HIL test method and device based on intelligent driving

Abstract

The invention relates to the field of automotive electronics, and provides an HIL test method and device based on intelligent driving. The device comprises a video generation device used for generating an initial virtual scene image according to a test task and displaying the initial virtual scene image at a first position in a video camera obscura; the lens assembly is arranged in the video camera obscura and used for receiving the initial virtual scene image; the to-be-tested component is used for collecting a target virtual scene image at a preset position; the video camera obscura is configured to respond to the target virtual scene image and correspondingly adjust the optical environment of the test space; the real-time calculation unit is configured to calculate the real-time response of the virtual vehicle based on the target virtual scene image and the decision control instruction, and synchronously feed back the real-time response to the video generation equipment and the to-be-tested component; and the verification module is configured to verify the to-be-tested component according to a feedback result of the real-time computing unit. Compared with the prior art, the safety and reliability of the intelligent driving technology in real vehicle running can be improved.

Description

Technical Field

[0001] This application relates to the field of automotive electronics, and more particularly to a HIL testing device and method based on intelligent driving. Background Technology

[0002] Currently, autonomous driving technology is developing rapidly, evolving from early conceptualization to its current commercial application in a pace exceeding expectations. However, with the widespread adoption of this emerging technology, various problems have arisen in the field of autonomous driving. Frequent accidents have sparked widespread public concern and anxiety. For example, some autonomous vehicles have been rushed to market with immature perception systems, resulting in their inability to accurately identify obstacles such as road barriers, leading to collisions with other vehicles, pedestrians, or obstacles. These accidents not only cause significant loss of life and property but also raise questions about the safety of autonomous driving technology. Against this backdrop, the testing requirements for intelligent driving systems have become more stringent than ever before.

[0003] While HIL testing offers numerous advantages, it also faces several challenges in the field of autonomous driving. On one hand, the complexity of testing cameras, as key components for autonomous vehicles to perceive their external environment, is increasingly apparent. Traditional testing schemes typically design camera dark boxes for single cameras, which struggle to meet reliability requirements when multiple controllers operate in parallel. On the other hand, current common video injection methods have significant limitations in multi-camera testing. Video injection boards are expensive, and many OEMs, in order to simplify design and improve system integration, integrate cameras and controllers into a single unit to implement driver assistance functions. However, video injection is difficult to apply effectively under this integrated strategy, and the precision of video signal control cannot be fully guaranteed. This directly limits the diversity and realism of test scenarios, making it impossible to comprehensively and accurately evaluate the performance of intelligent driving systems in complex real-world road environments during laboratory testing. This has become a major bottleneck restricting further improvements in controller performance and the overall development of autonomous driving technology.

[0004] Based on the above, there is an urgent need for a HIL testing method and device based on intelligent driving, which can increase the number of video dark box output images exponentially within a limited cost, thereby efficiently supporting multi-controller parallel testing in autonomous driving, ensuring that autonomous driving technology has higher safety and reliability, and meeting the industry's needs for testing high-performance intelligent driving systems. Summary of the Invention

[0005] The purpose of this invention is to provide a HIL (High-Intensity Interval) testing method and apparatus based on intelligent driving, which can improve the safety and reliability of intelligent driving technology in real-world vehicle operation. The specific solution is as follows:

[0006] A HIL testing device based on intelligent driving, characterized in that the device comprises:

[0007] A video generation device is used to generate an initial virtual scene image based on a test task and display it in the first position within a video dark box;

[0008] The lens assembly, arranged inside the video dark box, is used to receive the initial virtual scene image and, during the process of propagating the initial virtual scene image from the first position to the preset position along a preset optical path, correct the optical parameters of the initial virtual scene image to obtain the target virtual scene image and display it at the preset position.

[0009] The component to be tested is movable and placed inside the video darkroom to acquire images of a target virtual scene at a preset location, and output decision control commands based on the target virtual scene images.

