Intelligent driving system real vehicle test method, system, device and medium

Abstract

The invention discloses an intelligent driving system real vehicle testing method, system and device and a medium, and belongs to the technical field of intelligent driving vehicle testing. The method comprises the steps that a test upper computer transmits virtual scene information to a real vehicle controller to be tested, and the virtual scene information comprises related information of various sensing elements; the to-be-tested real vehicle controller synthesizes the virtual scene information, the vehicle motion information and the vehicle body associated state information, generates a transverse and longitudinal control instruction, and transmits the transverse and longitudinal control instruction to the vehicle body module; the vehicle body module executes the transverse and longitudinal control instruction to control the vehicle to run, and uploads the transverse and longitudinal speeds and acceleration of the vehicle to the test upper computer through the real vehicle controller to be tested in the running process of the vehicle, so as to complete the closed-loop simulation test of the real vehicle of the intelligent driving system in a virtual scene; according to the method, a mode of combining a simulation environment and a real vehicle is adopted, and the virtual scene information comprises related information of various sensing elements, so that closed-loop simulation of a high-order intelligent driving function can be realized.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent driving vehicle testing, and in particular to an intelligent driving system real vehicle testing method, system, equipment and computer-readable storage medium. Background Art

[0002] With the rapid development of intelligent driving technology, the requirements for the test efficiency of intelligent driving functions are getting higher and higher. How to improve the test efficiency of intelligent driving functions is becoming more and more important.

[0003] In the related technologies, there are three main ways to test the intelligent driving function. The first is to build a real test scene and use a real car to test the intelligent driving function; the second is to use a vehicle dynamics model to simulate the intelligent driving function in a simulation environment; the third is to combine the simulation environment with the real car and load virtual obstacles at preset positions to simulate the intelligent driving function.

[0004] However, in the first method, a real vehicle is used for testing in a real test scenario, which is extremely dangerous and has high requirements for the consistency of the test scenario, making it difficult to reproduce the scenario; in the second method, since the vehicle dynamics model is significantly different from the real vehicle, the simulation results of the intelligent driving function performance are inaccurate; in the third method, only virtual obstacles are simulated, and only low-level intelligent driving functions such as braking functions can be tested and evaluated. Summary of the invention

[0005] The present application provides a real-vehicle testing method, system, device and computer-readable storage medium for an intelligent driving system, which can solve technical problems existing in the prior art, such as the extremely high risk of testing in real test scenarios and the difficulty in reproducing scenarios; the inaccurate simulation results of testing using vehicle dynamics models; and the combination of a simulation environment and a real vehicle, which can only allow for testing and evaluation of low-level intelligent driving functions.

[0006] In a first aspect, an embodiment of the present application provides an intelligent driving system real vehicle testing method, which is applied to an intelligent driving system real vehicle testing system, wherein the intelligent driving system real vehicle testing system includes a test host computer, a real vehicle controller to be tested, and a body module, and the intelligent driving system real vehicle testing method includes:

[0007] The test host computer transmits virtual scene information to the real vehicle controller to be tested, wherein the virtual scene information includes relevant information of multiple perception elements;

[0008] The controller of the actual vehicle to be tested integrates the virtual scene information, vehicle motion information and body-related status information to generate lateral and longitudinal control instructions, and transmits the lateral and longitudinal control instructions to the body module;

[0009] The body module executes lateral and longitudinal control instructions to control the vehicle's driving, and uploads the vehicle's lateral and longitudinal speeds and accelerations to the test host computer through the actual vehicle controller to be tested during the vehicle's driving process, so as to complete the closed-loop simulation test of the intelligent driving system real vehicle in a virtual scene.

[0010] In combination with the first aspect, in one implementation, the process of generating the virtual scene information includes:

[0011] Static scene elements and dynamic scene elements are edited on the high-precision map file loaded into the scene simulation tool of the test host computer to generate virtual scene information.

[0012] In combination with the first aspect, in one implementation, the virtual scene information includes a high-precision map, lane line information, obstacle information, speed limit sign information, and initial positioning information of the actual vehicle to be tested.

