Testing Method, Device, Electronic Device, Medium and Product for Autonomous Vehicle

Abstract

The present disclosure provides a test method, device, electronic device, medium and product for an autonomous driving vehicle, relating to the technical field of autonomous driving, and particularly to technical fields such as autonomous driving vehicle testing, extended display, and artificial intelligence. The specific implementation solution is as follows: when performing virtual testing on an autonomous driving vehicle based on target image content, and the autonomous driving vehicle outputs corresponding driving actions based on driving environment information, obtain target driving parameters, where the target image content is the image content of the virtual test scenario displayed by a display device, the driving environment information is the environmental information collected from the target image content, the virtual test scenario includes a virtual vehicle, and the driving actions of the virtual vehicle match the driving actions of the autonomous driving vehicle; generate a test result based on the target virtual driving parameters. The present disclosure uses mapping a real vehicle to a virtual scenario, which can significantly reduce the test cost while improving the accuracy of the test results of autonomous driving vehicle testing.

Description

Technical Field

[0001] The present disclosure relates to the field of autonomous driving technologies, and in particular, to technologies such as autonomous driving vehicle testing, extended reality (XR), and artificial intelligence (AI). Specifically, it relates to a testing method, device, electronic device, medium, and product for an autonomous driving vehicle. Background Art

[0002] In the related art, during the production and manufacturing of autonomous driving vehicles, it is usually necessary to test the autonomous driving vehicles. For example, it is usually necessary to test whether the autonomous driving vehicle can perform corresponding expected driving actions when facing various possible emergencies in the autonomous driving mode. Summary of the Invention

[0003] The present disclosure provides a testing method, device, electronic device, medium, and product for an autonomous driving vehicle.

[0004] According to a first aspect of the present disclosure, there is provided a testing method for an autonomous driving vehicle, which is applied to an autonomous driving vehicle in an overhead state, and a display device is provided in front of the field of view of the autonomous driving vehicle. Wherein, the method includes:

[0005] When performing virtual testing on the autonomous driving vehicle based on target image content, and the autonomous driving vehicle outputs corresponding driving actions based on driving environment information, obtaining target driving parameters of the autonomous driving vehicle, where the target image content is the image content corresponding to the virtual testing scenario displayed by the display device, the driving environment information is the driving environment information collected from the target image content, the virtual testing scenario includes a virtual vehicle, and during the virtual testing process, the driving actions of the virtual vehicle match the driving actions of the autonomous driving vehicle;

[0006] Generating a test result based on the target virtual driving parameters.

[0007] According to a second aspect of the present disclosure, there is provided a testing device for an autonomous driving vehicle, which is applied to an autonomous driving vehicle in an overhead state, and a display device is provided in front of the field of view of the autonomous driving vehicle. Wherein, the device includes:

[0008] An acquisition module, configured to acquire target driving parameters of the autonomous vehicle when performing a virtual test on the autonomous vehicle based on target image content, and the autonomous vehicle outputs corresponding driving actions based on driving environment information, where the target image content is the image content corresponding to the virtual test scenario displayed by the display device, the driving environment information is the driving environment information collected from the target image content, the virtual test scenario includes a virtual vehicle, and during the virtual test, the driving actions of the virtual vehicle match the driving actions of the autonomous vehicle;

[0009] A generation module, configured to generate a test result based on the target virtual driving parameters.

[0010] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0011] At least one processor; and

[0012] A memory communicatively connected to the at least one processor; wherein,

[0013] The memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the method described in the first aspect above.

[0014] According to a fourth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, where the computer instructions are used to cause the computer to execute the method described in the first aspect above.

[0015] According to a fifth aspect of the present disclosure, there is provided a computer program product, including a computer program, where the computer program, when executed by a processor, implements the method described in the first aspect.

[0016] In the embodiments of the present disclosure, by using a real autonomous vehicle in combination with a virtual test scenario for testing, in this way, during the test, the real autonomous vehicle can obtain driving environment information from the virtual driving scenario and output corresponding driving actions, and then, a test result can be generated based on the target driving parameters of the autonomous vehicle during the test. During this test process, since the autonomous vehicle does not need to drive in a real road environment, it is beneficial to reduce the test cost. At the same time, during the test process, a test result can also be generated based on the driving parameters of the real autonomous vehicle. Therefore, it is beneficial to improve the accuracy of the test result. Description of the Drawings

[0017] The drawings are used to better understand the solution and do not constitute a limitation to the present disclosure. Among them:

[0018] Figure 1 It is a flowchart of a test method for an autonomous vehicle provided by an embodiment of the present disclosure;

[0019] Figure 2 It is one of the schematic diagrams of the positional relationship between the autonomous vehicle and the display device in an embodiment of the present disclosure;

[0020] Figure 3 It is the schematic diagram of the positional relationship between the autonomous vehicle and the wheel angle detection device in an embodiment of the present disclosure;

[0021] Figure 4 It is the schematic diagram of the positional relationship between the autonomous vehicle and the wheel speed detection device in an embodiment of the present disclosure;

[0022] Figure 5 It is the second schematic diagram of the positional relationship between the autonomous vehicle and the display device in an embodiment of the present disclosure;

[0023] Figure 6 It is the schematic diagram of the structure of a test device for an autonomous vehicle provided by an embodiment of the present disclosure;

[0024] Figure 7 It is the schematic diagram of the structure of the acquisition module in an embodiment of the present disclosure;

[0025] Figure 8 It is the schematic diagram of the structure of the detection sub-module in an embodiment of the present disclosure;

[0026] Figure 9 The block diagram of the electronic device for implementing the test method of the autonomous vehicle provided by the embodiment of the present disclosure. Detailed implementation manners

[0027] The following makes an explanation of the exemplary embodiments of the present disclosure with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted below.