[0010] A video darkroom, wherein the internal space of the video darkroom is a light-adjustable test space, configured to adjust the optical environment of the test space in response to a target virtual scene image;

[0011] The real-time machine computing unit is electrically connected to the video generation device and the component under test, respectively. It is configured to calculate the real-time reaction of the virtual vehicle based on the target virtual scene image and the decision control instructions output by the component under test, and synchronously feed back the reaction results to the video generation device and the component under test.

[0012] The verification module is configured to verify the component under test based on the feedback results from the real-time machine computing unit, and output a test report based on the verification results.

[0013] Furthermore, the video generation device includes:

[0014] The video generation unit is configured to generate a corresponding initial virtual scene image based on the test task;

[0015] The first display unit, located in the first position inside the video dark box, is used to display the initial virtual scene image.

[0016] Furthermore, the lens assembly includes at least: a beam splitter and a plurality of lenses; wherein, the beam splitter is used to split the initial virtual scene image at the first position into a plurality of initial virtual scene images; so that each initial virtual scene image is transmitted from the first position along a preset optical path; the plurality of lenses correct the optical parameters of the initial virtual scene images during the transmission process to form a high-definition target virtual scene image, and display it at the corresponding preset position, so that the component under test can obtain a target virtual scene image that meets the test requirements;

[0017] The optical parameters include at least: field of view and distortion parameters; the distortion parameters include at least: spherical aberration, chromatic aberration and distortion coefficient.

[0018] Furthermore, the component to be tested includes: a number of cameras to be tested that are the same as the preset number but arranged in different positions, a moving component for adjusting the arrangement position of each camera to be tested, and a controller module electrically connected to the camera to be tested.

[0019] The camera under test is used to acquire images of a target virtual scene at a corresponding preset position and send the target virtual scene images to the controller module;

[0020] The controller module includes a plurality of test controllers, the same number as the number of cameras to be tested; wherein each test controller analyzes and calculates based on the target virtual scene image and outputs corresponding decision control commands.

[0021] The movable component includes at least: a telescopic support rod arranged at the lower end of the camera under test, and a guide rail that slides with the telescopic support rod.

[0022] Furthermore, the real-time machine computing unit includes: a host computer and a real-time machine;

[0023] The host computer is used to receive multi-source data and coordinate the interaction timing of the multi-source data; wherein, the host computer is used to perform timing synchronization and conflict detection on the decision control instructions of multiple controllers under test, and then forward them to the real-time machine;

[0024] The multi-source data includes: scene data from the video generation device, control commands from the component under test, and feedback results from the real-time machine;

[0025] The real-time machine is configured to perform real-time calculations based on the target virtual scene image received from the video generation device and the decision control commands of each controller under test synchronized with the host computer, using a vehicle dynamics model, and output synchronized feedback data; the feedback data includes: execution results, execution status, and abnormal data;

[0026] Accordingly, the verification module is configured to compare the feedback results of the real-time machine with the decision control instructions output by the controller under test based on a unified time reference, so as to verify whether the decision control instructions output by the controller under test are reasonable.

[0027] Furthermore, the verification module is also configured to compare the feedback results of the real-time machine with the decision control instructions of each controller under test, and verify whether the decision control instructions of each controller under test are reasonable.

[0028] The rationality of the collaborative commands is verified by combining the comprehensive feedback results of the vehicle dynamics model with the collaborative commands of multiple controllers under test.

[0029] A test report will be generated based on the results of the above dual verification.

[0030] A HIL testing method based on intelligent driving, applied to the aforementioned device, the method comprising the following steps:

[0031] Step S1: Generate an initial virtual scene image based on the test task and display it in the first position within the video dark box;

[0032] Step S2: During the process of propagating the initial virtual scene image from the first position to the preset position along the preset optical path, the optical parameters of the initial virtual scene image are corrected to obtain the target virtual scene image and display it at the preset position;

[0033] Step S3: Generate decision control commands based on the target virtual scene image acquired at the preset location;

[0034] Step S4: In response to the target virtual scene image, adapt and adjust the optical environment of the test space;

[0035] Step S5: Based on the target virtual scene image and decision control commands, calculate the real-time response of the virtual vehicle, output the response data with timestamps, and verify the performance of the component under test based on the response data.

