test case has multiple, and the intelligent driving system function includes automatic lane changing, adaptive cruise, lane centering, automatic emergency braking, etc.

[0042] In step S102, a target logic scene corresponding to each target test case is established according to the at least one target test case, the target logic scene is split into at least one static logic scene and at least one dynamic logic scene, and a static template scene and a dynamic template scene are obtained according to the at least one static logic scene and the at least one dynamic logic scene, respectively.

[0043] In the embodiments of the present application, the target logic scene corresponding to each target test case is established according to the at least one target test case, including: identifying the scene description and the scene schematic diagram of each target test case; and establishing the target logic scene corresponding to each target test case by using the scene description and the scene schematic diagram of each target test case.

[0044] In the embodiments of the present application, the target logic scene corresponding to each target test case is established according to the at least one target test case, including: identifying the scene description and the scene schematic diagram of each target test case; and establishing the target logic scene corresponding to each target test case by using the scene description and the scene schematic diagram of each target test case.

[0045] It can be understood that, according to the scene description and the schematic diagram of the target test case UseCase, the corresponding target logic scene is established, and is split into a static logic scene and a dynamic logic scene.

[0046] For example, how a UseCase forms a logic scene, a scene schematic diagram of a UseCase required by a certain intelligent driving system is as shown in FIG. 1. Figure 2 The scene schematic diagram of the UseCase is as shown in FIG. 1, which aims to test whether an algorithm can control the vehicle speed, maintain a safe distance, and safely drive into a ramp according to the driving state of other traffic participants. The static road network type required by the UseCase is a main road into a ramp, the main road is a three-lane road, the ramp road is a single-lane road, the lane close to the ramp side is an emergency lane, there is a guide lane at the ramp entrance, including a junction, and the key parameters of the static road network affecting the simulation test include: the length of the variable lane starting point to the variable lane end point at the ramp entrance, the ramp lane width, the ramp entrance guide lane width, and the road speed limit value. The dynamic scene involved in the UseCase is that a target vehicle in front of the vehicle cuts into the ramp entrance guide lane, and the key parameters of the dynamic scene affecting the test include the initial vehicle speed, the target vehicle speed (Vplayer1), the lane changing time, and the vehicle starting lane changing position. According to the ODD and system experience requirements of the intelligent driving system development, the state space of each key parameter is determined to form a logic scene.

[0047] In the embodiments of the present application, the static template scene and the dynamic template scene are obtained according to at least one static logic scene and at least one dynamic logic scene, including: classifying elements of the at least one static logic scene and the at least one dynamic logic scene respectively according to a preset classification strategy to obtain element classification results, and integrating the element classification results to obtain classified elements of the static logic scene and classified elements of the dynamic logic scene; using a ROD module of a preset VTD software to build a scene for the classified elements of the static logic scene to obtain the static template scene; and using a SE module of the preset VTD software to build a scene for the classified elements of the dynamic logic scene to obtain the dynamic template scene.

[0048] The preset classification strategy refers to a method of classifying the static logic scene and the dynamic logic scene.

[0049] It should be noted that after the UseCase is established, all static scenes and dynamic scenes are classified, and the purpose of classification is to form a scene framework containing all parameters, Figure 3 、 Figure 4 This shows a possible classification method, which fixes part of the scene parameters, so that subsequent specific scenes can be generated using simple scripts, solving the technical problem of automatically generating scenes.

[0050] It can be understood that the static template scene and the dynamic template scene are built by the ROD module and the SE module of the VTD software respectively.

[0051] In step S103, a plurality of scene files are generated according to the number of the target test case, the static template scene, the dynamic template scene, and the element value range in the static logic scene and the dynamic logic scene, and a test scene library of automatic functions is constructed by using the plurality of scene files.

[0052] It can be understood that all static logic scenes are classified and integrated, the ROD module of the VTD software is used to build a dynamic template scene, an.xodr file is exported, classification elements are labeled and named according to the classification elements, and the values of corresponding elements in the.xodr file are modified to parameter names; all dynamic logic scenes are classified and integrated, the SE module of the VTD software is used to build a dynamic template scene, an.xml file is exported, elements are named according to their properties, the values of corresponding elements in the.xml file are modified to parameter names, and the classified elements are used as labels and names of the dynamic template scene.

