Intelligent Driving Vehicle Testing Method and Device

Abstract

The present application provides a method and device for testing an intelligent driving vehicle. The method includes: in response to an intelligent driving test instruction, loading a corresponding virtual driving scenario for the intelligent driving vehicle located in an actual driving scenario; obtaining first real-time pose information of the intelligent driving vehicle in the actual driving scenario; determining second real-time pose information of the intelligent driving vehicle in the virtual driving scenario based on the first real-time pose information; generating an automatic driving adjustment strategy based on the second real-time pose information, real-time driving environment information provided by the virtual driving scenario, and a preset intelligent driving algorithm; and controlling the intelligent driving vehicle to execute the automatic driving adjustment strategy in the virtual driving scenario and the actual driving scenario respectively. The technical solution of the present application can reduce the error caused by data conversion between the virtual driving scenario and the actual driving scenario during the testing process and improve the accuracy of the test results.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and particularly to a method and device for testing intelligent driving vehicles.

Background Art

[0002] In recent years, with the rapid development of intelligent driving technology, how to verify and evaluate the driving safety of intelligent driving vehicles has become crucial. Obviously, the safety and reliability testing of intelligent driving technology requires long-term, extensive, and repeated operations, and its related influencing factors include scenarios, equipment, personnel, and other external conditions. Currently, generally, the scenarios in the preset scenario library can be used to test the algorithm files to be tested, without the need to build an actual driving scenario, so as to reduce the testing cost.

[0003] However, this fully virtual testing method depends on the richness of the preset scenario library, and the scenarios that the preset scenario library can cover are limited, and the accuracy and practicality of its testing results are limited. At the same time, establishing rich scenario data will also bring a large amount of computing work, with extremely high costs. Moreover, using the fully virtual testing method cannot fully and efficiently reproduce various problems that intelligent driving vehicles may face in actual scenarios.

[0004] In response to this, some technical solutions combining virtuality and reality are also provided in the related art. While controlling the physical vehicle in the actual scenario, this actual scenario is reproduced as an operable virtual scenario to cancel the traditional driver operation and improve testing safety. However, this method has high construction standards for the actual scenario, not only bringing high cost consumption, but also being unable to cover a large number of complex and changeable scenarios due to the limitation of scenario construction capabilities, and the covered scenario range of the testing is limited, which also affects the reliability of the testing results.

[0005] Therefore, how to balance the testing cost and the reliability of testing results in the testing of intelligent driving vehicles has become an urgent technical problem to be solved currently.

Summary of the Invention

[0006] The embodiments of this application provide a method and device for testing intelligent driving vehicles, aiming to solve the technical problems of high testing cost and insufficient reliability of testing results in the testing methods of intelligent driving vehicles in the related art.

[0007] In a first aspect, the embodiments of this application provide a method for testing intelligent driving vehicles, including:

[0008] In response to an intelligent driving test instruction, load a corresponding virtual driving scenario for the intelligent driving vehicle located in the actual driving scenario;

[0009] Obtain the first real-time pose information of the intelligent driving vehicle in the actual driving scenario;

[0010] Based on the first real-time pose information, determine the second real-time pose information of the intelligent driving vehicle in the virtual driving scenario;

[0011] Based on the second real-time pose information, the real-time driving environment information provided by the virtual driving scenario, and a preset intelligent driving algorithm, generate an autonomous driving adjustment strategy;

[0012] Control the intelligent driving vehicle to execute the autonomous driving adjustment strategy in the virtual driving scenario and the actual driving scenario respectively.

[0013] In an embodiment of the present application, optionally, the determining the second real-time pose information of the intelligent driving vehicle in the virtual driving scenario based on the first real-time pose information includes:

[0014] Based on the pose offset information between the actual driving scenario and the virtual driving scenario and the first real-time pose information, determine the second real-time pose information of the intelligent driving vehicle in the virtual driving scenario.

[0015] In an embodiment of the present application, optionally, when loading a corresponding virtual driving scenario for the intelligent driving vehicle located in the actual driving scenario, it further includes:

[0016] Obtain the first initial pose information of the intelligent driving vehicle in the actual driving scenario and the second initial pose information in the virtual driving scenario;

[0017] Determine the pose offset information of the intelligent driving vehicle between the actual driving scenario and the virtual driving scenario by taking the difference between the first initial pose information and the second initial pose information.

[0018] In an embodiment of the present application, optionally, when loading a corresponding virtual driving scenario for the intelligent driving vehicle located in the actual driving scenario, it further includes:

[0019] Obtain the first initial pose information of the intelligent driving vehicle in the actual driving scenario and the second initial pose information in the virtual driving scenario;

[0020] Obtain the difference between the first initial pose information and the second initial pose information;

[0021] Based on the type of the virtual driving scenario, determine the first difference adjustment coefficient corresponding to the virtual driving scenario;

[0022] Determine the pose offset information of the intelligent driving vehicle between the actual driving scenario and the virtual driving scenario based on the difference between the first initial pose information and the second initial pose information, and the first difference adjustment coefficient.

[0023] In an embodiment of the present application, optionally, when loading a corresponding virtual driving scenario for an intelligent driving vehicle located in an actual driving scenario, it further includes:

[0024] Obtain the first initial pose information of the intelligent driving vehicle in the actual driving scenario and the second initial pose information in the virtual driving scenario;

[0025] Obtain the difference between the first initial pose information and the second initial pose information;

[0026] Based on the preset scenario coefficients corresponding to the actual driving scenario and the virtual driving scenario respectively, determine the scenario difference degree between the actual driving scenario and the virtual driving scenario;

[0027] Based on the scenario difference degree, determine the second difference adjustment coefficient;

[0028] Determine the pose offset information of the intelligent driving vehicle between the actual driving scenario and the virtual driving scenario based on the difference between the first initial pose information and the second initial pose information, and the second difference adjustment coefficient.

[0029] In an embodiment of the present application, optionally, the loading of the corresponding virtual driving scenario for the intelligent driving vehicle located in the actual driving scenario includes:

[0030] Build a virtual-real combined simulation system for the intelligent driving vehicle, where the virtual-real combined simulation system includes a host computer, a rapid prototyping machine, the intelligent driving vehicle, a combined navigation module, and a communication module.

[0031] The host computer is used to load a virtual driving scenario file reproduced from real vehicle environment data and display the virtual driving scenario corresponding to the virtual driving scenario file. The virtual driving scenario file includes environmental information and motion association information of historical traffic participants in the virtual driving scenario.

[0032] The combined navigation module is used to locate the intelligent driving vehicle;

[0033] The rapid prototyping machine is used to run the preset intelligent driving algorithm based on the information provided by the host computer, the intelligent driving vehicle, and the combined navigation module respectively, and control each target actuator of the intelligent driving vehicle to execute the corresponding autonomous driving adjustment strategy based on the operation result.

[0034] The host computer, the rapid prototyping machine, the intelligent driving vehicle, and the integrated navigation module are connected through the communication module.

[0035] In an embodiment of the present application, optionally, controlling each target actuator of the intelligent driving vehicle to execute a corresponding autonomous driving adjustment strategy includes:

[0036] Sending control instructions required by the autonomous driving adjustment strategy to the drive system, braking system, and steering system of the intelligent driving vehicle;

[0037] Sending a warning instruction to the warning module of the intelligent driving vehicle.