[0036] An electronic device, characterized in that it comprises: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0037] The memory stores a computer program that, when executed by the processor, causes the processor to perform the steps of the method.

[0038] A computer-readable storage medium is characterized in that it stores a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of the method.

[0039] A simulation platform, characterized in that it comprises:

[0040] An electronic device for implementing the steps of the method;

[0041] A processor that runs a program, and when the program runs, it executes the steps of the method from data output by the electronic device.

[0042] A storage medium for storing a program that, when run, executes the steps of the method on data output from an electronic device.

[0043] The above solution achieves the following beneficial technical effects:

[0044] This application provides a HIL (Hardware-In-the-Lake) testing method and apparatus based on intelligent driving. First, an initial virtual scene image is generated by a video generation device according to the test task. Then, the optical parameters of the initial virtual scene image are corrected by a lens assembly, and the design parameters of the lens assembly are selected to enable cameras at different positions to accurately capture high-resolution images of the target virtual scene. Combined with an adjustable video darkroom, a high degree of simulation of complex and variable scenes is achieved. Because the position of the component under test inside the video darkroom is adjustable, simultaneous testing of multiple cameras and multiple controllers can be completed. This feature fully demonstrates flexibility in the design. Finally, a real-time machine computing unit simulates the execution actions of different controllers in the target virtual scene, and a verification module verifies the feedback results, thereby completing the performance test of the component under test and improving the safety and stability of autonomous driving operation. Attached Figure Description

[0045] Figure 1 A flowchart of the HIL testing method based on intelligent driving;

[0046] Figure 2 This is an overall structural diagram of the HIL test device based on intelligent driving.

[0047] Figure 3 This is a diagram showing the composition of the lens assembly;

[0048] Figure 4 This is a partial composition diagram of the component to be tested;

[0049] Figure 5 This is a structural topology diagram of a HIL test device based on intelligent driving, as shown in one embodiment. Detailed Implementation

[0050] To make the purpose, technical solution, and advantages of this application clearer, the following will be described in conjunction with the appendix. Figures 1-5This application will be described in further detail. It is obvious that the described embodiments are merely some, not all, of the embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments described herein without inventive effort are within the scope of protection of this application.

[0051] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the application. The singular forms “a,” “said,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0052] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0053] It should be understood that although the terms first, second, third, etc., may be used in the embodiments of this application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, first may also be referred to as second without departing from the scope of the embodiments of this application, and similarly, second may also be referred to as first.

[0054] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0055] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0056] It should be noted that any symbols and / or numbers present in the specification that are not marked in the accompanying drawings are not reference numerals.

[0057] The optional embodiments of this application are described in detail below with reference to the accompanying drawings.

[0058] Figure 1 The HIL testing device based on intelligent driving is shown, the device comprising:

[0059] A video generation device is used to generate an initial virtual scene image based on a test task and display it in the first position within a video dark box;

[0060] The lens assembly, arranged inside the video dark box, is used to receive the initial virtual scene image and, during the process of propagating the initial virtual scene image from the first position to the preset position along a preset optical path, correct the optical parameters of the initial virtual scene image to obtain the target virtual scene image and display it at the preset position.

[0061] The component to be tested is movable and placed inside the video darkroom to acquire images of a target virtual scene at a preset location, and output decision control commands based on the target virtual scene images.

[0062] A video darkroom, wherein the internal space of the video darkroom is a light-adjustable test space, configured to adjust the optical environment of the test space in response to a target virtual scene image;

[0063] The real-time machine computing unit is electrically connected to the video generation device and the component under test, respectively. It is configured to calculate the real-time reaction of the virtual vehicle based on the target virtual scene image and the decision control instructions output by the component under test, and synchronously feed back the reaction results to the video generation device and the component under test.