[0013] In combination with the first aspect, in one implementation, the real vehicle controller to be tested integrates virtual scene information, vehicle motion information and vehicle body related state information to generate lateral and longitudinal control instructions, including:

[0014] Add deflection simulation to the initial positioning information in the virtual scene information to obtain absolute position information;

[0015] Determine fused positioning information based on the absolute position information and the vehicle motion information;

[0016] Based on the fused positioning information, determine the road condition information in front of the vehicle in the virtual scene;

[0017] Comprehensively analyze road condition information, vehicle body status information, lane line information in virtual scene information, obstacle information and speed limit sign information to generate lateral and longitudinal control instructions.

[0018] In combination with the first aspect, in one implementation, after completing a closed-loop simulation test of a real vehicle of the intelligent driving system in a virtual scene, the method further includes:

[0019] In the current virtual scene, determine static scene elements within a preset distance range in front of the vehicle;

[0020] Determine whether there is a problem scene containing the static scene element in the problem scene library;

[0021] If the problem scene includes the static scene elements, the problem scene including the static scene elements is used as the target scene, and the dynamic traffic participant elements in the target scene are written into the current virtual scene.

[0022] In combination with the first aspect, in one implementation, after completing a closed-loop simulation test of a real vehicle of the intelligent driving system in a virtual scene, the method further includes:

[0023] The performance of the controller of the real vehicle to be tested is analyzed and evaluated based on the motion data of the real vehicle to be tested in the virtual scene.

[0024] In a second aspect, an embodiment of the present application provides a real vehicle testing system for an intelligent driving system, the real vehicle testing system for an intelligent driving system comprising:

[0025] A test host computer is used to transmit virtual scene information to the real vehicle controller to be tested, wherein the virtual scene information includes relevant information of multiple perception elements;

[0026] The real vehicle controller to be tested is used to integrate virtual scene information, vehicle motion information and body-related state information to generate lateral and longitudinal control instructions, and transmit the lateral and longitudinal control instructions to the body module;

[0027] The body module is used to execute lateral and longitudinal control instructions to control the vehicle's driving, and upload the vehicle's lateral and longitudinal speeds and accelerations to the test host computer through the actual vehicle controller to be tested during the vehicle's driving process, so as to complete the closed-loop simulation test of the intelligent driving system real vehicle in a virtual scene.

[0028] In conjunction with the second aspect, in one implementation, the process of generating the virtual scene information includes:

[0029] Static scene elements and dynamic scene elements are edited on the high-precision map file loaded into the scene simulation tool of the test host computer to generate virtual scene information.

[0030] In the third aspect, an embodiment of the present application provides an intelligent driving system real vehicle test device, which includes a processor, a memory, and an intelligent driving system real vehicle test program stored in the memory and executable by the processor, wherein when the intelligent driving system real vehicle test program is executed by the processor, the steps of the intelligent driving system real vehicle test method as described in any one of the first aspects are implemented.

[0031] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a smart driving system real vehicle test program is stored. When the smart driving system real vehicle test program is executed by a processor, the steps of the smart driving system real vehicle test method as described in any one of the first aspects are implemented.

[0032] The beneficial effects brought by the technical solution provided by the embodiments of the present application include:

[0033] The virtual scene information is transmitted to the controller of the actual vehicle to be tested through the test host computer, and the virtual scene information includes relevant information of multiple perception elements; the controller of the actual vehicle to be tested integrates the virtual scene information, vehicle motion information and body-related status information to generate lateral and longitudinal control instructions, and transmits the lateral and longitudinal control instructions to the body module; the body module executes the lateral and longitudinal control instructions to control the vehicle's driving, and uploads the lateral and longitudinal speeds and accelerations of the vehicle to the test host computer through the controller of the actual vehicle to be tested during the vehicle's driving, so as to complete the closed-loop simulation test of the actual vehicle of the intelligent driving system in a virtual scene. The present application adopts a method of combining the simulation environment with the actual vehicle, which avoids the problem of low simulation accuracy of the intelligent driving function due to the use of a vehicle dynamics model, and at the same time avoids the high risk of using an actual vehicle for testing in a real test scenario and the difficulty in scene reproduction; in addition, since the virtual scene information includes relevant information of multiple perception elements, closed-loop simulation of high-order intelligent driving functions can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 This is a flow chart of the first embodiment of the real vehicle testing method of the intelligent driving system of the present application;

