Vehicle traveling file testing method and apparatus, processor, and electronic device

Abstract

The present disclosure provides a vehicle traveling file testing method and apparatus, a processor, and an electronic device. The method comprises: collecting test scene information of a vehicle under test, wherein the test scene information is used for at least representing the traveling environmental conditions of the vehicle; acquiring a scene file corresponding to the test scene information; using a simulation test system of the vehicle to simulate the scene file so as to obtain a virtual scene corresponding to the scene file, wherein the virtual scene is used for simulating the traveling environmental conditions; calling a traveling file under test of the vehicle to control the vehicle to travel in the virtual scene so as to obtain a traveling result; and testing the traveling result to obtain a test result, wherein the test result is used for representing whether the traveling file under test in the traveling result passes the test in the virtual scene.

Description

Vehicle driving file test method, device, processor and electronic device Cross-reference to related applications

[0001] The present disclosure claims priority from a Chinese patent application No. 202410831839.3 filed on June 25, 2024, and entitled "Vehicle driving file test method, device, processor and electronic device", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present disclosure relates to the technical field of vehicles, and in particular, to a vehicle driving file test method, device, processor and electronic device. BACKGROUND

[0003] Currently, autonomous vehicles rely on a variety of advanced technologies, such as artificial intelligence, visual computing, radar, and global positioning systems, to work together and achieve autonomous driving. These technologies enable vehicles to drive automatically and safely without the active operation of a driver. In this process, computer simulation of autonomous driving systems becomes a key technology for testing and experimentation, which not only provides a foundation for the development of autonomous vehicles, but also is an important tool for formulating future technical standards related to autonomous driving.

[0004] Simulation testing is a method of simulating real static environments and dynamic traffic scenarios through computer simulation technology, in order to test autonomous vehicles and algorithms in a virtual environment. However, how to simulate the diversity and effectiveness of autonomous driving systems is an important problem currently faced.

[0005] In related technologies, if the autonomous driving of a vehicle needs to be tested in different test scenarios, it is not only concentrated in general driving scenarios, but also requires test personnel to manually select and set test scenarios. The above method not only increases the manual operation in the testing process, but also reduces the efficiency of the test, resulting in low efficiency of the autonomous driving test of the vehicle. Therefore, there is still a technical problem of low efficiency of the driving file test of the vehicle.

[0006] In view of the above technical problem of low efficiency of the driving file test of the vehicle, no effective solution has been proposed so far. SUMMARY

[0007] The embodiments of the present disclosure provide a vehicle driving file test method, device, processor and electronic device to at least solve the technical problem of low efficiency of the driving file test of the vehicle.

[0008] According to an aspect of an embodiment of the present disclosure, a driving file test method of a vehicle is provided. The method can include: collecting test scene information of a vehicle to be tested, wherein the test scene information is used to represent at least a driving environment condition of the vehicle; obtaining a scene file corresponding to the test scene information; simulating the scene file by using a simulation test system of the vehicle to obtain a virtual scene corresponding to the scene file, wherein the virtual scene is used to simulate the driving environment condition; calling a to-be-tested driving file of the vehicle, controlling the vehicle to drive in the virtual scene, and obtaining a driving result; and testing the driving result to obtain a test result, wherein the test result is used to indicate whether the to-be-tested driving file passes the test in the virtual scene.

[0009] Optionally, the collecting of the test scene information of the vehicle to be tested includes: collecting, on a graphical user interface of a terminal corresponding to the vehicle, test requirement information used to test the to-be-tested driving file, wherein the test requirement information includes the test scene information; and the method further includes: selecting, on the graphical user interface, a configuration parameter of the simulation test system, wherein the configuration parameter is used to start the simulation test system.

[0010] Optionally, the obtaining of the scene file corresponding to the test scene information includes: in response to the obtaining of the test scene information and the configuration parameter on the graphical user interface, obtaining the scene file by using the to-be-tested driving file.

[0011] Optionally, before the obtaining of the scene file by using the to-be-tested driving file, the method further includes: in response to the obtaining of the test scene information and the configuration parameter, starting the to-be-tested driving file; connecting the test driving file and the simulation test system by using a communication protocol or an Ethernet mode; and obtaining the scene file by using the to-be-tested driving file, including: controlling, by using a script of the vehicle, the to-be-tested driving file to filter out the scene file matching the test scene information from a scene folder.

[0012] Optionally, the scene folder includes scene files, scene names corresponding to the scene files, and path information, the path information being used to indicate storage locations of the scene files, and the method of controlling the to-be-tested driving file by using the script of the vehicle and screening out the scene files corresponding to the test scene information from the scene folder includes: detecting the to-be-tested driving file to obtain a detection result, the detection result being used to indicate whether the to-be-tested driving file includes source code; in response to the detection result being that the to-be-tested driving file does not include source code, reading the scene names and the path information in the scene folder by using the script; controlling the to-be-tested driving file to screen out the scene name corresponding to the test scene information from the scene names read by using the script, and determining the scene file corresponding to the test scene information from the scene folder according to the path information corresponding to the scene name. The method further includes: in response to the detection result of the to-be-tested driving file being that the to-be-tested driving file includes source code, reading the path information corresponding to the scene file from the source code, and determining the scene file corresponding to the test scene information from the scene folder according to the path information.

[0013] Optionally, the method of testing the driving result to obtain a test result includes: in response to obtaining the driving result, calling driving data in a real scene corresponding to the virtual scene, the driving data being used to indicate the driving result obtained by controlling the vehicle to drive in the real scene; comparing the driving data and the driving result to obtain a comparison result, the comparison result being used to indicate a similarity degree between the driving data and the driving result; and determining the test result based on the comparison result.

[0014] Optionally, the method of determining the test result based on the comparison result includes: in response to the comparison result being that the similarity degree is greater than or equal to a similarity degree threshold, determining the test result to be that the to-be-tested driving file passes the test in the virtual scene; and in response to the comparison result being that the similarity degree is less than the similarity degree threshold, determining the test result to be that the to-be-tested driving file fails the test in the virtual scene.

[0015] Optionally, after determining the test result to be that the to-be-tested driving file fails the test in the virtual scene in response to the comparison result being that the similarity degree is less than the similarity degree threshold, the method further includes: correcting the to-be-tested driving file by using the test result to obtain a target to-be-tested driving file, the accuracy of the driving result of the target to-be-tested driving file in the virtual scene being higher than the accuracy of the driving result of the to-be-tested driving file in the virtual scene.

[0016] According to another aspect of the embodiments of the present disclosure, a device for testing a driving file of a vehicle is also provided. The device can include: a collection component configured to collect test scene information of a vehicle to be tested, wherein the test scene information is used to represent at least a driving environment condition of the vehicle; an acquisition component configured to acquire a scene file corresponding to the test scene information; a simulation component configured to simulate the scene file by using a simulation test system of the vehicle to obtain a virtual scene corresponding to the scene file, wherein the virtual scene is used to simulate the driving environment condition; a control component configured to call a to-be-tested driving file of the vehicle, control the vehicle to drive in the virtual scene, and obtain a driving result; and a test component configured to test the driving result to obtain a test result, wherein the test result is used to represent whether the to-be-tested driving file fails the test in the virtual scene.

[0017] According to another aspect of the embodiments of the present disclosure, a computer readable storage medium is also provided. The computer readable storage medium includes a stored program, wherein the program, when executed, controls a device in which the computer readable storage medium is located to perform the method for testing a driving file of a vehicle according to the embodiments of the present disclosure.