[0028] Please refer to Figure 1 , Figure 1 It is the schematic flowchart of a test method for an autonomous vehicle provided by an embodiment of the present disclosure. The test method for the autonomous vehicle includes the following steps:

[0029] Step 101: When performing virtual testing on the autonomous vehicle 210 based on the target image content, and the autonomous vehicle 210 outputs corresponding driving actions based on the driving environment information, obtain the target driving parameters of the autonomous vehicle 210. Herein, the target image content is the image content corresponding to the virtual test scenario displayed on the display device 220, the driving environment information is the driving environment information collected from the target image content, the virtual test scenario includes a virtual vehicle, and during the virtual test, the driving actions of the virtual vehicle match those of the autonomous vehicle 210.

[0030] Step 102: Generate a test result based on the target virtual driving parameters.

[0031] Among them, the above virtual test scenario can be various driving scenarios that the autonomous vehicle 210 may encounter during driving. For example, the virtual test scenario can include driving scenarios such as a pedestrian crossing the road, a vehicle in front changing lanes, and following a vehicle normally. By testing the autonomous vehicle 210 based on the above test scenarios, it is convenient to determine whether the corresponding functional modules in the autonomous vehicle 210 can accurately identify the above test scenarios and make corresponding responses to different test scenarios. For example, when testing the autonomous vehicle 210 based on the pedestrian crossing the road scenario, determine whether the autonomous vehicle 210 can decelerate or avoid reasonably to avoid colliding with pedestrians.

[0032] Specifically, the images in the above virtual test scenario can be generated based on a virtual simulation platform, and the image content of the virtual test scenario is displayed based on the display device 220. The image content of the virtual test scenario can be simulation data pre-constructed based on the virtual simulation platform. For example, when the virtual test scenario is a "pedestrian crossing the road scenario" and the virtual vehicle is driving virtually in the virtual test scenario, an animation content of a pedestrian crossing the road can be simulated in front of the field of view of the virtual vehicle to facilitate testing whether the autonomous vehicle 210 can output the expected driving behavior when facing this test scenario.

[0033] The above autonomous vehicle 210 outputs an overhead state, that is, all the wheels of the autonomous vehicle 210 are in a suspended state. For example, please refer to Figure 2 , in an embodiment of the present disclosure, the autonomous vehicle 210 can be lifted from the bottom by a lifting device 250 to make the autonomous vehicle 210 in a suspended state. Specifically, please refer to Figure 2, a jacking device 250 can be provided near each of the four wheels of the autonomous vehicle 210. Then, the four jacking devices 250 are respectively controlled to extend to lift the autonomous vehicle 210 to a suspended state. In this way, during the process of the autonomous vehicle 210 outputting corresponding driving actions, the wheels of the autonomous vehicle 210 can output corresponding actions, but the position of the autonomous vehicle 210 will remain unchanged.

[0034] The virtual test scenario may specifically include a road traffic scenario. The virtual vehicles included in the virtual test scenario specifically mean that the roads in the road traffic scenario include virtual vehicles; that is, the target image content includes the image content of the virtual vehicles.

[0035] The above display device 220 can be a common display device 220 in the related art. For example, the display device 220 can be a display screen or a projection display device 220, etc. And the display interface of the display device 220 is located in front of the field of view of the autonomous vehicle 210. Please refer to Figure 2 , in an embodiment of the present disclosure, a display device 220 can be placed in front of the field of view of the autonomous vehicle 210, and the display end face of the display device 220 faces the front of the autonomous vehicle 210.

[0036] During the process of the virtual test, the driver can control the virtual vehicle by operating the vehicle in the real world, and the virtual vehicle simulates the virtual driving of the autonomous vehicle 210 in the virtual test scenario. Specifically, when the display device 220 displays the target image content, the autonomous vehicle 210 collects the external driving environment information from the target image content displayed by the display device 220, and then outputs corresponding driving actions in response to the driving environment information. Then, the target driving parameters corresponding to the driving actions of the autonomous vehicle 210 are obtained, and then the target driving parameters are transmitted to the simulation platform, so that the simulation platform controls the virtual vehicle to output driving actions matching the autonomous vehicle 210 based on the target driving parameters, thereby realizing the process of the virtual vehicle simulating the virtual driving of the autonomous vehicle 210 in the virtual test scenario.

[0037] Among them, the driving environment information may include various types of environment information that need to be collected during the driving process of the vehicle. For example, the driving environment information may include the attribute information of various road traffic elements. Among them, the road traffic elements may include: vehicles traveling on the road, various obstacles, various traffic signs, pedestrians and other elements. The attribute information may include attribute information such as position and speed. The target driving parameters may include all control parameters for controlling the autonomous driving vehicle 210 to output autonomous driving actions. For example, vehicle speed parameters, steering wheel angle parameters, etc.