[0064] The verification module is configured to verify the component under test based on the feedback results from the real-time machine computing unit, and output a test report based on the verification results.

[0065] Specifically, this application can generate initial virtual scene images according to different test tasks and display them at the first position of the video darkroom. Then, the initial virtual scene images are split into multiple initial virtual scene images by a lens assembly and transmitted along a preset optical path, so that cameras at different positions can acquire target virtual images at designated locations. Moreover, during the transmission process, the lens assembly optimizes and adjusts the optical parameters of the initial virtual scene images and simultaneously combines them with the adjustable light intensity test space inside the video darkroom to achieve a high degree of simulation of complex and variable scenes. In terms of design, since the positions of the multiple cameras to be tested in the test component are adjustable inside the video darkroom, they can acquire target virtual scene images at different preset positions, thereby realizing parallel performance testing of multiple cameras and multiple controllers. Furthermore, through a real-time machine computing unit, the execution actions of different controllers in the target virtual scene are simulated, and the feedback results after the simulation execution are verified through a verification module, thereby obtaining performance tests of multiple cameras and multiple controllers.

[0066] For example, the system's given test task is to verify the collaborative performance of a front-view camera (corresponding to controller A), a side-view camera (corresponding to controller B), and a rear-view camera (corresponding to controller C) at an intersection. The front-view camera is fixed at a preset position in the center of the video dark box to capture the scene in front of the intersection; the side-view camera is positioned at a preset position on the left side of the video dark box via a moving component to capture vehicles approaching from the left; and the rear-view camera is positioned at a preset position at the rear of the video dark box to capture pedestrians behind the intersection. Lens components display the corresponding target virtual scene images at the three preset positions. The three cameras under test each capture their own scene images and send them to their respective controllers A, B, and C. Controllers A, B, and C output corresponding decision control commands based on their respective captured scene images, such as controller A outputting a braking command, controller B outputting a deceleration command, and controller C outputting a warning command. The real-time computing unit timestamps the three commands to avoid calculation errors caused by time misalignment. Then, based on the synchronized commands and scene images, it simulates the execution of actions and feeds the results back to the verification module. The verification module verifies the commands and corresponding feedback of each controller, such as:

[0067] Controller A: Outputs within 30ms, braking force is 60%, braking command results in deceleration that meets requirements, good performance;

[0068] Controller B: Deceleration command force 30%, distance from oncoming vehicle on the left exceeds safe clearance, poor performance;

[0069] Collaborative verification: The combination of commands from the three controllers did not cause vehicle instability, indicating that the collaboration was reasonable.

[0070] Furthermore, the video generation device includes:

[0071] The video generation unit is configured to generate a corresponding initial virtual scene image based on the test task;

[0072] The first display unit, located in the first position inside the video dark box, is used to display the initial virtual scene image.

[0073] The video generation unit is connected to the first display end via an HDMI cable, and the first display end is placed in a video dark box for display. The video generation unit is connected to the real-time computing unit via a network cable and transmits information in full-duplex mode.

[0074] The testing space inside the video dark box is constructed as a closed optical environment to provide a stable display platform for the initial virtual scene images generated by the video generation equipment. The lighting conditions inside the video dark box are strictly controlled to ensure the color accuracy and contrast of the projected image. The size design of the video dark box must meet the installation requirements of different cameras, and the materials must possess good optical properties, such as low reflectivity and high diffuse reflectivity, to reduce optical interference.

[0075] Furthermore, the lens assembly includes at least: a beam splitter and a plurality of lenses; wherein, the beam splitter is used to split the initial virtual scene image at the first position into a plurality of initial virtual scene images; so that each initial virtual scene image is transmitted from the first position along a preset optical path; the plurality of lenses correct the optical parameters of the initial virtual scene images during the transmission process to form a high-definition target virtual scene image, and display it at the corresponding preset position, so that the component under test can obtain a target virtual scene image that meets the test requirements;

[0076] The optical parameters include at least: field of view and distortion parameters; the distortion parameters include at least: spherical aberration, chromatic aberration and distortion coefficient.

