Automatic driving test method, control device, vehicle and storage medium
By building simulation scenarios on actual roads and establishing digital twin vehicles, using simulation environment data to control vehicle responses with real environment data, the problems of high cost, time-consuming and insufficient authenticity in autonomous driving tests are solved, and more efficient and more Accurate test results.
Patent Information
- Application Number
- CN202411150145.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-21
- Publication Date
- 2024-11-12
AI Technical Summary
The existing autonomous driving testing methods are costly, time-consuming and inaccurate, making them difficult to meet the needs, and lack a method with lower cost, more convenient testing and more efficient testing.
By building simulation scenarios on actual roads, establishing digital twin vehicles, and using simulation environment data to control vehicle responses with real environment data, enhancing the authenticity and accuracy of the test, while reducing test costs and time.
It realizes the authenticity and accuracy of simulation tests in autonomous driving tests, reduces the cost and time of actual vehicle tests, and the vehicle information obtained is more complete, comprehensive and accurate.
Smart Images

Figure CN118928449A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to a testing method, and in particular to an automatic driving testing method. Background Art
[0002] With the development of autonomous driving, relatively mature assisted driving technologies such as adaptive cruise, advanced cruise, front collision warning, and emergency braking have emerged. Although the autonomous driving technologies that have been put into use are relatively mature, there are still certain risks, so it is necessary to test the functional performance of autonomous driving technologies. There are currently two main methods for testing the autonomous driving capabilities of vehicles. One is to use driving simulation technology to test the autonomous driving algorithm. This method requires artificially setting scene data to simulate the autonomous driving scene of the actual vehicle, and then verifying the functional performance of the autonomous driving algorithm in the cloud. This method is low-cost, time-saving, and highly reusable, but the constructed scene is different from the actual road scene, and the authenticity is lacking; the other is to deploy the autonomous driving software on the actual vehicle and test the vehicle's autonomous driving capabilities in actual scenes and roads such as venues, urban areas, and highways. However, this method has high cost, the entire test cycle takes a long time, and the test scene is greatly restricted by the actual road and environment. Therefore, the current method for autonomous driving testing is difficult to meet people's needs, and there is an urgent need for a lower-cost, more convenient, and more efficient autonomous driving testing method. Summary of the invention
[0003] The purpose of the present invention is to provide an autonomous driving testing method to solve one or more technical problems existing in the prior art, and at least provide a beneficial option or create conditions.
[0004] An automatic driving test method according to an embodiment of the first aspect of the present invention includes: Construct a simulation scenario based on the actual road test scenario, and load the test conditions into the simulation scenario; Obtain real environment data from real test vehicles; Establishing a digital twin vehicle corresponding to the location of the real test vehicle in the simulation scene, and obtaining simulation environment data of the location of the digital twin vehicle; The real test vehicle is controlled to react according to the simulation environment data and the real environment data, and real vehicle information of the real test vehicle is obtained.
[0005] This technical solution has at least the following beneficial effects: the vehicle that needs to be tested for autonomous driving is used as the real test vehicle, and a simulation scene is built according to the road scene that the real test vehicle needs to travel when conducting the autonomous driving test. The simulation scene contains the scene information required for autonomous driving, such as lane lines, speed limit signs, etc. According to the need to conduct autonomous driving tests on the vehicle under different conditions, the required test conditions can be loaded in the simulation scene, and the position of the real test vehicle in the actual road test scene at this time can be corresponding to the position in the simulation scene, so as to establish a digital twin vehicle identical to the real test vehicle. At this time, there is a real test of the real test vehicle and a test of the digital twin vehicle. Through simulation testing of the real test vehicle, the real environment data of the real test vehicle's location is obtained, and the simulation environment data of the digital twin vehicle is also obtained. When the real test vehicle is conducting autonomous driving tests, it is necessary to make driving responses based on the simulation environment data and the real environment data. In this way, when the real test vehicle is conducting real-car autonomous driving tests, the simulation test can be used to add test conditions that do not exist on the actual road to the real-car test for comprehensive consideration. This can not only enhance the authenticity and accuracy of the simulation test, but also reduce the cost of arranging test conditions during real-car testing, save testing time, and make the real vehicle information obtained more sufficient, comprehensive, and accurate.
