Automatic driving simulation test method, device, electronic device and storage medium

Abstract

The present invention provides an automatic driving simulation test method and device. The automatic driving simulation test method includes obtaining key data of a standard scene, the key data including: map file and scene rendering file information used in the standard scene, and initial operation information of a main vehicle in the initial state of the standard scene; generating a pure map scene without a target vehicle based on the map file and scene rendering file information used in the standard scene; controlling the main vehicle to simulate operation in the pure map scene, and when the operation information of the main vehicle in the pure map scene is consistent with the initial operation information of the main vehicle in the initial state of the standard scene, switching the pure map scene to the standard scene; performing an automatic driving simulation test on the main vehicle in the standard scene without modifying the standardized scene file, thereby improving test efficiency.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving simulation testing technology, and in particular to an autonomous driving simulation testing method, device, electronic device and storage medium. Background Art

[0002] With the rapid development of autonomous driving technology, simulation testing is becoming increasingly important within the overall autonomous driving system testing landscape. To further enhance the testing value of simulation platforms, automated testing is essential. However, achieving fully automated testing is extremely difficult for hardware-in-the-loop (HIL) simulation testing. The current mainstream approach to HIL simulation testing uses standardized scenario files to simulate autonomous vehicles. However, these files do not consider whether the host vehicle's position and state meet the initial scenario conditions, making them inoperable on simulation platforms. To address this issue, related technologies have adapted standardized scenario files. For example, scripts can be used to modify the initial conditions of the scenario files, ensuring that the host vehicle reaches a certain state before triggering corresponding actions on the target vehicle. Alternatively, standardized scenarios can be implemented by extracting all the information in the standard scenario files and generating interactive commands to control the target vehicle's behavior. However, both script modifications and interactive command generation require secondary development of the original standard scenario files, which is not only costly but also reduces testing efficiency. Summary of the Invention

[0003] The present invention provides an autonomous driving simulation test method and device to solve the defects of traditional autonomous driving simulation test methods, such as the need for secondary development of standard scenario files, which is costly and affects test efficiency.

[0004] The present invention provides an automatic driving simulation test method, comprising:

[0005] Acquire key data of the standard scene, including: map file and scene rendering file information used in the standard scene, and initial operation information of the main vehicle in the initial state of the standard scene;

[0006] Generate a pure map scene without a target vehicle based on the map file and scene rendering file information used in the standard scene;

[0007] controlling the host vehicle to simulate running in the pure map scene, and switching the pure map scene to the standard scene when the running information of the host vehicle in the pure map scene is consistent with the initial running information of the host vehicle in the initial state of the standard scene;

[0008] An automatic driving simulation test is performed on the main vehicle in the standard scenario.

[0009] The present invention provides an autonomous driving simulation test method, wherein the control of the main vehicle to simulate operation in the pure map scene includes:

[0010] Get scene tag information in standard scenes;

[0011] Determining an initialization position of the main vehicle according to the scene marking information;

[0012] The initialization position of the main vehicle is used as the operation starting point in the pure map scene to control the simulation operation of the main vehicle.

[0013] The present invention provides an autonomous driving simulation test method, wherein when the scene marking information is special location scene information, determining the initialization position of the main vehicle according to the scene marking information includes:

[0014] Get the detailed location information of the main vehicle;

[0015] The initialization position of the host vehicle is calculated based on the detailed position information.

[0016] The present invention provides an autonomous driving simulation test method, wherein when the scene marking information is non-special location scene information, determining the initialization position of the main vehicle according to the scene marking information includes:

[0017] The starting position of the map is used as the initial position of the main vehicle.

[0018] The present invention provides an automatic driving simulation test method, wherein the control of the main vehicle simulation operation includes:

[0019] Reading the map file through a simulation simulator;

[0020] The main vehicle is controlled to run in simulation according to the map file, and during the running process, the running information is obtained according to the vehicle dynamics model, where the running information includes the current position, current speed and current state of the main vehicle.

[0021] The present invention provides an autonomous driving simulation test method, wherein the simulator is further used to:

[0022] Generate target vehicle information that is stored in a data structure and has empty values.