[0077] It should be noted that a beam splitter can split incident light into multiple beams traveling in different directions. The basic principle of beam splitting is based on the reflection and refraction of light at the surfaces of different media. For example, a beam splitter consists of two media, medium 1 and medium 2, with incident light entering from medium 1 and striking the interface of the beam splitter. According to Fresnel's formula, the ratio of reflected light to transmitted light is expressed as: ; For reflectivity, Let n be the transmittance, and n1 and n2 be the refractive indices of medium 1 and medium 2, respectively. By appropriately selecting the material and angle of the beam-splitting prism, the direction and intensity of the reflected and transmitted light can be controlled, thereby splitting a beam of light into beams in multiple directions. Each beam is then imaged through an independent lens, and the lens imaging follows the Gaussian formula: Where f is the focal length of the lens, u is the object distance, and v is the image distance. The lens assembly is designed to ensure that each lens can focus the split light rays onto its corresponding imaging plane, forming a clear image. For example, in a lens assembly where each lens has a focal length of f and an object distance of u, the image distance v can be calculated using the formula above. Furthermore, to ensure image sharpness and resolution, aberrations are corrected in the lenses, such as spherical aberration, chromatic aberration, and distortion. The distortion coefficient can be expressed as... ω is the field of view angle, and h is the image height.

[0078] Based on the distance between each camera and the target virtual scene image, lenses with matching performance parameters are pre-selected.

[0079] Continuing the previous example, to ensure the synchronization and consistency of the three images, it is necessary to precisely control the optical path difference of each optical path. The optical path difference refers to the difference in optical distance that light travels along different paths. Assuming the optical paths of the light in the three paths after beam splitting are L1, L2, and L3, the optical path difference can be expressed as: By adjusting the position, angle, and spacing of the lenses, the optical path difference can be kept within the allowable error range. For example, the optical path difference can be compensated for by fine-tuning the position of the lenses, ensuring temporal and spatial consistency among the three images.

[0080] For example, if the light rays after beam splitting pass through three independent lens assemblies, each with a focal length of f=50mm and an object distance of u=100mm, then the image distance v can be calculated as 100mm using the Gaussian formula, ensuring that each image forms a clear image on the corresponding imaging plane.

[0081] After completing beam splitting, lens imaging, and optical path difference control, the lens group projects three images onto three different imaging planes, each corresponding to a controller. The light from each image is transmitted to the corresponding imaging plane through an independent optical path. The imaging plane can be an independent screen or an imaging sensor directly connected to the controller.

[0082] It is understood that, under the premise that the optical path difference is less than the design preset value, the lenses correct the optical parameters of the initial virtual scene image, adjust the field of view to match the acquisition range of the camera, eliminate optical errors through distortion parameters, and finally form a high-definition and synchronized target virtual scene image, which is then displayed at the corresponding preset position so that the component under test can acquire images that are synchronized in time and space, supporting the parallel performance testing of multiple controllers.

[0083] Furthermore, the component to be tested includes: a number of cameras to be tested that are the same as the preset number but arranged in different positions, a moving component for adjusting the arrangement position of each camera to be tested, and a controller module electrically connected to the camera to be tested.

[0084] The camera under test is used to acquire images of a target virtual scene at a corresponding preset position and send the target virtual scene images to the controller module;

[0085] The controller module includes a plurality of test controllers, the same number as the number of cameras to be tested; each test controller analyzes and calculates based on the target virtual scene image and outputs corresponding decision control commands; each test camera corresponds one-to-one with a test controller.

[0086] The movable component includes at least: a telescopic support rod disposed at the lower end of the camera under test, and a guide rail that slides with the telescopic support rod. The height of the camera under test is adjusted by the telescopic support rod, and the position of the camera under test is adjusted by the sliding engagement of the telescopic support rod and the guide rail.