[0038] In a second aspect, an embodiment of the present application provides an intelligent driving vehicle testing device, including:

[0039] A driving scenario configuration unit, configured to load a corresponding virtual driving scenario for the intelligent driving vehicle located in the actual driving scenario in response to an intelligent driving test instruction;

[0040] A first real-time pose information acquisition unit, configured to acquire first real-time pose information of the intelligent driving vehicle in the actual driving scenario;

[0041] A second real-time pose information determination unit, configured to determine second real-time pose information of the intelligent driving vehicle in the virtual driving scenario based on the first real-time pose information;

[0042] An autonomous driving adjustment strategy generation unit, configured to generate an autonomous driving adjustment strategy based on the second real-time pose information, the real-time driving environment information provided by the virtual driving scenario, and a preset intelligent driving algorithm;

[0043] An autonomous driving adjustment strategy execution unit, configured to control the intelligent driving vehicle to execute the autonomous driving adjustment strategy in the virtual driving scenario and the actual driving scenario respectively.

[0044] In an embodiment of the present application, optionally, the second real-time pose information determination unit is configured to:

[0045] Determine the second real-time pose information of the intelligent driving vehicle in the virtual driving scenario based on the pose offset information between the actual driving scenario and the virtual driving scenario and the first real-time pose information.

[0046] In an embodiment of the present application, optionally, the device further includes:

[0047] An initial pose information acquisition unit, configured to obtain a first initial pose information of the intelligent driving vehicle in the actual driving scenario and a second initial pose information in the virtual driving scenario when loading a corresponding virtual driving scenario for the intelligent driving vehicle located in the actual driving scenario;

[0048] A first determination unit, configured to determine pose offset information of the intelligent driving vehicle between the actual driving scenario and the virtual driving scenario based on the difference between the first initial pose information and the second initial pose information.

[0049] In an embodiment of the present application, optionally, the device further includes:

[0050] An initial pose information acquisition unit, configured to obtain a first initial pose information of the intelligent driving vehicle in the actual driving scenario and a second initial pose information in the virtual driving scenario when loading a corresponding virtual driving scenario for the intelligent driving vehicle located in the actual driving scenario;

[0051] A difference acquisition unit, configured to obtain the difference between the first initial pose information and the second initial pose information;

[0052] A first difference adjustment coefficient determination unit, configured to determine a first difference adjustment coefficient corresponding to the virtual driving scenario based on the type of the virtual driving scenario;

[0053] A second determination unit, configured to determine pose offset information of the intelligent driving vehicle between the actual driving scenario and the virtual driving scenario based on the difference between the first initial pose information and the second initial pose information, and the first difference adjustment coefficient.

[0054] In an embodiment of the present application, optionally, the device further includes:

[0055] An initial pose information acquisition unit, configured to obtain a first initial pose information of the intelligent driving vehicle in the actual driving scenario and a second initial pose information in the virtual driving scenario when loading a corresponding virtual driving scenario for the intelligent driving vehicle located in the actual driving scenario;

[0056] A difference acquisition unit, configured to obtain the difference between the first initial pose information and the second initial pose information;

[0057] A scene difference degree determination unit, configured to determine the scene difference degree between the actual driving scenario and the virtual driving scenario based on preset scene coefficients corresponding to the actual driving scenario and the virtual driving scenario respectively;

[0058] A second difference adjustment coefficient determination unit, configured to determine a second difference adjustment coefficient based on the scene difference degree;

[0059] A third determination unit, configured to determine the pose offset information of the intelligent driving vehicle between the actual driving scene and the virtual driving scene based on the difference between the first initial pose information and the second initial pose information, and the second difference adjustment coefficient.

[0060] In an embodiment of the present application, optionally, the driving scene configuration unit includes:

[0061] A virtual-real combined simulation system construction unit, configured to build a virtual-real combined simulation system for the intelligent driving vehicle, where the virtual-real combined simulation system includes a host computer, a rapid prototyping machine, the intelligent driving vehicle, a combined navigation module, and a communication module.

[0062] The host computer is configured to load a virtual driving scene file reproduced from real vehicle environment data and display the virtual driving scene corresponding to the virtual driving scene file, where the virtual driving scene file includes environment information and motion association information of historical traffic participants in the virtual driving scene.

[0063] The combined navigation module is configured to locate the intelligent driving vehicle.

[0064] The rapid prototyping machine is configured to run the preset intelligent driving algorithm based on the information provided by the host computer, the intelligent driving vehicle, and the combined navigation module respectively, and control each target actuator of the intelligent driving vehicle to execute the corresponding automatic driving adjustment strategy based on the operation result.

[0065] The host computer, the rapid prototyping machine, the intelligent driving vehicle, and the combined navigation module are connected through the communication module.

[0066] In an embodiment of the present application, optionally, the automatic driving adjustment strategy execution unit is configured to:

[0067] Send control instructions required by the automatic driving adjustment strategy to the drive system, the braking system, and the steering system of the intelligent driving vehicle; send a warning instruction to the warning module of the intelligent driving vehicle.

[0068] In a third aspect, an embodiment of the present application provides a computer device, including: at least one processor; and a memory communicatively connected to the at least one processor; where the memory stores instructions executable by the at least one processor, and the instructions are configured to execute the method described in the first aspect above.

[0069] Fourthly, an embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions for executing the method described in the first aspect above.

[0070] In view of the technical problems of high test cost and insufficient reliability of test results in the intelligent driving vehicle test method in the related art, on the basis of combining virtual driving scenarios with actual driving scenarios for remote testing, it is not necessary to replicate the actual driving scenario consistent with the virtual driving scenario. Instead, it is only necessary to control the intelligent driving vehicle to move according to the real-time driving environment information provided by the virtual driving scenario in an ordinary test site, and the same result as driving the intelligent driving vehicle in the actual scenario corresponding to the virtual driving scenario can be obtained. In other words, it is not necessary to replicate complex scenarios for the intelligent driving vehicle, but to enable it to obtain the data possessed by complex scenarios in ordinary actual driving scenarios, so as to achieve the effect of testing the intelligent driving vehicle in complex scenarios. At the same time, in the present application, considering the differences between virtual driving scenarios and actual driving scenarios, the first real-time pose information of the intelligent driving vehicle in the actual driving scenario is corrected to obtain the second real-time pose information of the intelligent driving vehicle in the virtual driving scenario, so as to reduce the error caused by data conversion between virtual driving scenarios and actual driving scenarios during the test process and improve the accuracy of test results.

BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0072] Figure 1 Shows a flowchart of an intelligent driving vehicle test method according to an embodiment of the present application;

[0073] Figure 2 Shows a schematic diagram of a virtual-real combined simulation system according to an embodiment of the present application;

[0074] Figure 3 Shows a flowchart of obtaining pose offset information according to an embodiment of the present application;

[0075] Figure 4 Shows a network topology diagram of an intelligent driving vehicle in-the-loop test system based on real vehicle environment data injection according to an embodiment of the present application;

[0076] Figure 5Shows a network topology diagram of an in-the-loop test system for an intelligent driving vehicle based on real vehicle environment data injection according to another embodiment of the present application;

[0077] Figure 6 Shows a schematic diagram of a historical scenario according to an embodiment of the present application;

[0078] Figure 7 Shows a schematic diagram combining a virtual scenario and an actual scenario according to an embodiment of the present application;

[0079] Figure 8 Shows a block diagram of a computer device according to an embodiment of the present application;

[0080] Figure 9 Shows a block diagram of a computer device according to another embodiment of the present application.