[0038] It can be understood that during the virtual driving of the virtual vehicle in the virtual test scenario, the image content displayed by the display device 220 can change with the position change of the virtual vehicle, so as to simulate the scenario of the autonomous driving vehicle 210 driving on the real road. During this process, various dangerous actions can be completed by the virtual vehicle in the virtual test scenario. For example, various collision actions. Since the autonomous driving vehicle 210 does not need to collide in the real world during the test, the test cost can be effectively reduced. At the same time, since during the test, the driving environment is perceived based on the real autonomous driving vehicle 210, and at the same time, the target driving parameters output by the real autonomous driving vehicle 210 are used to control the virtual vehicle to complete the corresponding test behaviors, it is beneficial to improve the authenticity of the test results.

[0039] The above test results may include a first test result and a second test result. Among them, the first test result is the test result of passing the test, and the second test result is the test result of failing the test. Specifically, since during the test of the autonomous driving vehicle 210 based on the above virtual test scenario, when the autonomous driving vehicle 210 outputs the expected driving actions, the first test result can be output. When the autonomous driving vehicle 210 outputs other driving actions outside the expectation, the second test result can be output. Therefore, based on the target driving parameters of the autonomous driving vehicle 210 during the virtual test process, it can be determined whether the autonomous driving vehicle 210 outputs the expected driving actions.

[0040] In an embodiment of the present disclosure, at least two candidate test scenarios may be pre-configured in the simulation platform. For example, the at least two candidate test scenarios may include common driving scenarios such as a scenario where a person crosses the road, a scenario where the vehicle in front changes lanes, and a scenario of normal following. And at least two expected driving parameters may be preset, wherein the at least two candidate test scenarios correspond one-to-one with the at least two expected driving parameters, and the expected driving parameters corresponding to different candidate test scenarios are different, and the at least two expected driving parameters correspond one-to-one with at least two expected driving actions. The virtual test scenario is any one of the at least two candidate test scenarios. When the target driving parameter is obtained, it is determined whether the target driving parameter matches the expected driving parameter corresponding to the virtual test scenario. If so, the first test result is output; if not, the second test result is output. That the target driving parameter matches the expected driving parameter corresponding to the virtual test scenario may mean that the difference between the target driving parameter and the expected driving parameter corresponding to the virtual test scenario is less than a preset threshold.

[0041] In this embodiment, the real autonomous driving vehicle 210 is used in combination with the virtual test scenario for testing. Thus, during the test, the real autonomous driving vehicle 210 can obtain driving environment information from the virtual driving scenario and output corresponding driving actions. Then, a test result can be generated based on the target driving parameter of the autonomous driving vehicle 210 during the test. During this test process, since the autonomous driving vehicle 210 does not need to drive on a real road environment, it is beneficial to reduce the test cost. At the same time, a test result can be generated based on the driving parameter of the real autonomous driving vehicle 210 during the test. Therefore, it is beneficial to improve the accuracy of the test result.

[0042] The above-mentioned target driving parameter may include the steering wheel angle parameter of the autonomous driving vehicle 210. In order to implement the step of "obtaining the target driving parameter of the autonomous driving vehicle 210 in step 101" above, the following uses a specific embodiment to further explain the acquisition process of the steering wheel angle parameter.

[0043] Optionally, please refer to Figure 2 , a wheel angle detection device 260 is provided on the autonomous driving vehicle 210, and the wheel angle detection device 260 is arranged on the side of the first wheel 212 of the autonomous driving vehicle 210. The step of "obtaining the target driving parameter of the autonomous driving vehicle 210" in the above step 101 includes:

[0044] Detecting the attitude parameter of the first wheel 212 based on the wheel angle detection device 260;

[0045] Determine the steering wheel angle parameter based on the attitude parameter.

[0046] Specifically, please refer to Figure 2 , the first wheel 212 may be one of the front wheels of the autonomous vehicle 210. The attitude parameter may include the steering angle of the first wheel 212, and the steering angle of the wheel refers to the angle by which the first vehicle rotates when the steering wheel rotates. Since during the rotation of the steering wheel, the first wheel 212 will rotate synchronously with the steering wheel according to a set ratio, and the rotation direction of the first wheel 212 is the same as that of the steering wheel. Therefore, the corresponding relationship between the steering angle of the first wheel 212 and the steering wheel angle parameter can be determined in advance. In this way, after obtaining the attitude parameter of the first vehicle, since the attitude parameter includes the steering angle of the first wheel 212, the steering wheel angle parameter can be determined according to the corresponding relationship, thereby completing the acquisition process of the steering wheel angle parameter.

[0047] It can be understood that the above-mentioned wheel steering angle detection device 260 is a detection device independent of the steering wheel angle detection sensor built into the autonomous vehicle 210. Specifically, the wheel steering angle detection device 260 may be a device added on the basis of the autonomous vehicle 210 to implement the test method provided in the present disclosure, and the detection result of the wheel steering angle detection device 260 can be directly transmitted to the virtual simulation platform, so that the virtual simulation platform can control the virtual vehicle based on the steering wheel angle parameter subsequently.