[0023] The present invention provides an autonomous driving simulation test method, wherein the simulator is further used to:

[0024] generating an automated test step sequence according to the scenario tag information;

[0025] Perform an automatic driving simulation test on the main vehicle according to the sequence of automated testing steps.

[0026] The present invention provides an autonomous driving simulation test method, which, before switching the pure map scene to the standard scene, further includes:

[0027] Determine whether the switching key data meets the preset conditions;

[0028] When the operating information of the main vehicle in the pure map scene is consistent with the initial operating information of the main vehicle in the initial state of the standard scene, and the switching key data meets the preset conditions, the pure map scene is switched to the standard scene.

[0029] The present invention provides an automatic driving simulation test method, wherein the switching key data includes lane line information and target vehicle information.

[0030] The present invention provides an automatic driving simulation test method, wherein the initial operating information of the main vehicle in the initial state of the standard scenario includes:

[0031] The initial speed, initial position information and status information of the main vehicle.

[0032] The present invention also provides an automatic driving simulation test device, comprising:

[0033] An acquisition module is used to acquire key data of a standard scene, wherein the key data includes: map files and scene rendering file information used in the standard scene, and initial operation information of the main vehicle in the initial state of the standard scene;

[0034] A generation module, configured to generate a pure map scene without a target vehicle based on the map file and scene rendering file information used in the standard scene;

[0035] a switching module, configured to control the host vehicle to simulate operation in the pure map scene, and switch the pure map scene to the standard scene when the operation information of the host vehicle in the pure map scene is consistent with the initial operation information of the host vehicle in the initial state of the standard scene;

[0036] The test module is used to perform an automatic driving simulation test on the main vehicle in the standard scenario.

[0037] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and runnable on the processor, wherein when the processor executes the program, an autonomous driving simulation test method as described above is implemented.

[0038] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements the autonomous driving simulation test method as described in any one of the above.

[0039] The present invention provides an autonomous driving simulation test method, device, electronic device and storage medium. The method obtains key data of a standard scene, the key data including: map file and scene rendering file information used in the standard scene, and initial operation information of a main vehicle in the initial state of the standard scene; generates a pure map scene without a target vehicle based on the map file and scene rendering file information used in the standard scene; controls the main vehicle to simulate operation in the pure map scene, and when the operation information of the main vehicle in the pure map scene is consistent with the initial operation information of the main vehicle in the initial state of the standard scene, switches the pure map scene to the standard scene; performs an autonomous driving simulation test on the main vehicle in the standard scene without modifying the standardized scene file, thereby improving test efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0041] Figure 1 This is one of the flow charts of the autonomous driving simulation test method provided by the present invention;

[0042] Figure 2 This is the second flow chart of the autonomous driving simulation test method provided by the present invention;

[0043] Figure 3 This is the third flow chart of the autonomous driving simulation test method provided by the present invention;

[0044] Figure 4 This is a schematic diagram of the automated test sequence generation process provided by the present invention;

[0045] Figure 5 This is a schematic diagram of a typical scenario provided by the present invention;

[0046] Figure 6 This is a flow chart of the automatic driving simulation test device provided by the present invention;

[0047] Figure 7 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0048] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0049] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0050] See also Figure 1 , Figure 1 This is a flow chart of the automatic driving simulation test method provided by the present invention. Figure 1 As shown, the autonomous driving simulation test method includes:

[0051] Step 101: Acquire key data of the standard scene, including but not limited to: map file and scene rendering file information used in the standard scene, and initial operation information of the main vehicle in the initial state of the standard scene;

[0052] Virtual roads and traffic environments are fundamental to testing autonomous driving algorithms, and these virtual roads and traffic environments are implemented using simulators. Simulators require map files and scene rendering files. Map files contain the scene's road geometry, such as lane type, lane width, and lane attributes. Scene rendering files simulate real-world elements, such as medians, streetlights, green belts, trees, and buildings.

[0053] Therefore, to generate a correct pure map scene file without the target vehicle, it is necessary to obtain the same map and scene rendering files as the simulated formal scene (the scene in the standard scene file).

