Automatic driving test method, automatic driving test device, vehicle and storage medium

Abstract

The invention relates to the field of automatic driving, in particular to an automatic driving test method and device, a vehicle and a storage medium, and the method comprises the steps: determining a first driving scene corresponding to a vehicle platform and a second driving scene corresponding to a driving simulator; acquiring first driving data of a first operation object for operating the vehicle platform based on the first driving scene, wherein the first operation object is a driver or an automatic driving system; acquiring second driving data of a second operation object for operating the driving simulator based on the second driving scene, wherein the second operation object is a driver; and performing an automatic driving test according to the first driving data and / or the second driving data. Through deep coupling of the vehicle platform and the driving simulator, the driving data of the automatic driving system and the driver in the same driving scene or different driving scenes are obtained, the problems that the driving simulator cannot accurately restore the real response of the vehicle and the test scene is single are solved, and the effectiveness of the automatic driving test can be improved.

Description

Autonomous driving test method, autonomous driving test equipment, vehicle, and storage medium Technical Field

[0001] The present application relates to the field of autonomous driving, and in particular to an autonomous driving test method, autonomous driving test equipment, a vehicle, and a storage medium. Background Art

[0002] With the rapid development and continuous improvement of autonomous vehicle technology worldwide, it is particularly important to accurately, scientifically and comprehensively test and evaluate the various performance of test vehicles based on a test system that is completely independent of the test vehicle.

[0003] Currently, simulation testing using driving simulators is a common vehicle testing method. However, these simulators have limitations in modeling sensors and vehicle dynamics, making them unable to accurately reproduce the vehicle's actual responses, resulting in low effectiveness in autonomous driving testing. Furthermore, driving simulators can only test a single driving scenario, which differs significantly from real-world scenarios, further reducing the effectiveness of autonomous driving testing.

[0004] Therefore, how to improve the effectiveness of autonomous driving tests has become an urgent problem that needs to be solved.

[0005] Summary of the Invention

[0006] This application provides an autonomous driving test method, autonomous driving test equipment, vehicle and storage medium. By deeply coupling the vehicle platform and the driving simulator, driving data of the autonomous driving system and the driver in the same driving scenario or different driving scenarios are obtained, which solves the problems that the driving simulator cannot accurately restore the real response of the vehicle and the test scenario is single, and can improve the effectiveness of autonomous driving testing.

[0007] In a first aspect, the present application provides an autonomous driving test method, which is applied to a vehicle, wherein the vehicle includes a vehicle platform, an autonomous driving system, and a driving simulator. The method includes:

[0008] Determine a first driving scenario corresponding to the vehicle platform and a second driving scenario corresponding to the driving simulator; obtain first driving data of a first operating object operating the vehicle platform based on the first driving scenario, where the first operating object is the driver or the automatic driving system; obtain second driving data of a second operating object operating the driving simulator based on the second driving scenario, where the second operating object is the driver; and perform an automatic driving test based on the first driving data and / or the second driving data.

[0009] In a second aspect, the present application further provides an autonomous driving test device, the autonomous driving test device comprising a processor and a memory;

[0010] The memory is used to store computer programs;

[0011] The processor is used to execute the computer program and implement the autonomous driving test method as described above when executing the computer program.

[0012] On the third aspect, the present application also provides a vehicle, which includes a vehicle platform, an autonomous driving system, a driving simulator, a shooting device and the autonomous driving test equipment as described above.

[0013] In a fourth aspect, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the processor implements the autonomous driving test method as described above.

[0014] The present application discloses an autonomous driving test method, autonomous driving test equipment, a vehicle and a storage medium. By determining a first driving scenario corresponding to a vehicle platform and a second driving scenario corresponding to a driving simulator, the driving scenarios corresponding to the autonomous driving system and the driver can be obtained, wherein the driving scenarios corresponding to the two can be the same or different, and driving tests can be performed subsequently in the same driving scenario or different driving scenarios; by obtaining first driving data of a first operating object manipulating the vehicle platform based on the first driving scenario, and obtaining second driving data of a second operating object manipulating the driving simulator based on the second driving scenario, and performing an autonomous driving test based on the first driving data and / or the second driving data, deep coupling of the vehicle platform and the driving simulator can be achieved, and driving data of the autonomous driving system and the driver in the same driving scenario or different driving scenarios can be obtained, which solves the problem that the driving simulator cannot accurately restore the real response of the vehicle and the test scenario is single, and can improve the effectiveness of the autonomous driving test. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0016] FIG1 is a schematic diagram of a vehicle provided in an embodiment of the present application;

[0017] FIG2 is a schematic diagram of an automatic driving system provided in an embodiment of the present application;

[0018] FIG3 is a schematic diagram of a driving simulator provided in an embodiment of the present application;

[0019] FIG4 is a schematic diagram of another vehicle provided in an embodiment of the present application;

[0020] FIG5 is a schematic diagram of another vehicle provided in an embodiment of the present application;

[0021] FIG6 is a schematic structural diagram of an autonomous driving test device provided in an embodiment of the present application;

[0022] FIG7 is a schematic flowchart of an autonomous driving testing method provided in an embodiment of the present application;

[0023] FIG8 is a schematic flowchart of another autonomous driving test method provided in an embodiment of the present application;

[0024] FIG9 is a schematic flowchart of another autonomous driving test method provided in an embodiment of the present application;

[0025] FIG10 is a schematic flowchart of another autonomous driving test method provided in an embodiment of the present application;

[0026] FIG11 is a schematic flowchart of another autonomous driving test method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0028] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined, or partially merged, so the actual execution order may vary depending on the actual situation.

[0029] It should be understood that the terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0030] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0031] The embodiments of the present application provide an autonomous driving test method, autonomous driving test equipment, a vehicle, and a storage medium. The autonomous driving test method can be applied to the autonomous driving test equipment. By deeply coupling the vehicle platform and a driving simulator, driving data from the autonomous driving system and the driver in the same or different driving scenarios can be obtained. This solves the problems of the driving simulator's inability to accurately reproduce the vehicle's actual response and the singleness of the test scenarios, thereby improving the effectiveness of autonomous driving tests.

[0032] For example, the autonomous driving test equipment may include a server or a terminal. The server may be a standalone server or a server cluster. The terminal may be an electronic device such as a smartphone, tablet computer, laptop computer, or desktop computer.

[0033] For example, the autonomous driving test equipment can be set inside the vehicle or outside the vehicle. In the embodiment of the present application, the autonomous driving test equipment is set inside the vehicle as an example to illustrate how to obtain driving data.

[0034] Please refer to Figure 1, which is a schematic diagram of a vehicle 10 provided in an embodiment of the present application. As shown in Figure 1, the vehicle 10 may include a vehicle platform 11, an autonomous driving system 12, a driving simulator 13, a camera 14, and an autonomous driving test device 15.

[0035] It should be noted that the vehicle 10 is a complete vehicle, for example, a vehicle that can be driven or work normally. The vehicle platform 11 may include a steering device, a braking device, an acceleration device, a gear shifting device, and the like. Among them, the steering device is used to control the steering of the vehicle 10, such as the steering wheel assembly of the vehicle 10. The braking device is used to control the deceleration and stopping of the vehicle 10 during driving, such as the brake pedal of the vehicle 10. The acceleration device is used to control the acceleration or deceleration of the vehicle 10. The gear shifting device is used to control the gear switching of the vehicle 10, such as the gear lever of the vehicle 10, and the like. In the embodiment of the present application, the vehicle 10 may also be referred to as a real vehicle.