Detailed implementation manners

[0081] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0082] Figure 1 Shows a flowchart of a method for testing an intelligent driving vehicle according to an embodiment of the present application.

[0083] As Figure 1 shown, the method for testing an intelligent driving vehicle according to an embodiment of the present application includes:

[0084] Step 102, in response to an intelligent driving test instruction, load a corresponding virtual driving scenario for the intelligent driving vehicle located in the actual driving scenario.

[0085] The virtual driving scenario refers to a scenario in which the driving situation of the intelligent driving vehicle needs to be tested, and the actual driving scenario is the test site where the intelligent driving vehicle for testing actually moves. In response to the intelligent driving test instruction, the actual movement of the intelligent driving vehicle in the actual driving scenario can be displayed as a virtual image in the virtual driving scenario for remote intelligent control of the intelligent driving vehicle. The intelligent control described here includes AI control and / or manual remote control.

[0086] Step 104, obtain first real-time pose information of the intelligent driving vehicle in the actual driving scenario.

[0087] Step 106: Determine the second real-time pose information of the intelligent driving vehicle in the virtual driving scenario based on the first real-time pose information.

[0088] The pose information of the intelligent driving vehicle includes at least its three azimuth angles and three rotation angles, which reflect the actual driving state of the intelligent driving vehicle. Further, when the intelligent driving vehicle in the actual driving scenario is projected into the virtual driving scenario, there will be a certain error due to the projection ability. Therefore, after adjusting based on the first real-time pose information of the intelligent driving vehicle in the actual driving scenario, the second real-time pose information of the intelligent driving vehicle in the virtual driving scenario can be obtained. Thus, the error generated by data conversion during the combination of virtual and real can be reduced, which helps to reduce the influence of errors on the test results.

[0089] Step 108: Generate an autonomous driving adjustment strategy based on the second real-time pose information, the real-time driving environment information provided by the virtual driving scenario, and a preset intelligent driving algorithm.

[0090] Step 110: Control the intelligent driving vehicle to execute the autonomous driving adjustment strategy in the virtual driving scenario and the actual driving scenario respectively.

[0091] The real-time driving environment information provided by the virtual driving scenario includes: the in-scene data measured by on-vehicle sensors such as lidar, millimeter-wave radar, ultrasonic radar, and cameras of historical vehicles in the historical actual scenario to which the virtual driving scenario belongs; all relevant information of the historical vehicles, static traffic participants, and dynamic traffic participants in the historical actual scenario, such as the ID, category, outer contour size, entry time into the scene, exit time from the scene, movement trajectory, heading angle, etc. of the traffic participants; the changes in the driving data of the drive system, braking system, and steering system of the historical vehicle in the historical actual scenario, such as the changes in the brake valve state, steering wheel angle, throttle opening, etc. Among them, the historical vehicle and the intelligent driving vehicle are of the same model.

[0092] Generally speaking, the real-time driving environment information provided by the virtual driving scenario covers the self-situation that the intelligent driving vehicle used in the test should have and the environmental information that it may face in this test. Thus, combined with the accurate real-time pose information of the intelligent driving vehicle in the virtual driving scenario, the autonomous driving adjustment strategy that the intelligent driving vehicle should execute in the current virtual driving scenario can be calculated through a preset intelligent driving algorithm.

[0093] Further, executing the autonomous driving adjustment strategy includes: sending control commands required by the autonomous driving adjustment strategy to the drive system, braking system, and steering system of the intelligent driving vehicle; and sending warning commands to the warning module of the intelligent driving vehicle.

[0094] Based on the above technical solution, when combining the virtual driving scenario with the actual driving scenario for remote testing, it is not necessary to reproduce the actual driving scenario consistent with the virtual driving scenario. Instead, it only needs to control the intelligent driving vehicle to move according to the real-time driving environment information provided by the virtual driving scenario in an ordinary test site, and the same result as driving the intelligent driving vehicle in the actual scenario corresponding to the virtual driving scenario can be obtained. In other words, it is not necessary to reproduce a complex scenario for the intelligent driving vehicle, but to enable it to obtain the data possessed by the complex scenario in an ordinary actual driving scenario, thus achieving the effect of testing the intelligent driving vehicle in a complex scenario.

[0095] Meanwhile, in this application, considering the differences between the virtual driving scenario and the actual driving scenario, after correcting the first real-time pose information of the intelligent driving vehicle in the actual driving scenario, the second real-time pose information of the intelligent driving vehicle in the virtual driving scenario is obtained, so as to reduce the error caused by data conversion between the virtual driving scenario and the actual driving scenario during the testing process and improve the accuracy of the test results.

[0096] In a possible design, a virtual-real combined simulation system can be built for the intelligent driving vehicle.

[0097] Optionally, as Figure 2 shown, the virtual-real combined simulation system includes a host computer, a rapid prototyping machine, the intelligent driving vehicle, an integrated navigation module, and a communication module. Among them, the host computer, the rapid prototyping machine, the intelligent driving vehicle, and the integrated navigation module are connected through the communication module.

[0098] The host computer is used to load the virtual driving scenario file reproduced from real vehicle environment data, display the virtual driving scenario corresponding to the virtual driving scenario file, and upload the information involved in the virtual driving scenario file to the rapid prototyping machine. Among them, the virtual driving scenario file includes environmental information and the motion association information of historical traffic participants in the virtual driving scenario, and this motion association information includes but is not limited to the motion state of historical traffic participants and the position of historical traffic participants.

[0099] The integrated navigation module is used to locate the intelligent driving vehicle, that is, obtain real-time positioning information and send this positioning information to the rapid prototyping machine.

[0100] The rapid prototyping machine is used to run the preset intelligent driving algorithm based on the information provided by the host computer, the intelligent driving vehicle, and the integrated navigation module respectively, and control each target actuator of the intelligent driving vehicle to execute the corresponding automatic driving adjustment strategy based on the operation result.

[0101] In a possible design, step 106 includes: determining the second real-time pose information of the intelligent driving vehicle in the virtual driving scenario based on the pose offset information between the actual driving scenario and the virtual driving scenario and the first real-time pose information.

[0102] It should be noted that the pose information includes three azimuth angles and three rotation angles of the vehicle. Here, the pose offset information refers to the pose offset information corresponding to each value among the three azimuth angles and three rotation angles. Among them, the pose offset information corresponding to each value is different and respectively represents the influence magnitude of its corresponding value caused by the conversion between the actual driving scenario and the virtual driving scenario.

[0103] In a possible design, when loading the corresponding virtual driving scenario for the intelligent driving vehicle located in the actual driving scenario, it is first necessary to determine the pose offset information between the actual driving scenario and the virtual driving scenario.