[0054] In the embodiment of the present invention, the initial operation information of the main vehicle in the initial state of the standard scene includes, but is not limited to: the initial speed, initial position information and state information of the main vehicle.

[0055] Step 102: Generate a pure map scene without the target vehicle based on the map file and scene rendering file information used in the standard scene;

[0056] The map file of the pure map scenario is consistent with the map file used in the formal simulation scenario. The pure map scenario can take into account various factors such as the dynamic model, the initialization status of the autonomous driving algorithm, and the current status of the simulation platform. The pure map scenario is the scenario in which the vehicle operates before reaching the initial speed, position, and status required by the formal simulation scenario.

[0057] For scenarios without specific map or location requirements, the same pure map scenario can be used as long as the map and scene rendering files are the same. For example, for autonomous logistics trucks operating on highways, there is no need to specify specific roads or locations. Many scenarios in which autonomous logistics trucks operate, such as approaching a stationary target vehicle ahead, slowing down a target vehicle, slowing down a preceding vehicle during a lane change, and multi-vehicle interaction, do not require specific roads or locations. Therefore, this can reduce the cost of generating pure map scenarios to a certain extent, thereby improving testing efficiency.

[0058] Step 103: Control the host vehicle to simulate running in the pure map scene. When the running information of the host vehicle in the pure map scene is consistent with the initial running information of the host vehicle in the initial state of the standard scene, switch the pure map scene to the standard scene.

[0059] Step 104: Perform an autonomous driving simulation test on the host vehicle in a standard scenario.

[0060] The embodiment of the present invention can control the state of the main vehicle to meet the required initial conditions when loading the standardized scenario file, thereby achieving the purpose of directly using the standardized scenario file for autonomous driving simulation automation testing without any modification.

[0061] The autonomous driving simulation test method requires that the simulator used by the simulation platform support standardized scenario files, such as OpenSCENARIO files or simulator-customized scenario files with a certain degree of universality. Standardized scenario files refer to scenario files that comply with the OpenSCENARIO standard developed by the ASAM organization, and do not consider whether the position and status of the main vehicle meet the initial conditions of the scenario. In other words, the initial state of the scenario may require the main vehicle to have a speed of 80kph and be in an autonomous driving state. However, because the hardware-in-the-loop simulation platform needs to consider various factors such as the dynamic model, the initialization of the autonomous driving algorithm, and the current state of the simulation platform, it is difficult to reach the initial state of the standard scenario file at the beginning of the simulation. Therefore, the standard scenario file cannot be used directly for testing. Traditional autonomous driving simulation test methods require the standardized scenario file to be adaptively processed before the simulation test, and the original standard scenario file must be secondary developed. This is not only costly but also affects the test efficiency.

[0062] The autonomous driving simulation test method provided by an embodiment of the present invention obtains key data of a standard scenario, the key data including: map file and scene rendering file information used in the standard scenario, and initial operation information of the main vehicle in the initial state of the standard scenario; generates a pure map scene without a target vehicle based on the map file and scene rendering file information used in the standard scenario; controls the main vehicle to simulate operation in the pure map scene, and when the operation information of the main vehicle in the pure map scene is consistent with the initial operation information of the main vehicle in the initial state of the standard scene, switches the pure map scene to the standard scene; performs an autonomous driving simulation test on the main vehicle in the standard scene without modifying the standardized scenario file, thereby improving test efficiency.

[0063] The embodiment of the present invention pre-generates a pure map scene file without a target vehicle that is consistent with the map and scene rendering files used in the standard scene (simulation formal scene), then controls the main vehicle to run in the scene so that it meets the initial conditions required by the simulation formal scene, and finally switches to the simulation formal scene to complete the test. This solves the problem that the standardized scene files generated by current mainstream autonomous driving scene development and management tools cannot be directly applied to the simulation platform, and can realize the direct use of standardized scenes.