[0018] According to another aspect of the embodiments of the present disclosure, a processor is also provided. The processor is used to execute a program, wherein the program, when executed, performs the method for testing a driving file of a vehicle according to the embodiments of the present disclosure.

[0019] According to another aspect of the embodiments of the present disclosure, a computer program product is also provided. The computer program product includes a computer program, which, when executed by a processor, implements the method for testing a driving file of a vehicle according to the embodiments of the present disclosure.

[0020] In the embodiments of the present disclosure, if it is necessary to perform simulation testing on the driving file of the vehicle, the test scene information of a test personnel can be collected to determine a scene file corresponding to the test scene information. The scene file can be input into a simulation test system to simulate the driving environment condition corresponding to the scene file to obtain a corresponding virtual scene. In the virtual scene, a to-be-tested driving file of the vehicle can be called to control the vehicle to drive in the virtual scene to obtain a driving result. The driving result can be tested to determine a test result of whether the current to-be-tested driving file is accurate in the virtual scene, and the to-be-tested driving file is determined to be accurate through the test result, so that it is further determined that the to-be-tested driving file can meet the standard for being put into use for automatic driving, thereby solving the technical problem of low testing efficiency of the driving file of the vehicle and achieving the technical effect of improving the testing efficiency of the driving file of the vehicle. BRIEF DESCRIPTION OF DRAWINGS

[0021] The accompanying drawings, which are included to provide a further understanding of the disclosure and constitute a part of the disclosure, illustrate embodiments of the disclosure and together with the description given below serve to explain the disclosure, and do not limit the disclosure. In the drawings:

[0022] FIG. 1 is a flowchart of a driving file test method of a vehicle according to an embodiment of the disclosure;

[0023] FIG. 2 is a schematic diagram of a simulation test system for autonomous driving according to an embodiment of the disclosure;

[0024] FIG. 3 is a schematic diagram of an algorithm folder according to an embodiment of the disclosure;

[0025] FIG. 4 is a schematic diagram of a road file searching method according to an embodiment of the disclosure;

[0026] FIG. 5 is a schematic diagram of a driving file test device of a vehicle according to an embodiment of the disclosure. DETAILED DESCRIPTION

[0027] In order to enable persons skilled in the art to better understand the present disclosure scheme, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, not all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by persons skilled in the art without creative labor should be within the scope of protection of the present disclosure.

[0028] It should be noted that the terms "first", "second", and the like in the specification and claims of the present disclosure and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or components does not necessarily have to be limited to the steps or components clearly listed, but can include other steps or components not clearly listed or inherent to these processes, methods, products or devices.

[0029] According to the embodiments of the present disclosure, an embodiment of a driving file test method of a vehicle is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that described herein.

[0030] FIG. 1 is a flowchart of a driving file test method of a vehicle according to an embodiment of the present disclosure. As shown in FIG. 1, the method can include the following steps:

[0031] In step S102, test scenario information of a vehicle to be tested is collected.

[0032] In the technical solution provided in step S102 of the present disclosure, the test scenario information is used to represent at least the driving environment of the vehicle, and can be the test requirement of the tester for the test scenario, which can also be referred to as a test scenario or a driving scenario, and can include different road conditions, weather conditions, and traffic conditions, etc. The vehicle can be an autonomous vehicle. The tester can also be referred to as a user.

[0033] In this embodiment, the test requirement of the user for the vehicle to be tested can be collected to obtain the corresponding test scenario information.

[0034] Optionally, in order to ensure the efficiency of the driving file test, a tool capable of automatically selecting and setting the test scenario can be developed to reduce manual operation and improve efficiency. For example, the tester can select appropriate test scenario information on the corresponding operation interface according to the test requirement of the tester for the driving file.

[0035] In step S104, a scenario file corresponding to the test scenario information is obtained.

[0036] In the technical solution provided in step S104 of the present disclosure, the scenario file can be a scenario file in a scenario folder corresponding to the test scenario information.

[0037] In this embodiment, after the test scenario information of the vehicle to be tested is collected, the scenario file corresponding to the test scenario information can be determined.

[0038] Optionally, after the test requirement of the tester is determined, the scenario file meeting the test requirement can be searched from a large number of scenario files.

[0039] For example, by searching the scenario file, a suitable test scenario can be automatically selected from a predefined scenario library. These scenario files can include various driving environments such as urban roads, highways, complex intersections, etc., as well as different weather conditions and traffic conditions. It should be noted that the above scenario files are only for illustration and are not specifically limited herein.

[0040] Optionally, by utilizing machine learning and data-driven methods, an intelligent system can be developed to automatically select and set test scenarios, reducing human intervention, improving test efficiency, and ensuring that various possible situations are covered, thereby improving the comprehensiveness of the test and achieving automated test scenario selection. It should be noted that the above-mentioned selection of automated test scenarios is only for illustration and is not specifically limited here.

[0041] In step S106, the simulation test system of the vehicle is used to simulate the scene file to obtain a virtual scene corresponding to the scene file.

[0042] In the technical solution of step S106 of the present disclosure, the simulation test system can be a simulation test software, also known as a simulation software, such as a Virtual Test Drive (VTD) system. It is a software platform for virtual simulation testing. The simulation test system can be used to evaluate the performance of the autonomous driving system in different scenarios and environments. The virtual scene can be used to simulate the driving environment conditions.

[0043] In this embodiment, after obtaining the scene file corresponding to the test scenario information, the simulation test system of the vehicle can be used to simulate the virtual scene corresponding to the scene file.

[0044] Optionally, after obtaining the scene file that meets the test requirements, the scene file can be transmitted to the simulation test system. The simulation test system can identify the driving environment conditions in the scene file and perform simulation to obtain a virtual scene corresponding to the scene file, so that the virtual scene can be tested.

[0045] In step S108, the to-be-tested driving file of the vehicle is called to control the vehicle to drive in the virtual scene to obtain driving results.

[0046] In the technical solution of step S108 of the present disclosure, the to-be-tested driving file can be a measured algorithm in the vehicle, which can be a specific algorithm that needs to be evaluated and verified in simulation testing, and can be various algorithms for perceiving, decision-making, and controlling the vehicle, such as target detection and tracking, environment modeling, path planning, and behavior prediction. The measured algorithm can be a Highway Pilot (HWP) algorithm, which is only for illustration and does not specifically limit the algorithm for controlling the autonomous driving of the vehicle. It should be noted that the functions of the above-mentioned measured algorithm are only for illustration and are not specifically limited here.

[0047] In this embodiment, after the simulation test system of the vehicle is used to simulate the scene file to obtain a corresponding virtual scene, the to-be-tested driving file of the vehicle can be called to control the vehicle to drive in the virtual scene to obtain driving results.

[0048] Optionally, after the scene file is determined, the scene file can be transmitted to the simulation test system, and the measured algorithm is called to control the simulation test system to simulate the scene file, and the scene test is performed in the virtual scene by using the measured algorithm, that is, the perception, decision and control of vehicle driving in the virtual scene are performed by the measured algorithm, and the corresponding driving result is obtained.

[0049] Optionally, the measured algorithm can include target detection and tracking, which is used to detect obstacles, pedestrians, vehicles and the like in the surrounding environment, and track their motion states. The measured algorithm can also include environment modeling, which is used to model and represent the perceived environment information, so that the automatic driving system makes decisions and plans. The measured algorithm can include path planning, which is used to formulate the driving path of the vehicle according to the environment information and the target, to ensure safe and efficient driving. The measured algorithm can include behavior prediction, which is used to predict the behavior of other traffic participants, so that the automatic driving system makes corresponding decisions. In addition, the measured algorithm can also include the decision and control algorithm of the automatic driving system, which is used to realize the functions of autonomous driving and obstacle avoidance of the vehicle. In the simulation test, the above algorithms are loaded into the simulation platform, and the simulation test is performed through the data input by the simulation environment, to evaluate the performance, robustness and safety, etc. Therefore, for the development and test of the automatic driving system, the measured algorithm is a crucial part, and the accuracy and reliability of the measured algorithm are crucial for the safety and performance of the entire automatic driving system.

