Automatic parking function real vehicle closed-loop simulation test method, system, equipment and medium

Abstract

The invention discloses an automatic parking function real vehicle closed-loop simulation test method, system and device and a medium, and belongs to the technical field of intelligent driving vehicle testing. The method comprises the steps that a test upper computer takes format-standardized first scene data as current scene data and transmits the current scene data to a to-be-tested vehicle, and the first scene data is test scene data screened from a real road acquisition database; the to-be-tested vehicle identifies a virtual parking space in the current scene data and transmits an identification result to the test upper computer; the test upper computer updates the relative position between the to-be-tested vehicle and the virtual parking space in real time based on the identification result and the real-time motion data of the to-be-tested vehicle in the automatic parking process; and the to-be-tested vehicle generates transverse and longitudinal control instructions to control the to-be-tested vehicle to be automatically parked in the virtual parking space in combination with the relative position and the real-time vehicle body associated data, so that the problems of low virtual scene trueness and inaccurate simulation precision caused by the adoption of a vehicle dynamics model in traditional simulation are solved.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent driving vehicle testing, and specifically to a closed-loop simulation test method, system, device and computer-readable storage medium for an automatic parking function real vehicle. Background Art

[0002] With the rapid development of intelligent driving technology, the requirements for testing efficiency of various intelligent driving functions are getting higher and higher. Among them, how to test the automatic parking function efficiently and accurately is becoming more and more important.

[0003] In the prior art, there are two main ways to test the automatic parking function. The first is to build a real test scene and use a real car to test the automatic parking function; the second is to simulate ultrasonic radar input to build a virtual perception scene and combine it with a virtual vehicle dynamics model to simulate the automatic parking function.

[0004] However, in the first method, a real vehicle is used for testing in a real test scenario, which has problems such as limited scenarios, low safety, and low test efficiency. In the second method, only ultrasonic radar input is simulated, and only spatial parking space simulation tests can be performed. In addition, because the vehicle dynamics model is significantly different from the real vehicle, the simulation accuracy is low. Summary of the invention

[0005] The present application provides a closed-loop simulation test method, system, device and computer-readable storage medium for an automatic parking function real vehicle, which can solve the problems existing in the prior art of using a real vehicle for testing in a real test scenario, such as limited scenarios, low safety, and low test efficiency; and technical problems such as only simulating ultrasonic radar input, which can only perform simulation tests on spatial parking spaces, and low simulation accuracy due to the large difference between the vehicle dynamics model and the real vehicle.

[0006] In a first aspect, an embodiment of the present application provides a closed-loop simulation test method for an automatic parking function, which is applied to a closed-loop simulation test system for an automatic parking function. The closed-loop simulation test system for an automatic parking function includes a test host computer and a vehicle to be tested. The closed-loop simulation test method for an automatic parking function includes:

[0007] The test host computer uses the first scene data in a standardized format as the current scene data and transmits it to the vehicle to be tested, wherein the first scene data is the test scene data selected from the real road sampling database;

[0008] The vehicle to be tested identifies the virtual parking space in the current scene data, obtains the identification result, and transmits the identification result to the test host computer;

[0009] The test host computer updates the relative position between the vehicle under test and the virtual parking space in real time based on the recognition result and the real-time motion data output by the inertial measurement unit of the vehicle under test during the automatic parking process, and transmits the relative position to the vehicle under test;

[0010] The vehicle under test generates lateral and longitudinal control instructions in combination with the relative position and real-time vehicle body associated data to control the vehicle under test to automatically park in the virtual parking space, thereby realizing a closed-loop simulation test of the automatic parking function of the vehicle under test under the first scenario data.

[0011] In combination with the first aspect, in one implementation, identifying the virtual parking space in the current scene data to obtain the identification result includes:

[0012] Performing perception fusion on the camera video data and the ultrasonic radar data in the first scene data to obtain a perception fusion result;

[0013] The virtual parking space in the first scene data is identified by combining the perception fusion result and the initial vehicle body association data in the first scene data to obtain a parking space identification result.

[0014] In combination with the first aspect, in one implementation, the real-time updating of the relative position between the vehicle to be tested and the virtual parking space based on the recognition result and the real-time motion data output by the inertial measurement unit of the vehicle to be tested during the automatic parking process includes:

[0015] Determine the real-time vehicle posture information based on the real-time motion data output by the inertial measurement unit of the vehicle to be tested during the automatic parking process and the initial vehicle posture information in the recognition result;

[0016] The relative position between the vehicle to be tested and the virtual parking space is updated in real time by combining the real-time vehicle posture information and the virtual parking space posture information in the recognition result.