[0006] According to some embodiments of the present invention, the autonomous driving test method further includes: The reaction of the digital twin vehicle is controlled according to the simulated environment data and the real environment data, and simulated vehicle information of the digital twin vehicle is obtained.
[0007] According to some embodiments of the present invention, the autonomous driving test method further includes: The simulation scene is synchronously corrected according to the real environment data.
[0008] According to some embodiments of the present invention, the autonomous driving test method further includes: The digital twin vehicle is controlled to be synchronized according to the real vehicle information.
[0009] According to some embodiments of the present invention, the real vehicle information includes vehicle posture, vehicle position and vehicle performance parameters, and controlling the digital twin vehicle to synchronize according to the real vehicle information includes: Control the digital twin vehicle to synchronize the vehicle posture, the vehicle position and at least one of the vehicle performance parameters.
[0010] According to some embodiments of the present invention, the test conditions include pedestrians crossing, the preceding vehicle braking suddenly, or a side lane vehicle driving into the current lane at a close distance, and the loading of the test conditions in the simulation scenario includes: At least one of the pedestrian crossing, the preceding vehicle braking suddenly, and the side-lane vehicle driving into the current lane at a close distance is loaded into the simulation scene.
[0011] According to some embodiments of the present invention, controlling the real test vehicle to react according to the simulation environment data and the real environment data includes: Setting the priority of the simulation environment data to be higher than the priority of the real environment data; Performing information fusion on the simulated environment data and the real environment data to obtain fused environment data; The real test vehicle is controlled to react according to the fused environment data.
[0012] According to a second aspect of an embodiment of the present invention, a vehicle control device includes a memory, a processor, and a program stored in the memory and executable on the processor, wherein the program implements the above-mentioned automatic driving test method when executed by the processor.
[0013] This technical solution has at least the following beneficial effects: the vehicle control device can be installed in the vehicle to realize automatic driving test of the vehicle. When using a real test vehicle to conduct actual vehicle automatic driving test, the simulation test can be used to add test conditions that do not exist on the actual road to the actual vehicle test for comprehensive consideration, which can not only enhance the authenticity and accuracy of the simulation test, but also reduce the cost of arranging test conditions during actual vehicle testing, save testing time, and make the real vehicle information obtained more sufficient, comprehensive and accurate.
[0014] A vehicle according to an embodiment of the third aspect of the present invention includes a memory, a processor, and a program stored in the memory and executable on the processor, wherein the program implements the above-mentioned automatic driving test method when executed by the processor.
[0015] This technical solution has at least the following beneficial effects: when a vehicle needs to undergo an autonomous driving test, the above-mentioned autonomous driving test method can be used, so that when a real test vehicle is used to conduct an actual vehicle autonomous driving test, the simulation test can be used to add test conditions that do not exist on actual roads to the actual vehicle test for comprehensive consideration, which can not only enhance the authenticity and accuracy of the simulation test, but also reduce the cost of arranging test conditions during actual vehicle testing, save testing time, and make the real vehicle information obtained more sufficient, comprehensive, and accurate.
[0016] According to a computer-readable storage medium of an embodiment of the fourth aspect of the present invention, the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the above-mentioned autonomous driving test method.
[0017] This technical solution has at least the following beneficial effects: the above-mentioned autonomous driving test method can be implemented as a computer program and tangibly included in a computer-readable storage medium. When the processor uses this computer-readable storage medium to perform autonomous driving testing, simulation testing can be used to add test conditions that do not exist on actual roads to actual vehicle testing for comprehensive consideration. This can not only enhance the authenticity and accuracy of the simulation test, but also reduce the cost of arranging test conditions during actual vehicle testing, save testing time, and make the real vehicle information obtained more sufficient, comprehensive, and accurate.
[0018] Additional aspects and advantages of the present invention will be described in part in the following description and will be apparent from the following description. This disclosure may be apparent or learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly describes the drawings required for use in the description of the embodiments. Obviously, the drawings described are only part of the embodiments of the present invention, not all of the embodiments, and those skilled in the art can also obtain other design solutions and drawings based on these drawings without creative work.
[0020] Figure 1 It is a flow chart of the automatic driving test method of the present invention.
[0021] Figure 2 This is a flow chart of step S410 of the autonomous driving test method of the present invention. DETAILED DESCRIPTION
[0022] Embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.