[0050] In step S110, the driving result is tested to obtain a test result.

[0051] In the technical solution of step S110 of the present disclosure, the test result can be used to indicate whether the to-be-tested driving file passes the test in the virtual scene. If the driving result is accurate, it can be indicated that the to-be-tested driving file passes the test in the current virtual scene. If the driving result is not accurate, it can be indicated that the to-be-tested driving file does not pass the test in the current virtual scene.

[0052] In this embodiment, after the to-be-tested driving file of the vehicle is called to control the vehicle to drive in the virtual scene and the driving result is obtained, the driving result can be tested to obtain a corresponding test result. Through the test result, it can be determined whether the to-be-tested driving file passes the test in the virtual scene.

[0053] Optionally, after the driving result is determined, the driving result corresponding to the driving result in the virtual scene in the real vehicle test can be obtained. Through the comparison between the above two driving results, it can be determined whether the driving result in the virtual scene is accurate. If not, potential problems in the to-be-tested driving file can be determined and processed.

[0054] In the embodiment of the present disclosure, the simulation test is combined with the actual road test, so that the advantages of both can be fully utilized. The algorithm and strategy are verified and optimized through the simulation test, and then the results of the simulation test are verified through the real vehicle test and potential problems are found, that is, the driving results of the simulation test are compared with the driving results of the real vehicle test to determine whether the simulation test is accurate, and if not, the tested algorithm needs to be corrected and optimized, thereby improving the technical effect of the safety of the vehicle automatic driving.

[0055] In the step S102 to the step S110 of the present disclosure, if the driving file of the vehicle needs to be simulated and tested, the test scene information of the tester can be collected to determine the scene file corresponding to the test scene information. The scene file can be input into the simulation test system to simulate the driving environment corresponding to the scene file, and the corresponding virtual scene is obtained. In the virtual scene, the driving file to be tested of the vehicle can be called to control the vehicle to drive in the virtual scene, and the driving result is obtained. The driving result can be tested to determine the test result of whether the driving result of the current driving file to be tested in the virtual scene is accurate. The test result is used to determine whether the driving file to be tested is accurate, to further determine whether the driving file to be tested can meet the standard of being put into automatic driving use, thereby solving the technical problem of low driving file test efficiency of the vehicle, and achieving the technical effect of improving the driving file test efficiency of the vehicle.

[0056] The above method of the embodiment will be further introduced below.

[0057] As an optional embodiment, in the step S102, the test scene information of the vehicle to be tested is collected, including: collecting test demand information for testing the driving file to be tested on a graphical user interface of a terminal corresponding to the vehicle, wherein the test demand information includes the test scene information; the method further includes: selecting configuration parameters of the simulation test system on the graphical user interface, wherein the configuration parameters are used to start the simulation test system.

[0058] In the embodiment, in the process of collecting the test scene information of the vehicle to be tested, the test demand of the driving file to be tested can be collected on the graphical user interface of the terminal corresponding to the vehicle. The configuration parameters of the simulation test system can also be selected on the graphical user interface, and the test demand can include the test scene information. The configuration parameters can be used to start the simulation test system, and can include the target setup and the project.

[0059] Optionally, in the virtual simulation environment, setup generally refers to a process of configuring and setting up the simulation environment, which can include selecting parameters of the simulation environment, initializing various settings of the simulation environment, setting conditions and scenarios of the test, etc. That is, setup refers to the setting or configuration of the simulation test, which can include initialization of the test environment, setting of parameters, loading of simulation models, configuration of simulation parameters, etc. The setup parameter is used to define the preliminary settings of the test to ensure that the simulation test can be carried out as expected.

[0060] Optionally, the project parameter refers to a project file of the simulation test, which can be a file containing test-related information, including test scenarios, test parameters, simulation models, input and output settings, etc. In the project file, a comprehensive description and definition of the simulation test can be contained to quickly load and execute the test when needed. Project refers to a specific project or task in the virtual simulation environment, and in this case, project is a specific test project, which can include plans and processes for testing specific scenarios or systems. In the virtual simulation environment, the process of testing and simulating the system involves the configuration of the simulation environment and the setting of the specific test project.

[0061] Optionally, in the terminal, the target setup and project can be selected to convert the VTD into an autoStart mode. The simulation test system can automatically select the most suitable test scenario according to the test requirements and goals of the test personnel.

[0062] As an optional embodiment, in step S104, the scene file corresponding to the test scenario information is obtained, including: in response to obtaining the test scenario information and the configuration parameters on the graphical user interface, obtaining the scene file by using the to-be-tested driving file.

[0063] In this embodiment, in the process of obtaining the scene file corresponding to the test scenario information, after obtaining the test scenario information and the configuration parameters on the graphical user interface, the to-be-tested driving file can be controlled to obtain the scene file.

[0064] Optionally, after obtaining the test scenario information and the configuration parameters on the graphical user interface of the terminal, the scene file corresponding to the test scenario information received on the current graphical user interface can be retrieved by the tested algorithm.

[0065] As an optional embodiment, before the scenario file is acquired by the to-be-tested driving file, the method further comprises: in response to acquiring the test scenario information and the configuration parameters, starting the to-be-tested driving file; connecting the test driving file and the simulation test system by using a communication protocol or an Ethernet; and acquiring the scenario file by the to-be-tested driving file, comprising: controlling the to-be-tested driving file by using a script of the vehicle, and screening the scenario file matching the test scenario information from a scenario folder.

[0066] In this embodiment, before the scenario file is acquired by the to-be-tested driving file, if the test scenario information and the configuration parameters are acquired from a graphical user interface, the to-be-tested driving file can be started, and the to-be-tested driving file and the simulation test system can be connected by using a communication protocol or an Ethernet. After the connection is completed, if the to-be-tested driving file needs to be controlled to acquire the scenario file, the to-be-tested driving file can be controlled by using a script of the vehicle, and the scenario file matching the currently received test scenario information can be screened from a scenario folder, wherein the scenario folder can be a specified folder. The specified folder can be included in an algorithm folder. The algorithm folder can further include a to-be-tested algorithm and an executable program folder.

[0067] Optionally, the to-be-tested algorithm can retrieve the corresponding scenario file in the specified folder by using the script. The to-be-tested algorithm can be started on a terminal, and the simulation test software and the to-be-tested algorithm can be connected by using a communication protocol, an Ethernet or the like.

[0068] Optionally, the script is a control script for simulation testing of an automatic driving system. The workflow of the script can include retrieving a scenario file, starting a to-be-tested algorithm and running simulation test software. The script can retrieve the corresponding scenario file in the specified folder, and the scenario file describes different driving scenarios. The script can start the to-be-tested algorithm on a terminal, and the software and the to-be-tested algorithm can be connected by using a communication protocol, an Ethernet or the like. The script can run the simulation test software, and test the performance of the to-be-tested algorithm in different scenarios.