[0104] Optionally, the method for determining the pose offset information between the actual driving scenario and the virtual driving scenario includes:

[0105] First, obtain the first initial pose information of the intelligent driving vehicle in the actual driving scenario and the second initial pose information in the virtual driving scenario; then, determine the pose offset information of the intelligent driving vehicle between the actual driving scenario and the virtual driving scenario by taking the difference between the first initial pose information and the second initial pose information.

[0106] That is to say, directly take the difference between the pose information of the intelligent driving vehicle in the actual driving scenario and the pose information in the virtual driving scenario at the initial stage of the test as the pose offset information between the actual driving scenario and the virtual driving scenario.

[0107] Optionally, the method for determining the pose offset information between the actual driving scenario and the virtual driving scenario further includes:

[0108] First, obtain the first initial pose information of the intelligent driving vehicle in the actual driving scenario and the second initial pose information in the virtual driving scenario; and obtain the difference between the first initial pose information and the second initial pose information; then, based on the type of the virtual driving scenario, determine the first difference adjustment coefficient corresponding to the virtual driving scenario; based on the difference between the first initial pose information and the second initial pose information and the first difference adjustment coefficient, determine the pose offset information of the intelligent driving vehicle between the actual driving scenario and the virtual driving scenario.

[0109] Specifically, first obtain the difference between the pose information of the intelligent driving vehicle in the actual driving scenario and the pose information in the virtual driving scenario at the initial stage of the test. Further, since there are various virtual driving scenarios, the more complex the virtual driving scenario is, the greater the difference between it and the actual driving scenario presented by the test site. Therefore, the virtual driving scenarios can be classified according to their complexity. In this way, the virtual driving scenarios of the same type have a similar degree of difference from the actual driving scenario presented by the test site.

[0110] Further, this degree of difference can be used as the first difference adjustment coefficient corresponding to the virtual driving scenario. That is to say, the larger the first difference adjustment coefficient corresponding to the type of the virtual driving scenario, the greater the difference between the virtual driving scenario and the actual driving scenario, and the greater the possible error generated by the data conversion between the two. Then, the greater the space for adjusting the difference between the first initial pose information and the second initial pose information.

[0111] Optionally, the first difference adjustment coefficient is greater than 0 and less than 1.

[0112] Optionally, the pose offset information between the actual driving scenario and the virtual driving scenario is the product of the difference between the first initial pose information and the second initial pose information and the first difference adjustment coefficient.

[0113] Such as Figure 3 As shown, the method for determining the pose offset information between the actual driving scenario and the virtual driving scenario further includes:

[0114] Step 302, obtain the first initial pose information of the intelligent driving vehicle in the actual driving scenario and the second initial pose information in the virtual driving scenario.

[0115] Step 304, obtain the difference between the first initial pose information and the second initial pose information.

[0116] Step 306, based on the preset scenario coefficients corresponding to the actual driving scenario and the virtual driving scenario respectively, determine the scenario difference degree between the actual driving scenario and the virtual driving scenario.

[0117] Specifically, the preset scenario coefficient of each scenario represents the compatibility degree of this scenario with other scenarios. The gap between the preset scenario coefficients corresponding to the actual driving scenario and the virtual driving scenario respectively reflects the difference between the actual driving scenario and the virtual driving scenario.

[0118] Optionally, determine the scenario difference degree between the actual driving scenario and the virtual driving scenario as the difference between the preset scenario coefficients corresponding to the actual driving scenario and the virtual driving scenario respectively.

[0119] Step 308: Determine a second difference adjustment coefficient based on the scene difference degree.

[0120] The second difference adjustment coefficient is used to reflect the size of the space that needs to be adjusted for the difference between the first initial pose information and the second initial pose information. In fact, the higher the scene difference degree between the actual driving scene and the virtual driving scene, the more complex the virtual driving scene, the greater the difference between it and the actual driving scene presented by the test site, and the greater the error corresponding to the conversion of the initial pose information of the two.

[0121] Optionally, determine the square root value of the scene difference degree as the second difference adjustment coefficient to reduce the entropy value in the process of calculating the scene difference degree.

[0122] Step 310: Determine the pose offset information of the intelligent driving vehicle between the actual driving scene and the virtual driving scene based on the difference between the first initial pose information and the second initial pose information, and the second difference adjustment coefficient.

[0123] Optionally, the second difference adjustment coefficient is greater than 0 and less than 1.

[0124] Optionally, the pose offset information between the actual driving scene and the virtual driving scene is the product of the difference between the first initial pose information and the second initial pose information and the second difference adjustment coefficient.

[0125] In summary, the technical problem to be solved by the present invention is to provide a method and system for vehicle-in-the-loop testing of an intelligent driving vehicle based on real vehicle environment data injection, aiming to carry out vehicle-in-the-loop testing of an intelligent driving vehicle based on real vehicle data injection with low cost, high efficiency, high reliability, and wide application, and meet the technical requirements of high authenticity, good reliability, and strong repeatability in vehicle-in-the-loop testing of intelligent driving.

[0126] To achieve the above object, the present invention provides a vehicle-in-the-loop testing system for an intelligent driving vehicle based on real vehicle environment data injection, including a host computer, a rapid prototyping machine, a combined navigation module, and a test vehicle (i.e., the aforementioned intelligent driving vehicle). The architecture schematic diagram of the system is as shown in the aforementioned Figure 2 wherein the combined navigation module is used to update the current pose of the test vehicle, the host computer is used to load a virtual historical scene file and visualize the test scene content in real time, the rapid prototyping machine is used to receive the positioning, motion information of the test vehicle and the position, motion state, map and other environmental information of traffic participants in the scene file, and the test vehicle is used to execute control instructions from the rapid prototyping machine to realize actions such as driving, parking, and parking.

[0127] The specific steps of the operation of this system are as follows:

[0128] S1: Preparation for vehicle-in-the-loop testing;

[0129] S2: Conduct in-loop testing and obtain control instructions based on the current virtual scenario;

[0130] S3: Conduct in-loop testing and update the pose of the virtual vehicle in the virtual scenario;

[0131] S4: Repeat the testing;

[0132] S5: Conduct new scenario testing.

[0133] Optionally, step S1 includes the following steps:

[0134] S11: Configure the host computer, rapid prototyping machine, vehicle, integrated navigation, and communication module, and synchronize test data in real time;

[0135] S12: Select and load a historical scenario file reproduced based on real vehicle environment data;

[0136] S13: Configure the CAN communication module in the rapid prototyping machine to collect, including but not limited to, chassis, vehicle body, and positioning information;

[0137] S14: Load and configure the positioning calibration module in the rapid prototyping machine;

[0138] S15: Load the intelligent driving algorithm module in the rapid prototyping machine, compile and generate a real-time file, and set the rapid prototyping machine to start automatically when powered on.

[0139] Furthermore, the real-time synchronization of test data in step S11 depends on communication methods such as the CAN network, cellular network, and Ethernet. The network topology diagram is as Figure 4 shown, and specifically includes the following steps:

[0140] S111: Connect the host computer and the rapid prototyping machine using Ethernet communication, and connect the rapid prototyping machine to the chassis and vehicle body through the CAN network;

[0141] S112: Use the communication module to receive the real-time pose of the vehicle from the vehicle remote monitoring center and send it to the rapid prototyping machine;

[0142] S113: Solve the data congestion problem caused by parallel transmission of multiple data streams to meet the requirements of real-time synchronous transmission.