[0023] In the description of the present invention, it should be understood that descriptions involving orientations, such as up, down, front, back, left, right, etc., and orientations or positional relationships indicated are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.
[0024] In the description of the present invention, "several" means one or more, "more" means more than two, "greater than", "less than", "exceed" etc. are understood as not including the number itself, and "above", "below", "within" etc. are understood as including the number itself. If there is a description of "first" or "second", it is only used for the purpose of distinguishing the technical features, and cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.
[0025] In the description of the present invention, unless otherwise clearly defined, terms such as setting, installing, connecting, etc. should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in the present invention in combination with the specific content of the technical solution.
[0026] Reference Figure 1 According to an automatic driving test method of an embodiment of the first aspect of the present invention, the method includes but is not limited to the following steps: Step S100, construct a simulation scene according to the scene of the actual road test, and load the test conditions in the simulation scene. Autonomous driving relies on the surrounding environmental information to control the vehicle. Therefore, in order to make the simulation scene closer to the environmental information during the vehicle test, it is necessary to predetermine the actual road for testing the vehicle, and propose a simulation scene based on the scene of the actual road test. For example, use multiple cameras and radars to record the scene of the actual road, filter out redundant scenes according to the test requirements, and select the core scenes for verifying the vehicle's autonomous driving capabilities. However, according to the test requirements, some test conditions will not be met in the actual road. If they are directly arranged on the actual road, it will take a long time and cost a lot. Therefore, the test conditions are loaded in the simulation scene.
[0027] Step S200, obtaining the real environment data of the real test vehicle. Since the actual driving information and environmental factors will change in real time during the actual road test, it is necessary to keep obtaining the environmental information of the real test vehicle, including the speed of the test vehicle, the driver's driving intention, the road weather environment, and the positions of surrounding vehicles and pedestrians.
[0028] Step S310, establish a digital twin vehicle corresponding to the position of the real test vehicle in the simulation scene, and obtain the simulation environment data of the position of the digital twin vehicle. The real test vehicle is tested on the actual road, and correspondingly, the position of the real test vehicle on the actual road has a corresponding position in the simulation scene, and the digital twin vehicle is established at this position for simulation testing. Since different test conditions are loaded in the simulation scene, the environmental information in the simulation scene is different from the real environmental data, and it is necessary to keep the acquisition of the environmental information of the digital twin vehicle.
[0029] Step S410, controlling the real test vehicle to react according to the simulated environment data and the real environment data, and obtaining the real vehicle information of the real test vehicle. The scene of the real vehicle test is replicated in the simulation test, and the test conditions are further loaded in the simulation test. At this time, a more realistic test environment can be built in the simulation test. Therefore, the real test vehicle is controlled to react according to the simulated environment data and the real environment data. At this time, the real test vehicle can make a more realistic and accurate autonomous driving reaction, thereby obtaining the real vehicle information of the real test vehicle in the autonomous driving test reaction.
[0030] As can be seen from the above, the vehicle that needs to be tested for autonomous driving is used as the real test vehicle. A simulation scene is built according to the road scene that the real test vehicle needs to travel when performing the autonomous driving test. The simulation scene contains the scene information required for autonomous driving, such as lane lines, speed limit signs, etc. According to the needs of the vehicle for autonomous driving tests under different conditions, the required test conditions can be loaded in the simulation scene, and the position of the real test vehicle in the actual road test scene at this time can be corresponding to the position of the real test vehicle in the simulation scene. A digital twin vehicle identical to the real test vehicle is established. At this time, there is a real test of the real test vehicle and a simulation test of the digital twin vehicle. The real environment data of the location of the real test vehicle is obtained, and the simulation environment data of the digital twin vehicle is also obtained. When the real test vehicle is performing the autonomous driving test, it is necessary to make a driving response based on the simulation environment data and the real environment data. In this way, when the real test vehicle is performing the real vehicle autonomous driving test, the simulation test can be used to add the test conditions that do not exist in the actual road to the real vehicle test for comprehensive consideration, which can not only enhance the authenticity and accuracy of the simulation test, but also reduce the cost of arranging the test conditions during the real vehicle test, save the test time, and make the obtained real vehicle information more sufficient, comprehensive and accurate.