[0087] It is understood that this application can support performance testing of multiple cameras and controllers under test, overcoming the limitations of traditional single testing; since the camera and controller modules are directly electrically connected, there is no need to disassemble the video signal, which can be adapted to integrated all-in-one solutions, ensuring stable image signal transmission and solving the problems of insufficient video injection control accuracy and narrow applicability.

[0088] Furthermore, the real-time machine computing unit includes: a host computer and a real-time machine;

[0089] The host computer is used to receive multi-source data and coordinate the interaction timing of the multi-source data; wherein, the host computer is used to perform timing synchronization (such as unified timestamp) and conflict detection on the decision control instructions of multiple controllers under test (such as determining priority through preset rules and executing safety instructions first), and then forward them to the real-time machine;

[0090] The multi-source data includes: scene data from the video generation device, control commands from the component under test, and feedback results from the real-time machine;

[0091] The real-time machine is configured to perform real-time calculations based on the target virtual scene image received from the video generation device and the decision control commands of each controller under test synchronized with the host computer, using a vehicle dynamics model, and output synchronized feedback data; the feedback data includes: execution results, execution status, and abnormal data;

[0092] Accordingly, the verification module is configured to compare the feedback results of the real-time machine with the decision control instructions output by the controller under test based on a unified time reference, so as to verify whether the decision control instructions output by the controller under test are reasonable.

[0093] Specifically, the timing synchronization mechanism of the host computer solves the problem of instruction timing misalignment caused by hardware delays in multiple controllers. Conflict detection proactively avoids contradictory instructions from multiple controllers, ensuring the physical rationality of the instructions input to the real-time machine and providing a reliable foundation for subsequent calculations. The real-time machine receives the target virtual scene image from the video generation device and the decision control instructions of each controller under test after synchronization with the host computer. It outputs timestamped feedback data through the vehicle dynamics model, ensuring the continuity of the time chain in the testing process. This allows the virtual vehicle's reaction to accurately reflect the actual effect of the instructions. Furthermore, the feedback results are precisely aligned with the decision control instructions, thereby achieving performance evaluation of individual controllers and the collaborative performance of controllers.

[0094] Furthermore, the verification module is also configured to compare the feedback results of the real-time machine with the decision control instructions of each controller under test, and verify whether the decision control instructions of each controller under test are reasonable.

[0095] The rationality of the coordinated commands is verified by combining the comprehensive feedback results of the vehicle dynamics model with the coordinated commands of multiple controllers under test.

[0096] A test report will be generated based on the results of the above dual verification.

[0097] Specifically, this application accurately verifies independent performance by comparing individual controllers with feedback results one-to-one, and evaluates the rationality of the overall collaborative logic through correlation analysis of multi-controller collaborative commands and comprehensive feedback. This dual verification, combined with the output test report, can not only pinpoint problems with individual controllers but also uncover potential risks in multi-component collaboration, significantly improving the depth and reliability of test evaluation and perfectly meeting the complex testing requirements of multi-system collaboration in intelligent driving.

[0098] Figure 5 This is a structural topology diagram of a HIL test device based on intelligent driving, as shown in one embodiment.

[0099] Figure 5 In the process, the image station transmits video to the video dark box via HDMI. The video dark box interacts with the camera controller and the host computer via CAN bus and real-time machine via UDP protocol. The real-time machine processes data internally using IO-model (input-output model) and relies on time synchronization to ensure data timing consistency. All modules cooperate with each other to complete the test process.

[0100] It is understood that the real-time machine is configured to perform clock calibration with the host computer, video generation device, and controller under test based on a precise time protocol to ensure that the time error of each module in the system is ≤ a preset value;

[0101] When receiving control commands synchronized from the host computer and scene data from the video generation device, the system verifies the consistency between the data timestamp and the local reference clock, marks out-of-tolerance data as time anomalies, and triggers an alarm.

[0102] Based on the verified target virtual scene image and the decision control instructions of each controller under test, real-time calculations are performed using the vehicle dynamics model to output synchronous feedback data with precise timestamps. The feedback data includes: execution results (including instruction execution time and physical parameter change curves), execution status (including time synchronization status markers), and abnormal data (including time-related anomalies such as time deviation and calculation delay exceeding limits).