[0036] The automated driving system 12 refers to a system comprised of hardware and software that can continuously perform all dynamic driving tasks, regardless of operating conditions. For example, the automated driving system 12 refers to a system comprised of hardware and software that can continuously perform some or all dynamic driving tasks (DDTs). Dynamic driving tasks are the perception, decision-making, and execution required to operate a vehicle in road traffic.

[0037] Please refer to Figure 2, which is a schematic diagram of an autonomous driving system 12 provided in an embodiment of the present application. As shown in Figure 2, the autonomous driving system 12 may include a sensor 120, a perception module 121, a planning module 122, and a control module 123, etc.

[0038] The sensors 120 may include, but are not limited to, laser radars, visual cameras, millimeter-wave radars, and ultrasonic radars. For example, a visual camera installed on the vehicle 10 is used to collect image information around the vehicle 10. For another example, a laser radar installed on the vehicle 10 is used to collect point cloud information around the vehicle 10.

[0039] It should be noted that the sensor 120 is used to obtain external sensor information and perform preprocessing. The perception module 121 is used to perform operations such as target recognition, tracking, positioning, state perception, and mapping on the sensor information obtained by the sensor 120. The planning module 122 is used to perform operations such as prediction, global path planning, behavior planning, and trajectory planning on the perception information of the perception module 121, and output trajectory information. The control module 123 is used to perform vehicle control calculations based on the trajectory information output by the planning module 122, obtain control results such as the steering, braking, and acceleration input signals of the vehicle, and output the control results to the vehicle platform 11.

[0040] In the embodiment of the present application, as shown in FIG2 , the autonomous driving system 12 can obtain external sensor information through a sensor 120 and can also obtain external sensor information through a human-machine interaction device 124. The human-machine interaction device 124 can be a drone.

[0041] In the embodiment of the present application, the driving simulator 13 may include, but is not limited to, a compact driving simulator, a full-vehicle driving simulator, or a high-performance driving simulator. Among them, a compact driving simulator uses a simulated driver's seat and is generally equipped with an LCD display, a manual or automatic transmission, a handbrake, and a steering wheel with force feedback; a full-vehicle driving simulator uses a real vehicle, equipped with a six-degree-of-freedom motion platform, and a ring-shaped display system; a high-performance driving simulator uses a real vehicle or a portion of a real vehicle, equipped with a high-speed motion system to simulate vehicle motion, and uses a ring-shaped display system.

[0042] Please refer to Figure 3, which is a schematic diagram of a driving simulator 13 provided in an embodiment of the present application. As shown in Figure 3, the driving simulator 13 may include a control mechanism 130, a data acquisition module 131, a control center 132, a traffic simulation module 133, visual software 134, a display device 135, and an actuator 136.

[0043] The control mechanism 130 is used to receive driver inputs and generate corresponding input signals, which may include steering inputs, braking inputs, acceleration inputs, and so on. The data acquisition module 131 may include, but is not limited to, pressure sensors, gravity sensors, speed sensors, and other sensors for collecting driver inputs. Sensors installed on the control mechanism 130 perform pre-processing, such as filtering, on the driver's input signals. For example, the data acquisition module 131 may be installed on the steering wheel to monitor whether the driver operates the steering wheel during autonomous driving. Another example is that the data acquisition module 131 may be installed on the vehicle to monitor whether the driver brakes the vehicle during autonomous driving. The control center 132 calculates the vehicle's motion posture based on the input signals based on the vehicle's kinematic or dynamic model, and obtains the vehicle's motion posture. Based on the motion posture output by the control center 132, the traffic simulation module 133 updates the vehicle's motion posture in the simulation scene using the vehicle's motion posture system. It also calculates changes in the motion postures of other vehicles based on pre-set driver models and updates the simulation scene. The visual software 134 models and renders the traffic simulation data in three-dimensional space. The display device 135 may include a display screen, a VR device, a projection device, etc., and is used to realistically display the scene rendered by the vision software 134 to obtain a virtual driving scene.

[0044] As shown in Figure 3, the driver can operate according to the responses of the vehicle platform 11 and the display device 135. The actuator 136 is used to execute the vehicle motion posture output by the control center 132 and feedback it to the driver, and is used to manipulate the vehicle platform 11 according to the vehicle motion posture output by the control center 132.

[0045] The camera 14 is used to capture the driving scene around the vehicle 10 to obtain a real driving scene. For example, the camera 14 can capture the scene in front of the vehicle 10, the scene on the left side of the vehicle 10, and the scene on the right side of the vehicle 10, etc.

[0046] The autonomous driving test equipment 15 is used to collect operational data from the vehicle platform 11, driving data from the autonomous driving system 12, and driving data from the driving simulator 13. For example, the equipment may collect first driving data from the autonomous driving system 12 manipulating the vehicle platform 11 based on a first driving scenario; or second driving data from the driver manipulating the driving simulator 13 based on a second driving scenario. The first and second driving scenarios may be real driving scenarios captured by the camera 14 or virtual driving scenarios displayed on the display screen of the driving simulator 13.

[0047] Please refer to Figure 4, which is a schematic diagram of another vehicle 10 provided in an embodiment of the present application. As shown in Figure 4, a driving simulator 13 can be installed in the passenger seat of vehicle 10, allowing the driver to directly observe the actual driving scene. Of course, when the driving simulator 13 is installed in the passenger seat of vehicle 10, the driver can also view the actual driving scene through the display screen of the driving simulator 13.

[0048] Please refer to Figure 5, which is a schematic diagram of another vehicle 10 provided in an embodiment of the present application. As shown in Figure 5, a driving simulator 13 can be installed in the rear seat of the vehicle 10. In this case, the driver can view the real driving scene through the display screen of the driving simulator 13.

[0049] Please refer to Figure 6, which is a schematic diagram of the structure of an autonomous driving test device 15 provided in an embodiment of the present application. As shown in Figure 6, the autonomous driving test device 15 may include a processor 1001 and a memory 1002, wherein the processor 1001 and the memory 1002 may be connected via a bus, such as an I2C (Inter-Integrated Circuit) bus or any other suitable bus.

[0050] Memory 1002 may include a storage medium and an internal memory. The storage medium may store an operating system and a computer program. The computer program includes program instructions that, when executed, cause the processor to perform any of the autonomous driving test methods.

[0051] Among them, the processor 1001 is used to provide computing and control capabilities to support the operation of the entire autonomous driving test equipment 15.

[0052] The processor 1001 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0053] In one embodiment, the processor 1001 is configured to run a computer program stored in the memory 1002 to implement the following steps:

[0054] Determine a first driving scenario corresponding to the vehicle platform and a second driving scenario corresponding to the driving simulator; obtain first driving data of a first operating object operating the vehicle platform based on the first driving scenario, where the first operating object is the driver or the automatic driving system; obtain second driving data of a second operating object operating the driving simulator based on the second driving scenario, where the second operating object is the driver; and perform an automatic driving test based on the first driving data and / or the second driving data.

[0055] In one embodiment, the first driving scene is a real driving scene captured by a camera, and the first operating object is the autonomous driving system; when acquiring first driving data of the first operating object manipulating the vehicle platform based on the first driving scene, the processor 1001 is configured to implement:

[0056] The first driving data obtained by the automatic driving system manipulating the vehicle platform based on the real driving scenario is collected.

[0057] In one embodiment, the second driving scenario is a real driving scenario; when acquiring the second driving data of the second operation object manipulating the driving simulator based on the second driving scenario, the processor 1001 is configured to implement:

[0058] The second driving data obtained by the driver operating the driving simulator based on the real driving scenario is collected.