[0048] The above-mentioned wheel steering angle detection device 260 may be various types of detection devices capable of implementing attitude detection in the related art. For example, the wheel steering angle detection device 260 may include a photographing device 261, which collects an image of the first wheel 212 to identify the attitude of the first wheel 212. In addition, the wheel steering angle detection device 260 may also include a plurality of infrared distance detection devices, which respectively detect the distances between a plurality of points on the first wheel 212 and the infrared distance detection devices, and then calculate the attitude of the first vehicle based on the distance detection results.

[0049] In this embodiment, since the process of obtaining the steering wheel angle parameter is not detected based on the steering wheel angle detection sensor built into the autonomous vehicle 210, this obtaining process does not need to invade the internal bus of the autonomous vehicle 210, thus realizing non-invasive acquisition of the steering wheel angle parameter. Since the invasive (Hack) method is used to directly read the data on the Controller Area Network (CAN) bus of the autonomous vehicle 210, it will bring great inconvenience to the verification before the vehicle rolls off the production line. Therefore, compared with the invasive (Hack) method of directly reading the data on the Controller Area Network (CAN) bus of the autonomous vehicle 210 to obtain the steering wheel angle parameter, the method of the present disclosure can avoid the problem of bringing inconvenience to the verification before the vehicle rolls off the production line.

[0050] To implement the step of "detecting the attitude parameter of the first wheel 212 based on the wheel angle detection device 260", the structure and detection principle of the wheel angle detection device 260 will be further explained below with a specific embodiment.

[0051] Specifically, in an embodiment of the present disclosure, a fluorescent member 230 may be provided on the surface of the first wheel 212. The wheel angle detection device 260 may include a light emitting member 262 and a photographing device 261. The light emitting member 262 and the photographing device 261 are respectively disposed on the side of the first wheel 212, and the emitting end of the light emitting member 262 faces the fluorescent member 230, and the photographing end face of the photographing device 261 faces the first wheel 212. Detecting the attitude parameter of the first wheel 212 based on the wheel angle detection device 260 includes:

[0052] Collecting a photographed image based on the photographing device 261, where the photographed image is a photographed image collected when the light emitting member 262 excites the fluorescent member 230 to emit fluorescence, and the photographed image includes the image content of the fluorescent member 230;

[0053] Performing image recognition on the photographed image to obtain the attitude parameter.

[0054] Please refer to Figure 2 and Figure 3 , the fluorescent member 230 may include a mounting member 232 and a fluorescent tape 231. The mounting member 232 is cylindrical, and the mounting member 232 is perpendicularly disposed on the hub end face of the first wheel 212 and fixedly connected to the center point of the hub end face. The fluorescent tape 231 is wound around the outer surface of the mounting member 232.

[0055] Specifically, when the light emitted by the light-emitting component 262 irradiates the fluorescent tape 231, the fluorescent tape 231 is excited, so that the fluorescent tape 231 emits fluorescence. Among them, the fluorescence emitted by the fluorescent tape 231 is fluorescence with a strong contrast to the surrounding light. In this way, it is beneficial to accurately identify the position of the fluorescent tape 231 during the subsequent image recognition process, and determine the attitude information of the first wheel 212 based on the position of the fluorescent tape 231.

[0056] Among them, during the process of the steering wheel driving the first wheel 212 to rotate, the mounting component 232 will drive the fluorescent tape 231 to rotate synchronously, that is, as the position of the first wheel 212 changes, the position of the fluorescent tape 231 will also change. Therefore, the corresponding relationship between the rotation angle of the first wheel 212 and the position of the fluorescent tape 231 can be determined in advance. In this way, in the subsequent process, only by obtaining the position of the fluorescent tape 231, the rotation angle of the first wheel 212 can be determined according to this corresponding relationship.

[0057] The above-mentioned photographing device 261 can be various types of photographing devices 261 in the related art, and the position of the photographing device 261 is fixed. During the rotation of the first wheel 212, the fluorescent tape 231 is always within the image acquisition range of the photographing device 261. Since the position of the photographing device 261 is fixed, therefore, based on the image photographed by the photographing device 261, the position of the fluorescent tape 231 can be determined, and then based on the position of the fluorescent tape 231, the rotation angle of the first wheel 212 can be determined by using the above corresponding relationship. Therefore, the above-mentioned image recognition of the photographed image to obtain the attitude parameters can specifically include: recognizing the position of the fluorescent tape 231 in the photographed image to obtain a position recognition result, and determining the rotation angle of the first wheel 212 according to the corresponding relationship based on the position recognition result, so as to complete the determination process of the attitude parameters.

[0058] In this embodiment, by using the fluorescent component 230 to identify a certain position area of the first wheel 212, since the fluorescent component 230 can emit fluorescence with a strong contrast to the surrounding light after being excited, the identification effect of the first wheel 212 is improved. In this way, it is beneficial to improve the accuracy of recognition in the subsequent image recognition process, and further beneficial to improve the accuracy of the obtained attitude parameters.

[0059] In an embodiment of the present disclosure, in order to improve the accuracy of the obtained attitude parameters, before "performing image recognition on the photographed image to obtain the attitude parameters", the photographed image can also be preprocessed to filter out interference factors in the photographed image, which is beneficial to improve the accuracy of recognition in the image recognition process. The specific implementation process can be:

[0060] Performing image recognition on the captured image to obtain the pose parameters includes:

[0061] Performing image processing on the captured image based on a preset image processing method to obtain a target image, where the preset image processing method at least includes: noise filtering processing;

[0062] Performing image recognition on the target image to obtain target orientation information, where the target orientation information includes the direction indicated by the fluorescent member 230;

[0063] Determining the pose parameters based on the target orientation information and a preset reference direction, where the pose parameters include the angle between the direction indicated by the fluorescent member 230 and the preset reference direction.