[0103] Accordingly, the verification module is configured to compare the feedback result of the real-time machine (based on a unified time reference) with the decision control command output by the controller under test (time stamp synchronized by the host computer) after time alignment, so as to verify whether the decision control command output by the controller under test is reasonable, and output a test report based on the verification result.

[0104] On the other hand, this application provides a HIL testing method based on intelligent driving, the method comprising the following steps:

[0105] Step S1: Generate an initial virtual scene image based on the test task and display it in the first position within the video dark box;

[0106] Step S2: During the process of propagating the initial virtual scene image from the first position to the preset position along the preset optical path, the optical parameters of the initial virtual scene image are corrected to obtain the target virtual scene image and display it at the preset position;

[0107] Step S3: Generate decision control commands based on the target virtual scene image acquired at the preset location;

[0108] Step S4: In response to the target virtual scene image, adapt and adjust the optical environment of the test space;

[0109] Step S5: Based on the target virtual scene image and decision control commands, calculate the real-time response of the virtual vehicle (such as synchronous feedback to the video generation device and the component under test), output the response data with timestamps, and verify the performance of the component under test based on the response data.

[0110] Specifically, by correcting the optical parameters of the initial virtual scene image, the target virtual scene image is obtained. Combined with video darkroom adaptation to adjust the optical environment (such as simulating strong light or rainy night), the image captured by the camera not only conforms to the laws of physical optics (no distortion, high definition) but also reproduces the complex real-world environmental features, solving the technical problem of scene distortion in traditional video injection. The scene can be dynamically adjusted through real-time feedback data from the virtual vehicle. For example, when the risk of collision with the virtual vehicle increases, the video generation device updates the dangerous scene, thereby completing the performance testing of independent performance of a single controller and collaborative control of multiple controllers. This adapts to the testing requirements of multi-controller collaboration in intelligent driving and solves the defects of traditional testing such as delayed feedback and one-sided evaluation.

[0111] This application provides an electronic device, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0112] The memory stores a computer program that, when executed by a processor, causes the processor to perform the steps of the method.

[0113] This application also provides a computer-readable storage medium storing steps of the method that can be performed by an electronic device.

[0114] This application also provides a simulation platform, including:

[0115] An electronic device for implementing the steps of the method;

[0116] The processor runs a program that, when running, executes the steps of a hydrogen fuel cell engine pre-ignition fault diagnosis method based on data output from electronic devices.

[0117] A storage medium for storing a program that, when run, executes the steps of the method on data output from an electronic device.

[0118] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0119] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A HIL testing device based on intelligent driving, characterized in that, The device includes: A video generation device is used to generate an initial virtual scene image based on a test task and display it in the first position within a video dark box; The lens assembly, arranged inside the video dark box, is used to receive the initial virtual scene image and, during the process of propagating the initial virtual scene image from the first position to the preset position along a preset optical path, correct the optical parameters of the initial virtual scene image to obtain the target virtual scene image and display it at the preset position. The component to be tested is movable and placed inside the video darkroom to acquire images of a target virtual scene at a preset location, and output decision control commands based on the target virtual scene images. A video darkroom, wherein the internal space of the video darkroom is a light-adjustable test space, configured to adjust the optical environment of the test space in response to a target virtual scene image; The real-time machine computing unit is electrically connected to the video generation device and the component under test, respectively. It is configured to calculate the real-time reaction of the virtual vehicle based on the target virtual scene image and the decision control instructions output by the component under test, and synchronously feed back the reaction results to the video generation device and the component under test. The verification module is configured to verify the component under test based on the feedback results from the real-time machine computing unit, and output a test report based on the verification results.

2. The apparatus according to claim 1, characterized in that, The video generation device includes: The video generation unit is configured to generate a corresponding initial virtual scene image based on the test task; The first display unit, located in the first position inside the video dark box, is used to display the initial virtual scene image.