[0064] Based on any of the above embodiments, Figure 2 As shown, the main vehicle is controlled to run in a pure map scenario, including:

[0065] Step 201: Acquire scene marking information in a standard scene;

[0066] Step 202: Determine the initialization position of the host vehicle based on the scene marking information;

[0067] In some embodiments of the present invention, when the scene marking information is special location scene information, determining the initialization position of the host vehicle according to the scene marking information includes:

[0068] Get the detailed location information of the main vehicle;

[0069] The initial position of the main vehicle is calculated based on the detailed position information.

[0070] For some scenarios that have requirements for roads or positions, such as the target vehicle merging into a ramp, the target vehicle stopping at a curve, tunnel scenarios, etc., by generating the corresponding pure map scene and calculating the initial position of the main vehicle, the high applicability of the scenario usage method can be guaranteed.

[0071] In some embodiments of the present invention, when the scene marking information is non-special location scene information, determining the initialization position of the host vehicle according to the scene marking information includes:

[0072] The starting position of the map is used as the initial position of the main vehicle.

[0073] In this embodiment of the present invention, the initial speed, position, and status of the host vehicle are controlled to meet the corresponding initial conditions before switching to the actual scene. Position information includes two types. For most scenarios without special map or position requirements, only the lane information of the host vehicle, such as the rightmost lane or the second lane from the right, is required. For scenarios with special map or position requirements, detailed position information of the host vehicle, including coordinates and azimuth, is required.

[0074] Step 203: Using the initial position of the host vehicle as the running starting point in the pure map scene, control the simulation running of the host vehicle.

[0075] In an embodiment of the present invention, controlling the host vehicle to simulate running in a pure map scene includes:

[0076] Step 2031: Reading a map file through a simulation simulator;

[0077] Step 2032: Control the host vehicle to run simulation according to the map file, and obtain operation information according to the vehicle dynamics model during the operation. The operation information includes but is not limited to the current position, current speed and current state of the host vehicle.

[0078] In some embodiments of the present invention, the simulation simulator is further used to:

[0079] Generating target vehicle information stored in a data structure with empty values ​​can ensure the connection of target vehicle data during the switch from a pure map scene to a formal simulation scene, thereby ensuring the validity of the target vehicle information.

[0080] Based on any of the above embodiments, Figure 3 As shown, before switching the pure map scene to the standard scene, it also includes:

[0081] Step 301: Determine whether the switching key data meets the preset conditions;

[0082] In the embodiment of the present invention, the key data to be switched includes lane line information and target vehicle information.

[0083] Step 302: When the operating information of the host vehicle in the pure map scene is consistent with the initial operating information of the host vehicle in the initial state of the standard scene, and the switching key data meets the preset conditions, the pure map scene is switched to the standard scene.

[0084] In an embodiment of the present invention, before loading the simulation formal scene, the simulator needs to first load the pure map scene, and then control the main vehicle to run to the initial speed, position and state required by the simulation formal scene in the pure map scene, and finally switch to the simulation formal scene for testing. If the speed, state, etc. of the main vehicle change during the scene switching process, the entire test process will fail. Therefore, it is necessary to determine whether the key switching data during the scene switching process meets the preset conditions to ensure the validity and accuracy of the key switching data. The key switching data that need to be considered mainly include lane line information and target vehicle information. Among them, lane line information is mainly used for virtual drivers (simulating drivers manually driving vehicles) or automatic driving algorithms to control the vehicle to drive in the center. At the same time, lane line information is generally a prerequisite for automatic driving operation. Therefore, it is necessary to ensure the validity and accuracy of lane line information. Since there is no target vehicle in the pure map scene, it is only necessary to retain the data structure composed of target vehicle information emitted by various sensor models to ensure the validity of the target vehicle information.

[0085] Based on any of the above embodiments, the simulation simulator is further used to:

[0086] Generate automated test step sequences based on scenario tagging information;

[0087] Perform autonomous driving simulation tests on the main vehicle according to the sequence of automated test steps.

[0088] like Figure 4 As shown in the figure, the automated test sequence preparation phase can obtain the map file and scene rendering file information used in the standard scene, as well as the initial operation information of the main vehicle in the initial state of the standard scene. The automated test sequence generation phase can generate the specific steps of the simulation automated test, thereby ensuring that the simulated formal scene can be directly used in the automated test process, greatly improving the value of simulation testing in the entire autonomous driving test system.