[0069] As an optional embodiment, the scene folder includes scene files, scene names corresponding to the scene files, and path information, the path information being used to indicate storage positions of the scene files, wherein the script of the vehicle is used to control the to-be-tested driving file, to filter out the scene files corresponding to the test scene information from the scene folder, including: detecting the to-be-tested driving file to obtain a detection result, wherein the detection result is used to indicate whether the to-be-tested driving file includes source code; in response to the detection result being that the to-be-tested driving file does not include source code, reading the scene names and the path information in the scene folder by using the script; controlling the to-be-tested driving file to filter out the scene name corresponding to the test scene information from the scene names read by the script, and determining the scene file corresponding to the test scene information from the scene folder according to the path information corresponding to the scene name; the method further includes: in response to the detection result of the to-be-tested driving file being that the to-be-tested driving file includes source code, reading the path information corresponding to the scene file from the source code, and determining the scene file corresponding to the test scene information from the scene folder according to the path information.

[0070] In this embodiment, in the process of filtering the scene files from the scene folder by using the script to control the to-be-tested driving file, the to-be-tested driving file can be detected to determine whether the to-be-tested driving file includes source code, to obtain a corresponding detection result. If the detection result is that the to-be-tested driving file does not include source code, the scene names and the path information in the scene folder can be read by using the script. The to-be-tested driving file is controlled to filter out the scene name corresponding to the test scene information from the scene names read by the script, and the scene file corresponding to the test scene information is determined from the scene folder according to the path information corresponding to the scene name, wherein the scene folder can include scene files, scene names corresponding to the scene files, and path information. The scene name can be a road file name. The path information can be a path where the scene file is stored, which can also be referred to as a path file. The scene file can also be referred to as a road file.

[0071] Optionally, road files are typically used to describe road networks and road condition information, which are important data in autonomous driving systems. Road files are used in simulation environments so that the system can simulate real-world road conditions. Road files typically include road layout, describing the geometry, curvature, slope, intersection, and other information of the road. Traffic signs and markings, including various traffic signs, road markings, and lane lines, are used to simulate the traffic identification of real roads. Intersections and traffic lights describe the location and control information of intersections and traffic lights, as well as the turning and stopping rules of vehicles. Obstacles and road conditions describe obstacles, road conditions, and other factors that affect vehicle driving on the road, such as wet and slippery roads, snow, etc. Vehicle trajectories can include actual trajectory data of historical vehicles to simulate real vehicle driving conditions. The above road files play a key role in the simulation testing of autonomous driving systems, providing data to simulate real road environments for autonomous driving systems, helping the system to simulate various scenarios and evaluate the performance and reliability of autonomous driving systems under different road conditions.

[0072] Optionally, if the detection result of the to-be-tested driving file is that there is a source code in the to-be-tested driving file, the path information corresponding to the scene file can be directly read from the source code, and the scene file corresponding to the test scene information can be directly determined from the scene folder according to the path information.

[0073] Optionally, in general, the process of starting the automatic test script is triggered by the test personnel or the automatic test framework, and the input test requirements can be used to configure and determine the specific content of the test. The above test requirements can include the scenes to be tested, the parameters of the test, the expected results of the test, etc. The test personnel can trigger the execution of the automatic test script through a specific interface or command, and then according to the setting of the test requirements, the script will automatically start the tested algorithm and the simulation test software, and perform corresponding tests and evaluations. The automatic test framework or test management system can also start the automatic test script according to the predetermined plan, trigger event or external trigger. For example, mechanisms such as timing trigger, code submission trigger, continuous integration / continuous deployment trigger, etc. can be set to automatically execute the test script. In summary, the start of the automatic test script is triggered by the test personnel or the automatic test framework, and the input test requirements can affect the execution mode and results of the test.

[0074] Optionally, a script refers to a piece of computer program or instruction sequence that can be used to perform specific tasks or operations. The script is described as the basis for implementing the entire framework. The script usually contains a series of computer commands and operations that will be executed in the order and logic defined in the script. The script can contain variables and parameters for storing data or configuration, which are usually used to control the behavior of the script. The script can contain conditional statements, loops and other flow control structures to perform different operations according to specific conditions or situations. The script can contain defined functions and subprograms to achieve code componentization and reuse. In the field of autonomous driving, scripts can be used to control the start of simulation test software, the execution of the algorithm under test, the setting of test scenarios, and other operations. The writing and execution of scripts can achieve the automation and control of the test process of autonomous driving systems.

[0075] Optionally, the script plays a key role as the basis of the entire system. Starting the algorithm under test and simulation test software, the script is used to start the algorithm under test and simulation test software in the system, so that the entire test process can begin. Executable program integration, the script can also integrate the required code files in the algorithm folder and integrate the code files into an executable program, which helps to manage and prepare the algorithm under test uniformly. Control of scene test process, the script can control the simulation software to perform scene testing by controlling the algorithm under test, which means that the script can achieve automatic control and coordination of the test process. After the test is completed, the script can close the algorithm under test and the test software to complete the entire test process, which helps to automatically manage and execute the simulation test process of autonomous driving systems. As the basis, the script provides control and management of the entire test process, thereby achieving automated operation of the test.

[0076] Optionally, the script is the basis for implementing the entire framework, which is used to start the algorithm under test and start the test software on the terminal. The executable program integrates the required code files in the algorithm folder together. The algorithm under test controls the simulation software to perform scene testing, and the algorithm and test software are closed after the test is completed.

[0077] Optionally, the script plays a fundamental role in the entire simulation test framework of the autonomous driving system as the basis of the entire framework. The script can start the algorithm under test and the simulation test software, and plays a key role in the entire test process. The script is used to start the algorithm under test and the simulation test software on the terminal, which means that the script is the launcher of the entire test process and can coordinate and control the running of the algorithm under test and the simulation test software. The script can also integrate the required code files in the algorithm folder and compile to generate an executable program. This makes the entire test process more automated and efficient. Before running the test, the script first stores the required scenario files in the designated folder and stores the executable program generated by compiling the algorithm in a dedicated executable program folder. This helps to uniformly manage and prepare the resources required for testing. The script controls the algorithm under test to control the simulation software to perform scenario testing. This means that the script can achieve automated control and coordination of the test process. After the test is completed, the script is responsible for closing the algorithm under test and the test software to complete the entire test process. In summary, the script plays the roles of launcher, integrator and controller in the simulation test framework of the autonomous driving system, and achieves automated control and coordination of the entire test process.

[0078] Optionally, the required scenario files can be stored in the designated folder in advance, and the executable program generated by running the algorithm can be stored in the executable program folder.

[0079] Optionally, the required scenario files can be stored in the designated folder, which can include descriptions of various driving scenarios, road layouts, traffic conditions, etc. The algorithm can be run to compile an executable program, which will be used to control the simulation software to perform scenario testing. The generated executable program can be stored in a designated executable program folder. Through the above steps, the scenario files required for testing can be prepared in the designated folder, and the executable program generated by compiling can be stored in another folder. These preparations lay the foundation for the simulation test of the autonomous driving system.

[0080] Optionally, the executable program folder is used to store the compiled program files of the tested algorithm. These executable program files can contain computer instructions that can be directly executed by the computer. The above-mentioned program files can be compiled binary files that can run in a specific operating system environment. The above-mentioned executable program files will be used to control the simulation test software to perform scenario testing. By calling the above-mentioned executable program files in the script, the tested algorithm can be tested automatically. This automated testing process helps to improve the efficiency of testing and ensures the consistency and comprehensiveness of testing. Therefore, the role of the executable program folder in this process is to store the executable files of the tested algorithm generated by compilation, which will be called by the script to perform simulation testing.

[0081] Optionally, the tester needs to test the Highway Pilot (HWP) algorithm. During the testing process, first, the scene is set up and selected according to the test outline to select the scene for this test. Then, copy all the road files of the scene to the algorithm folder, and create a new text file under the specified folder, write all the road file names and paths of the scene into the text file. Since the algorithm is in a static library without source code, it is necessary to read the road file name in the script to let the algorithm find the corresponding scene file.