[0017] In combination with the first aspect, in one implementation, combining the relative position and the real-time vehicle body associated data to generate lateral and longitudinal control instructions includes:

[0018] Calculating a planned path for automatic parking by combining the relative position and the real-time vehicle body association data;

[0019] Based on the planned path, lateral and longitudinal control instructions are generated.

[0020] In combination with the first aspect, in one implementation, the real-time vehicle body-related data includes vehicle speed, gear position and steering wheel angle; the real-time motion data includes three-axis acceleration, three-axis angular velocity and attitude angle.

[0021] In combination with the first aspect, in one implementation, after completing a real vehicle closed-loop simulation test of the automatic parking function of the vehicle to be tested under the first scenario data, the method further includes:

[0022] The test host computer uses the second scene data with standardized format as the current scene data and transmits it to the vehicle under test, and returns to the step of the vehicle under test identifying the virtual parking space in the current scene data, until the actual vehicle closed-loop simulation test of the automatic parking function of the vehicle under test under the second scene data is completed;

[0023] The second scene data is test scene data that is different from the first scene data and is screened from a real road sampling database.

[0024] In a second aspect, an embodiment of the present application provides a real vehicle closed-loop simulation test system for an automatic parking function, the real vehicle closed-loop simulation test system for an automatic parking function comprising:

[0025] The test host computer is used to use the first scene data after the format is standardized as the current scene data and transmit it to the vehicle to be tested, wherein the first scene data is the test scene data screened from the real road sampling database; it is also used to update the relative position between the vehicle to be tested and the virtual parking space in real time based on the recognition result and the real-time motion data output by the inertial measurement unit of the vehicle to be tested during the automatic parking process, and transmit the relative position to the vehicle to be tested;

[0026] The vehicle under test is used to identify the virtual parking space in the current scene data, obtain the identification result, and transmit the identification result to the test host computer; it is also used to combine the relative position and the real-time vehicle body related data to generate lateral and longitudinal control instructions to control the vehicle under test to automatically park in the virtual parking space, thereby realizing the real vehicle closed-loop simulation test of the automatic parking function of the vehicle under test under the first scene data.

[0027] In conjunction with the second aspect, in one implementation, the vehicle to be tested is specifically used for:

[0028] Performing perception fusion on the camera video data and the ultrasonic radar data in the first scene data to obtain a perception fusion result;

[0029] The virtual parking space in the first scene data is identified by combining the perception fusion result and the initial vehicle body association data in the first scene data to obtain a parking space identification result.

[0030] In the third aspect, an embodiment of the present application provides a real-vehicle closed-loop simulation test device for an automatic parking function, the real-vehicle closed-loop simulation test device for the automatic parking function comprising a processor, a memory, and a real-vehicle closed-loop simulation test program for the automatic parking function stored in the memory and executable by the processor, wherein when the real-vehicle closed-loop simulation test program for the automatic parking function is executed by the processor, the steps of the real-vehicle closed-loop simulation test method for the automatic parking function as described in any one of the first aspects are implemented.

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

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

[0033] The first scene data in a standardized format is used as the current scene data by the test host computer, and is transmitted to the vehicle to be tested, wherein the first scene data is the test scene data selected from the real road sampling database; then the vehicle to be tested recognizes the virtual parking space in the current scene data, obtains the recognition result, and transmits the recognition result to the test host computer; further, the test host computer updates the relative position between the vehicle to be tested and the virtual parking space in real time based on the recognition result and the real-time motion data output by the inertial measurement unit of the vehicle to be tested during the automatic parking process, and transmits the relative position to the vehicle to be tested; finally, the vehicle to be tested combines The relative position and real-time vehicle body associated data are used to generate lateral and longitudinal control instructions to control the vehicle to be tested to automatically park in the virtual parking space, thereby realizing a real-vehicle closed-loop simulation test of the automatic parking function of the vehicle to be tested under the first scene data. The present application uses real data feedback in the parking space recognition stage to achieve high-performance evaluation of the perception system, which solves the problem of low realism of virtual scenes in traditional simulations; uses real vehicles to perform parking operations in the vehicle parking stage, which solves the problem of inaccurate simulation accuracy caused by the use of vehicle dynamics models in traditional simulations; and can also realize simulation tests of various parking spaces such as linear parking spaces and spatial parking spaces. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 The overall architecture diagram of the closed-loop simulation test system for the automatic parking function provided in one embodiment of the present application;