[0059] In one embodiment, the second driving scene is a virtual driving scene displayed by the driving simulator; when obtaining second driving data of the second operating object operating the driving simulator based on the second driving scene, the processor 1001 is configured to implement:

[0060] The second driving data obtained by the driver operating the driving simulator based on the virtual driving scene is collected.

[0061] In one embodiment, the processor 1001 is further configured to implement:

[0062] Acquire real motion parameters, which are the motion parameters of the vehicle when the autonomous driving system manipulates the vehicle platform based on the real driving scenario; acquire virtual motion parameters, which are the motion parameters corresponding to the simulated vehicle in the driving simulator when the driver operates the driving simulator based on the virtual driving scenario; and perform motion compensation on the driving simulator based on the virtual motion parameters and the real motion parameters.

[0063] In one embodiment, when performing motion compensation on the driving simulator according to the virtual motion parameters and the real motion parameters, the processor 1001 is configured to implement:

[0064] A difference is calculated based on the virtual motion parameter and the real motion parameter to obtain a motion parameter difference; and motion compensation is performed on the driving simulator based on the motion parameter difference.

[0065] In one embodiment, the processor 1001 is further configured to implement:

[0066] Based on a preset interval time, the virtual driving scene is updated according to the real driving scene.

[0067] In one embodiment, the first driving scene is a virtual driving scene displayed by the driving simulator, and the first operating subject is the driver; before obtaining first driving data of the first operating subject manipulating the vehicle platform based on the first driving scene, the processor 1001 is further configured to:

[0068] The driving simulator is switched to a dual-control mode, wherein the dual-control mode is used for the driver to control the vehicle platform through the driving simulator, and for the driver to control the simulated vehicle in the driving simulator through the driving simulator.

[0069] In one embodiment, when acquiring first driving data of a first operating object manipulating the vehicle platform based on the first driving scene, the processor 1001 is configured to implement:

[0070] The first driving data obtained by the driver manipulating the vehicle platform through the driving simulator based on the virtual driving scene is collected.

[0071] In one embodiment, the second driving scene is the virtual driving scene; when obtaining the second driving data of the second operating object operating the driving simulator based on the second driving scene, the processor 1001 is configured to implement:

[0072] The second driving data obtained by the driver manipulating the simulated vehicle in the driving simulator based on the virtual driving scene is collected.

[0073] In one embodiment, the processor 1001 is further configured to implement:

[0074] Acquire real motion parameters, where the real motion parameters are motion parameters of the vehicle when the driver manipulates the vehicle platform through the simulated driver based on the virtual driving scene; and update the virtual driving scene according to the real motion parameters.

[0075] In one embodiment, the real motion parameter includes real mileage information of the vehicle; when the processor 1001 updates the virtual driving scene according to the real motion parameter, it is configured to implement:

[0076] The mileage information of the simulated vehicle in the virtual driving scene is updated according to the real mileage information.

[0077] In one embodiment, the processor 1001 is further configured to implement:

[0078] Acquire third driving data obtained by the autonomous driving system performing simulated driving in a simulated environment; obtain fourth driving data obtained by the driver manipulating the vehicle platform through a simulated driver based on a real driving scenario; and perform an autonomous driving test based on the third driving data and / or the fourth driving data.

[0079] In one embodiment, when obtaining the third driving data obtained by the autonomous driving system performing simulated driving in a simulated environment, the processor 1001 is configured to implement:

[0080] Based on the real driving scenario, real sensor information corresponding to the vehicle is obtained; simulated driving data obtained by the automatic driving system performing simulated driving in the simulation environment according to the real sensor information is collected; and the fourth driving data is determined based on the simulated driving data.

[0081] In one embodiment, the drivers include a first driver and a second driver; the processor 1001 is further configured to implement:

[0082] When the autonomous driving system operates the vehicle platform based on a real driving scenario, if a takeover request from the autonomous driving system is received, the first driver is prompted to take over the vehicle platform.

[0083] In one embodiment, after prompting the first driver to take over the vehicle platform, the processor 1001 is further configured to:

[0084] When it is determined that the first driver fails to take over the driving task, the second driver is prompted to take over the vehicle platform through the driving simulator.

[0085] In one embodiment, after prompting the second driver to take over the vehicle platform through the driving simulator, the processor 1001 is further configured to:

[0086] Acquire fifth driving data and perform an autonomous driving test based on the fifth driving data, where the fifth driving data includes operating data of the vehicle platform, driving data of the autonomous driving system, driving data of the first driver, and driving data of the second driver.

[0087] The following describes some embodiments of the present application in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features therein may be combined with each other.

[0088] Please refer to Figure 7, which is a schematic flow chart of an autonomous driving test method provided in an embodiment of the present application. This autonomous driving test method can be applied to autonomous driving test equipment. By deeply coupling the vehicle platform and driving simulator, driving data from the autonomous driving system and the driver in the same or different driving scenarios is obtained. This solves the problems of driving simulators' inability to accurately reproduce the vehicle's real-world responses and the single nature of the test scenarios, thereby improving the effectiveness of autonomous driving tests. As shown in Figure 7, the autonomous driving test method includes steps S101 to S104.

[0089] Step S101: Determine a first driving scenario corresponding to the vehicle platform and a second driving scenario corresponding to the driving simulator.

[0090] It should be noted that, in the embodiments of the present application, driving scenes may include real driving scenes and virtual driving scenes. The real driving scene is the scene of the real environment seen by the driver or the scene of the real environment captured by a shooting device, for example, various scenes when a vehicle is driving on a real road. The virtual driving scene is a constructed virtual scene, which can be constructed based on the real driving scene. For example, constructing a virtual driving scene may include establishing a road logic layer, designing a simulation scene, adding simulated vehicles, and setting traffic flow information, etc. The specific construction process is not limited here.

[0091] For example, the first driving scene corresponding to the vehicle platform and the second driving scene corresponding to the driving simulator can be determined based on the user's selection operation. The first driving scene can be a real driving scene or a virtual driving scene; the second driving scene can be a real driving scene or a virtual driving scene. For example, based on the test requirements, the user can set the first driving scene corresponding to the vehicle platform as a real driving scene, and the second driving scene corresponding to the driving simulator as a real driving scene. In this way, the driving data of the autonomous driving system and the driver in the same driving scene can be collected simultaneously, realizing deep coupling between the vehicle platform and the driving simulator. For another example, based on the test requirements, the user can set the first driving scene corresponding to the vehicle platform as a real driving scene, and the second driving scene corresponding to the driving simulator as a virtual driving scene. In this way, the driving data of the autonomous driving system and the driver in different driving scenarios can be collected simultaneously.

[0092] For example, after determining a first driving scenario corresponding to the vehicle platform and a second driving scenario corresponding to the driving simulator, the first driving scenario corresponding to the vehicle platform and the second driving scenario corresponding to the driving simulator can be obtained. For example, if the first driving scenario is a real driving scenario, an image of the surrounding environment of the vehicle can be captured by a camera as the real driving scenario. If the operator is the driver, the driver can directly observe the real driving scenario. For another example, if the first driving scenario is a virtual driving scenario, a pre-built virtual driving scenario can be displayed on a display screen in the driving simulator.

[0093] It should be noted that when the driver directly observes the real driving scene, the driving simulator can be set up in the front seat of the vehicle, as shown in Figure 4. When the driver views the real driving scene captured by the camera through the display screen in the driving simulator, the driving simulator can be set up in the front or rear seat of the vehicle, as shown in Figure 4 or Figure 5.

[0094] By determining the first driving scenario corresponding to the vehicle platform and the second driving scenario corresponding to the driving simulator, the driving scenarios corresponding to the autonomous driving system and the driver can be obtained. The driving scenarios corresponding to the two can be the same or different, and subsequent driving tests can be carried out in the same driving scenario or different driving scenarios.