[0031] The automatic driving test method also includes step S420: controlling the reaction of the digital twin vehicle according to the simulated environment data and the real environment data, and obtaining the simulated vehicle information of the digital twin vehicle. In the simulation test, the digital twin vehicle is also controlled to react to the automatic driving according to the simulated environment data and the real environment data, and the simulation test result, that is, the simulated vehicle information of the digital twin vehicle during the simulation test, is obtained. In this way, the real vehicle information obtained from the real vehicle test can be compared with the simulated vehicle information obtained from the simulation test, which can maximize the problems that are easily overlooked in the real vehicle test and improve the accuracy and comprehensiveness of the automatic driving test.
[0032] The autonomous driving test method further includes step S500: controlling the digital twin vehicle to synchronize according to the real vehicle information. After the real vehicle test and the simulation test, the speed, steering wheel angle and other information of the real test vehicle and the digital twin vehicle will be different. At this time, such information is updated and synchronized with the digital twin vehicle so that the digital twin vehicle and the real test vehicle maintain the same working conditions, thereby further maintaining the accuracy during the autonomous driving test.
[0033] There are many kinds of real vehicle information, such as vehicle attitude information such as the pitch degree of the vehicle, or vehicle position information, or vehicle performance parameter information such as vehicle speed, steering wheel angle, braking status, etc. Therefore, in step S500, the digital twin vehicle is controlled to be synchronized according to the real vehicle information, including: controlling the digital twin vehicle to synchronize at least one of the vehicle attitude, vehicle position and vehicle performance parameters. Depending on the requirements for the autonomous driving test, one or more of the vehicle attitude, vehicle position and vehicle performance parameters in the digital twin vehicle can be synchronized to be the same as the real test vehicle, so as to further maintain the accuracy during the autonomous driving test.
[0034] The automatic driving test method further includes step S320: synchronously correcting the simulation scene according to the real environment data. Since the environment information of the real test vehicle will continue to change in real time when the real test vehicle is conducting the real vehicle test, it will be different from the initially constructed simulation scene at this time. In order to better reproduce the scene of the real vehicle test, the simulation scene information will be continuously updated and corrected, thereby ensuring that the subsequent automatic driving of the vehicle is more accurate according to the simulation environment data and the real environment data, and improving the accuracy of the results obtained in the subsequent simulation test of the digital twin vehicle.
[0035] When establishing the simulation scene in step S100, one of the situations that needs to be considered is: pedestrians crossing in front of the vehicle when the vehicle is driving normally. Pedestrians crossing on actual roads is a very dangerous test scenario, but successfully dealing with this scenario is a necessary ability for autonomous driving. In the simulation test, in order to test the ability of the current autonomous driving algorithm to deal with this scenario, it is necessary to set different vehicle speeds, different pedestrian crossing speeds, and also adjust the distance from the vehicle when the pedestrian starts to cross. If this actual condition is added directly during the actual vehicle test, it is also necessary to control the speed of the vehicle, the distance between the dummy and the vehicle, and the speed at which the dummy is dragged. However, if the actual vehicle test does not have a general understanding of the maximum speed and distance that the actual vehicle test platform can meet, it is easy to cause damage to the test equipment. In addition, it is also necessary to consider the sudden braking of the vehicle in front when the vehicle is driving or the side road vehicle driving into the current lane at a close distance when the vehicle is driving. For the scenario of sudden braking of the front vehicle, if the simulation test only relies on the scenario built by the tester without the support of real vehicle testing, it is easy for the simulation test to deviate from the actual road scenario or miss some details of the current scenario, which makes the simulation test lack credibility and authenticity. In order to improve the credibility of the simulation test, it is necessary to use a real vehicle to reproduce the same test scenario as the simulation test. For example, in the test scenario of sudden braking of the front vehicle, it is necessary to calibrate the conditions of the speed of the front vehicle before sudden braking, the acceleration of the front vehicle when sudden braking, the driving speed of the test vehicle, and the distance between the two vehicles when the front vehicle suddenly brakes, and collect more data from the real vehicle test in detail. After collecting these data, the corresponding parameter information can be changed in the simulation scenario in step S320, so that the data obtained from the simulation test is close to the actual road conditions.