[0082] Optionally, the tester selects the test scene according to the test outline and copies the road files of these scenes to the algorithm folder. A new text file is created under the specified folder, and all the road file names and paths of the scene are written into the text file, which helps to read and match the scene in the subsequent automated testing process. The tester needs to write a script to read the road file name and path in the text file during the testing process, and let the algorithm find the corresponding scene file to perform testing. Through the above steps, the tester can automatically test the HWP algorithm, and fully utilize the existing scene and road files to verify the performance and robustness of the algorithm under various scenarios. This automated testing process can improve the testing efficiency and consistency, and help to ensure the accuracy and reliability of the algorithm.

[0083] Optionally, according to the test outline, a test scene can be set up and selected in the simulation environment. This may involve selecting appropriate roads and traffic conditions, and setting various parameters and conditions for the test. After the test scene is selected, all relevant scene road files can be copied to the algorithm folder. The above-mentioned scene road files can include road layout, traffic flow, obstacle position, etc. A text file can be created under the specified folder, and the names and paths of all scene road files are written in the text, which helps the script to automatically read and process these files. Since the algorithm is placed in a static library without source code, logic needs to be written in the script to enable the algorithm to find the corresponding scene file according to the path and file name in the text file for testing. The above-mentioned entire process involves test scene selection, file processing and script writing, which can realize the automatic association of scene data and algorithms to perform simulation testing of autonomous driving systems, which helps to improve the efficiency and consistency of testing and ensures the comprehensiveness of testing.

[0084] Optionally, the test outline refers to a detailed test plan prepared for system testing, which can include test objectives, scope, methods, resources, schedules, risk assessments, and specific test requirements, aiming to ensure that system testing can be carried out according to the established plan. The test outline can be prepared by test planners, test engineers, etc. Specifically, the test outline can include the following contents: test objectives, which can clearly define the overall objectives and expected results of system testing. Test scope, which can define the specific scope of system testing, including testing of functions, performance, compatibility, etc. Test methods, which can determine the specific methods, tools and processes used in system testing. Test resources, which can determine the human, material, time and other resources required for system testing. Schedule, which can develop the time schedule and plan for system testing. Risk assessment, which can assess the risks and problems that may be faced by system testing, and develop corresponding risk response measures. Test requirements, which can clearly define the specific requirements and standards of system testing. The preparation of the test outline helps the effective implementation of system testing, ensures the comprehensiveness, accuracy and reliability of testing, and provides detailed guidance and planning for testers, so that system testing can be carried out according to the established plan.

[0085] Optionally, it is very important to determine whether the measured algorithm has source code (i.e. readable program code), because the source code has the following functions and reasons: readability and understanding, the source code can make the developer and tester better understand the implementation details and working principle of the algorithm, which helps to improve the understanding of the algorithm, so as to better test and evaluate. Modification and customization, having source code means that the algorithm can be modified and customized according to the needs to meet the specific testing requirements or scene requirements, which is very important for the customized testing of autonomous driving system. Debugging and troubleshooting, source code helps to debug and troubleshoot, when problems are found in the testing process, the source code can be used to track and fix the problems. Security and credibility, for critical autonomous driving algorithms, having source code can help verify its security and reliability, thereby increasing the credibility of the algorithm. Adapt to future needs, source code enables the algorithm to adapt to future demand changes, such as new function requirements, performance optimization, etc. In summary, having the source code of the measured algorithm is extremely important for the testing and evaluation process. Source code can provide more operability, transparency and flexibility, which helps to ensure the performance and safety of autonomous driving system.

[0086] For example, if the measured algorithm has source code, the road file corresponding to the current test scene information can be directly obtained. If the measured algorithm has no source code, the static library can obtain the road file corresponding to the current test scene information through a script.

[0087] As an optional embodiment, in step S110, the driving result is tested to obtain a test result, including: in response to obtaining the driving result, calling driving data in a real scene corresponding to the virtual scene, wherein the driving data is used to represent the driving result obtained by controlling the vehicle to drive in the real scene; comparing the driving data and the driving result to obtain a comparison result, wherein the comparison result is used to represent the similarity between the driving data and the driving result; determining the test result based on the comparison result.

[0088] In this embodiment, in the process of testing the driving result to obtain the test result, when the driving result is obtained, the driving data in the real scene corresponding to the virtual scene can be called. By comparing the driving data and the driving result, a comparison result is obtained. Based on the comparison result, the test result can be determined.

[0089] Optionally, the driving data can be used to represent the driving result obtained by controlling the vehicle to drive in the real scene, which can also be called real data, that is, the result obtained by real vehicle testing in the real scene. The comparison result can be used to represent the similarity between the driving data and the driving result.

[0090] In the embodiments of the present disclosure, the simulation test and the real vehicle test results can be combined, that is, the simulation test and the actual road test are combined to make full use of the advantages of both. The algorithm and strategy are verified and optimized through the simulation test, and then the simulation test results are verified through the real vehicle test and potential problems are found.

[0091] As an optional embodiment, based on the comparison result, the test result is determined, including: in response to the similarity degree being greater than or equal to the similarity degree threshold, determining that the test result is that the to-be-tested driving file passes the test in the virtual scene; and in response to the similarity degree being less than the similarity degree threshold, determining that the test result is that the to-be-tested driving file fails the test in the virtual scene.

[0092] In this embodiment, in the process of determining the test result based on the comparison result, if the similarity degree is greater than or equal to the similarity degree threshold, it is determined that the test result is that the to-be-tested driving file passes the test in the virtual scene. If the similarity degree is less than the similarity degree threshold, it can be determined that the test result is that the to-be-tested driving file fails the test in the virtual scene, wherein the similarity degree threshold can be a pre-set value, or can be set by itself according to the actual test situation, for example, it can be pre-set to 98%. It should be noted that the setting method and size of the above-mentioned similarity degree threshold are only for illustration, and are not limited here.

[0093] Optionally, if the similarity degree between the simulation test driving result and the real vehicle test driving data is high, that is, the similarity degree is greater than or equal to the similarity degree threshold, it can be indicated that the simulation test driving result is relatively accurate, indicating that the current measured algorithm passes the verification and does not need to be optimized and adjusted. If the similarity degree between the driving result and the driving data is low, that is, the similarity degree is less than the similarity degree threshold, it can be indicated that the simulation test driving result is relatively abnormal, indicating that the current measured algorithm fails the verification and still needs to be optimized to solve potential problems.

[0094] As an optional embodiment, after determining that the test result is that the to-be-tested driving file fails the test in the virtual scene in response to the similarity degree being less than the similarity degree threshold, the method further includes: correcting the to-be-tested driving file using the test result to obtain a target to-be-tested driving file, wherein the accuracy of the driving result of the target to-be-tested driving file in the virtual scene is higher than the accuracy of the driving result of the to-be-tested driving file in the virtual scene.

[0095] In this embodiment, after determining that the test result is that the to-be-tested driving file fails the test in the virtual scene in response to the similarity degree being less than the similarity degree threshold, the to-be-tested driving file can be modified using the test result to obtain a modified target to-be-tested driving file, wherein the accuracy of the driving result of the target to-be-tested driving file in the virtual scene is higher than the accuracy of the driving result of the to-be-tested driving file in the virtual scene, that is, the target to-be-tested driving file is more accurate than the to-be-tested driving file.