[0089] Typical scenarios for autonomous driving include Figure 5 As shown in the figure, for the scenario on the left side without specific position requirements, during the preparation phase of the automated test sequence, the host vehicle is in autonomous driving mode, traveling at 80 kph in the rightmost lane. The target vehicle is located in the second lane to the right, initially 150 meters from the host vehicle and traveling at 60 kph. When the distance between the target vehicle and the host vehicle is shortened to 80 meters, it changes lanes right to the host vehicle's lane. The lane change takes 2 seconds, while decelerating to 30 kph at a deceleration rate of -1 m / s², and then traveling at a constant speed. For this scenario, the initial position of the vehicle in the map-only scene can be set as the starting point of the map; the map file and scenario file can be used as input files for the virtual simulator; the acquired initial conditions of the host vehicle (autonomous driving mode, 80 kph speed, and location in the rightmost lane) are stored for subsequent vehicle control and judgment.

[0090] The automated test sequence generated in the automated test sequence generation phase is:

[0091] (1) Initialize the vehicle position and azimuth to the starting position of the map, and set the speed to 0.

[0092] (2) The simulator loads the pure map scene file. It should be noted that the position of the main vehicle in the scene is determined by the dynamic model, and the initialization of the vehicle position is based on the vehicle dynamics model.

[0093] (3) Start the autonomous driving algorithm. Use specific methods to get the autonomous driving algorithm running.

[0094] (4) The host computer controls the movement of the main vehicle. It controls the input of the vehicle dynamics model and other vehicle inputs (such as the automatic driving start button), thereby controlling the vehicle movement and whether the vehicle enters the automatic driving state.

[0095] (5) Based on the feedback information, determine whether the vehicle is in the rightmost lane, whether it has entered the automatic driving state, and whether the initial condition of 80 kph is met. If not, wait until the conditions are met or the current test sequence times out.

[0096] (6) After the initial conditions are met, the control simulator switches to the formal scene, and at the same time, the virtual simulator is started to send valid and accurate lane line information and target vehicle information.

[0097] (7) Determine whether the formal scene is loaded successfully based on the status feedback from the simulator. If not, continue waiting until the loading is successful or the current test sequence times out.

[0098] (8) Close the virtual simulator immediately after the official scene is loaded successfully.

[0099] (9) Run the simulation formal scenario and conduct autonomous driving algorithm testing.

[0100] This automated test sequence can be directly embedded before the automated driving algorithm simulation test sequence, enabling the direct use of standard scenario files in automated testing. Testing has shown this method to be effective and applicable to most scenarios, significantly improving the efficiency of automated testing.

[0101] For the scenario with specific positioning requirements on the right side of the figure, the target vehicle is parked at the center of a left curve with a curvature radius of 700m and is located in the leftmost lane. The host vehicle is in autonomous driving mode and is driving towards the target vehicle at a speed of 80kph from 200m behind the target vehicle in the same lane.

[0102] For this scenario, we first know from the scene marker information that this is a special location scenario, so we need to obtain the detailed initial position information of the main vehicle. Then, based on the main vehicle's initial speed (80 kph) and state (autonomous driving state) required by the scenario, we calculate the time it takes for the main vehicle to accelerate from a standstill to 80 kph and reserve a certain amount of time for the autonomous driving algorithm to initialize (a total of about 30 seconds, a distance of about 500 meters). Finally, we parse the map file used by the scenario and offset 500 meters along the road from the initial position specified by the scenario as the vehicle's initial position in the pure map scenario.

[0103] The automated test sequence generated in the automated test sequence generation phase is:

[0104] (1) Initialize the vehicle position and azimuth, and set the speed to 0.

[0105] (2) The simulator loads the pure map scene file.

[0106] (3) Start the autonomous driving algorithm.

[0107] (4) The host computer controls the movement of the main vehicle.

[0108] (5) Based on the feedback information, determine whether the vehicle is in the leftmost lane, whether it has entered the automatic driving state, whether the vehicle speed meets the requirement of 80 kph, and whether the vehicle position is less than a certain value from the initial position specified in the formal scenario. If not, wait until the conditions are met or the test sequence times out.