[0143] Specifically, the methods for solving the data congestion problem in step S113 include, but are not limited to, external devices such as network bridges.

[0144] Further, the historical scenario file used in step S12 is a scenario file based on the collection by in-vehicle sensors, offline processing by the host computer, and online playback. The data of this file comes from the real driving environment. The in-vehicle sensors include, but are not limited to, lidar, millimeter-wave radar, ultrasonic radar, cameras, etc. This file also records all the scenario information of the host vehicle, static, and dynamic traffic participants. These scenario information include, but are not limited to, the ID, category, outline dimensions, entry time into the scenario, exit time from the scenario, motion trajectory, heading angle, etc. of the traffic participants.

[0145] Further, on the one hand, the positioning information collected in step S13 can be used by the scenario model running in the host computer to achieve the purpose of receiving and updating the positioning information of the host vehicle in the virtual scenario in real time, so that the system has a good scenario visualization effect; on the other hand, the positioning information can be used by the motion control module to design and implement intelligent driving functions. In addition, the vehicle body information includes, but is not limited to, the wiper state, seat belt, etc., which can be used as the vehicle body conditions for the decision-making module.

[0146] Further, step S14 can realize that test experiments can be carried out on any site. The scenarios used for testing include, but are not limited to, the scenarios required by standards and regulations and the scenarios reproduced by real vehicle data. The specific steps are as follows:

[0147] S141: Read and input the pose of the host vehicle at the current moment, and convert the longitude and latitude coordinates into coordinates (X, Y, Yaw, V X , V Y , Psi) in the high-precision map through coordinate transformation;

[0148] S142: Obtain the historical pose (X l , Y l , Yaw l , V Xl , V Yl , Psi l ) of the host vehicle in the to-be-tested scenario and configure it as the target pose (X i , Y i , Yaw i , V Xi , V Yi , Psi i , i = 1, 2, 3,...) of the host vehicle in this test scenario;

[0149] S143: Calculate the actual pose (X, Y, Yaw, V X , V Y , Psi) of the test vehicle at the initial moment and the target pose (X i , Y i , Yaw i , V Xi , V Yi , Psii ) the position offset (a 1 , a 2 , a 3 , a 4 , a 5 , a 6 ), and configure it as a pose transformation parameter to be used for calibrating the current pose of the test vehicle in real time in this test scenario. The relationship between the actual pose, the target pose, the historical pose, and the position offset is as follows.

[0150]

[0151] Optionally, step S2 includes the following steps:

[0152] S21: Start the rapid prototyping machine, run the scenario software in the upper computer, and the upper computer sends virtual scenario information to the rapid prototyping machine;

[0153] S22: The driver drives the test vehicle according to the test requirements, and the rapid prototyping machine calculates and generates warning and control instructions and sends them to the test vehicle.

[0154] Furthermore, the virtual scenario information in step S21 can be sent to the rapid prototyping machine via Ethernet by the API of the scenario software.

[0155] Furthermore, the warning instructions generated in step S22 are executed for sound and light warnings by the cockpit display screen or buzzer, and the control instructions include but are not limited to acceleration, braking, steering, etc.

[0156] Preferably, step S3 includes the following steps:

[0157] S31: The test vehicle receives the control instructions from the rapid prototyping machine and forwards them to each target mechanism;

[0158] S32: Each target executing mechanism executes the control instructions and feeds back the status signals of the target mechanism to the control module in the rapid prototyping machine;

[0159] S33: The rapid control prototype machine receives the new self-vehicle pose at the current moment and forwards it to the virtual scenario interface and the planning module in the upper computer at the same time, in order to achieve the purpose of real-time updating of the current pose of the virtual self-vehicle model and real-time planning;

[0160] S34: The system repeats steps S31 to S33 until the test vehicle stops or does not meet the test requirements and terminates this round of testing;

[0161] Furthermore, the target mechanisms in step S31 include but are not limited to the drive system, the braking system, and the steering system.

[0162] Further, the target mechanism feedback signal in step S32 includes, but is not limited to, brake valve state, steering wheel angle, throttle opening, etc.

[0163] Further, the new self-pose in step S33 is the coordinate (X i , Y i , Yaw i , V Xi , V Yi , Psi i ) in the high-precision map after coordinate transformation.

[0164] Optionally, step S4 is used to repeat the test steps under the same test case, that is, the historical pose in step S142 has not changed. Specifically, it includes the following steps:

[0165] S41: Place the actual vehicle back into the real scene corresponding to the virtual scene to be tested, and reset the rapid prototyping machine;

[0166] S42: Repeat steps S2 to S3, retest, and record the test results.

[0167] Further, the corresponding real scene mentioned in step S41 refers to a scene similar to the previous test experiment. Here, it is not required that the positioning of the repeated experiment is strictly consistent. The positioning error can be overcome by the positioning calibration module in step S41, and resetting the prototype machine will not affect the parameters pre-configured in the positioning calibration module.

[0168] Preferably, step S5 is used to repeat the experiment under different test cases, that is, the historical pose (X l , Y l , Yaw l , V Xl , V Yl , Psi l ) in step S142 has changed. Specifically, it includes the following steps:

[0169] S51: Place the actual vehicle in a new scene to be tested, and re-execute step S14;

[0170] S52: Repeat steps S2 - S3, retest, and record the test results.

[0171] Further, the purpose of updating the scene to be tested in step S51 is to update the historical pose.

[0172] Therefore, the virtual test scenario can save the cost of scenario construction and ensure test safety; the actual driving scenarios with high complexity, strong continuity, and high authenticity are involved in the test, which can improve the authenticity of scenario data; the scenario reproduction has strong repeatability, and the test scenario can be obtained at low cost; the real test scenario does not need to be exactly the same as the scenario file, and only the positioning and calibration module needs to be configured, which saves the cost of scenario reproduction to a certain extent; the architecture scheme of host computer - rapid prototyping machine - real vehicle can improve the reliability of test results under the condition of ensuring test real-time performance.

[0173] Specifically, the present invention can use the virtual test scenario to replace the actual test scenario. On the one hand, it saves the cost of scenario design, and on the other hand, it can greatly improve the safety of scenario testing. This method only needs to configure scenario elements in the scenario software to complete various test scenarios, making the scenario construction work simple and easy to start.

[0174] The virtual scenario used in the present invention is derived from the driving environment data collected by the real vehicle, and has the characteristics of continuity, complexity, and conforming to real driving habits. This method can avoid the problems of single and overly idealized scenarios under the standard design scenario as much as possible, which is beneficial to simulation testing to obtain the conditions required for vehicle driving in a discontinuous scenario.

[0175] The scenario data used in the present invention is derived from in-vehicle sensors, which can realize the low-cost acquisition of scenario data. A large amount of scenario data can be obtained without vehicle-road-cloud collaboration, which is suitable for the current development stage of autonomous driving technology. In addition, the present invention is provided with a positioning and calibration module, which enables the vehicle not to be limited to the test site exactly the same as the scenario file during the test. Only when the site is empty and meets the test requirements, and the pose transformation parameters are configured during use. At the same time, the present invention adopts the architecture scheme of host computer - rapid prototyping machine - real vehicle, which can overcome the data delay problem on the communication transmission chain to a certain extent, provide good real-time communication conditions for the system, and in addition, the real vehicle application method better avoids the disadvantage of insufficient reliability of bench tests.