[0095] Step S102: Acquire first driving data of a first operating object operating the vehicle platform based on the first driving scenario, where the first operating object is a driver or the automatic driving system.

[0096] In an embodiment of the present application, driving data of a driver or an autonomous driving system manipulating a vehicle platform may be obtained.

[0097] In some embodiments, first driving data of a driver manipulating a vehicle platform based on a first driving scenario is obtained, where the first driving scenario can be a real driving scenario or a virtual driving scenario.

[0098] It should be noted that the first driving data may include the driver's operating behavior and vehicle driving information. The driver's operating behavior may include, but is not limited to, steering, braking, accelerating, and turning on the lights. The driving information may include, but is not limited to, the vehicle's trajectory, vehicle speed, braking information, steering information, and acceleration information.

[0099] In other embodiments, first driving data is obtained by the autonomous driving system manipulating the vehicle platform based on a first driving scenario. The first driving scenario can be a real driving scenario or a virtual driving scenario. When the first driving scenario is a real driving scenario, the autonomous driving system can receive the real driving scenario captured by a camera.

[0100] It should be noted that the first driving data may include the operating data of the autonomous driving system and the driving information of the vehicle. The operating data of the autonomous driving system may include, but is not limited to, sensor data, perception data, planning data, and control data. The driving information may include, but is not limited to, the vehicle's trajectory, vehicle speed, braking information, steering information, and acceleration information.

[0101] By obtaining the first driving data of the first operation object manipulating the vehicle platform based on the first driving scenario, the driving data of the autonomous driving system or the driver manipulating the vehicle platform based on a real driving scenario or a virtual driving scenario can be obtained, which solves the problem of a single test scenario and improves the effectiveness of the autonomous driving test.

[0102] Step S103: Acquire second driving data of a second operating object operating the driving simulator based on the second driving scenario, where the second operating object is the driver.

[0103] For example, second driving data of the driver operating the driving simulator based on a second driving scenario may be obtained, wherein the second driving scenario may be a real driving scenario or a virtual driving scenario.

[0104] For example, the second driving data of the driver operating the driving simulator based on a real driving scene is obtained. For another example, the second driving data of the driver operating the driving simulator based on a virtual driving scene is obtained.

[0105] It should be noted that the second driving data may include the driver's operating behavior and the driving information of the simulated vehicle. The driver's operating behavior may include, but is not limited to, steering, braking, accelerating, and turning on the lights. The driving information of the simulated vehicle may include, but is not limited to, the vehicle's trajectory, vehicle speed, braking information, steering information, and acceleration information.

[0106] It should be noted that the autonomous driving test method provided in the embodiments of the present application can be applied to a variety of scenarios. For example, in a first autonomous driving test scenario, first driving data of the autonomous driving system manipulating the vehicle platform based on the first driving scenario can be obtained, and second driving data of the driver manipulating the driving simulator based on the second driving scenario can be obtained. For another example, in a second autonomous driving test scenario, first driving data of the driver manipulating the vehicle platform based on the first driving scenario can be obtained, and second driving data of the driver manipulating the driving simulator based on the second driving scenario can be obtained. The first driving scenario and the second driving scenario can be real driving scenarios or virtual driving scenarios.

[0107] By obtaining the second driving data of the driver operating the driving simulator based on the second driving scenario, the second driving data of the driver operating the driving simulator based on the real driving scenario or the virtual driving scenario can be obtained, the test scenario is richer, and the effectiveness of subsequent autonomous driving tests is improved.

[0108] Step S104: Perform an automatic driving test based on the first driving data and / or the second driving data.

[0109] In the embodiments of the present application, after obtaining driving data, autonomous driving testing can be performed based on the driving data. For example, the driving data can be tested and evaluated to determine various autonomous driving performance and parameters. The specific testing and evaluation process is not limited herein.

[0110] In some embodiments, an autonomous driving test may be performed based on the first driving data.

[0111] For example, when the first driving data is driving data of the autonomous driving system manipulating the vehicle platform based on a real driving scenario, by performing an autonomous driving test on the first driving data, the mutual influence between the perception module and the planning module in the autonomous driving system can be tested.

[0112] It can be understood that when an autonomous driving system operates a vehicle platform based on real-world driving scenarios, the perception module receives real-world information, the planning module plans this information, and considers its uncertainty. Finally, the control information output by the planning module acts on the real world. Specifically, the perception module's information is transmitted to the planning module, which in turn influences the perception module's information through the real world. Therefore, by operating the vehicle platform based on real-world driving scenarios, the interaction between the planning and perception modules can be tested.

[0113] For example, when the first driving data is driving data of the driver manipulating the vehicle platform based on a real driving scenario, the driver's real driving data can be obtained by conducting an autonomous driving test on the first driving data, which to a certain extent reduces unrealistic factors such as the driver's behavior and psychology when manipulating the driving simulator, thereby improving the authenticity and effectiveness of the autonomous driving test.

[0114] In other embodiments, an autonomous driving test may be performed based on the second driving data.

[0115] For example, when the second driving data is driving data of the driver operating the driving simulator based on a real driving scenario, by testing the second driving data, it is possible to test the situation in which the driver operates the driving simulator in a real driving scenario, thereby improving the effectiveness and authenticity of the autonomous driving test.

[0116] For example, when the second driving data is driving data of a driver operating a driving simulator based on a virtual driving scenario, the driving behavior of the driver in the virtual driving scenario can be tested by testing the second driving data.

[0117] In other embodiments, an autonomous driving test may be performed based on the first driving data and the second driving data.

[0118] For example, when the first driving data is driving data of the autonomous driving system manipulating the vehicle platform based on a real driving scenario, and the second driving data is driving data of the driver manipulating the driving simulator based on the real driving scenario, by conducting an autonomous driving test on the first driving data and the second driving data, the driving data of the autonomous driving system and the driver in the same driving scenario can be obtained, which solves the problem that the driving simulator cannot accurately restore the real response of the vehicle and can improve the effectiveness of the autonomous driving test.

[0119] For example, when the first driving data is the driving data of the driver manipulating the vehicle platform based on a real driving scenario, and the second driving data is the driving data of the driver manipulating the driving simulator based on a virtual driving scenario, the driving data of the autonomous driving system and the driver in different driving scenarios can be obtained, which solves the problem of the single test scenario of the driving simulator and can improve the effectiveness of the autonomous driving test.

[0120] Please refer to Figure 8, which is a schematic flowchart of another autonomous driving test method provided in an embodiment of the present application, which may specifically include the following steps S201 to S203.

[0121] Step S201: Collect the first driving data obtained by the automatic driving system manipulating the vehicle platform based on the real driving scenario.

[0122] For example, when the first driving scene is a real driving scene captured by a shooting device and the first operation object is an automatic driving system, first driving data obtained by the automatic driving system manipulating the vehicle platform based on the real driving scene can be collected.

[0123] For example, the first driving data may include operational data of the autonomous driving system and driving information of the real vehicle. The operational data of the autonomous driving system may include, but is not limited to, sensor data, perception data, planning data, and control data. The driving information of the real vehicle may include, but is not limited to, vehicle trajectory, vehicle speed, braking information, steering information, and acceleration information. For example, braking information may be collected by a sensor installed on the vehicle's brake pedal. In another example, steering information may be collected by a sensor installed on the vehicle's steering wheel.

[0124] By collecting first driving data obtained by the autonomous driving system manipulating the vehicle platform based on a real driving scenario, the driving data of the autonomous driving system in the real driving scenario can be obtained.

[0125] Step S202: collecting the second driving data obtained by the driver operating the driving simulator based on the real driving scenario.