[0096] Optionally, if the driving result obtained by the current simulation test does not meet the expectation, that is, the similarity degree with the driving data of the real vehicle test is low, it can be indicated that there is a problem in the measured algorithm of the current simulation test, and the measured algorithm needs to be modified and optimized later to improve the accuracy of the test driving result.

[0097] In the embodiments of the present disclosure, if it is necessary to perform simulation testing on the driving file of the vehicle, the test scene information of the tester can be collected to determine the scene file corresponding to the test scene information. The scene file can be input into the simulation test system to simulate the driving environment corresponding to the scene file to obtain a corresponding virtual scene. In the virtual scene, the to-be-tested driving file of the vehicle can be called to control the vehicle to drive in the virtual scene to obtain a driving result. The driving result can be tested to determine a test result of whether the driving result of the current to-be-tested driving file in the virtual scene is accurate. The test result is used to determine whether the to-be-tested driving file is accurate to further determine whether the to-be-tested driving file can meet the standard for being put into use of automatic driving, thereby solving the technical problem of low efficiency of testing the driving file of the vehicle and achieving the technical effect of improving the efficiency of testing the driving file of the vehicle.

[0098] The technical solutions of the embodiments of the present disclosure will be described below in conjunction with preferred embodiments.

[0099] At present, autonomous vehicles rely on a variety of advanced technologies, such as artificial intelligence, visual computing, radar, and global positioning systems, to work together and achieve unmanned driving. The cooperative work of the above technologies enables autonomous vehicles to drive automatically and safely without the active operation of a driver. At the same time, computer simulation technology provides a basis for the development of autonomous vehicles and helps to formulate future technical standards related to autonomous driving. The continuous progress and application of these technologies will provide important support for the development of future intelligent transportation systems and unmanned vehicles.

[0100] Simulation testing is crucial for the development and testing of autonomous driving systems. While current simulation testing for autonomous driving mainly focuses on general driving scenarios, there are challenges in how to conduct more diverse and effective simulation testing for autonomous driving systems. Here are some suggestions and solutions for this problem: Automated scenario generation: Develop tools that can automatically generate diverse scenarios to reduce the workload of testers manually selecting and setting up test scenarios. This may require the integration of machine learning and scenario generation techniques to enable the testing system to automatically select the most appropriate test scenarios. Diverse scenario testing: Explore a wider variety of and more complex test scenarios to comprehensively evaluate the performance and robustness of autonomous driving systems. This may require the introduction of more variables and abnormal situations, as well as the evaluation of autonomous driving system behavior in different scenarios. Real-time simulation and testing: Research methods for real-time simulation and testing to more accurately simulate dynamic environments and traffic scenarios in actual driving processes. This may require improvements in simulation algorithms and hardware performance to achieve higher precision in real-time simulation. Combination of virtual and actual testing: Combine simulation testing with actual road testing to take full advantage of both. Verify and optimize algorithms and strategies through simulation testing, and then verify the results of simulation testing and discover potential problems through real vehicle testing.

[0101] Optionally, the above methods and strategies will help improve the diversity and effectiveness of simulation testing for autonomous driving systems, ensuring the performance and safety of the system in different scenarios. By combining automated scenario generation, diverse scenario testing, real-time simulation, and combining virtual and actual testing, the test coverage and quality of autonomous driving systems can be further improved, thereby promoting the development of autonomous driving technology.

[0102] The embodiments of the present disclosure propose a method for retrieving scenario files for simulation testing of autonomous driving, which realizes automated simulation testing of autonomous driving in various driving scenarios and reduces manual operations and improves efficiency. In brief, the method can automatically retrieve diverse driving scenario files, which describe different driving conditions and environments, to ensure that diverse driving scenarios are covered in testing, realize automated simulation testing, and enable the system to automatically select and set test scenarios, thereby reducing manual operations and improving testing efficiency. By reducing manual operations and automatically selecting appropriate test scenarios, the efficiency of autonomous driving simulation testing can be improved, thereby speeding up the testing process. In summary, the method has the advantage of providing automated simulation testing of autonomous driving, reducing manual operations and improving testing efficiency, which is of great significance for the development and testing of autonomous driving systems. Because the method helps to more comprehensively evaluate the performance and safety of autonomous driving systems in various driving scenarios, it solves the technical problem of low efficiency of vehicle driving file testing and achieves the technical effect of improving the efficiency of vehicle driving file testing.

[0103] The embodiments of the present disclosure are further described below.

[0104] In the embodiments of the present disclosure, FIG. 2 is a schematic diagram of a simulation test system for automatic driving according to the embodiments of the present disclosure, as shown in FIG. 2, the system can include a script 201, an executable program file 202, a measured algorithm 203, simulation test software 204, and scene test 205, wherein the script 201 is the basis for implementing the entire framework, used to start the measured algorithm 203 and start the simulation test software 204 on the terminal, the executable program file 202 integrates the code files required in the algorithm folder, the measured algorithm 203 controls the simulation test software 204 to perform scene test 205, and closes the measured algorithm 203 and the simulation test software 204 after the test is completed.

[0105] FIG. 3 is a schematic diagram of an algorithm folder according to the embodiments of the present disclosure, as shown in FIG. 3, the algorithm folder 300 can include a specified folder 301, a measured algorithm 302, and an executable program folder 303. The required scene files can be stored in the specified folder 301, and the executable program generated by running the algorithm is stored in the executable program folder 303.

[0106] Optionally, the script written makes the measured algorithm 302 retrieve the scene files corresponding to the specified folder, starts the measured algorithm on the terminal, and connects the software and the measured algorithm by using a communication protocol, Ethernet, or the like. Then the simulation test software is run, and after the test is completed, the measured algorithm and the simulation test software are closed. The time required for closing the software is different for different simulation test software, so as to avoid that the next algorithm is automatically started before the test software is completed, resulting in interruption of the test. Then the next scene file is read, and the above process is repeated to test the scenes one by one.

[0107] Optionally, the script is a control script for a simulation test of an automatic driving system. The workflow of the script is as follows: retrieving a scenario file, the script retrieves the corresponding scenario file in the specified folder, and the scenario file describes different driving scenarios. Starting the algorithm under test, the script starts the algorithm under test on the terminal, and connects the software and the algorithm under test using a communication protocol, Ethernet, etc. Running the simulation test software, the script runs the simulation test software to test the performance of the algorithm under test in different scenarios. Turning off the algorithm under test and the simulation test software, after the test is completed, the script will turn off the algorithm under test and the simulation test software. For different simulation test software, different time is needed to ensure that the software is completely closed, so as to avoid the test software not ending running and the next algorithm starting automatically, resulting in interruption of the test. Reading the next scenario file, the script continues to loop and read the next scenario file to test each scenario one by one. The above script setting makes the whole simulation test process automatic, which can effectively test the performance and reliability of the automatic driving system in different scenarios, and improves the efficiency and consistency of the test.

[0108] Taking the VTD test HWP algorithm as an example, first, the scene can be built and selected according to the test outline, the scene of this test is selected, all the road files of the scene are copied to the algorithm folder, and then a text is newly created under the specified folder, and the road file name and path of all the scenes are written into the text. Because the algorithm is in a static library without source code, the road file name is read in the script to let the algorithm find the corresponding scene file. FIG. 4 is a schematic diagram of a method for finding a road file according to an embodiment of the present disclosure. As shown in FIG. 4, the method can include the following steps:

[0109] Step S401, acquiring an algorithm under test.

[0110] In this embodiment, if the algorithm under test needs to be tested, the algorithm under test to be tested can be acquired.

[0111] Step S402, detecting whether there is source code in the algorithm under test.