[0176] In an embodiment of the present application, the reliability of the ADAS function can be tested by using the intelligent driving vehicle-in-the-loop test method and system. The experimental vehicle used is a bus, and the transmission devices installed on the vehicle include a forward binocular camera, blind area detection cameras on both the left and right sides, image acquisition cameras for blind areas on both the left and right sides, ultrasonic radars, integrated navigation, a bridge, a gateway, a 5G communication module, a baseline real-time machine, and a test PC. The network topology diagram of the above devices is as Figure 5 shown.

[0177] In the preparation stage of the vehicle-in-the-loop test, first, components such as a test PC, baseline, instrument panels of a certain type of bus, integrated navigation, and 5G communication modules are configured to meet the requirement of real-time synchronization of test data. Among them, an Ethernet communication method is used to establish a data connection between the test PC and the baseline. The baseline communicates with the gateway, forward binocular cameras, and blind spot detection cameras on both sides of the bus via CAN communication. The gateway on the bus is used to forward the status of body devices such as seat belts and windshield wipers, as well as ultrasonic radar warnings, working status, and 5G communication content. The 5G communication module receives the real-time vehicle pose from the vehicle remote monitoring center and sends it to the baseline. To avoid data congestion caused by parallel transmission of multiple data streams, a bridge device is installed in front of the parallel CAN interfaces of the baseline to process data in real time.

[0178] After the equipment is configured, a historical scenario file reproduced based on real vehicle environment data needs to be selected and loaded. This historical scenario, as Figure 6 shown, includes a test vehicle, traffic participants, and a high-precision map. The traffic participants consist of two pedestrians O 1 and O 2 and a passenger car. There is one road and two lanes in the high-precision map. This scenario file belongs to the result of traffic participants after the fusion of vehicle-mounted lidar and cameras, and can output real-time poses of traffic participants, as well as scenario information such as lane width, number of lanes, road, and traffic light positions.

[0179] After determining the scenario file, the virtual scenario and the actual test scenario need to be combined to complete real-time vehicle pose positioning and scenario updating. This process is as Figure 7 shown. The initial pose of the test vehicle in the virtual historical scenario is (X l , Y l , Yaw l , V Xl , V Yl , Psi l ), and the initial pose in the actual scenario is (X, Y, Yaw, V X , V Y , Psi). The position offset (a 1 , a 2 , a 3 , a 4 , a 5 , a 6 ) can be calculated as follows.

[0180]

[0181] Therefore, the instantaneous self-vehicle pose calibrated by the positioning and calibration module can be calculated as follows.

[0182]

[0183] Where i is the true value at the current moment, i - 1 represents the previous moment. After configuring the positioning and calibration module, the intelligent driving algorithm to be tested needs to be loaded into the baseline.

[0184] In the loop test and obtain the control instruction based on the current virtual scenario link, the driver first drives the test vehicle to the test location, then starts the baseline and runs the scenario software on the test PC. Finally, the driver drives the test vehicle according to the test requirements, and the baseline calculates and generates early warning and control instructions in real time and sends them to the vehicle chassis. Among them, the virtual scenario information is generated by the API of the scenario software and sent down to the baseline via Ethernet. The early warning instruction is executed by the cockpit display screen or buzzer for sound and light warnings. The control instructions include acceleration, braking, steering and other instructions.

[0185] In the loop test and update the virtual vehicle pose in the virtual scenario link, the test vehicle first receives the control instruction from the baseline and forwards it to each target mechanism. Subsequently, the baseline receives the new self-vehicle pose at the current moment and forwards it to the virtual scenario interface and the planning module in the test PC at the same time, which is used to update the current pose of the virtual self-vehicle model and real-time planning. During this process, the system continuously executes this operation until the test vehicle stops or does not meet the test requirements and terminates this round of testing. Among them, the vehicle-end systems participating in the execution are the drive system, the braking system and the steering system, and the target mechanism feedback signals are the brake valve state, the steering wheel angle and the throttle opening.

[0186] In the repeated test link, the position offset in the positioning and calibration module remains unchanged. It is only necessary to place the real vehicle back into the real scenario corresponding to the virtual scenario to be tested, reset the rapid prototype machine, and repeat the loop test and obtain the control instruction based on the current virtual scenario link and the loop test and update the virtual vehicle pose in the virtual scenario link.

[0187] In the new scenario test link, the position offset in the positioning and calibration module has changed. It is necessary to first place the real vehicle in the new scenario to be tested or update the historical pose in the scenario to be tested, then reconfigure the positioning and calibration module, and finally repeat the loop test and obtain the control instruction based on the current virtual scenario link and the loop test and update the virtual vehicle pose in the virtual scenario link.

[0188] It should be noted that the data acquisition devices used in the present invention include, but are not limited to, lidar, millimeter-wave radar, ultrasonic radar, monocular camera, binocular camera, etc.; the high-precision map formats used in the present invention include, but are not limited to, OpenDrive, OpenStreetMap, HERE HD Live Map, etc.; the scenario file formats used in the present invention include, but are not limited to, OpenScenario; the applicable scenarios of the present invention include, but are not limited to, open roads, closed parks, test roads, etc.; the ego vehicle mentioned in the present invention includes, but is not limited to, passenger vehicles, commercial vehicles, engineering vehicles, unmanned vehicles, etc.; the scenario design or simulation software used in the present invention includes, but is not limited to, CARLA, PreScan, RoadRunner, Matlab / Simulink, etc.; the rapid control prototyping machines used in the present invention include, but are not limited to, Baseline, Performance, dSpace, etc.

[0189] An embodiment of the present application provides an intelligent driving vehicle test device, including:

[0190] A driving scenario configuration unit, configured to load a corresponding virtual driving scenario for an intelligent driving vehicle located in an actual driving scenario in response to an intelligent driving test instruction;

[0191] A first real-time pose information acquisition unit, configured to acquire first real-time pose information of the intelligent driving vehicle in the actual driving scenario;

[0192] A second real-time pose information determination unit, configured to determine second real-time pose information of the intelligent driving vehicle in the virtual driving scenario based on the first real-time pose information;

[0193] An automatic driving adjustment strategy generation unit, configured to generate an automatic driving adjustment strategy based on the second real-time pose information, the real-time driving environment information provided by the virtual driving scenario, and a preset intelligent driving algorithm;

[0194] An automatic driving adjustment strategy execution unit, configured to control the intelligent driving vehicle to execute the automatic driving adjustment strategy in the virtual driving scenario and the actual driving scenario respectively.

[0195] In an embodiment of the present application, optionally, the second real-time pose information determination unit is configured to:

[0196] Determine the second real-time pose information of the intelligent driving vehicle in the virtual driving scenario based on the pose offset information between the actual driving scenario and the virtual driving scenario and the first real-time pose information.