[0035] Figure 2 This is a flowchart diagram of the first embodiment of the closed-loop simulation test method for the automatic parking function of the present application;

[0036] Figure 3A schematic diagram of a process for identifying parking spaces by injecting road data provided in an embodiment of the present application;

[0037] Figure 4 A working principle diagram of a virtual parking space simulation module provided in one embodiment of the present application;

[0038] Figure 5 A second flowchart of a closed-loop simulation test of an automatic parking function provided in an embodiment of the present application;

[0039] Figure 6 This is a functional module diagram of an embodiment of a closed-loop simulation test system for an automatic parking function of a real vehicle of the present application;

[0040] Figure 7 This is a schematic diagram of the hardware structure of the real vehicle closed-loop simulation test equipment for the automatic parking function involved in the embodiment of the present application. DETAILED DESCRIPTION

[0041] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0042] The automatic parking function real vehicle closed-loop simulation test method provided in the present application is applied to the automatic parking function real vehicle closed-loop simulation test system, and the automatic parking function real vehicle closed-loop simulation test system includes a test host computer and a vehicle to be tested. Figure 1 The overall architecture diagram of the closed-loop simulation test system for the automatic parking function provided in one embodiment of the present application is as follows: Figure 1 As shown, the test host computer includes an automated test module, a data processing module, a virtual parking space simulation module, and an Ethernet communication module. The test host computer and the intelligent parking controller of the vehicle under test interact through the Ethernet communication module. The vehicle under test includes an intelligent parking controller and an actuator module, and the intelligent parking controller includes an Ethernet communication module, a perception module, a planning module, and a control module.

[0043] The test environment is a flat and open test site, that is, the vehicle to be tested is located in a flat and open test site. The present application uses a real vehicle to simulate automatic parking, which can solve the problem of low simulation accuracy in the prior art of using a vehicle dynamics model to simulate automatic parking.

[0044] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0045] In a first aspect, an embodiment of the present application provides a closed-loop simulation test method for an automatic parking function. Figure 2 , Figure 2 This is one of the flow charts of the first embodiment of the closed-loop simulation test method for the automatic parking function of the present application. Figure 2 As shown, the closed-loop simulation test method for the automatic parking function includes:

[0046] Step 210: The test host computer uses the first scene data in a standardized format as current scene data and transmits it to the vehicle to be tested, wherein the first scene data is test scene data selected from a real road sampling database;

[0047] The test scene data in the real road sampling database includes the following parts: the first part is the camera video data obtained by using the surround view camera on the vehicle to shoot real scenes such as underground parking lots, ground parking lots, and road parking spaces; the second part is the ultrasonic radar data obtained by using the radar sensor on the vehicle to shoot real scenes such as underground parking lots, ground parking lots, and road parking spaces; the third part is the initial body-related data, which includes the vehicle speed, gear position, and steering wheel angle when the vehicle does not perform automatic parking. Since the first scene data includes camera video data and ultrasonic radar data, full coverage test verification of spatial parking spaces and linear parking spaces can be achieved.

[0048] In the specific implementation, the automated test module in the test host computer selects the first test scene data from the real road sampling database and then transmits it to the data processing module. Since the storage format and data name of the data in different vehicle models are inconsistent, in order to improve the compatibility of the data, the data processing module standardizes the format of the first test scene data and transmits the first scene data after format standardization as the current scene data to the Ethernet communication module. Finally, the Ethernet communication module transmits the current scene data to the vehicle to be tested.

[0049] Step 220: the vehicle to be tested identifies the virtual parking space in the current scene data, obtains an identification result, and transmits the identification result to the test host computer;

[0050] In the specific implementation, the vehicle under test recognizes the virtual parking space in the current scene data through the perception module, obtains the recognition result, and transmits the recognition result to the virtual parking space module in the test host computer to complete the real data feedback.

[0051] Step 230: The test host computer updates the relative position between the vehicle under test and the virtual parking space in real time based on the recognition result and the real-time motion data output by the inertial measurement unit of the vehicle under test during the automatic parking process, and transmits the relative position to the vehicle under test;

[0052] The real-time motion data includes three-axis acceleration, three-axis angular velocity and attitude angle.

[0053] The test host computer updates the relative position between the vehicle under test and the virtual parking space in real time based on the real-time motion data, the initial vehicle posture information in the recognition results, and the virtual parking space posture information in the recognition results, and transmits the relative position to the intelligent parking controller in the vehicle under test through the Ethernet communication module.