[0126] It should be noted that, as shown in Figure 4, when the driving simulator is located in the front seat of a real vehicle, the driver can see the real driving scene in real time. Of course, the driver can also receive the real driving scene captured by the camera through the display screen in the driving simulator. As shown in Figure 5, when the driving simulator is located in the back seat of a real vehicle, the driver can also see the real driving scene captured by the camera through the display screen in the driving simulator.

[0127] For example, second driving data obtained by the driver operating the driving simulator based on a real driving scenario can be collected. The second driving data may include the driver's operating behavior and the driving information of the simulated vehicle. The driver's operating behavior may include, but is not limited to, steering, braking, accelerating, and turning on the lights. The driving information of the simulated vehicle may include, but is not limited to, the vehicle's trajectory, vehicle speed, braking information, steering information, and acceleration information.

[0128] For example, the driver's operating behavior can be captured using a camera and sensors in a driving simulator. For example, the driver's braking operation can be captured using sensors installed on the brakes of the driving simulator. For another example, the driver's steering operation can be captured using sensors installed on the steering wheel of the driving simulator.

[0129] By collecting the second driving data obtained by the driver operating the driving simulator based on the real driving scene, the driver's driving data of the simulated vehicle in the real driving scene can be obtained, thereby improving the diversity of driving data.

[0130] Step S203: Perform an automatic driving test based on the first driving data and / or the second driving data.

[0131] In some embodiments, an autonomous driving test can be conducted on first driving data obtained by the autonomous driving system manipulating the vehicle platform based on a real driving scenario. The specific testing process is not limited herein. It should be noted that by conducting an autonomous driving test on first driving data obtained by the autonomous driving system manipulating the vehicle platform based on a real driving scenario, the interaction between the perception module and the planning module in the autonomous driving system can be tested, thereby improving the effectiveness of the autonomous driving test.

[0132] In other embodiments, autonomous driving tests can be conducted using second driving data obtained by the driver manipulating a driving simulator based on a real driving scenario. It should be noted that by testing the second driving data obtained by the driver manipulating a driving simulator based on a real driving scenario, the driver's actual reactions in a real driving scenario can be measured, thereby improving the effectiveness of the autonomous driving test.

[0133] In other embodiments, an autonomous driving test can be conducted on the first driving data and the second driving data. It should be noted that by conducting an autonomous driving test on the first driving data of the autonomous driving system manipulating the vehicle platform based on a real driving scenario and the second driving data of the driver manipulating the driving simulator based on a real driving scenario, driving data of the autonomous driving system and the driver in the same driving scenario can be obtained, thus resolving the issue of the driving simulator being unable to accurately reproduce the vehicle's actual response and improving the effectiveness of the autonomous driving test.

[0134] It can be understood that in the prior art, the driving simulator has the problem of inaccurate control accuracy in restoring the real response of the vehicle. The embodiment of the present application tests the driving data corresponding to the autonomous driving system and the driver in the same driving scenario, and can compare the real response of the vehicle platform and the real response of the driving simulator in the same driving scenario, thereby improving the effectiveness and authenticity of the autonomous driving test.

[0135] Please refer to Figure 9, which is a schematic flowchart of another autonomous driving test method provided in an embodiment of the present application, which may specifically include the following steps S301 to S303.

[0136] Step S301: Collect the first driving data obtained by the automatic driving system manipulating the vehicle platform based on the real driving scenario.

[0137] It can be understood that step S301 is the same as the above step S201 and will not be described again here.

[0138] Step S302: collecting the second driving data obtained by the driver operating the driving simulator based on the virtual driving scene.

[0139] Exemplarily, the second driving data may include the driver's operating behavior and driving information of the simulated vehicle. For example, the driver's operating behavior may be collected using a camera and sensors in a driving simulator. The specific process for collecting the second driving data can be found in the specific process of step S202 above and will not be further described here.

[0140] Step S303: Perform an automatic driving test based on the first driving data and / or the second driving data.

[0141] In some embodiments, an autonomous driving test can be conducted based on first driving data obtained by the autonomous driving system manipulating the vehicle platform based on a real driving scenario. The specific testing process is not limited herein. It should be noted that by conducting an autonomous driving test based on first driving data obtained by the autonomous driving system manipulating the vehicle platform based on a real driving scenario, the interaction between the perception module and the planning module in the autonomous driving system can be tested, thereby improving the effectiveness of the autonomous driving test.

[0142] In other embodiments, autonomous driving testing can be performed based on second driving data obtained by the driver manipulating a driving simulator based on a virtual driving scenario. The specific testing process is not limited herein. It should be noted that by testing the second driving data obtained by the driver manipulating a driving simulator based on a virtual driving scenario, the driver's driving behavior in the virtual driving scenario can be tested.

[0143] In other embodiments, autonomous driving tests can be performed on the first driving data and the second driving data. It should be noted that by performing autonomous driving tests on the first driving data of the autonomous driving system manipulating the vehicle platform based on a real driving scenario and the second driving data of the driver manipulating the driving simulator based on a virtual driving scenario, driving data of the autonomous driving system and the driver in different driving scenarios can be obtained. This solves the problem of the single test scenario of the driving simulator, enriches the driving data, and improves the effectiveness of the autonomous driving test.

[0144] It should be noted that when the driver operates the driving simulator based on a virtual driving scenario, the driver only relies on the response of the virtual vehicle in the driving simulator to operate, and does not receive the actual response of the real vehicle, resulting in the driver being unable to provide feedback on the actual response of the real vehicle. To address this issue, embodiments of the present application can also perform motion compensation on the driving simulator based on the actual motion parameters of the vehicle, so that the driver can also receive the actual response of the vehicle when operating the driving simulator. The following will describe the motion compensation of the driving simulator in detail.

[0145] In some embodiments, the specific process of motion compensation includes: obtaining real motion parameters; obtaining virtual motion parameters; and performing motion compensation on the driving simulator based on the virtual motion parameters and the real motion parameters. The real motion parameters are the motion parameters of the vehicle when the autonomous driving system manipulates the vehicle platform based on a real driving scenario; and the virtual motion parameters are the motion parameters corresponding to the simulated vehicle in the driving simulator when the driver operates the driving simulator based on a virtual driving scenario.

[0146] For example, when acquiring real motion parameters, sensors installed on the vehicle chassis can be used to collect the vehicle's six degrees of freedom (DOF) as the vehicle's real motion parameters. The six degrees of freedom can include translational and rotational degrees of freedom. It should be noted that translational freedom refers to the distance of translation along the X, Y, and Z axes, while rotational freedom refers to the angle of rotation around the X, Y, and Z axes.

[0147] For example, a driving simulator may include a six-degree-of-freedom platform. When acquiring virtual motion parameters, the six degrees of freedom of the driving simulator may be acquired via the six-degree-of-freedom platform provided on the driving simulator, and the six degrees of freedom may be used as virtual motion parameters. It is understood that the motion parameters of the driving simulator are equivalent to the motion parameters corresponding to the simulated vehicle in the driving simulator.

[0148] In some embodiments, performing motion compensation on a driving simulator based on virtual motion parameters and real motion parameters may include: calculating a difference between the virtual motion parameters and the real motion parameters to obtain a motion parameter difference; and performing motion compensation on the driving simulator based on the motion parameter difference.

[0149] For example, when performing motion parameter compensation on the driving simulator according to the virtual motion parameters and the real motion parameters, the virtual motion parameters may be subtracted from the real motion parameters to obtain a motion parameter difference.