[0064] Among them, the above preset image processing method may further include other image processing methods such as grayscale processing and image size transformation processing. The above noise filtering processing may specifically be: using a Kalman filtering method to filter the noise in the image.

[0065] Specifically, in the embodiments of the present disclosure, the fluorescent member 230 includes the above-mentioned mounting member 232 and fluorescent tape 231. Since the fluorescent tape 231 is disposed around the outer surface of the mounting member 232, therefore, the images captured by the imaging device 261 of the fluorescent member 230 all include a strip-shaped area, and this strip-shaped area is the area where the fluorescent member 230 is located, that is, the captured image also includes this strip-shaped area. Correspondingly, the target image after processing the captured image by using the preset image processing method will also include this strip-shaped area. Therefore, the position of the strip-shaped area in the target image can be recognized by using an image recognition algorithm in related technologies, and then the direction indicated by the strip-shaped area (that is, the direction indicated by the above-mentioned fluorescent member 230) can be determined. The direction indicated by the strip-shaped area is: the extending direction of the fluorescent tape 231 (that is, the length direction of the fluorescent tape 231).

[0066] The above preset reference direction may be a pre-determined reference direction. For example, the preset reference direction may be a reference direction such as a horizontal direction or a vertical direction. In an embodiment of the present disclosure, the angle between the direction indicated by the fluorescent member 230 and the preset reference direction may be defined as the target angle. During the process of the steering wheel driving the first wheel 212 to rotate, the mounting member 232 will drive the fluorescent tape 231 to rotate synchronously, thereby causing the change in the magnitude of the target angle. Therefore, the corresponding relationship between the rotation angle of the first wheel 212 and the magnitude of the target angle can be determined in advance. In this way, in the subsequent process, only by calculating the target angle can the rotation angle of the first wheel 212 be determined, and then the attitude parameter can be obtained.

[0067] In this embodiment, before image recognition, image processing is performed on the captured image by means of preset image processing, which is beneficial to filtering out noise information in the captured image, and thus can improve the accuracy of recognition in the subsequent image recognition process.

[0068] The above target driving parameter may further include the vehicle speed parameter of the autonomous vehicle 210. To implement the step of "acquiring the target driving parameter of the autonomous vehicle 210 in step 101" above, the following further explains the acquisition process of the vehicle speed parameter of the autonomous vehicle 210 with a specific embodiment.

[0069] Optionally, the target driving parameter includes the vehicle speed parameter of the autonomous vehicle 210. A wheel speed detection device 240 is provided on the autonomous vehicle 210. The wheel speed detection device 240 is provided on the side of the second wheel 211 of the autonomous vehicle 210. The acquisition of the target driving parameter of the autonomous vehicle 210 includes:

[0070] Detecting the vehicle speed parameter based on the wheel speed detection device 240.

[0071] Wherein, the second wheel 211 may be any one of the driving wheels of the autonomous vehicle 210, that is, when the autonomous vehicle 210 is in the autonomous driving mode, the second wheel 211 rotates.

[0072] It can be understood that the above wheel speed detection device 240 is a detection device independent of the vehicle speed sensor built into the autonomous driving vehicle 210. Specifically, the wheel speed detection device 240 is a device specially added to implement the test method of the present disclosure, and the detection result of the wheel speed detection device 240 can be directly transmitted to the simulation platform. Among them, the above wheel speed detection device 240 can be: various types of detection devices in the related art that can implement wheel speed detection. For example, an identification bit can be set on the surface of the second wheel 211, and by identifying the rotation speed of the identification bit, the rotation speed of the second wheel 211 can be determined. And the circumference of the second wheel 211 can be directly obtained. Therefore, the product of the rotation speed of the second wheel 211 and the circumference of the second wheel 211 can be taken, and this product can be determined as the vehicle speed of the autonomous driving vehicle 210, thereby realizing the calculation process of the vehicle speed parameter.

[0073] In this embodiment, since the process of obtaining the wheel speed parameter is not detected based on the wheel speed sensor built into the autonomous driving vehicle 210, this acquisition process does not need to invade the internal bus of the autonomous driving vehicle 210, thus realizing non-invasive acquisition of the wheel speed parameter. Since the invasive (Hack) method is adopted to directly read the data on the Controller Area Network (CAN) bus of the autonomous driving vehicle 210, it will bring great inconvenience to the verification before the vehicle rolls off the production line. Therefore, compared with the invasive (Hack) method of directly reading the data on the Controller Area Network (CAN) bus of the autonomous driving vehicle 210 to obtain the wheel speed parameter, the method of the present disclosure can avoid the problem of bringing inconvenience to the verification before the vehicle rolls off the production line.

[0074] In order to implement the step of "detecting the wheel speed parameter of the second wheel 211 based on the wheel speed detection device 240", the structure and detection principle of the wheel speed detection device 240 will be further explained below with a specific embodiment.