[0035] Figure 2 A schematic diagram of a real vehicle testing solution for an intelligent driving system based on a virtual scene provided in an embodiment of the present application;

[0036] Figure 3 A schematic diagram of the overall solution architecture of the real vehicle test of the intelligent driving system provided in one embodiment of the present application;

[0037] Figure 4 A schematic diagram of a scenario reconstruction automated test architecture provided in an embodiment of the present application;

[0038] Figure 5 This is a functional module diagram of an embodiment of a real vehicle testing system for an intelligent driving system of the present application;

[0039] Figure 6 This is a schematic diagram of the hardware structure of the real vehicle testing equipment of the intelligent driving system involved in the embodiment of the present application. DETAILED DESCRIPTION

[0040] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0041] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0042] In a first aspect, an embodiment of the present application provides a real-vehicle testing method for an intelligent driving system, which is applied to a real-vehicle testing system for an intelligent driving system. The real-vehicle testing system for the intelligent driving system includes a testing host computer, a real-vehicle controller to be tested, and a body module.

[0043] In one embodiment, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the real vehicle testing method of the intelligent driving system of this application. Figure 1 As shown, the real vehicle testing method of the intelligent driving system includes:

[0044] Step 110: The test host computer transmits virtual scene information to the real vehicle controller to be tested, wherein the virtual scene information includes relevant information of multiple perception elements;

[0045] Figure 2 A schematic diagram of a real vehicle test solution for an intelligent driving system based on a virtual scene provided in an embodiment of the present application, Figure 2 It can be seen that this application uses an actual vehicle to travel on an actual road, and the test host computer sends corresponding virtual scene information to the controller of the actual vehicle to be tested based on virtual positioning. The virtual scene information is full perception information, including relevant information of multiple perception elements, including high-precision maps, lane line information, obstacle information, speed limit sign information and initial positioning information of the actual vehicle to be tested.

[0046] Step 120: The real vehicle controller to be tested integrates the virtual scene information, the vehicle motion information and the body-related state information to generate lateral and longitudinal control instructions, and transmits the lateral and longitudinal control instructions to the body module;

[0047] Among them, the vehicle body related status information includes the vehicle speed, current steering, the speed of the preceding vehicle, the status of each subsystem, etc.; the vehicle motion information includes three-axis acceleration, three-axis angular velocity, attitude angle, etc.

[0048] During the specific implementation, the controller of the actual vehicle to be tested receives the virtual scene information transmitted by the test host computer, and first determines the fused positioning information through the virtual scene information and the vehicle motion information; then, based on the fused positioning information, determines the road condition information in front of the vehicle in the virtual scene; finally, comprehensively analyzes the road condition information, vehicle body-related status information, and virtual scene information, generates lateral and longitudinal control instructions, and transmits the lateral and longitudinal control instructions to the vehicle body module.

[0049] Step 130, the body module executes the lateral and longitudinal control instructions to control the vehicle's driving, and during the vehicle's driving, the vehicle's lateral and longitudinal speeds and accelerations are uploaded to the test host computer through the actual vehicle controller to complete a closed-loop simulation test of the intelligent driving system actual vehicle in a virtual scene.

[0050] In specific implementation, the steering system, braking system and drive system in the body module execute the lateral and longitudinal control instructions and control the vehicle's driving. During the vehicle's driving, the lateral and longitudinal speeds and accelerations of the vehicle are uploaded to the Ethernet communication module in the test host computer through the Ethernet communication module in the actual vehicle controller to complete the closed-loop simulation test of the intelligent driving system in a virtual scene.