[0150] For example, when the translation distance along the X-axis in the real motion parameters is x1, and the translation distance along the X-axis in the virtual motion parameters is x2, the translation distance x2 is subtracted from the translation distance x1, and the resulting translation distance difference x2-x1 can be used as the motion parameter difference. For another example, when the translation distance along the Y-axis in the real motion parameters is y1, and the translation distance along the Y-axis in the virtual motion parameters is y2, the translation distance y2 is subtracted from the translation distance y1, and the resulting translation distance difference y2-y1 can be used as the motion parameter difference. For other parameters in the six degrees of freedom, the method for calculating motion parameter differences is the same as described above and is not further described here.

[0151] In some embodiments, when motion compensation is performed on a driving simulator based on motion parameter differences, the motion parameter differences can be input into a control center in the driving simulator, and the control center predicts the motion state and motion trajectory of the driving simulator based on the motion parameter differences based on a vehicle kinematic model, and outputs the motion state and motion trajectory to an actuator in the driving simulator; the execution result controls the motion state of the driving simulator based on the received motion state and motion trajectory.

[0152] It can be understood that the motion state of the driving simulator is equivalent to the motion state of the simulated vehicle in the driving simulator. By controlling the motion state of the driving simulator, the driver can receive a real response from the virtual vehicle.

[0153] The above-described embodiment can perform motion compensation on the driving simulator based on the motion parameter difference, thereby superimposing the virtual vehicle's real-world responses onto the driving simulator. This allows the driver to receive the virtual vehicle's real-world responses while operating the driving simulator. The driver can then provide feedback on the virtual vehicle's real-world responses, thereby improving the effectiveness and authenticity of driver data collection. It will be appreciated that when the driving simulator is installed on a real vehicle, the driver only receives the real-world responses of the real vehicle and cannot directly receive the real-world responses of the virtual vehicle in the driving simulator.

[0154] In an embodiment of the present application, in order to solve the problem of distortion of driving data caused by the driver operating the driving simulator according to the virtual driving scene for a long time, the embodiment of the present application can also update the virtual driving scene according to the real driving scene.

[0155] In some embodiments, the virtual driving scene is updated based on a preset interval according to the real driving scene.

[0156] For example, while the driver is operating the driving simulator based on the virtual driving scenario, the virtual driving scenario can be updated based on the actual driving scenario, allowing the driver to operate the driving simulator based on the updated virtual driving scenario. The preset interval can be set based on actual conditions, and the specific value is not limited herein. For example, the interval can be 10 seconds, and the virtual driving scenario can be updated every 10 seconds based on the actual driving scenario.

[0157] The above embodiment, by updating the virtual driving scene according to the real driving scene, can enable the driver to operate the driving simulator based on the updated virtual driving scene, thereby solving the problem of distortion of driving data caused by the driver operating the driving simulator according to the virtual driving scene for a long time, improving the validity of the driving data, and further improving the validity of the autonomous driving test.

[0158] In the embodiment of the present application, in addition to controlling the simulated vehicle in the driving simulator individually, the driver can also control the simulated vehicle in the driving simulator and the real vehicle at the same time.

[0159] Please refer to Figure 10, which is a schematic flowchart of another autonomous driving test method provided in an embodiment of the present application, which may specifically include the following steps S401 to S404.

[0160] Step S401: Switch the driving simulator to a dual-control mode, where the dual-control mode is used for the driver to control the vehicle platform through the driving simulator, and for the driver to control the simulated vehicle in the driving simulator through the driving simulator.

[0161] It should be noted that in the embodiments of the present application, the driving simulator may include a single control mode and a dual control mode. The single control mode is used to control the simulated vehicle in the driving simulator through the driving simulator, and is suitable for scenarios where the simulated vehicle is controlled solely through the driving simulator. The dual control mode is used for the driver to control the vehicle platform through the driving simulator, and for the driver to control the simulated vehicle in the driving simulator through the driving simulator, and is suitable for scenarios where both the simulated vehicle and the real vehicle are controlled simultaneously through the driving simulator.

[0162] Exemplarily, the driving simulator can be switched to the dual control mode according to a switching instruction or switching operation input by the user. It should be noted that a mode switching switch can be provided in the driving simulator to switch the driving simulator from the single control mode to the dual control mode through the mode switching switch.

[0163] Step S402: collecting the first driving data obtained by the driver manipulating the vehicle platform through the driving simulator based on the virtual driving scene.

[0164] It should be noted that when the driver operates the driving simulator, they can apply their inputs to the vehicle platform through the control mechanism, control center, and actuators within the driving simulator. For example, the control mechanism receives the driver's inputs, the control center calculates the vehicle's motion profile based on the output signals corresponding to the inputs, and the actuators control the vehicle platform based on the vehicle's motion profile. In this case, the autonomous driving system does not operate the vehicle platform.

[0165] For example, first driving data obtained by a driver manipulating a vehicle platform through a driving simulator based on a virtual driving scenario may be collected. The first driving data may include the driver's operating behavior and driving information of the real vehicle, and may also include operating data of the driving simulator.

[0166] Step S403: collecting the second driving data obtained by the driver manipulating the simulated vehicle in the driving simulator based on the virtual driving scene.

[0167] It can be understood that step S403 is the same as step S302 and will not be described again here.

[0168] Step S404: Perform an automatic driving test based on the first driving data and / or the second driving data.

[0169] In some embodiments, an autonomous driving test can be conducted on first driving data obtained by a driver manipulating a vehicle platform through a driving simulator based on a virtual driving scenario. The specific testing process is not limited herein. It should be noted that by conducting an autonomous driving test on first driving data obtained by a driver manipulating a vehicle platform through a driving simulator based on a virtual driving scenario, the driver's actual reaction behavior when encountering dangerous or extreme conditions in the virtual driving scenario can be tested, thereby improving the effectiveness and authenticity of the autonomous driving test while ensuring the driver's personal safety.

[0170] It can be understood that when the driver manipulates the vehicle platform through a driving simulator based on a virtual driving scenario, it is equivalent to the driver actually driving the vehicle, but the scenario is a virtual driving scenario. Therefore, the actual occurrence of dangers in the virtual driving scenario can be avoided, and the driver's real driving data under dangerous and extreme conditions can be obtained, thereby improving the effectiveness and authenticity of the autonomous driving test.

[0171] In other embodiments, an autonomous driving test may be conducted on second driving data obtained by the driver manipulating a simulated vehicle in a driving simulator based on a virtual driving scenario. It should be noted that by testing the second driving data obtained by the driver manipulating the driving simulator based on the virtual driving scenario, the driver's driving behavior in the virtual driving scenario can be tested.

[0172] In other embodiments, autonomous driving tests can be conducted on the first driving data and the second driving data. It should be noted that by testing the first driving data obtained by the driver manipulating the vehicle platform through a driving simulator based on a virtual driving scenario, and the second driving data obtained by the driver manipulating the driving simulator based on the virtual driving scenario, it is possible to test the driver manipulating the simulated vehicle based on the actual responses of the real vehicle, thereby deeply coupling the driving simulator with the vehicle platform and improving the effectiveness and authenticity of autonomous driving tests.

[0173] In the embodiment of the present application, in order to improve the realism of the virtual driving scene, the virtual driving scene can also be updated according to the real motion parameters of the real vehicle. The following will describe how to update the virtual driving scene.

[0174] In some embodiments, the virtual driving scene update process may include: obtaining real motion parameters; and updating the virtual driving scene based on the real motion parameters. The real motion parameters are the vehicle motion parameters when the driver manipulates the vehicle platform through the simulated driver based on the virtual driving scene.

[0175] For example, the real motion parameters may include not only the six degrees of freedom of the vehicle but also the real mileage information of the vehicle, wherein the real mileage information may include but is not limited to the real vehicle's speed, total mileage, position coordinates, etc.