[0075] Optionally, the wheel speed detection device 240 includes a Hall sensor 241, and a magnetic part 270 is provided on the end face of the second wheel 211. During the rotation of the second wheel 211, the second wheel 211 can drive the magnetic part 270 to move to a position opposite to the Hall sensor 241. The detecting the wheel speed parameter of the second wheel 211 based on the wheel speed detection device 240 includes:

[0076] Obtaining the pulse signal output by the Hall sensor 241;

[0077] Determining the wheel speed parameter based on the pulse signal.

[0078] Specifically, the magnetic member 270 can be installed on the end face of the hub of the second wheel 211, and the Hall sensor 241 can be in a relative position with the end face of the hub of the second wheel 211. When the second wheel 211 drives the magnetic member 270 to move to a position opposite to the Hall sensor 241, the Hall sensor 241 can output a high level, and when the second wheel 211 drives the magnetic member 270 to move to other positions outside the relative position, the Hall sensor 241 can output a low level. Thus, by calculating the time difference between two consecutive high levels output by the Hall sensor 241, the wheel speed of the second wheel 211 can be calculated.

[0079] Please refer to Figure 2 and Figure 4 The wheel speed detection device 240 may further include a support rod 242, and the Hall sensor 241 is connected to the top end of the support rod 242 so that the Hall sensor 241 faces the end face of the second wheel 211.

[0080] Among them, the number of the magnetic members 270 can be at least one. For example, in an embodiment of the present disclosure, please further refer to Figure 2 and Figure 4 When the number of the magnetic members 270 is 4, the 4 magnetic members 270 are placed at equal distances on the outermost side of the hub, so that the included angles of the four magnetic members 270 with the horizontal line are 0°, 90°, 180°, and 360° respectively. In this way, among the pulse signals output by the Hall sensor 241, the value of the time difference between any two adjacent high levels can be determined as one-fourth of the wheel speed of the second wheel 211. It can be understood that the embodiment of the present disclosure does not limit the number of the magnetic members 270. For example, please refer to Figure 5 In another embodiment of the present disclosure, when the number of the magnetic members 270 is 1, in this way, among the pulse signals output by the Hall sensor 241, the value of the time difference between any two adjacent high levels can be determined as the wheel speed of the second wheel 211.

[0081] In this embodiment, by using the cooperation of the Hall sensor 241 and the magnetic member 270 and utilizing the magnet induction principle, the acquisition process of the wheel speed parameter is completed to realize a non-invasive parameter acquisition process.

[0082] In an embodiment of the present disclosure, the specific implementation process of testing the autonomous driving vehicle 210 may include the following steps:

[0083] Select a driving scenario. The driving scenario is divided into a preset scenario and a custom scenario, that is, the above virtual test scenario is selected.

[0084] Click to start the evaluation and enter the evaluation mode.

[0085] Drive the autonomous vehicle 210 in the real-world scenario either manually or in fully autonomous driving mode. Use the above-mentioned wheel angle detection device 260 to obtain the angle parameter of the first wheel 212. At the same time, use the wheel speed detection device 240 to obtain the wheel speed parameter of the second wheel 211, and send the angle parameter and wheel speed parameter to the simulation platform in real time, so that the simulation platform can calculate the steering wheel angle parameter and vehicle speed parameter based on the angle parameter and wheel speed parameter.

[0086] The simulation platform controls the virtual vehicle to perform virtual driving in the virtual test scenario according to the calculated steering wheel angle parameter and vehicle speed parameter.

[0087] The simulation platform records the driving process to facilitate analyzing whether the vehicle will have the expected output reaction under the specified input. Among them, the specified input can be various types of emergencies during the driving process of the virtual vehicle. For example, when the virtual test scenario is a scenario where a pedestrian crosses the road, the specified input is a pedestrian crossing the road. Thus, the test process of the autonomous vehicle 210 is realized.

[0088] It should be noted that by using the test method provided in the embodiments of the present disclosure, the test cost can be reduced, the test process is easy to implement, and it has characteristics such as low coupling, high aggregation, and repeatability, solving the problem of using high-cost hardware for testing in traditional test methods. Moreover, the accuracy of the test results obtained by using the test method provided in the embodiments of the present disclosure is relatively high.

[0089] Please refer to Figure 6 , Figure 6 which is a schematic structural diagram of a test device 600 for an autonomous vehicle 210 provided in the embodiments of the present disclosure. The test device 600 for the autonomous vehicle 210 is applied to the autonomous vehicle 210, the autonomous vehicle 210 is in an overhead state, and a display device 220 is provided in front of the field of view of the autonomous vehicle 210. Among them, the device includes:

[0090] An acquisition module 601, configured to obtain the target driving parameters of the autonomous vehicle 210 when performing a virtual test on the autonomous vehicle 210 based on the target image content, and the autonomous vehicle 210 outputs corresponding driving actions based on the driving environment information. Among them, the target image content is the image content corresponding to the virtual test scenario displayed by the display device 220, the driving environment information is the driving environment information collected from the target image content, the virtual test scenario includes a virtual vehicle, and during the virtual test, the driving actions of the virtual vehicle match the driving actions of the autonomous vehicle 210;

[0091] A generation module 602, configured to generate a test result based on the target virtual driving parameter.