[0109] (6) After the conditions are met, the simulator is controlled to switch to the formal scene, and the virtual simulator is started to send valid and accurate lane line information and target vehicle information.

[0110] (7) Determine whether the formal scene is loaded successfully based on the status feedback from the simulator. If not, continue waiting until the loading is successful or the current test sequence times out.

[0111] (8) Close the virtual simulator immediately after the official scene is loaded successfully.

[0112] (9) Run the simulation formal scenario and conduct autonomous driving algorithm testing.

[0113] The autonomous driving simulation testing method provided by an embodiment of the present invention directly applies the standard simulation scenario files generated by mainstream autonomous driving simulation scenario development and management tools to the automated testing process of the autonomous driving simulation platform, thereby greatly improving the efficiency of iterative testing of autonomous driving algorithms.

[0114] Figure 6 This is a functional structure diagram of the automatic driving simulation test device provided by the present invention. Figure 6As shown, the autonomous driving simulation test device includes:

[0115] An acquisition module 601 is configured to acquire key data of a standard scene, including map files and scene rendering file information used in the standard scene, and initial operation information of the host vehicle in the initial state of the standard scene;

[0116] A generating module 602 is configured to generate a pure map scene without a target vehicle based on the map file and scene rendering file information used in the standard scene;

[0117] A switching module 603 is used to control the host vehicle to simulate running in a pure map scene, and when the running information of the host vehicle in the pure map scene is consistent with the initial running information of the host vehicle in the initial state of the standard scene, the pure map scene is switched to the standard scene;

[0118] The test module 604 is used to perform an autonomous driving simulation test on the host vehicle in a standard scenario.

[0119] The autonomous driving simulation test device provided by an embodiment of the present invention obtains key data of a standard scenario, the key data including: map file and scene rendering file information used in the standard scenario, and initial operation information of the main vehicle in the initial state of the standard scenario; generates a pure map scene without a target vehicle based on the map file and scene rendering file information used in the standard scenario; controls the main vehicle to simulate operation in the pure map scene, and when the operation information of the main vehicle in the pure map scene is consistent with the initial operation information of the main vehicle in the initial state of the standard scene, switches the pure map scene to the standard scene; performs an autonomous driving simulation test on the main vehicle in the standard scene without modifying the standardized scenario file, thereby improving test efficiency.

[0120] Figure 7 An example of a physical structure diagram of an electronic device is shown below. Figure 7As shown, the electronic device may include: a processor 710, a communications interface 720, a memory 730, and a communications bus 740, wherein the processor 710, the communications interface 720, and the memory 730 communicate with each other via the communications bus 740. The processor 710 may call logic instructions in the memory 730 to execute an autonomous driving simulation test method, which includes: obtaining key data of a standard scenario, the key data including: map files and scene rendering file information used in the standard scenario, and initial operating information of the host vehicle in the initial state of the standard scenario; generating a pure map scenario without a target vehicle based on the map files and scene rendering file information used in the standard scenario; controlling the host vehicle to simulate operation in the pure map scenario, and when the operating information of the host vehicle in the pure map scenario is consistent with the initial operating information of the host vehicle in the initial state of the standard scenario, switching the pure map scenario to the standard scenario; and performing an autonomous driving simulation test on the host vehicle in the standard scenario.

[0121] In addition, the logic instructions in the above-mentioned memory 730 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0122] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the autonomous driving simulation test method provided by the above-mentioned methods, the method comprising: obtaining key data of the standard scene, the key data comprising: map file and scene rendering file information used in the standard scene, and initial operation information of the main vehicle in the initial state of the standard scene; generating a pure map scene without a target vehicle based on the map file and scene rendering file information used in the standard scene; controlling the main vehicle to simulate operation in the pure map scene, and when the operation information of the main vehicle in the pure map scene is consistent with the initial operation information of the main vehicle in the initial state of the standard scene, switching the pure map scene to the standard scene; and performing an autonomous driving simulation test on the main vehicle in the standard scene.