[0176] In some embodiments, updating the virtual driving scene according to the real motion parameters may include updating the mileage information of the simulated vehicle in the virtual driving scene according to the real mileage information.

[0177] For example, the mileage information of the simulated vehicle in the virtual driving scene may be updated at regular intervals based on the real mileage information.

[0178] It should be noted that the mileage information of the simulated vehicle may include the driving speed, total mileage, and location coordinates of the real vehicle. In the embodiment of the present application, the location coordinates of the simulated vehicle are primarily updated. Of course, other information may also be updated. For example, the location coordinates of the simulated vehicle may be updated based on the location coordinates in the real mileage information. For another example, the total mileage of the simulated vehicle may be updated based on the total mileage in the real mileage information.

[0179] In the above embodiment, by updating the mileage information of the simulated vehicle in the virtual driving scene according to the real mileage information, the authenticity of the virtual driving scene can be improved, thereby improving the authenticity of the autonomous driving test.

[0180] Please refer to Figure 11, which is a schematic flowchart of another autonomous driving test method provided in an embodiment of the present application, which may specifically include the following steps S501 to S503.

[0181] Step S501: Acquire third driving data obtained by the automatic driving system performing simulated driving in a simulation environment.

[0182] It should be noted that in the embodiment of the present application, the autonomous driving system may not operate the vehicle platform, but instead perform simulated driving according to real driving scenarios in a constructed simulation environment.

[0183] In some embodiments, obtaining third driving data obtained by the autonomous driving system performing simulated driving in a simulated environment may include: obtaining real sensor information corresponding to the vehicle based on a real driving scenario; collecting simulated driving data obtained by the autonomous driving system performing simulated driving in the simulated environment based on the real sensor information; and determining third driving data based on the simulated driving data.

[0184] The real sensor information is sensor information detected by sensors and / or human-machine interaction devices in the vehicle. The human-machine interaction devices are located outside the vehicle and connected to the vehicle via wireless communication. For example, the human-machine interaction device can be a drone, which can communicate with the vehicle via WiFi, Bluetooth, 4G, or 5G.

[0185] For example, real sensor information collected by sensors in a vehicle can be obtained in a real driving scenario. Of course, real sensor information collected by sensors in a human-computer interaction device can also be obtained in a real driving scenario.

[0186] For example, after obtaining the real sensor information, the real sensor information can be sent to the autonomous driving system so that the autonomous driving system can perform simulated driving based on the real sensor information in a simulated environment. For example, the autonomous driving system can use a perception module, a planning module, and a control module to perform simulated driving based on the real sensor information to obtain simulated driving data.

[0187] For example, after collecting simulated driving data obtained by the automatic driving system performing simulated driving in a simulated environment based on real sensor information, the simulated driving data can be determined as the third driving data.

[0188] It should be noted that the simulation environment is a newly constructed test environment, similar to the test environment in a driving simulator, used for the automated driving system to simulate driving. The specific construction process of the simulation environment is not limited here.

[0189] By acquiring the third driving data obtained by the automatic driving system performing simulated driving in the simulation environment, the driving data of the automatic driving system performing simulated driving can be obtained.

[0190] Step S502: Acquire fourth driving data obtained by the driver manipulating the vehicle platform through a simulated driver based on a real driving scenario.

[0191] It can be understood that step S502 is the same as the above step S202 and will not be described again here.

[0192] Step S503: Perform an automatic driving test based on the third driving data and / or the fourth driving data.

[0193] Exemplarily, after obtaining the third driving data and the fourth driving data, an autonomous driving test may be performed based on the third driving data and / or the fourth driving data.

[0194] In some embodiments, an autonomous driving test can be performed on third driving data obtained by the autonomous driving system during simulated driving in a simulated environment. The specific testing process is not limited herein. It should be noted that by performing an autonomous driving test on the third driving data obtained by the autonomous driving system during simulated driving in a simulated environment, the autonomous driving capability of the autonomous driving system in the simulated environment can be tested, thereby improving the effectiveness of the autonomous driving test.

[0195] In other embodiments, the third driving data and the fourth driving data may be subjected to an autonomous driving test, wherein the specific testing process is not limited herein.

[0196] It should be noted that the third driving data obtained by simulating the driving of the autonomous driving system in a simulation environment and the fourth driving data obtained by the driver manipulating the vehicle platform through a simulated driver based on a real driving scenario can simultaneously evaluate the driving capabilities of the driver and the autonomous driving system online. For areas where the autonomous driving system's capabilities are insufficient in the same driving scenario, the driver's driving data can be used for analysis and improvement, thereby improving the effectiveness of the autonomous driving test.

[0197] It should be noted that when the autonomous driving system is unable to operate the vehicle platform, a driver is required to take over the vehicle platform. In the embodiment of the present application, the driver's ability to take over can also be tested when the autonomous driving system is unable to operate the vehicle platform.

[0198] It should be noted that the driver can include a first driver and a second driver. The first driver can be in the driver's seat of the vehicle and can take over the vehicle platform at any time; the second driver can be in the front passenger seat of the vehicle or in the back seat of the vehicle. Correspondingly, the simulator can be set up in the front passenger seat or in the back seat of the vehicle.

[0199] In some embodiments, when the autonomous driving system operates the vehicle platform based on a real driving scenario, if a takeover request from the autonomous driving system is received, the first driver is prompted to take over the vehicle platform.

[0200] It should be noted that when the autonomous driving system detects that the vehicle encounters danger, hardware failure, software failure, or the vehicle does not meet the operational design domain (ODD), it can send a takeover request to the autonomous driving test equipment, so that the autonomous driving test equipment can prompt the first driver to take over the vehicle platform according to the takeover request.

[0201] For example, a first driving takeover message may be output to remind the first driver to take over the vehicle platform. The first driving takeover message may be output via a warning light or voice, which is not limited here.

[0202] In some embodiments, after prompting the first driver to take over the vehicle platform, the autonomous driving test method provided in the embodiments of the present application may also include: when it is determined that the first driver has failed to take over the driving task, prompting the second driver to take over the vehicle platform through a driving simulator.

[0203] For example, if the first driver is not detected taking over the vehicle platform within a preset time, it is determined that the driver has failed to take over the driving task. The preset time can be set according to actual conditions, and the specific value is not limited here.

[0204] For example, a second driving takeover message may be output to remind the first driver to take over the vehicle platform. The second driving takeover message may be output via a display screen in the simulator, a warning light, or voice output, without limitation.

[0205] It should be noted that, in order to avoid dangerous accidents, when it is determined that the first driver has not taken over the vehicle platform, it is necessary to promptly remind the second driver to take over the vehicle platform.

[0206] In some embodiments, after prompting the second driver to take over the vehicle platform through the driving simulator, it may also include: obtaining fifth driving data, and performing an autonomous driving test based on the fifth driving data, wherein the fifth driving data includes the operating data of the vehicle platform, the driving data of the autonomous driving system, the driving data of the first driver, and the driving data of the second driver.

[0207] For example, an autonomous driving test may be performed on the vehicle platform's operating data, the autonomous driving system's driving data, the first driver's driving data, and the second driver's driving data. The specific testing process is not limited herein.

[0208] The above embodiment, by conducting an autonomous driving test on the operating data of the vehicle platform, the driving data of the autonomous driving system, the driving data of the first driver and the driving data of the second driver, can test the first driver's actual takeover ability in a real driving scenario when the autonomous driving system is unable to control the vehicle, and test the second driver's actual takeover ability when the first driver is unable to take over the vehicle, thereby improving the authenticity and effectiveness of the autonomous driving test.