[0053] In the embodiment of the present application, the plurality of scene files are generated according to the number of the target test case, the static template scene, the dynamic template scene, and the element value of the static logic scene and the dynamic logic scene, including: writing the number of the target test case, the name of the static template scene, the name of the dynamic template scene, and the element value range in the static logic scene and the dynamic logic scene into a preset file to generate a scene design document, wherein the name of the static template scene and the dynamic template scene are respectively named according to the classification elements; the scene design document is read by using a preset script, and the static logic scene and the dynamic logic scene are traversed within the element value range to generate a plurality of scene files.

[0054] It can be understood that the Use case number, the corresponding static scene template name, the dynamic scene template name, and the element value range of the logic scene are written into the Excel file to form a specific scene design document. According to the specific scene design document, the parameter value range is read by using a script to automatically generate a plurality of scene files corresponding to the test requirement, including.xodr file,.osgb file, and.xml scene file.

[0055] The test scene library construction method of the automatic driving function will be described below through a specific embodiment, as shown in Figure 5 , the steps are as follows:

[0056] 1. First, the logic scene is designed according to the Use Case of the automatic driving to form a logic scene library. The intelligent driving system functions include automatic lane changing, adaptive cruise, lane centering, automatic emergency braking, etc. The following will take a Use Case as an example to illustrate how to form a logic scene.

[0057] The scene diagram of the Use Case of a certain intelligent driving system requirement is shown in Figure 2 , which aims to test whether the algorithm can control the vehicle speed, maintain a safe distance, and safely enter the ramp according to the driving state of other traffic participants. The static road network type required by the Use Case is the main road into the ramp, the main road is three lanes, the ramp road is single lane, the lane close to the ramp side is the emergency lane, there is a guide lane at the ramp entrance, including a junction, wherein the key parameters of the static road network affecting the simulation test include: the length of the variable lane starting point to the variable lane end point at the ramp entrance, the ramp lane width, the ramp entrance guide lane width, the road speed limit value. The dynamic scene involved in the Use Case is that the target vehicle in front of the vehicle cuts into the ramp entrance guide lane, and the key parameters of the dynamic scene affecting the test include the initial vehicle speed, the target vehicle speed (Vplayer1), the lane changing time, and the vehicle starting lane changing position. According to the ODD and system experience requirements of the intelligent driving system research and development, the state space of each key parameter is determined to form a logic scene

[0058] 2. Build logical scenarios for each Use Case according to the above approach, and classify all static and dynamic scenarios. The purpose of classification is to form a scenario framework that includes all parameters. Figure 3 , Figure 4 This demonstrates a possible classification method, which fixes some scene parameters, thus enabling the generation of specific scenes using simple scripts and solving the technical challenge of automated scene generation.

[0059] 3. Use the ROD and SE modules of the VTD software to build template scenarios and replace the factors affecting the test with parameter names. Taking the logical scenario of the above Use Case as an example, when generating the static scenario template, the specific coordinates of the lane change start point can be replaced with ExitStart_x and ExitStart_y. Combining the road network file structure generated by ROD, the specific coordinates of the lane change end point can be replaced with ExitEnd_x and ExitEnd_y, the ramp curvature can be replaced with Ramp_Radius, the speed limit value of each road can be replaced with Vmainroad_max, Vexit_max, and Vramp_max, the width of the ramp entrance traffic lane can be replaced with Exit_width, and the width of the ramp lane can be replaced with Ramp_width. Combining the road network scenario file structure generated by SE, in the dynamic scenario, the vehicle speed of the current vehicle can be replaced with Vego, the target vehicle speed can be replaced with Vplayer1, the coordinates of the lane change trigger position can be replaced with LaneChangeTrigger_x and LaneChangeTrigger_y, and the lane change time can be replaced with LaneChange_time. The naming of static and dynamic template scenarios is the complete set of category elements. If the aforementioned logical scenarios belong to one category, four tags are needed: ramp, main road entrance ramp, three-lane main road, and single-lane ramp. The static scenario template is named Ramp_EnterRamp_mainroad3_Ramp1. The dynamic template scenario requires three tags: target car 1, gear shift trigger, lane change trigger, and route. The dynamic scenario template is named Player1_LaneChange1_Vchange1_Route1. The purpose of tagging is to quickly find the corresponding scenario template for the Use Case. The purpose of naming in this way is to intuitively understand the immutable elements included in the template scenario through the name.