[0123] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0124] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0125] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An autonomous driving simulation test method, characterized in that: include: Acquire key data of the standard scene, including: map file and scene rendering file information used in the standard scene, and initial operation information of the main vehicle in the initial state of the standard scene; Generate a pure map scene without a target vehicle based on the map file and scene rendering file information used in the standard scene; controlling the host vehicle to simulate running in the pure map scene, and switching the pure map scene to the standard scene when the running information of the host vehicle in the pure map scene is consistent with the initial running information of the host vehicle in the initial state of the standard scene; Before switching the pure map scene to the standard scene, the method further includes: Determining whether the key switching data meets the preset conditions, wherein the key switching data includes lane line information and target vehicle information; When the operating information of the host vehicle in the pure map scene is consistent with the initial operating information of the host vehicle in the initial state of the standard scene, and the switching key data meets the preset conditions, the pure map scene is switched to the standard scene; and whether the switching key data during the scene switching process meets the preset conditions is determined to ensure the validity and accuracy of the switching key data; An automatic driving simulation test is performed on the main vehicle in the standard scenario.

2. The autonomous driving simulation test method according to claim 1, characterized in that: The controlling the main vehicle to run in the pure map scene in a simulation manner includes: Get scene tag information in standard scenes; Determining an initialization position of the main vehicle according to the scene marking information; The initialization position of the main vehicle is used as the operation starting point in the pure map scene to control the simulation operation of the main vehicle.

3. The autonomous driving simulation test method according to claim 2, characterized in that: When the scene marking information is special location scene information, determining the initialization position of the host vehicle according to the scene marking information includes: Get the detailed location information of the main vehicle; The initialization position of the host vehicle is calculated based on the detailed position information.

4. The autonomous driving simulation test method according to claim 2, characterized in that: When the scene marking information is non-special location scene information, determining the initialization position of the host vehicle according to the scene marking information includes: The starting position of the map is used as the initial position of the main vehicle.

5. The autonomous driving simulation test method according to claim 2, characterized in that: The controlling the main vehicle to run simulation includes: Reading the map file through a simulation simulator; The main vehicle is controlled to run in simulation according to the map file, and during the running process, the running information is obtained according to the vehicle dynamics model, where the running information includes the current position, current speed and current state of the main vehicle.

6. The autonomous driving simulation test method according to claim 5, characterized in that: The simulation simulator is also used to: Generate target vehicle information that is stored in a data structure and has empty values.

7. The autonomous driving simulation test method according to claim 5, characterized in that: The simulation simulator is also used to: generating an automated test step sequence according to the scenario tag information; Perform an automatic driving simulation test on the main vehicle according to the sequence of automated testing steps.

8. The autonomous driving simulation test method according to claim 1, characterized in that: The initial operating information of the main vehicle in the initial state of the standard scenario includes: The initial speed, initial position information and status information of the main vehicle.

9. An automatic driving simulation test device, characterized in that: include: An acquisition module is used to acquire key data of a standard scene, wherein the key data includes: map files and scene rendering file information used in the standard scene, and initial operation information of the main vehicle in the initial state of the standard scene; A generation module, configured to generate a pure map scene without a target vehicle based on the map file and scene rendering file information used in the standard scene; a switching module for controlling the host vehicle to simulate operation in the pure map scene, and switching the pure map scene to the standard scene when the operation information of the host vehicle in the pure map scene is consistent with the initial operation information of the host vehicle in the initial state of the standard scene; before switching the pure map scene to the standard scene, the module further includes: judging whether key switching data meets preset conditions, the key switching data including lane line information and target vehicle information; when the operation information of the host vehicle in the pure map scene is consistent with the initial operation information of the host vehicle in the initial state of the standard scene, and the key switching data meets the preset conditions, switching the pure map scene to the standard scene; judging whether the key switching data during the scene switching process meets the preset conditions to ensure the validity and accuracy of the key switching data; The test module is used to perform an automatic driving simulation test on the main vehicle in the standard scenario.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the autonomous driving simulation test method according to any one of claims 1 to 8 is implemented.

11. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the autonomous driving simulation test method according to any one of claims 1 to 8 is implemented.

Images