[0036] The test conditions include pedestrians crossing, the front vehicle braking suddenly, or the side lane vehicle driving into the current lane at a close distance. The test conditions are loaded in the simulation scene, including: loading at least one of pedestrians crossing, the front vehicle braking suddenly, and the side lane vehicle driving into the current lane at a close distance in the simulation scene. By introducing the test conditions in the simulation scene, the maximum speed and maximum distance that the current autonomous driving algorithm can successfully cope with can be evaluated in advance for the test scene of pedestrians crossing in the simulation test, so that the real test vehicle can be tested in a relatively safe scene, and serious damage to the test equipment during the test process can be avoided as much as possible. The mutual coordination of real vehicle testing and simulation testing is used to further improve the accuracy of autonomous driving testing.
[0037] In step S410, the real test vehicle is controlled to react according to the simulated environment data and the real environment data, such as Figure 2 As shown, including but not limited to the following steps: Step S411, setting the priority of the simulation environment data higher than the priority of the real environment data. There will be conflicting signals between the simulation scene and the actual road test scene. In order to ensure the effectiveness of the test, for the same signal, such as vehicle speed, the priority of the simulation environment data is higher than the real environment data obtained by the real test vehicle. In addition, for some test conditions added to simulate the scene, such as pedestrians crossing, sudden braking of the front vehicle, and vehicles coming from behind, the simulation environment data is used first to ensure the subsequent required autonomous driving test.
[0038] Step S412: Information fusion is performed on the simulated environment data and the real environment data to obtain fused environment data. When performing data fusion, for the same signal, the simulated environment data is used and the real environment data is discarded. The fused environment data finally obtained is used as the basis for the control decision of the autonomous driving test mode.
[0039] Step S413, control the real test vehicle to react according to the fused environment data. In this way, the data from the simulation test is used to enhance the pertinence of the real vehicle's autonomous driving capability test, effectively reducing the impact of the randomness of the actual road test, so that the real vehicle test does not need to actually face a certain scene to reflect the autonomous driving capability in that scene.
[0040] According to a second aspect of an embodiment of the present invention, a vehicle control device includes a memory, a processor, and a program stored in the memory and executable on the processor. When the program is executed by the processor, the above-mentioned automatic driving test method is implemented.
[0041] In the vehicle control device of this second aspect embodiment, it can be installed in a vehicle to realize automatic driving testing of the vehicle. When using a real test vehicle to conduct actual vehicle automatic driving testing, simulation testing can be used to add test conditions that do not exist on actual roads to the actual vehicle test for comprehensive consideration. This can not only enhance the authenticity and accuracy of the simulation test, but also reduce the cost of arranging test conditions during actual vehicle testing, save testing time, and make the real vehicle information obtained more sufficient, comprehensive, and accurate.
[0042] Take the example that the processor and memory in the vehicle control device can be connected through a bus. The memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one disk memory, a flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the control processor, and these remote memories may be connected to the control device via a network.
[0043] The non-transient software programs and instructions required to implement the control method of the above embodiment are stored in the memory, and when executed by the processor, the autonomous driving test method in the above embodiment is executed.
[0044] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0045] A vehicle according to an embodiment of the third aspect of the present invention includes a memory, a processor, and a program stored in the memory and executable on the processor, and the above-mentioned automatic driving test method is implemented when the program is executed by the processor. The vehicle can be a private car, such as a sedan, SUV, MPV or pickup truck. The vehicle can also be an operating vehicle, such as a van, bus, minivan or large trailer. The vehicle needs to have an electric motor that can output power or store mechanical energy as a generator. When the vehicle is a new energy vehicle, it can be a hybrid vehicle or a pure electric vehicle.
[0046] Since the vehicle applies all the technical solutions of the above-mentioned vehicle control device, it at least has all the beneficial effects brought by the technical solutions of the above-mentioned embodiments, which will not be repeated here.
[0047] In this third aspect embodiment, when a vehicle needs to perform an autonomous driving test, the above-mentioned autonomous driving test method can be used, so that when a real test vehicle is used to perform an actual vehicle autonomous driving test, a simulation test can be used to add test conditions that do not exist on the actual road to the actual vehicle test for comprehensive consideration. This can not only enhance the authenticity and accuracy of the simulation test, but also reduce the cost of arranging the test conditions during the actual vehicle test, save testing time, and make the real vehicle information obtained more sufficient, comprehensive, and accurate.