[0197] In an embodiment of the present application, optionally, the device further includes:

[0198] An initial pose information acquisition unit, configured to obtain first initial pose information of the intelligent driving vehicle in the actual driving scenario and second initial pose information in the virtual driving scenario when loading a corresponding virtual driving scenario for the intelligent driving vehicle located in the actual driving scenario;

[0199] A first determination unit, configured to determine pose offset information of the intelligent driving vehicle between the actual driving scenario and the virtual driving scenario based on the difference between the first initial pose information and the second initial pose information.

[0200] In an embodiment of the present application, optionally, the device further includes:

[0201] An initial pose information acquisition unit, configured to obtain first initial pose information of the intelligent driving vehicle in the actual driving scenario and second initial pose information in the virtual driving scenario when loading a corresponding virtual driving scenario for the intelligent driving vehicle located in the actual driving scenario;

[0202] A difference acquisition unit, configured to obtain the difference between the first initial pose information and the second initial pose information;

[0203] A first difference adjustment coefficient determination unit, configured to determine a first difference adjustment coefficient corresponding to the virtual driving scenario based on the type of the virtual driving scenario;

[0204] A second determination unit, configured to determine pose offset information of the intelligent driving vehicle between the actual driving scenario and the virtual driving scenario based on the difference between the first initial pose information and the second initial pose information, and the first difference adjustment coefficient.

[0205] In an embodiment of the present application, optionally, the device further includes:

[0206] An initial pose information acquisition unit, configured to obtain first initial pose information of the intelligent driving vehicle in the actual driving scenario and second initial pose information in the virtual driving scenario when loading a corresponding virtual driving scenario for the intelligent driving vehicle located in the actual driving scenario;

[0207] A difference acquisition unit, configured to obtain the difference between the first initial pose information and the second initial pose information;

[0208] A scene difference degree determination unit, configured to determine the scene difference degree between the actual driving scenario and the virtual driving scenario based on preset scene coefficients corresponding to the actual driving scenario and the virtual driving scenario respectively;

[0209] A second difference adjustment coefficient determination unit, configured to determine a second difference adjustment coefficient based on the scene difference degree;

[0210] A third determination unit, configured to determine the pose offset information of the intelligent driving vehicle between the actual driving scene and the virtual driving scene based on the difference between the first initial pose information and the second initial pose information, and the second difference adjustment coefficient.

[0211] In an embodiment of the present application, optionally, the driving scene configuration unit includes:

[0212] A virtual-real combined simulation system construction unit, configured to build a virtual-real combined simulation system for the intelligent driving vehicle, where the virtual-real combined simulation system includes a host computer, a rapid prototyping machine, the intelligent driving vehicle, a combined navigation module, and a communication module,

[0213] The host computer is configured to load a virtual driving scene file reproduced from real vehicle environment data and display the virtual driving scene corresponding to the virtual driving scene file, where the virtual driving scene file includes environment information and motion association information of historical traffic participants in the virtual driving scene;

[0214] The combined navigation module is configured to locate the intelligent driving vehicle;

[0215] The rapid prototyping machine is configured to run the preset intelligent driving algorithm based on the information provided by the host computer, the intelligent driving vehicle, and the combined navigation module respectively, and control each target execution mechanism of the intelligent driving vehicle to execute the corresponding automatic driving adjustment strategy based on the operation result;

[0216] The host computer, the rapid prototyping machine, the intelligent driving vehicle, and the combined navigation module are connected through the communication module.

[0217] In an embodiment of the present application, optionally, the automatic driving adjustment strategy execution unit is configured to:

[0218] Send control instructions required for the automatic driving adjustment strategy to the drive system, braking system, and steering system of the intelligent driving vehicle; send warning instructions to the warning module of the intelligent driving vehicle.

[0219] This device uses the solution described in any one of the above embodiments, and therefore has all the above technical effects, which will not be elaborated here.

[0220] In addition, in an embodiment, the present application provides a computer device, which may be a server, and its internal structure diagram may be as Figure 8As shown in the figure. The computer device includes a processor, a memory, a network interface, and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client through a network connection. When the computer program is executed by the processor, it can implement the method described in any of the above embodiments.

[0221] In one embodiment, the present application also provides a computer device, which may be a client, and its internal structure diagram may be as shown in Figure 9 As shown in the figure. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external server through a network connection. When the computer program is executed by the processor, it can implement the method described in any of the above embodiments.

[0222] Any of the above computer devices in the embodiments of the present application exists in various forms, including but not limited to:

[0223] (1) Mobile communication devices: The characteristics of such devices are that they have mobile communication functions and mainly aim to provide voice and data communication. Such terminals include: smart phones (such as iPhone), multimedia phones, functional phones, and low-end phones, etc.

[0224] (2) Ultra-mobile personal computer devices: Such devices belong to the category of personal computers, have computing and processing functions, and generally also have the characteristics of mobile Internet access. Such terminals include: PDA, MID, and UMPC devices, etc., such as iPad.

[0225] (3) Portable entertainment devices: Such devices can display and play multimedia content. Such devices include: audio and video players (such as iPod), handheld game consoles, e-books, and smart toys, wearable devices, and portable vehicle navigation devices.

[0226] (4) Server: A device that provides computing services. The components of a server include a processor, hard disk, memory, system bus, etc. A server is similar to a general computer architecture, but due to the need to provide highly reliable services, it has higher requirements in terms of processing power, stability, reliability, security, scalability, manageability, etc.

[0227] (5) Other electronic devices with data interaction functions.

[0228] In addition, an embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions, and the computer-executable instructions are used to perform the following steps:

[0229] In response to an intelligent driving test instruction, load a corresponding virtual driving scenario for an intelligent driving vehicle located in an actual driving scenario;

[0230] Obtain first real-time pose information of the intelligent driving vehicle in the actual driving scenario;

[0231] Based on the first real-time pose information, determine second real-time pose information of the intelligent driving vehicle in the virtual driving scenario;

[0232] Based on the second real-time pose information, real-time driving environment information provided by the virtual driving scenario, and a preset intelligent driving algorithm, generate an autonomous driving adjustment strategy;

[0233] Control the intelligent driving vehicle to execute the autonomous driving adjustment strategy in the virtual driving scenario and the actual driving scenario respectively.

[0234] It should be noted that the functions or steps that the above computer-readable storage medium or computer device can achieve can be referred to the relevant descriptions in the foregoing method embodiments. To avoid repetition, they will not be described in detail here.

[0235] The technical solution of the present application has been described in detail above in conjunction with the accompanying drawings. Through the technical solution of the present application, on the basis of combining the virtual driving scenario with the actual driving scenario for remote testing, there is no need to reproduce the actual driving scenario consistent with the virtual driving scenario, but only need to control the intelligent driving vehicle in a general test site to move according to the real-time driving environment information provided by the virtual driving scenario, and the same result as driving the intelligent driving vehicle in the actual scenario corresponding to the virtual driving scenario can be obtained. In other words, there is no need to reproduce a complex scenario for the intelligent driving vehicle, but let it obtain the data possessed by the complex scenario in a general actual driving scenario, and the effect of testing the intelligent driving vehicle in the complex scenario can be achieved. At the same time, in the present application, considering the differences between the virtual driving scenario and the actual driving scenario, after correcting the first real-time pose information of the intelligent driving vehicle in the actual driving scenario, the second real-time pose information of the intelligent driving vehicle in the virtual driving scenario is obtained, so as to reduce the error caused by data conversion between the virtual driving scenario and the actual driving scenario during the testing process and improve the accuracy of the test results.