3. The apparatus according to claim 2, characterized in that, The lens assembly includes at least one beam splitter and several lenses; wherein, the beam splitter is used to split the initial virtual scene image at the first position into several initial virtual scene images; so that each initial virtual scene image is transmitted from the first position along a preset optical path; the several lenses correct the optical parameters of the initial virtual scene images during the transmission process to form a high-definition target virtual scene image, and display it at the corresponding preset position so that the component under test can obtain a target virtual scene image that meets the test requirements; The optical parameters include at least: field of view and distortion parameters; the distortion parameters include at least: spherical aberration, chromatic aberration and distortion coefficient.

4. The apparatus according to claim 3, characterized in that, The component to be tested includes: a number of cameras to be tested that are the same as the preset number but arranged in different positions, a moving component for adjusting the arrangement position of each camera to be tested, and a controller module electrically connected to the camera to be tested. The camera under test is used to acquire images of a target virtual scene at a corresponding preset position and send the target virtual scene images to the controller module; The controller module includes a plurality of test controllers, the same number as the number of cameras to be tested; wherein each test controller analyzes and calculates based on the target virtual scene image and outputs corresponding decision control commands. The movable component includes at least: a telescopic support rod arranged at the lower end of the camera under test, and a guide rail that slides with the telescopic support rod.

5. The apparatus according to claim 4, characterized in that, The real-time machine computing unit includes: a host computer and a real-time machine; The host computer is used to receive multi-source data and coordinate the interaction timing of the multi-source data; wherein, the host computer is used to perform timing synchronization and conflict detection on the decision control instructions of multiple controllers under test, and then forward them to the real-time machine; The multi-source data includes: scene data from the video generation device, control commands from the component under test, and feedback results from the real-time machine; The real-time machine is configured to perform real-time calculations based on the target virtual scene image received from the video generation device and the decision control commands of each controller under test synchronized with the host computer, using a vehicle dynamics model, and output synchronized feedback data; the feedback data includes: execution results, execution status, and abnormal data; Accordingly, the verification module is configured to compare the feedback results of the real-time machine with the decision control instructions output by the controller under test based on a unified time reference, so as to verify whether the decision control instructions output by the controller under test are reasonable.

6. The apparatus according to claim 5, characterized in that, The verification module is further configured to compare the feedback results of the real-time machine with the decision control instructions of each controller under test, and verify whether the decision control instructions of each controller under test are reasonable. The rationality of the coordinated commands is verified by combining the comprehensive feedback results of the vehicle dynamics model with the coordinated commands of multiple controllers under test. A test report will be generated based on the results of the above dual verification.

7. A HIL testing method based on intelligent driving, characterized in that, Applied to the apparatus of any one of claims 1-6, the method comprises the following steps: Step S1: Generate an initial virtual scene image based on the test task and display it in the first position within the video dark box; Step S2: During the process of propagating the initial virtual scene image from the first position to the preset position along the preset optical path, the optical parameters of the initial virtual scene image are corrected to obtain the target virtual scene image and display it at the preset position; Step S3: Generate decision control commands based on the target virtual scene image acquired at the preset location; Step S4: In response to the target virtual scene image, adapt and adjust the optical environment of the test space; Step S5: Based on the target virtual scene image and decision control commands, calculate the real-time response of the virtual vehicle, output the response data with timestamps, and verify the performance of the component under test based on the response data.

8. An electronic device, characterized in that, include: The processor, communication interface, memory, and communication bus are connected, with the processor, communication interface, and memory communicating with each other via the communication bus. The memory stores a computer program that, when executed by the processor, causes the processor to perform the steps of the method of claim 7.

9. A computer-readable storage medium, characterized in that, It stores a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of the method of claim 7.

10. A simulation platform, characterized in that, include: An electronic device for implementing the steps of the method of claim 7; A processor that runs a program, which, when running, executes the steps of the method of claim 7 from data output by the electronic device. A storage medium for storing a program that, when run, performs the steps of the method of claim 7 on data output from an electronic device.

Images