[0051] In this embodiment, the virtual scene information is transmitted to the controller of the actual vehicle to be tested through the test host computer, and the virtual scene information includes relevant information of multiple perception elements; the controller of the actual vehicle to be tested integrates the virtual scene information, vehicle motion information and body-related state information to generate lateral and longitudinal control instructions, and transmits the lateral and longitudinal control instructions to the body module; the body module executes the lateral and longitudinal control instructions to control the vehicle's driving, and uploads the lateral and longitudinal speeds and accelerations of the vehicle to the test host computer through the controller of the actual vehicle to be tested during the vehicle's driving, so as to complete the closed-loop simulation test of the actual vehicle of the intelligent driving system in a virtual scene. The combination of the simulation environment and the actual vehicle avoids the problem of low simulation accuracy of the intelligent driving function due to the use of a vehicle dynamics model, and at the same time avoids the high risk of using an actual vehicle for testing in a real test scene and the difficulty in scene reproduction; in addition, since the virtual scene information includes relevant information of multiple perception elements, closed-loop simulation of high-order intelligent driving functions can be achieved.

[0052] Furthermore, in one embodiment, Figure 3 This is a schematic diagram of the overall solution architecture of the real vehicle test of the intelligent driving system provided in one embodiment of the present application, from Figure 3 It can be seen that the test host computer in this application includes a scene simulation tool, an Ethernet communication module and a vehicle dynamics module. Among them, the scene simulation tool is used to edit dynamic and static scene elements such as lane lines, speed limit signs, and traffic participants on the high-precision map file after loading the high-precision map file, so as to generate virtual scene information; and output the lane line information, obstacle information, speed limit sign information, initial positioning information and initial posture information and other scene information according to the virtual posture information of the vehicle in the virtual scene; the Ethernet communication module is used to receive the scene information output by the scene simulation tool and forward it to the actual vehicle controller to be tested, and at the same time receive the vehicle's lateral and longitudinal speeds and accelerations sent by the actual vehicle controller to be tested and forward them to the vehicle dynamics module; the vehicle dynamics module is used to receive the initial posture information and the vehicle's lateral and longitudinal speeds and acceleration information, calculate the updated posture information, and send it to the scene simulation tool.

[0053] from Figure 3 It can be seen that the actual vehicle controller to be tested in this application includes an Ethernet communication module, a Global Navigation Satellite System (GNSS) module, an Inertial Measurement Unit (IMU) module, a fusion positioning module, a high-precision map module and an intelligent driving regulation and control algorithm module. Among them, the Ethernet communication module is used to receive the virtual scene information output by the test host computer and forward it to the intelligent driving regulation and control algorithm module and the GNSS module respectively, and at the same time receive the lateral and longitudinal velocity and acceleration information of the vehicle body module and forward it to the test host computer; the GNSS module is used to receive the initial positioning information and add deflection simulation, and output the absolute position information to the fusion positioning module (here the real positioning signal of the vehicle is shielded, and the virtual positioning signal output by the virtual scene is used to achieve the matching of the actual test road and the virtual scene map); the IMU module outputs the vehicle motion information to the fusion positioning module based on the vehicle running status; the fusion positioning module is used to receive the absolute position information and the vehicle motion information, comprehensively solve the final fusion positioning information, and send it to the high-precision map module; the high-precision map module and The scene simulation tool loads the same high-precision map file, and obtains the road condition information in front of the vehicle in the virtual scene based on the received fused positioning information, such as road geometry and rule information, semantic information and real-time dynamic information, and outputs it to the intelligent driving regulation and control algorithm module; the intelligent driving regulation and control algorithm module is used to receive the lane line information, obstacle information and speed limit sign information in the virtual scene information transmitted by the Ethernet communication module, and is also used to receive the road condition information in front of the vehicle in the virtual scene transmitted by the high-precision map module, and is also used to receive the body-related status information feedback by the body module, and comprehensively analyzes the road condition information, body-related status information, lane line information, obstacle information and speed limit sign information in the virtual scene information, generates lateral and longitudinal control instructions, calculates the lateral and longitudinal control instructions, and sends them to the body module.