[0092] Optionally, the target driving parameter includes a steering wheel angle parameter of the autonomous vehicle 210. A wheel angle detection device 260 is provided on the autonomous vehicle 210. The wheel angle detection device 260 is disposed on a side of a first wheel 212 of the autonomous vehicle 210. Please refer to Figure 7 , the acquisition module 601 includes:

[0093] A detection sub-module 6011, configured to detect an attitude parameter of the first wheel 212 based on the wheel angle detection device 260;

[0094] A determination sub-module 6012, configured to determine the steering wheel angle parameter based on the attitude parameter.

[0095] Optionally, a fluorescent member 230 is provided on a surface of the first wheel 212. The wheel angle detection device 260 includes a light emitting member 262 and a photographing device 261. The light emitting member 262 and the photographing device 261 are respectively located on a side of the first wheel 212, and an emission end of the light emitting member 262 faces the fluorescent member 230, and a photographing end face of the photographing device 261 faces the first wheel 212. Please refer to Figure 8 , the detection sub-module 6011 includes

[0096] An image acquisition unit 60111, configured to acquire a photographed image based on the photographing device 261. The photographed image is a photographed image acquired when the light emitting member 262 excites the fluorescent member 230 to emit fluorescence, and the photographed image includes image content of the fluorescent member 230;

[0097] An image recognition unit 60112, configured to perform image recognition on the photographed image to obtain the attitude parameter.

[0098] Optionally, the image recognition unit 60112 is specifically configured to perform image processing on the photographed image based on a preset image processing means to obtain a target image, where the preset image processing means at least includes: noise filtering processing;

[0099] The image recognition unit 60112 is specifically further configured to perform image recognition on the target image to obtain the attitude parameter.

[0100] Optionally, the target driving parameter includes the vehicle speed parameter of the autonomous vehicle 210. A wheel speed detection device 240 is provided on the autonomous vehicle 210. The wheel speed detection device 240 is disposed on the side of the second wheel 211 of the autonomous vehicle 210. The obtaining module 601 is specifically configured to detect the wheel speed parameter of the second wheel 211 based on the wheel speed detection device 240;

[0101] The obtaining module 601 is specifically further configured to determine the vehicle speed parameter based on the wheel speed parameter.

[0102] Optionally, the wheel speed detection device 240 includes a Hall sensor 241. A magnetic member 270 is provided on the end face of the second wheel 211. During the rotation of the second wheel 211, the second wheel 211 can drive the magnetic member 270 to move to a position opposite to the Hall sensor 241. The obtaining module 601 is specifically configured to obtain the pulse signal output by the Hall sensor 241;

[0103] The obtaining module 601 is specifically further configured to determine the wheel speed parameter based on the pulse signal.

[0104] It should be noted that the test device 600 of the autonomous vehicle 210 provided in this embodiment can implement all the technical solutions of the above-mentioned test method embodiment of the autonomous vehicle 210, and thus can at least achieve all the above technical effects, which will not be elaborated here.

[0105] In the technical solution of the present disclosure, the acquisition, storage, and application of the user's personal information involved all comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0106] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0107] Figure 9 A schematic block diagram of an exemplary electronic device 900 that can be used to implement the embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0108] As Figure 9As shown, electronic device 900 includes a computing unit 901 which can perform various appropriate actions and processes according to computer programs stored in a read-only memory (ROM) 902 or computer programs loaded from a storage unit 908 into a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of device 900 can also be stored. The computing unit 901, ROM 902, and RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0109] A plurality of components in the electronic device 900 are connected to the I / O interface 905, including: an input unit 906, such as a keyboard, a mouse, etc.; an output unit 907, such as various types of displays, speakers, etc.; a storage unit 908, such as a magnetic disk, an optical disc, etc.; and a communication unit 909, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 909 allows the device 900 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0110] The computing unit 901 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 901 executes the various methods and processes described above, such as the test method of the autonomous vehicle 210. For example, in some embodiments, the test method of the autonomous vehicle 210 can be implemented as a computer software program which is tangibly contained in a machine-readable medium, such as the storage unit 908. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 900 via the ROM 902 and / or the communication unit 909. When the computer program is loaded into the RAM 903 and executed by the computing unit 901, one or more steps of the test method of the autonomous vehicle 210 described above are executed. Alternatively, in other embodiments, the computing unit 901 can be configured to execute the test method of the autonomous vehicle 210 by any other appropriate means (e.g., by means of firmware).

[0111] The various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), systems-on-chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that receives data and instructions from a storage system, at least one input device, and at least one output device, and transmits the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0112] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the program codes are executed by the processor or controller, the functions / operations specified in the flowchart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0113] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0114] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, speech input, or tactile input).

[0115] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), and the Internet.

[0116] A computer system can include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The relationship between the client and the server is generated by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, or a server of a distributed system, or a server incorporating a blockchain.

[0117] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in this disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and no limitation is imposed herein.

[0118] The above specific embodiments do not constitute a limitation on the protection scope of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the protection scope of this disclosure.