[0060] 4. Write the Use Case ID, the static scene template name and dynamic scene template name corresponding to the Use Case, and the state space in each template into an Excel file to form a scene design document.

[0061] 5, The script is written according to the content of the scene design document to traverse the state space to generate specific static scene and specific dynamic scene parameter values, and replace the parameter names in the scene template file with specific values, and then obtain a plurality of specific static road network, dynamic scene corresponding to the use case, and through the VTD shell command line, automatically generate a visual.osgb file without opening the ROD module, and after associating.xodr and.osgb to the dynamic scene.xml, the function verification scene library of the application scene template, scene design document automatic construction system is completed.

[0062] According to the test scene library construction method of the automatic driving function provided in the embodiment of the application, the corresponding static logical scene and dynamic logical scene can be established through the target test case, a plurality of scene files are generated by using a plurality of static template scenes and dynamic logical template scenes, and the test scene library is established, so that the scene is generated without using the real vehicle data collection and scene mining technology, the effectiveness of the scene is improved, and the scene building cost is reduced; the static template scene and the dynamic template scene are built through the ROD and SE modules of the VTD software, the workload and error rate of manual building are reduced, and the scene test efficiency is improved; the number of the target test case, the name of the static template scene, the name of the dynamic template scene, and the element value range in the static logical scene and the dynamic logical scene are written into the preset file, so that the specific scene design document is generated, and the scene test efficiency is improved; the target logical scene is established according to the scene description and the scene schematic diagram of the target test case, the efficiency of establishing the test scene is improved, and the scene test cost is reduced.

[0063] Secondly, the test scene library construction device of the automatic driving function according to the embodiment of the application is described with reference to the accompanying drawings.

[0064] Figure 6 The block schematic diagram of the test scene library construction device of the automatic driving function in the embodiment of the application is shown in the figure.

[0065] As shown in the figure, Figure 6 The test scene library construction device 10 of the automatic driving function includes an acquisition module 100, a splitting module 200 and a construction module 300.

[0066] The obtaining module 100 is configured to obtain at least one target test case of an automatic driving function; the splitting module 200 is configured to establish a target logical scene corresponding to each target test case according to the at least one target test case, split the target logical scene to obtain at least one static logical scene and at least one dynamic logical scene, and obtain a static template scene and a dynamic template scene according to the at least one static logical scene and the at least one dynamic logical scene respectively; and the constructing module 300 is configured to generate a plurality of scene files according to a number of the target test case, the static template scene, the dynamic template scene, and a value range of an element in the static logical scene and the dynamic logical scene, and construct a test scene library of the automatic function by using the plurality of scene files.

[0067] In the embodiment of the present application, the splitting module 200 is further configured to: classify the elements of the at least one static logical scene and the at least one dynamic logical scene according to a preset classification strategy to obtain element classification results, and integrate the element classification results to obtain classified elements of the static logical scene and classified elements of the dynamic logical scene; use a ROD module of a preset VTD software to build a scene of the classified elements of the static logical scene to obtain the static template scene; and use a SE module of the preset VTD software to build a scene of the classified elements of the dynamic logical scene to obtain the dynamic template scene.

[0068] In the embodiment of the present application, the constructing module 300 is further configured to: write the number of the target test case, a name of the static template scene, a name of the dynamic template scene, and the value range of the element in the static logical scene and the dynamic logical scene into a preset file to generate a scene design document, wherein the name of the static template scene and the name of the dynamic template scene are named according to the classified elements respectively; use a preset script to read the scene design document, and traverse the static logical scene and the dynamic logical scene within the value range of the element to generate a plurality of scene files.