[0054] In this embodiment, the absolute position information is obtained by adding deflection simulation to the initial positioning information in the virtual scene information; then, based on the absolute position information and the vehicle motion information, the fused positioning information is determined, which can improve the accuracy of determining the position of the actual vehicle to be tested in the high-precision map; further based on the fused positioning information, the road condition information in front of the vehicle in the virtual scene is determined; finally, the road condition information, vehicle body related status information, lane line information, obstacle information and speed limit sign information in the virtual scene information are comprehensively analyzed to generate lateral and longitudinal control instructions, which can make the performance of the actual vehicle controller to be tested in the virtual scene better and further improve the simulation accuracy of the intelligent driving function.

[0055] Furthermore, in one embodiment, after completing the closed-loop simulation test of the real vehicle of the intelligent driving system in a virtual scene, the method further includes:

[0056] Step 310: In the current virtual scene, determine static scene elements within a preset distance range in front of the vehicle;

[0057] Step 320: determine whether there is a problem scene containing the static scene element in the problem scene library;

[0058] Step 330: If the problem scene includes the static scene element, the problem scene including the static scene element is used as the target scene, and the dynamic traffic participant elements in the target scene are written into the current virtual scene.

[0059] The test host computer also includes a scene matching module, a scene reconstruction module and a problem scene library. The problem scene library includes problem scenes such as misidentification of curves and vehicles not giving way to the next car on the off-ramp. Figure 4 A schematic diagram of a scenario reconstruction automated testing architecture provided in one embodiment of the present application.

[0060] In specific implementation, after completing the closed-loop simulation test of the real vehicle of the intelligent driving system in a virtual scene, the scene simulation tool determines the static scene elements within the preset distance range in front of the vehicle in the current virtual scene, and transmits them to the scene matching module; the scene matching module receives the static scene elements within the preset distance range in front of the vehicle transmitted by the scene simulation tool, and matches and associates them with the problem scenes in the problem scene library. The static scene elements here include highways, viaducts, roundabouts, curves, ramps, traffic lights, etc. The matching association is specifically determined by judging whether there is a problem scene containing the static scene elements in the problem scene library; if the problem scene contains the static scene elements, the match is successful, and the scene matching module sends a matching signal to the problem scene library. At this time, the problem scene library uses the problem scene containing the static scene elements as the target scene, and outputs the dynamic traffic participant elements in the target scene to the scene reconstruction module; the scene reconstruction module writes the obtained dynamic traffic participant elements into the current virtual scene through the protocol interface, thereby reconstructing the target scene, and can directly and automatically test the performance of the vehicle controller in the target scene. Among them, the dynamic traffic participant elements include the relative position of the obstacle and the actual vehicle to be tested, the behavior data of the obstacle (lane change, braking, acceleration, etc.) and the speed of the obstacle.

[0061] Exemplarily, after completing a closed-loop simulation test of a real vehicle of the intelligent driving system in a virtual scene (for example, a front vehicle cutting in), in the current virtual scene, determine the static scene elements within a preset distance range in front of the vehicle, such as a ramp; determine whether there is a problem scene containing a ramp in the problem scene library; if there is a problem scene containing a ramp, such as a problem scene where the vehicle needs to exit the ramp but the vehicle in the adjacent lane does not give way, then the problem scene containing the ramp is used as the target scene, and the relevant information of the vehicle in the adjacent lane in the target scene is written into the current virtual scene, thereby reconstructing the target scene where the vehicle needs to exit the ramp but the vehicle in the adjacent lane does not give way, and the performance of the vehicle controller in the target scene can be directly and automatically tested.

[0062] In this embodiment, after completing the closed-loop simulation test of the real vehicle of the intelligent driving system in a virtual scene, the static scene elements within a preset distance range in front of the vehicle are determined in the current virtual scene; it is determined whether there is a problem scene containing the static scene elements in the problem scene library; if there is a problem scene containing the static scene elements, the problem scene containing the static scene elements is used as the target scene, and the dynamic traffic participant elements in the target scene are written into the current virtual scene, which can be associated with the problem scene library, thereby realizing real-time matching and reconstruction of the problem scene. After reconstructing the problem scene, the performance of the real vehicle controller to be tested in the problem scene can be automatically tested, thereby improving the test efficiency.