[0112] In this embodiment, whether there is source code in the algorithm under test can be detected. If yes, step S403 can be performed, otherwise, step S404 can be performed.

[0113] Step S403, acquiring a path file from the source code to determine a road file.

[0114] In this embodiment, if there is source code in the algorithm under test, the path file of the required road file can be directly acquired from the source code, and the corresponding road file can be determined according to the path file.

[0115] Step S404, reading the name of the road file in the script to find the road file.

[0116] In this embodiment, if there is no source code in the measured algorithm, the name of the required road file can be read from the script, and the corresponding road file can be found.

[0117] Optionally, the script is started in the VTD / bin terminal, the target setup and project are selected in the terminal, the script is converted into the autoStart mode, the executable file generated by the compilation is found in the algorithm folder, the algorithm is run, the scene file can be read in the path file text, and after each scene is tested, the VTD and the algorithm are closed, and the above process is repeated.

[0118] In the embodiments of the present disclosure, the code can be used to configure the simulation test file and the executable program, and the configured simulation test file can be run to sequentially execute the simulation test of each driving scene to be tested. The test situation in the test process can be seen in real time, and the test is automatically terminated if there is a scene error.

[0119] In the embodiments of the present disclosure, if the driving file of the vehicle needs to be simulated and tested, the test scene information of the tester can be collected, and the scene file corresponding to the test scene information is determined. The scene file can be input into the simulation test system to simulate the driving environment corresponding to the scene file, and the corresponding virtual scene is obtained. In the virtual scene, the driving file to be tested of the vehicle can be called to control the vehicle to drive in the virtual scene, and the driving result is obtained. The driving result can be tested to determine whether the driving result of the current driving file to be tested in the virtual scene is accurate, and the test result is obtained. The test result is used to determine whether the driving file to be tested is accurate, and the driving file to be tested is further determined to meet the standard of being put into automatic driving use, thereby solving the technical problem of low driving file test efficiency of the vehicle, and achieving the technical effect of improving the driving file test efficiency of the vehicle.

[0120] According to the embodiments of the present disclosure, a vehicle driving file test device is also provided. It should be noted that the vehicle driving file test device can be used to execute the vehicle driving file test method.

[0121] FIG. 5 is a schematic diagram of a vehicle driving file test device according to an embodiment of the present disclosure. As shown in FIG. 5, the vehicle driving file test device 500 can include an acquisition component 502, an obtaining component 504, a simulation component 506, a control component 508, and a test component 510.

[0122] The acquisition component 502 is configured to collect test scene information of a vehicle to be tested, wherein the test scene information is used to at least represent a driving environment of the vehicle.

[0123] The acquisition component 504 is configured to acquire a scene file corresponding to the test scene information.

[0124] The simulation component 506 is configured to simulate the scene file by using a simulation test system of the vehicle to obtain a virtual scene corresponding to the scene file, wherein the virtual scene is used to simulate the driving environment condition.

[0125] The control component 508 is configured to call a to-be-tested driving file of the vehicle, control the vehicle to drive in the virtual scene, and obtain a driving result.

[0126] The test component 510 is configured to test the driving result to obtain a test result, wherein the test result is used to indicate whether the to-be-tested driving file passes the test of the virtual scene.

[0127] Optionally, the acquisition component 502 can include an acquisition sub-component configured to acquire, on a graphical user interface of a terminal corresponding to the vehicle, test requirement information used to test the to-be-tested driving file, wherein the test requirement information includes the test scene information; and a selection sub-component configured to select, on the graphical user interface, a configuration parameter of the simulation test system, wherein the configuration parameter is used to start the simulation test system.

[0128] Optionally, the acquisition component 504 can include an acquisition sub-component configured to acquire, in response to acquiring the test scene information and the configuration parameter on the graphical user interface, the scene file by using the to-be-tested driving file.

[0129] Optionally, the apparatus can include a starting component configured to start the to-be-tested driving file in response to acquiring the test scene information and the configuration parameter; and a connection component configured to connect the test driving file and the simulation test system by using a communication protocol or an Ethernet mode. The acquisition sub-component can include a screening sub-component configured to control the to-be-tested driving file to screen out the scene file matched with the test scene information from a scene folder by using a script of the vehicle.

[0130] Optionally, the obtaining subcomponent can include a detecting subcomponent configured to detect the to-be-tested driving file to obtain a detection result, wherein the detection result is used to indicate whether the to-be-tested driving file includes source code; a reading subcomponent configured to read scene names and path information in the scene folder from the script in response to the detection result indicating that the to-be-tested driving file does not include source code; a first processing subcomponent configured to control the to-be-tested driving file to filter out a scene name corresponding to the test scene information from the scene names read from the script, and determine a scene file corresponding to the test scene information from the scene folder according to path information corresponding to the scene name; and a second processing subcomponent configured to read path information corresponding to the scene file from the source code in response to the detection result indicating that the to-be-tested driving file includes source code, and determine the scene file corresponding to the test scene information from the scene folder according to the path information.

[0131] Optionally, the test component 510 can include a calling component configured to call driving data in a real scene corresponding to the virtual scene in response to obtaining the driving result, wherein the driving data is used to indicate a driving result obtained by controlling the vehicle to drive in the real scene; a comparison component configured to compare the driving data and the driving result to obtain a comparison result, wherein the comparison result is used to indicate a similarity between the driving data and the driving result; and a determination component configured to determine a test result based on the comparison result.

[0132] Optionally, the determination component can include a first determination subcomponent configured to determine that the test result is that the to-be-tested driving file passes the test of the virtual scene in response to the comparison result indicating that the similarity is greater than or equal to a similarity threshold value; and a second determination subcomponent configured to determine that the test result is that the to-be-tested driving file fails the test of the virtual scene in response to the comparison result indicating that the similarity is less than the similarity threshold value.

[0133] Optionally, the apparatus can include a correction component configured to correct the to-be-tested driving file based on the test result to obtain a target to-be-tested driving file, wherein an accuracy of a driving result of the target to-be-tested driving file in the virtual scene is higher than an accuracy of a driving result of the to-be-tested driving file in the virtual scene.

[0134] In the embodiment of the present disclosure, the test scene information of the vehicle to be tested is collected by the collection component 502, wherein the test scene information is used to represent at least the driving environment condition of the vehicle; the scene file corresponding to the test scene information is obtained by the obtaining component 504; the scene file is simulated by the simulation component 506 using the simulation test system of the vehicle, to obtain the virtual scene corresponding to the scene file, wherein the virtual scene is used to simulate the driving environment condition; the vehicle to be tested driving file is called by the control component 508, to control the vehicle to drive in the virtual scene, to obtain the driving result; and the driving result is tested by the testing component 510, to obtain the test result, wherein the test result is used to represent whether the driving file to be tested passes the test of the virtual scene, thereby solving the technical problem of low driving file test efficiency of the vehicle, and achieving the technical effect of improving the driving file test efficiency of the vehicle.

[0135] According to the embodiment of the present disclosure, a computer readable storage medium is also provided, which includes a stored program, wherein the program executes the driving file test method of the vehicle.

[0136] According to the embodiment of the present disclosure, a processor is also provided, which is used to run a program, wherein the program executes the driving file test method of the vehicle when running.

[0137] The embodiment of the present disclosure also provides a computer program product. Optionally, in the embodiment, the computer program product can include a computer program, and the computer program implements the driving file test method of the vehicle of the above-mentioned embodiment of the present disclosure when executed by the processor.

[0138] According to the embodiment of the present disclosure, a vehicle is also provided, which is used to execute the driving file test method of the vehicle of the embodiment of the present disclosure.