[0069] In the embodiment of the present application, the constructing module 300 is further configured to: identify a scene description and a scene sketch of each target test case; and use the scene description and the scene sketch of each target test case to establish a target logical scene corresponding to each target test case.

[0070] It should be noted that the foregoing explanation and description of the embodiment of the method for constructing a test scene library of an automatic driving function also apply to the embodiment of the device for constructing a test scene library of an automatic driving function, which will not be described herein again.

[0071] The automatic driving function test scene library construction device provided by the embodiment of the application can establish corresponding static logic scenes and dynamic logic scenes through target test cases, generate a plurality of scene files by using a plurality of static template scenes and dynamic logic template scenes, establish a test scene library, and does not need to generate scenes by using real vehicle data collection and scene mining technology, thereby improving the effectiveness of the scenes and reducing the scene construction cost. The static template scenes and dynamic template scenes are constructed by using the ROD and SE modules of the VTD software, thereby reducing the workload and error rate of manual construction and improving the scene test efficiency. The number of the target test case, the name of the static template scene, the name of the dynamic template scene, and the element value range in the static logic scene and the dynamic logic scene are written into a preset file, thereby generating a specific scene design document and improving the scene test efficiency. The target logic scene is established according to the scene description and the scene schematic diagram of the target test case, thereby improving the efficiency of establishing the test scene and reducing the scene test cost.

[0072] Figure 7 The electronic device provided by the embodiment of the application is shown in the structural schematic diagram. The electronic device can include:

[0073] The memory 701, the processor 702, and the computer program stored in the memory 701 and executable on the processor 702.

[0074] The processor 702 implements the automatic driving function test scene library construction method provided in the above embodiment when executing the program.

[0075] Further, the electronic device further includes:

[0076] The communication interface 703 is used for communication between the memory 701 and the processor 702.

[0077] The memory 701 is used for storing the computer program executable on the processor 702.

[0078] The memory 701 can include a high-speed RAM (Random Access Memory, random access memory) memory, and can also include a non-volatile memory, for example, at least one disk memory.

[0079] If the memory 701, the processor 702 and the communication interface 703 are implemented independently, the communication interface 703, the memory 701 and the processor 702 can be connected with each other through a bus and complete communication between each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 7 Only one thick line is used to represent the bus in the figure, but it does not mean that there is only one bus or only one type of bus.

[0080] Optionally, in a specific implementation, if the memory 701, the processor 702 and the communication interface 703 are integrated on a chip, the memory 701, the processor 702 and the communication interface 703 can complete communication between each other through an internal interface.

[0081] The processor 702 can be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0082] The embodiments of the present application also provide a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the above-mentioned method for constructing a test scenario library of an automatic driving function.

[0083] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example" or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms is not necessarily for the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the present specification and the features of the different embodiments or examples without contradiction.

[0084] In addition, the terms "first", "second", etc. are used herein only to describe different instances, and do not imply or suggest relative importance or a number of the indicated technical features. Thus, the features defined with "first", "second" can explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "N" is at least two, such as two, three, etc., unless otherwise explicitly and specifically limited.

[0085] Any process or method descriptions or descriptions of the flow diagrams described herein or otherwise described in the present application can be understood as representing executable instructions, code or modules stored in a computer-readable storage medium, and the scope of the preferred embodiments of the present application includes additional implementations or implementations in which the functions described in the processes or methods described herein or otherwise described in the present application are implemented in different orders, in different ways, or are not implemented at all.

[0086] It should be understood that various parts of the present application can be implemented in hardware, software, firmware or a combination thereof. In the above-described embodiments, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. As in another embodiment implemented in hardware, any one or a combination of the following technologies known in the art can be used: discrete logic circuit with logic gate circuit for implementing logic functions on data signals, application specific integrated circuit with suitable combination logic gate circuit, programmable gate array, field programmable gate array, etc.

[0087] Those skilled in the art of the present technology can understand that all or part of the steps carried out by the above-mentioned embodiment methods can be completed by programs instructing related hardware, and the programs can be stored in a computer-readable storage medium, and the programs include one or a combination of the steps of the method embodiments when executed.

[0088] Although the embodiments of the present application have been shown and described above, it can be understood that the above-described embodiments are exemplary and cannot be understood as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above-described embodiments within the scope of the present application.