[0063] Furthermore, in one embodiment, after completing the closed-loop simulation test of the real vehicle of the intelligent driving system in a virtual scene, the method further includes:

[0064] The performance of the controller of the real vehicle to be tested is analyzed and evaluated based on the motion data of the real vehicle to be tested in the virtual scene.

[0065] Since the virtual scene information in this application is full perception information, it includes not only virtual obstacle information, but also high-precision maps, lane line information, speed limit sign information, and initial positioning information of the actual vehicle to be tested, etc. Therefore, after completing the closed-loop simulation test of the actual vehicle of the intelligent driving system in a virtual scene, the performance of the controller of the actual vehicle to be tested can be fully analyzed and evaluated based on the motion data of the actual vehicle to be tested in the virtual scene.

[0066] In a second aspect, an embodiment of the present application also provides a real vehicle testing system for an intelligent driving system.

[0067] In one embodiment, referring to Figure 5 , Figure 5 This is a functional module diagram of an embodiment of the intelligent driving system real vehicle testing system of the present application. Figure 5As shown in the figure, the real vehicle test system of the intelligent driving system includes:

[0068] The test host computer 501 is used to transmit virtual scene information to the real vehicle controller to be tested, wherein the virtual scene information includes relevant information of multiple perception elements;

[0069] The real vehicle controller 502 to be tested is used to integrate virtual scene information, vehicle motion information and vehicle body related state information to generate lateral and longitudinal control instructions, and transmit the lateral and longitudinal control instructions to the vehicle body module;

[0070] The body module 503 is used to execute lateral and longitudinal control instructions to control the vehicle's driving, and upload the vehicle's lateral and longitudinal speeds and accelerations to the test host computer through the actual vehicle controller to be tested during the vehicle's driving process, so as to complete the closed-loop simulation test of the intelligent driving system actual vehicle in a virtual scene.

[0071] Furthermore, in one embodiment, the process of generating the virtual scene information includes:

[0072] Static scene elements and dynamic scene elements are edited on the high-precision map file loaded into the scene simulation tool of the test host computer to generate virtual scene information.

[0073] Furthermore, in one embodiment, the virtual scene information includes a high-precision map, lane line information, obstacle information, speed limit sign information, and initial positioning information of the actual vehicle to be tested.

[0074] Furthermore, in one embodiment, the actual vehicle controller to be tested is specifically used for:

[0075] Add deflection simulation to the initial positioning information in the virtual scene information to obtain absolute position information;

[0076] Determine fused positioning information based on the absolute position information and the vehicle motion information;

[0077] Based on the fused positioning information, determine the road condition information in front of the vehicle in the virtual scene;

[0078] Comprehensively analyze road condition information, vehicle body status information, lane line information in virtual scene information, obstacle information and speed limit sign information to generate lateral and longitudinal control instructions.

[0079] Furthermore, in one embodiment, the test host computer is also used for:

[0080] After completing the closed-loop simulation test of the real vehicle of the intelligent driving system in a virtual scene, in the current virtual scene, determine the static scene elements within a preset distance range in front of the vehicle;

[0081] Determine whether there is a problem scene containing the static scene element in the problem scene library;

[0082] If the problem scene includes the static scene elements, the problem scene including the static scene elements is used as the target scene, and the dynamic traffic participant elements in the target scene are written into the current virtual scene.

[0083] Furthermore, in one embodiment, the intelligent driving system real vehicle testing system further includes an analysis module, and the analysis module is specifically used for:

[0084] After completing the closed-loop simulation test of the real vehicle of the intelligent driving system in a virtual scene, the performance of the controller of the real vehicle to be tested is analyzed and evaluated based on the motion data of the real vehicle to be tested in the virtual scene.