[0139] In the above-mentioned embodiments of the present disclosure, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0140] In several embodiments provided by the present disclosure, it should be understood that the disclosed technology can be implemented in other ways. Of course, the embodiment described above is only a schematic and exemplary description of the device. For example, the division of the components can be a logical function division, and in actual implementation, another division mode can be used, for example, a plurality of components or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed components can be indirect coupling or communication connection through some interfaces, components or indirect coupling or communication connection in electrical or other forms.

[0141] The components described as separate components may or may not be physically separate, and the components shown as separate components may or may not be physical components, i.e., may be located in one place or distributed over multiple components. Some or all of the components can be selected as needed to achieve the purposes of the embodiments of the present application.

[0142] In addition, the functional components in various embodiments of the present disclosure can be integrated into one processing component, or each component can exist physically alone, or two or more components can be integrated into one component. The integrated component can be realized in the form of hardware or in the form of a software functional component.

[0143] The integrated component, if realized in the form of a software functional component and sold or used as an independent product, can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present disclosure, essentially or the part that contributes to the prior art, or all or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present disclosure. The aforementioned storage medium includes: a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various other media that can store program codes.

[0144] The above description is only the preferred embodiments of the present disclosure, and it should be pointed out that, for those skilled in the art, without departing from the principles of the present disclosure, a number of improvements and refinements can be made, and these improvements and refinements should be considered as the protection scope of the present disclosure. Industrial applicability

[0145] The embodiments of the present disclosure can be applied in a simulation test process of a driving file of a vehicle. If it is necessary to simulate and test the driving file of the vehicle, the test scene information of a tester can be collected, and a scene file corresponding to the test scene information can be determined. The scene file can be input into a simulation test system to simulate and analogize a driving environment corresponding to the scene file, and a corresponding virtual scene can be obtained. In the virtual scene, a to-be-tested driving file of the vehicle can be called to control the vehicle to drive in the virtual scene, and a driving result can be obtained. The driving result can be tested to determine a test result of whether the driving result of the current to-be-tested driving file in the virtual scene is accurate. The test result can be used to determine whether the to-be-tested driving file is accurate, and further determine whether the to-be-tested driving file can reach a standard of being put into automatic driving use. Thus, the technical problem of low test efficiency of the driving file of the vehicle is solved, and the technical effect of improving the test efficiency of the driving file of the vehicle is achieved.

Claims

1. A method for testing vehicle driving records, comprising: Collect test scenario information of the vehicle to be tested, wherein the test scenario information is used to at least represent the driving environment conditions of the vehicle; Obtain the scene file corresponding to the test scene information; The simulation test system of the vehicle is used to simulate the scene file to obtain a virtual scene corresponding to the scene file, wherein the virtual scene is used to simulate the driving environment conditions; The vehicle's test driving file is invoked, and the vehicle is controlled to drive in the virtual scene to obtain the driving results; The driving results are tested to obtain test results, wherein the test results are used to indicate whether the driving file under test passes the test in the virtual scenario.

2. The method according to claim 1, wherein, Collect test scenario information for the vehicle under test, including: On the graphical user interface of the terminal corresponding to the vehicle, test requirement information for testing the driving file to be tested is collected, wherein the test requirement information includes the test scenario information; The method further includes: selecting configuration parameters of the simulation test system on the graphical user interface, wherein the configuration parameters are used to start the simulation test system.

3. The method according to claim 2, wherein, Obtain the scene file corresponding to the test scene information, including: In response to obtaining the test scenario information and configuration parameters on the graphical user interface, the scenario file is obtained using the test driving file.

4. The method according to claim 3, wherein, Before obtaining the scene file using the driving file to be tested, the method further includes: In response to obtaining the test scenario information and the configuration parameters, the test driving file is started; The test driving file and the simulation test system are connected using a communication protocol or Ethernet. The scene file is obtained using the driving file to be tested, including: Using the vehicle's script, the test driving file is controlled to filter out the scene files that match the test scene information from the scene folder.

5. The method according to claim 4, wherein, The scenario folder includes the scenario file, the scenario name corresponding to the scenario file, and path information. The path information indicates the storage location of the scenario file. The system uses the vehicle's script to control the test driving file and filters out scenario files matching the test scenario information from the scenario folder, including: The test file is inspected to obtain a test result, wherein the test result is used to indicate whether the test file includes source code; In response to the detection result that the test vehicle file does not include the source code, the script is used to read the scene name and the path information in the scene folder; The system controls the test driving file, filters out the scene names corresponding to the test scene information from the scene names read by the script, and determines the scene file that matches the test scene information from the scene folder according to the path information corresponding to the scene name; The method further includes: in response to the detection result of the test driving file being the source code, reading the path information corresponding to the scene file from the source code, and determining the scene file that matches the test scene information from the scene folder according to the path information.

6. The method according to claim 1, wherein, The driving results were tested to obtain test results, including: In response to obtaining the driving result, driving data from the real scene corresponding to the virtual scene is invoked, wherein the driving data is used to represent the driving result obtained by controlling the vehicle to drive in the real scene; The driving data and the driving results are compared to obtain a comparison result, wherein the comparison result is used to indicate the degree of similarity between the driving data and the driving results; Based on the comparison results, the test results are determined.

7. The method according to claim 6, wherein, Based on the comparison results, the test results are determined, including: In response to the comparison result being that the similarity is greater than or equal to the similarity threshold, the test result is determined to be that the test vehicle file passes the test in the virtual scene; In response to the comparison result being that the similarity is less than the similarity threshold, the test result is determined to be that the test vehicle file failed the test in the virtual scene.

8. The method according to claim 7, wherein, After determining that the test result is that the test vehicle file fails the test in the virtual scene in response to the comparison result being that the similarity is less than the similarity threshold, the method further includes: Using the test results, the test driving file is corrected to obtain a target test driving file, wherein the accuracy of the driving results of the target test driving file in the virtual scene is higher than the accuracy of the driving results of the test driving file in the virtual scene.

9. A testing device for vehicle driving records, comprising: The data acquisition component is configured to acquire test scenario information of the vehicle under test, wherein the test scenario information is used to at least represent the driving environment conditions of the vehicle; The component is configured to retrieve the scene file corresponding to the test scene information. The simulation component is configured to use the vehicle's simulation testing system to simulate the scene file to obtain a virtual scene corresponding to the scene file, wherein the virtual scene is used to simulate the driving environment conditions; The control component is configured to call the vehicle's test driving file, control the vehicle to drive in the virtual scene, and obtain driving results; The testing component is configured to test the driving results and obtain test results, wherein the test results are used to indicate whether the driving file under test passes the test in the virtual scenario.

10. A processor for running a program, wherein, The program, when run by the processor, executes the test method for the vehicle's driving file according to any one of claims 1 to 8.

11. A computer-readable storage medium comprising a stored program, wherein, When the program is executed, it controls the device containing the computer-readable storage medium to perform a test method for the vehicle's driving file as described in any one of claims 1 to 8.

12. An electronic device comprising a memory and a processor, the memory storing a computer program, the processor being configured to run the computer program to perform a test method for a driving file of a vehicle according to any one of claims 1 to 8.

13. A computer program product comprising a computer program that, when executed by a processor, implements a method for testing the driving file of a vehicle according to any one of claims 1 to 8.

14. A vehicle for performing a test method for the driving documents of the vehicle according to any one of claims 1 to 8.

15. A computer program product comprising: A non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements a test method for the driving files of the vehicle as described in any one of claims 1 to 8.

16. A computer program, when executed by a processor, implements a method for testing the driving file of the vehicle according to any one of claims 1 to 8.

Images