Claims

1. A method for constructing a test scenario library of an automatic driving function, characterized by, The method comprises the following steps: obtaining at least one target test case of an automatic driving function; establishing a target logical scene corresponding to each target test case according to the at least one target test case, splitting the target logical scene to obtain at least one static logical scene and at least one dynamic logical scene, and respectively obtaining a static template scene and a dynamic template scene according to the at least one static logical scene and the at least one dynamic logical scene; generating a plurality of scene files according to the number of the target test case, the static template scene, the dynamic template scene, and the element value range of the static logical scene and the dynamic logical scene, and constructing a test scene library of the automatic driving function by using the plurality of scene files; respectively obtaining a static template scene and a dynamic template scene according to the at least one static logical scene and the at least one dynamic logical scene, comprising: classifying elements of the at least one static logical scene and the at least one dynamic logical scene according to a preset classification strategy to obtain element classification results, and integrating the element classification results to obtain classified elements of the static logical scene and the dynamic logical scene; performing scene building on the classified elements of the static logical scene by using an ROD module of a preset VTD software to obtain the static template scene; performing scene building on the classified elements of the dynamic logical scene by using an SE module of the preset VTD software to obtain the dynamic template scene.

2. The method of claim 1, wherein, The generating of the plurality of scene files according to the number of the target test case, the static template scene, the dynamic template scene, and the element value range of the static logical scene and the dynamic logical scene comprises: writing the number of the target test case, the name of the static template scene, the name of the dynamic template scene, and the element value range of the static logical scene and the dynamic logical scene into a preset file to generate a scene design document, wherein the names of the static template scene and the dynamic template scene are respectively named according to the classified elements; reading the scene design document by using a preset script, and traversing the static logical scene and the dynamic logical scene within the element value range to generate the plurality of scene files.

3. The method of claim 1, wherein, The establishing of the target logical scene corresponding to each target test case according to the at least one target test case comprises: identifying a scene description and a scene sketch of each target test case; establishing the target logical scene corresponding to each target test case by using the scene description and the scene sketch of each target test case.

4. An automatic driving function test scenario library construction apparatus characterized by comprising: comprise: an obtaining module configured to obtain at least one target test case of an automatic driving function; a splitting module configured to establish a target logical scene corresponding to each target test case according to the at least one target test case, split the target logical scene to obtain at least one static logical scene and at least one dynamic logical scene, and respectively obtain a static template scene and a dynamic template scene according to the at least one static logical scene and the at least one dynamic logical scene; The constructing module is configured to generate a plurality of scene files according to the number of the target test case, the static template scene, the dynamic template scene, and the element value range in the static logic scene and the dynamic logic scene, and to construct a test scene library of the automatic driving function by using the plurality of scene files. According to a preset classification strategy, elements of the at least one static logic scene and the at least one dynamic logic scene are classified respectively to obtain element classification results, and classification elements of the static logic scene and classification elements of the dynamic logic scene are obtained by integrating the element classification results; The ROD module of a preset VTD software is used to build a scene of the classification elements of the static logic scene, and the static template scene is obtained; The SE module of the VTD software is used to build a scene of the classification elements of the dynamic logic scene, and the dynamic template scene is obtained.

5. The apparatus of claim 4, wherein, The constructing module is further configured to: According to the number of the target test case, the name of the static template scene, the name of the dynamic template scene, and the element value range in the static logic scene and the dynamic logic scene, a scene design document is written in a preset file, wherein the names of the static template scene and the dynamic template scene are named according to the classification elements respectively; A preset script is used to read the scene design document, and the static logic scene and the dynamic logic scene are traversed in the element value range to generate the plurality of scene files.

6. The apparatus of claim 4, wherein, The constructing module is further configured to: Identify the scene description and the scene sketch of each target test case; The target logic scene corresponding to each target test case is established by using the scene description and the scene sketch of each target test case.

7. An electronic device, comprising: It comprises: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the test scene library construction method of the automatic driving function according to any one of claims 1-3.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the test scene library construction method of the automatic driving function according to any one of claims 1-3.

Images