[0085] Among them, the functional implementation of each module in the above-mentioned intelligent driving system real vehicle testing device corresponds to the various steps in the above-mentioned intelligent driving system real vehicle testing method embodiment, and its functions and implementation processes will not be repeated here one by one.

[0086] On the third aspect, an embodiment of the present application provides a real vehicle testing device for an intelligent driving system. The real vehicle testing device for an intelligent driving system may be a personal computer (PC), a laptop computer, a server, or other device with data processing capabilities.

[0087] Reference Figure 6 , Figure 6 The hardware structure diagram of the intelligent driving system real vehicle test device involved in the embodiment of the present application is shown in FIG. In the embodiment of the present application, the intelligent driving system real vehicle test device may include a processor, a memory, a communication interface, and a communication bus.

[0088] The communication bus may be of any type and is used to interconnect the processor, the memory, and the communication interface.

[0089] The communication interface includes input / output (I / O) interface, physical interface and logical interface, etc., which are used to realize the interconnection of devices inside the intelligent driving system real vehicle test equipment, and the interface used to realize the interconnection between the intelligent driving system real vehicle test equipment and other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, a fiber optic interface, an ATM interface, etc.; the user device can be a display (Display), a keyboard (Keyboard), etc.

[0090] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0091] The processor can be a general-purpose processor, which can call the intelligent driving system real vehicle test program stored in the memory and execute the intelligent driving system real vehicle test method provided in the embodiment of the present application. The intelligent driving system real vehicle test includes: the test host computer transmits virtual scene information to the real vehicle controller to be tested, and the virtual scene information includes relevant information of multiple perception elements; the real vehicle controller to be tested integrates the virtual scene information, vehicle motion information and body-related status information to generate lateral and longitudinal control instructions, and transmits the lateral and longitudinal control instructions to the body module; the body module executes the lateral and longitudinal control instructions to control the vehicle driving, and uploads the vehicle's lateral and longitudinal speeds and accelerations to the test host computer through the real vehicle controller to be tested during the vehicle driving process, so as to complete the closed-loop simulation test of the intelligent driving system real vehicle in a virtual scene.

[0092] For example, the general processor may be a central processing unit (CPU). The method executed when the intelligent driving system real vehicle test program is called may refer to the various embodiments of the intelligent driving system real vehicle test method of the present application, which will not be repeated here.

[0093] Those skilled in the art will understand that Figure 6 The hardware structure shown in the figure does not constitute a limitation on the present application, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0094] In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium.

[0095] The computer-readable storage medium of the present application stores an intelligent driving system real vehicle test program, wherein when the intelligent driving system real vehicle test program is executed by the processor, the steps of the intelligent driving system real vehicle test method as described above are implemented. The real vehicle test of the intelligent driving system includes: the test host computer transmits virtual scene information to the real vehicle controller to be tested, and the virtual scene information includes relevant information of multiple perception elements; the real vehicle controller to be tested integrates the virtual scene information, vehicle motion information and body-related state information to generate lateral and longitudinal control instructions, and transmits the lateral and longitudinal control instructions to the body module; the body module executes the lateral and longitudinal control instructions to control the vehicle's driving, and during the vehicle's driving, the vehicle's lateral and longitudinal speeds and accelerations are uploaded to the test host computer through the real vehicle controller to be tested, so as to complete the closed-loop simulation test of the real vehicle of the intelligent driving system in a virtual scene.

[0096] Among them, the method implemented when the intelligent driving system real vehicle test program is executed can refer to the various embodiments of the intelligent driving system real vehicle test method of this application, and will not be repeated here.

[0097] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0098] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to different types.

[0099] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a specific way.

[0100] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; the “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0101] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.

[0102] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.