[0048] According to a computer-readable storage medium of an embodiment of the fourth aspect of the present invention, the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the above-mentioned autonomous driving test method.
[0049] In this fourth aspect embodiment, the above-mentioned autonomous driving test method can be implemented as a computer program and tangibly included in a computer-readable storage medium. When the processor uses this computer-readable storage medium to perform autonomous driving testing, simulation testing can be used to add test conditions that do not exist on actual roads to actual vehicle testing for comprehensive consideration. This can not only enhance the authenticity and accuracy of the simulation test, but also reduce the cost of arranging test conditions during actual vehicle testing, save testing time, and make the real vehicle information obtained more sufficient, comprehensive, and accurate.
[0050] It is worth noting that since the computer-readable storage medium of an embodiment of the present invention can execute the autonomous driving test method of any of the above-mentioned embodiments, the specific implementation methods and technical effects of the computer-readable storage medium of an embodiment of the present invention can refer to the specific implementation methods and technical effects of the autonomous driving test method of any of the above-mentioned embodiments.
[0051] In addition, an embodiment of the present invention also provides a computer program product, including a computer program or computer instructions, which are stored in a computer-readable storage medium. The processor of a computer device reads the computer program or computer instructions from the computer-readable storage medium, and the processor executes the computer program or computer instructions, so that the computer device executes the above-mentioned autonomous driving test method.
[0052] It is worth noting that since the computer program product of an embodiment of the present invention can execute the autonomous driving test method of any of the above-mentioned embodiments, the specific implementation methods and technical effects of the computer program product of an embodiment of the present invention can refer to the specific implementation methods and technical effects of the autonomous driving test method of any of the above-mentioned embodiments.
[0053] It will be appreciated by those skilled in the art that all or some of the steps and systems in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or transient medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically include computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.
[0054] The preferred embodiments of the present invention are specifically described above, but the invention is not limited to the embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.
Claims
1. An automatic driving test method, characterized in that: include: Construct a simulation scenario based on the actual road test scenario, and load the test conditions into the simulation scenario; Obtain real environment data from real test vehicles; Establishing a digital twin vehicle corresponding to the location of the real test vehicle in the simulation scene, and obtaining simulation environment data of the location of the digital twin vehicle; The real test vehicle is controlled to react according to the simulation environment data and the real environment data, and real vehicle information of the real test vehicle is obtained.
2. The automatic driving test method according to claim 1, characterized in that: The autonomous driving test method further includes: The reaction of the digital twin vehicle is controlled according to the simulated environment data and the real environment data, and simulated vehicle information of the digital twin vehicle is obtained.
3. The automatic driving test method according to claim 1, characterized in that: The autonomous driving test method further includes: The simulation scene is synchronously corrected according to the real environment data.
4. The automatic driving test method according to claim 1, characterized in that: The autonomous driving test method further includes: The digital twin vehicle is controlled to be synchronized according to the real vehicle information.
5. The automatic driving test method according to claim 4, characterized in that: The real vehicle information includes vehicle posture, vehicle position and vehicle performance parameters, and controlling the digital twin vehicle to synchronize according to the real vehicle information includes: Control the digital twin vehicle to synchronize the vehicle posture, the vehicle position and at least one of the vehicle performance parameters.
6. The automatic driving test method according to claim 1, characterized in that: The test conditions include pedestrians crossing, the front vehicle braking suddenly, or a side lane vehicle driving into the current lane at a close distance. The test conditions loaded in the simulation scenario include: At least one of the pedestrian crossing, the preceding vehicle braking suddenly, and the side-lane vehicle driving into the current lane at a close distance is loaded into the simulation scene.
7. The automatic driving test method according to claim 1, characterized in that: The controlling the real test vehicle to react according to the simulation environment data and the real environment data comprises: Setting the priority of the simulation environment data to be higher than the priority of the real environment data; Performing information fusion on the simulated environment data and the real environment data to obtain fused environment data; The real test vehicle is controlled to react according to the fused environment data.
8. A vehicle control device, comprising a memory, a processor, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the automatic driving test method as described in any one of claims 1 to 7.
9. A vehicle, characterized in that: It includes a memory, a processor, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the autonomous driving test method according to any one of claims 1 to 7 is implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the autonomous driving test method according to any one of claims 1 to 7.