Claims

1. A test method for an autonomous vehicle, applied to an autonomous vehicle. The autonomous vehicle is in an overhead state, and a display device is arranged in front of the field of view of the autonomous vehicle. Among them, A wheel rotation angle detection device is provided on the side of the first wheel of the autonomous vehicle. A strip-shaped fluorescent member is provided on the surface of the first wheel. The wheel rotation angle detection device includes a light-emitting member and a photographing device, and the emission end of the light-emitting member faces the fluorescent member, and the photographing end face of the photographing device faces the first wheel. The method includes: Based on the image content corresponding to the virtual test scenario displayed on the display device, perform a virtual test on the autonomous vehicle. The virtual test scenario includes a virtual vehicle. During the virtual test, the driving actions of the virtual vehicle match the driving actions of the autonomous vehicle; When the autonomous vehicle outputs corresponding driving actions based on the driving environment information collected from the image content, collect a photographed image based on the photographing device, where the photographed image is a photographed image collected when the light-emitting member excites the fluorescent member to emit fluorescence, and the photographed image includes the image content of the fluorescent member; Perform image processing on the photographed image based on a preset image processing means to obtain a target image, where the preset image processing means at least includes: noise filtering processing; Perform image recognition on the target image to obtain target orientation information, where the target orientation information includes the direction indicated by the fluorescent member; Determine the attitude parameter of the first wheel based on the target orientation information and a preset reference direction, where the attitude parameter includes the angle between the direction indicated by the fluorescent member and the preset reference direction; Determine the target driving parameter of the autonomous vehicle based on the attitude parameter, where the target driving parameter includes the steering wheel rotation angle parameter of the autonomous vehicle; Generate a test result based on the target virtual driving parameter.

2. The method according to claim 1, wherein The target driving parameter includes the vehicle speed parameter of the autonomous vehicle. A wheel speed detection device is provided on the side of the second wheel of the autonomous vehicle. Obtaining the target driving parameter of the autonomous vehicle includes: Detect the wheel speed parameter of the second wheel based on the wheel speed detection device; Determine the vehicle speed parameter based on the wheel speed parameter.

3. The method according to claim 2, wherein, The wheel speed detection device includes a Hall sensor. A magnetic member is provided on the end face of the second wheel. During the rotation of the second wheel, the second wheel can drive the magnetic member to move to a position opposite to the Hall sensor. Detecting the wheel speed parameter of the second wheel based on the wheel speed detection device includes: Obtain the pulse signal output by the Hall sensor; Determine the wheel speed parameter based on the pulse signal.

4. A test device for an autonomous vehicle, which is applied to the autonomous vehicle. The autonomous vehicle is in an overhead state, and a display device is arranged in front of the field of view of the autonomous vehicle. Among them, A wheel rotation angle detection device is provided on the side of the first wheel of the autonomous vehicle. A strip-shaped fluorescent member is provided on the surface of the first wheel. The wheel rotation angle detection device includes a light-emitting member and a photographing device, and the emission end of the light-emitting member faces the fluorescent member, and the photographing end face of the photographing device faces the first wheel. The device includes: An acquisition module for performing the following steps: Based on the image content corresponding to the virtual test scenario displayed by the display device, perform virtual testing on the autonomous driving vehicle. The virtual test scenario includes a virtual vehicle. During the virtual test, the driving actions of the virtual vehicle match the driving actions of the autonomous driving vehicle; When the autonomous driving vehicle outputs corresponding driving actions based on the driving environment information collected from the image content, collect a captured image based on the imaging device. The captured image is a captured image collected when the light-emitting member excites the fluorescent member to emit fluorescence, and the captured image includes the image content of the fluorescent member; Perform image processing on the captured image based on a preset image processing means to obtain a target image. The preset image processing means at least includes: noise filtering processing; Perform image recognition on the target image to obtain target orientation information. The target orientation information includes the direction indicated by the fluorescent member; Determine the attitude parameter of the first wheel based on the target orientation information and a preset reference direction. The attitude parameter includes the angle between the direction indicated by the fluorescent member and the preset reference direction; Determine the target driving parameter of the autonomous driving vehicle based on the attitude parameter. The target driving parameter includes the steering wheel angle parameter of the autonomous driving vehicle; A generation module for generating a test result based on the target virtual driving parameter.

5. The device according to claim 4, wherein, The target driving parameter includes the vehicle speed parameter of the autonomous driving vehicle. A wheel speed detection device is provided on the autonomous driving vehicle. The wheel speed detection device is provided on the side of the second wheel of the autonomous driving vehicle. The acquisition module is specifically configured to detect the wheel speed parameter of the second wheel based on the wheel speed detection device; The acquisition module is specifically further configured to determine the vehicle speed parameter based on the wheel speed parameter.

6. The apparatus according to claim 5, wherein, The wheel speed detection device includes a Hall sensor. A magnetic member is provided on the end face of the second wheel. During the rotation of the second wheel, the second wheel can drive the magnetic member to move to a position opposite to the Hall sensor. The acquisition module is specifically configured to acquire the pulse signal output by the Hall sensor; The acquisition module is specifically further configured to determine the wheel speed parameter based on the pulse signal.

7. An electronic device, comprising: At least one processor; And A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to execute the steps of the test method for an autonomous driving vehicle according to any one of claims 1-3.

8. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to execute the steps of the test method for an autonomous driving vehicle according to any one of claims 1-3.

9. A computer program product, comprising a computer program which, when executed by a processor, implements the steps of the test method for an autonomous driving vehicle according to any one of claims 1-3.

Images