[0103] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A real vehicle testing method for an intelligent driving system, characterized in that: Applied to the real vehicle test system of the intelligent driving system, the real vehicle test system of the intelligent driving system includes a test host computer, a real vehicle controller to be tested and a body module, and the real vehicle test method of the intelligent driving system includes: The test host computer transmits virtual scene information to the real vehicle controller to be tested, wherein the virtual scene information includes relevant information of multiple perception elements; The controller of the actual vehicle to be tested integrates the virtual scene information, vehicle motion information and body-related status information to generate lateral and longitudinal control instructions, and transmits the lateral and longitudinal control instructions to the body module; The body module executes lateral and longitudinal control instructions to control the vehicle's driving, and uploads the vehicle's lateral and longitudinal speeds and accelerations to the test host computer through the actual vehicle controller to be tested during the vehicle's driving process, so as to complete the closed-loop simulation test of the intelligent driving system real vehicle in a virtual scene.

2. The real vehicle testing method of the intelligent driving system according to claim 1, characterized in that: The generation process of the virtual scene information includes: Static scene elements and dynamic scene elements are edited on the high-precision map file loaded into the scene simulation tool of the test host computer to generate virtual scene information.

3. The real vehicle testing method of the intelligent driving system according to claim 1, characterized in that: The virtual scene information includes high-precision maps, lane line information, obstacle information, speed limit sign information and initial positioning information of the actual vehicle to be tested.

4. The real vehicle testing method of the intelligent driving system according to claim 3, characterized in that: The real vehicle controller to be tested integrates virtual scene information, vehicle motion information and vehicle body related state information to generate lateral and longitudinal control instructions, including: Add deflection simulation to the initial positioning information in the virtual scene information to obtain absolute position information; Determine fused positioning information based on the absolute position information and the vehicle motion information; Based on the fused positioning information, determine the road condition information in front of the vehicle in the virtual scene; Comprehensively analyze road condition information, vehicle body status information, lane line information in virtual scene information, obstacle information and speed limit sign information to generate lateral and longitudinal control instructions.

5. The real vehicle testing method of the intelligent driving system according to claim 1, characterized in that: After completing the closed-loop simulation test of the real vehicle of the intelligent driving system in a virtual scene, the method further includes: In the current virtual scene, determine static scene elements within a preset distance range in front of the vehicle; Determine whether there is a problem scene containing the static scene element in the problem scene library; If the problem scene includes the static scene elements, the problem scene including the static scene elements is used as the target scene, and the dynamic traffic participant elements in the target scene are written into the current virtual scene.

6. The real vehicle testing method of the intelligent driving system according to claim 1, characterized in that: After completing the closed-loop simulation test of the real vehicle of the intelligent driving system in a virtual scene, the method further includes: The performance of the controller of the real vehicle to be tested is analyzed and evaluated based on the motion data of the real vehicle to be tested in the virtual scene.

7. An intelligent driving system real vehicle testing system, characterized in that: The intelligent driving system real vehicle testing system comprises: A test host computer is used to transmit virtual scene information to the real vehicle controller to be tested, wherein the virtual scene information includes relevant information of multiple perception elements; The real vehicle controller to be tested is used to integrate virtual scene information, vehicle motion information and body-related state information to generate lateral and longitudinal control instructions, and transmit the lateral and longitudinal control instructions to the body module; The body module is used to execute lateral and longitudinal control instructions to control the vehicle's driving, and upload the vehicle's lateral and longitudinal speeds and accelerations to the test host computer through the actual vehicle controller to be tested during the vehicle's driving process, so as to complete the closed-loop simulation test of the intelligent driving system real vehicle in a virtual scene.

8. The real vehicle testing system for the intelligent driving system according to claim 7, characterized in that: The generation process of the virtual scene information includes: Static scene elements and dynamic scene elements are edited on the high-precision map file loaded into the scene simulation tool of the test host computer to generate virtual scene information.

9. An intelligent driving system real vehicle testing device, characterized in that: The intelligent driving system real vehicle test equipment includes a processor, a memory, and an intelligent driving system real vehicle test program stored in the memory and executable by the processor. When the intelligent driving system real vehicle test program is executed by the processor, the steps of the intelligent driving system real vehicle test method as described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an intelligent driving system real vehicle test program, wherein when the intelligent driving system real vehicle test program is executed by the processor, the steps of the intelligent driving system real vehicle test method as described in any one of claims 1 to 6 are implemented.

Images