[0236] Depending on the context, the word "if" as used herein can be interpreted as "when" or "while" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if determined" or "if detected (stated condition or event)" can be interpreted as "when determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)".

[0237] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. The singular forms "a", "the" and "said" used in the embodiments of the present application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0238] In several embodiments provided by the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms.

[0239] In addition, in each of the embodiments of the present application, the functional units may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware, or in the form of a hardware plus software functional unit.

[0240] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it may include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application may include non-volatile and / or volatile memories. Non-volatile memories may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0241] The above-described 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 foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for testing an intelligent driving vehicle, characterized in that: include: In response to the intelligent driving test instruction, loading a corresponding virtual driving scene for the intelligent driving vehicle in the actual driving scene; Acquire first real-time position information of the intelligent driving vehicle in the actual driving scene; Based on the first real-time position information, determining second real-time position information of the intelligent driving vehicle in the virtual driving scene; Generate an automatic driving adjustment strategy based on the second real-time posture information, the real-time driving environment information provided by the virtual driving scene, and a preset intelligent driving algorithm; Controlling the intelligent driving vehicle to execute the automatic driving adjustment strategy in the virtual driving scenario and the actual driving scenario respectively; The determining, based on the first real-time posture information, second real-time posture information of the intelligent driving vehicle in the virtual driving scene includes: Determining second real-time posture information of the intelligent driving vehicle in the virtual driving scene based on the posture offset information between the actual driving scene and the virtual driving scene and the first real-time posture information; When loading the corresponding virtual driving scene for the intelligent driving vehicle in the actual driving scene, it also includes: Acquire first initial position information of the intelligent driving vehicle in the actual driving scene and second initial position information of the intelligent driving vehicle in the virtual driving scene; Obtaining a difference between the first initial posture information and the second initial posture information; Determining a scene difference between the actual driving scene and the virtual driving scene based on preset scene coefficients corresponding to the actual driving scene and the virtual driving scene respectively; Based on the scene difference, determining a second difference adjustment coefficient, wherein a square root of the scene difference is determined as the second difference adjustment coefficient; Based on the difference between the first initial posture information and the second initial posture information, and the second difference adjustment coefficient, the posture offset information of the intelligent driving vehicle between the actual driving scene and the virtual driving scene is determined.

2. The method according to claim 1, characterized in that When loading the corresponding virtual driving scene for the intelligent driving vehicle in the actual driving scene, it also includes: Acquire first initial position information of the intelligent driving vehicle in the actual driving scene and second initial position information of the intelligent driving vehicle in the virtual driving scene; The difference between the first initial posture information and the second initial posture information is used to determine the posture offset information of the intelligent driving vehicle between the actual driving scene and the virtual driving scene.

3. The method according to claim 1, characterized in that When loading the corresponding virtual driving scene for the intelligent driving vehicle in the actual driving scene, it also includes: Acquire first initial position information of the intelligent driving vehicle in the actual driving scene and second initial position information of the intelligent driving vehicle in the virtual driving scene; Obtaining a difference between the first initial posture information and the second initial posture information; Determining a first difference adjustment coefficient corresponding to the virtual driving scene based on the type of the virtual driving scene; Based on the difference between the first initial posture information and the second initial posture information, and the first difference adjustment coefficient, the posture offset information of the intelligent driving vehicle between the actual driving scene and the virtual driving scene is determined.

4. The method according to any one of claims 1 to 3, characterized in that The method of loading a corresponding virtual driving scene for an intelligent driving vehicle in an actual driving scene includes: A virtual-reality combined simulation system is built for the intelligent driving vehicle, wherein the virtual-reality combined simulation system includes a host computer, a rapid prototyping machine, the intelligent driving vehicle, a combined navigation module and a communication module. The host computer is used to load a virtual driving scene file reproduced by real vehicle environment data and display the virtual driving scene corresponding to the virtual driving scene file, wherein the virtual driving scene file includes environment information and movement association information of historical traffic participants in the virtual driving scene; The combined navigation module is used to locate the intelligent driving vehicle; The rapid prototyping machine is used to run the preset intelligent driving algorithm based on the information provided by the host computer, the intelligent driving vehicle and the integrated navigation module, and control each target actuator of the intelligent driving vehicle to execute the corresponding automatic driving adjustment strategy based on the running result; The host computer, the rapid prototype machine, the intelligent driving vehicle and the combined navigation module are connected via the communication module.

5. The method according to claim 4, characterized in that The controlling each target execution mechanism of the intelligent driving vehicle to execute a corresponding automatic driving adjustment strategy includes: Sending control instructions required for the automatic driving adjustment strategy to the driving system, braking system and steering system of the intelligent driving vehicle; Sending a warning instruction to the warning module of the intelligent driving vehicle.

6. An intelligent driving vehicle testing device, characterized in that: include: A driving scenario configuration unit, configured to load a corresponding virtual driving scenario for an intelligent driving vehicle in an actual driving scenario in response to an intelligent driving test instruction; A first real-time position and posture information acquisition unit, used to acquire first real-time position and posture information of the intelligent driving vehicle in the actual driving scene; A second real-time posture information determining unit, configured to determine second real-time posture information of the intelligent driving vehicle in the virtual driving scene based on the first real-time posture information; an automatic driving adjustment strategy generating unit, configured to generate an automatic driving adjustment strategy based on the second real-time posture information, the real-time driving environment information provided by the virtual driving scene, and a preset intelligent driving algorithm; An automatic driving adjustment strategy execution unit, used to control the intelligent driving vehicle to execute the automatic driving adjustment strategy in the virtual driving scene and the actual driving scene respectively; The second real-time posture information determination unit is used for: Determining second real-time posture information of the intelligent driving vehicle in the virtual driving scene based on the posture offset information between the actual driving scene and the virtual driving scene and the first real-time posture information; An initial posture information acquisition unit, configured to acquire, when loading a corresponding virtual driving scene for an intelligent driving vehicle in an actual driving scene, first initial posture information of the intelligent driving vehicle in the actual driving scene and second initial posture information in the virtual driving scene; A difference acquisition unit, used to acquire a difference between the first initial posture information and the second initial posture information; a scene difference determination unit, configured to determine a scene difference between the actual driving scene and the virtual driving scene based on preset scene coefficients corresponding to the actual driving scene and the virtual driving scene respectively; a second difference adjustment coefficient determining unit, configured to determine a second difference adjustment coefficient based on the scene difference, wherein a square root of the scene difference is determined as the second difference adjustment coefficient; The third determination unit is used to determine the posture offset information of the intelligent driving vehicle between the actual driving scene and the virtual driving scene based on the difference between the first initial posture information and the second initial posture information, and the second difference adjustment coefficient.

7. A computer device, characterized in that: include: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores instructions executable by the at least one processor, and the instructions are configured to execute the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: Computer executable instructions are stored, and the computer executable instructions are used to execute the method according to any one of claims 1 to 5.

Images