[0209] A computer-readable storage medium is also provided in an embodiment of the present application. The computer-readable storage medium stores a computer program, and the computer program includes program instructions. The processor executes the program instructions to implement any one of the autonomous driving test methods provided in the embodiments of the present application.

[0210] For example, when the program is loaded by the processor, the following steps may be performed:

[0211] Determine a first driving scenario corresponding to the vehicle platform and a second driving scenario corresponding to the driving simulator; obtain first driving data of a first operating object operating the vehicle platform based on the first driving scenario, where the first operating object is the driver or the automatic driving system; obtain second driving data of a second operating object operating the driving simulator based on the second driving scenario, where the second operating object is the driver; and perform an automatic driving test based on the first driving data and / or the second driving data.

[0212] The computer-readable storage medium may be an internal storage unit of the autonomous driving test device described in the aforementioned embodiment, such as a hard disk or memory of the autonomous driving test device. The computer-readable storage medium may also be an external storage device of the autonomous driving test device, such as a plug-in hard disk, a smart media card (SMC), a secure digital card (SD card), a flash card, etc., equipped on the autonomous driving test device.

[0213] Furthermore, the computer-readable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, programs required for at least one function, etc.; the data storage area may store data created according to each program, etc.

[0214] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present application, and such modifications or substitutions should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. An autonomous driving testing method, characterized in that: Applied to a vehicle, the vehicle comprising a vehicle platform, an autonomous driving system, and a driving simulator, the method comprising: Determining a first driving scenario corresponding to the vehicle platform and a second driving scenario corresponding to the driving simulator; Acquiring first driving data of a first operating subject manipulating the vehicle platform based on the first driving scenario, where the first operating subject is a driver or the automatic driving system; Acquiring second driving data of a second operating subject operating the driving simulator based on the second driving scenario, where the second operating subject is the driver; An autonomous driving test is performed based on the first driving data and / or the second driving data.

2. The autonomous driving test method according to claim 1, wherein: The first driving scene is a real driving scene captured by a camera, and the first operation object is the automatic driving system; The acquiring first driving data of the first operation object manipulating the vehicle platform based on the first driving scene includes: The first driving data obtained by the automatic driving system manipulating the vehicle platform based on the real driving scenario is collected.

3. The autonomous driving test method according to claim 2, wherein: The second driving scenario is a real driving scenario; The acquiring of second driving data of the second operation object operating the driving simulator based on the second driving scenario includes: The second driving data obtained by the driver operating the driving simulator based on the real driving scenario is collected.

4. The autonomous driving test method according to claim 2, wherein: The second driving scene is a virtual driving scene displayed by the driving simulator; The acquiring of second driving data of the second operation object operating the driving simulator based on the second driving scenario includes: The second driving data obtained by the driver operating the driving simulator based on the virtual driving scene is collected.

5. The autonomous driving test method according to claim 4, characterized in that: The method further comprises: Acquiring real motion parameters, where the real motion parameters are motion parameters of the vehicle when the autonomous driving system manipulates the vehicle platform based on the real driving scenario; Acquiring virtual motion parameters, where the virtual motion parameters are motion parameters corresponding to the simulated vehicle in the driving simulator when the driver operates the driving simulator based on a virtual driving scenario; Motion compensation is performed on the driving simulator according to the virtual motion parameters and the real motion parameters.

6. The autonomous driving test method according to claim 5, characterized in that: The performing motion compensation on the driving simulator according to the virtual motion parameters and the real motion parameters includes: Calculating a difference between the virtual motion parameter and the real motion parameter to obtain a motion parameter difference; Motion compensation is performed on the driving simulator according to the motion parameter difference.

7. The autonomous driving test method according to any one of claims 4 to 6, characterized in that: The method further comprises: Based on a preset interval time, the virtual driving scene is updated according to the real driving scene.

8. The autonomous driving test method according to claim 1, wherein: The first driving scene is a virtual driving scene displayed by the driving simulator, and the first operating object is the driver. Before obtaining first driving data of the first operating object operating the vehicle platform based on the first driving scene, the method further includes: Switching the driving simulator to a dual-control mode, wherein the dual-control mode is used for the driver to control the vehicle platform through the driving simulator and for the driver to control the simulated vehicle in the driving simulator through the driving simulator; The acquiring first driving data of the first operation object manipulating the vehicle platform based on the first driving scene includes: The first driving data obtained by the driver manipulating the vehicle platform through the driving simulator based on the virtual driving scene is collected.

9. The automatic driving test method according to claim 8, characterized in that: The second driving scene is the virtual driving scene; The acquiring of second driving data of the second operation object operating the driving simulator based on the second driving scenario includes: The second driving data obtained by the driver manipulating the simulated vehicle in the driving simulator based on the virtual driving scene is collected.

10. The automatic driving test method according to claim 9, characterized in that: The method further comprises: Acquiring real motion parameters, where the real motion parameters are motion parameters of the vehicle when the driver manipulates the vehicle platform through the simulated driver based on the virtual driving scene; The virtual driving scene is updated according to the real motion parameters.

11. The automatic driving test method according to claim 10, characterized in that: The real motion parameters include real mileage information of the vehicle; and updating the virtual driving scene according to the real motion parameters includes: The mileage information of the simulated vehicle in the virtual driving scene is updated according to the real mileage information.

12. The autonomous driving test method according to claim 1, wherein: The method further comprises: Acquiring third driving data obtained by the automatic driving system performing simulated driving in a simulation environment; Acquiring fourth driving data obtained by the driver manipulating the vehicle platform through a simulated driver based on a real driving scenario; An automatic driving test is performed based on the third driving data and / or the fourth driving data.

13. The automatic driving test method according to claim 12, characterized in that: The obtaining of third driving data obtained by the automatic driving system performing simulated driving in a simulated environment includes: Based on the real driving scenario, obtaining real sensor information corresponding to the vehicle; collecting simulated driving data obtained by the autonomous driving system performing simulated driving in the simulated environment according to the real sensor information; The third driving data is determined based on the simulated driving data.

14. The automatic driving test method according to claim 13, characterized in that: The real sensing information is sensing information detected by sensors and / or a human-machine interaction device in the vehicle. The human-machine interaction device is arranged outside the vehicle and is connected to the vehicle via wireless communication.

15. The autonomous driving test method according to claim 1, wherein: The drivers include a first driver and a second driver; the method further includes: When the autonomous driving system operates the vehicle platform based on a real driving scenario, if a takeover request from the autonomous driving system is received, the first driver is prompted to take over the vehicle platform.

16. The autonomous driving test method according to claim 15, characterized in that: After prompting the first driver to take over the vehicle platform, the method further includes: When it is determined that the first driver fails to take over the driving task, the second driver is prompted to take over the vehicle platform through the driving simulator.

17. The autonomous driving test method according to claim 16, wherein: After prompting the second driver to take over the vehicle platform through the driving simulator, the method further includes: Acquire fifth driving data and perform an autonomous driving test based on the fifth driving data, where the fifth driving data includes operating data of the vehicle platform, driving data of the autonomous driving system, driving data of the first driver, and driving data of the second driver.

18. An autonomous driving test device, characterized in that: The autonomous driving test device includes a processor and a memory; The memory is used to store computer programs; The processor is used to execute the computer program and implement the autonomous driving test method according to any one of claims 1 to 17 when executing the computer program.

19. A vehicle, characterized in that: The vehicle includes a vehicle platform, an autonomous driving system, a driving simulator, a shooting device, and the autonomous driving test equipment as described in claim 18.

20. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, enables the processor to implement the autonomous driving test method according to any one of claims 1 to 17.

Images