[0054] Step 240: The vehicle under test generates lateral and longitudinal control instructions based on the relative position and the real-time vehicle body associated data to control the vehicle under test to automatically park in the virtual parking space, thereby realizing a closed-loop simulation test of the automatic parking function of the vehicle under test under the first scenario data.

[0055] During specific implementation, the intelligent parking controller in the vehicle under test combines the real-time body-related data such as the relative position, real-time vehicle speed, real-time gear position and real-time steering wheel angle to generate lateral and longitudinal control instructions; and transmits the lateral and longitudinal control instructions to the actuator, which executes the lateral and longitudinal control instructions and automatically parks the vehicle under test in the virtual parking space.

[0056] After successful parking, the virtual parking space simulation module sends a parking completion signal to the automated testing module, and the automated testing module analyzes and summarizes the test results of this round of scenario simulation testing.

[0057] In this embodiment, the first scene data after the format is standardized is used as the current scene data by the test host computer, and is transmitted to the vehicle to be tested, wherein the first scene data is the test scene data screened from the real road sampling database; then the vehicle to be tested recognizes the virtual parking space in the current scene data, obtains the recognition result, and transmits the recognition result to the test host computer; further, the test host computer updates the relative position between the vehicle to be tested and the virtual parking space in real time based on the recognition result and the real-time motion data output by the inertial measurement unit of the vehicle to be tested during the automatic parking process, and transmits the relative position to the vehicle to be tested; finally, the vehicle to be tested The vehicle combines the relative position and real-time vehicle body associated data to generate lateral and longitudinal control instructions to control the vehicle to be tested to automatically park in the virtual parking space, thereby realizing a real-vehicle closed-loop simulation test of the automatic parking function of the vehicle to be tested under the first scene data. The application uses real data feedback in the parking space recognition stage to achieve high-performance evaluation of the perception system, which solves the problem of low realism of virtual scenes in traditional simulations; uses real vehicles to perform parking operations in the vehicle parking stage, which solves the problem of inaccurate simulation accuracy caused by the use of vehicle dynamics models in traditional simulations; and can also realize simulation tests of various parking spaces such as linear parking spaces and spatial parking spaces.

[0058] Furthermore, in one embodiment, the identifying of the virtual parking space in the current scene data to obtain the identification result includes:

[0059] Step 310: Perform perception fusion on the camera video data and the ultrasonic radar data in the first scene data to obtain a perception fusion result;

[0060] Step 320: Identify the virtual parking space in the first scene data by combining the perception fusion result and the initial vehicle body associated data in the first scene data to obtain a parking space identification result.

[0061] Figure 3 A schematic diagram of the process of identifying parking spaces by reinjecting road data provided in one embodiment of the present application.

[0062] In specific implementation, after receiving the current scene data transmitted by the test host computer, the intelligent parking controller in the vehicle to be tested transmits the camera video data and ultrasonic radar data in the current scene data to the perception module, and transmits the initial vehicle body associated data in the current scene data to the planning module; then, the perception module transmits the perception fusion result to the planning module; finally, the planning module identifies the virtual parking space in the first scene data based on the perception fusion result and the initial vehicle body associated data in the first scene data to obtain a parking space identification result.

[0063] In this embodiment, the camera video data and ultrasonic radar data in the first scene data are perception-fused to obtain a perception fusion result; then the virtual parking space in the first scene data is identified in combination with the perception fusion result and the initial vehicle body associated data in the first scene data to obtain a parking space identification result; the use of real data feedback to simulate parking space search and identification is implemented to test and verify the perception algorithm, which can solve the problem that the performance of the perception system cannot be fully verified in the prior art.

[0064] Furthermore, in one embodiment, the real-time updating of the relative position between the vehicle to be tested and the virtual parking space based on the recognition result and the real-time motion data output by the inertial measurement unit of the vehicle to be tested during the automatic parking process includes:

[0065] Step 410: determining real-time vehicle posture information based on the real-time motion data output by the inertial measurement unit of the vehicle to be tested during the automatic parking process and the initial vehicle posture information in the recognition result;

[0066] Step 420: combining the real-time vehicle posture information and the virtual parking space posture information in the recognition result, and updating the relative position between the vehicle to be tested and the virtual parking space in real time.

[0067] Figure 4 This is a working principle diagram of a virtual parking space simulation module provided in one embodiment of the present application.

[0068] During specific implementation, the virtual parking space simulation module in the test host computer uses a vehicle kinematic model to continuously determine the real-time vehicle posture information based on the real-time motion data such as three-axis acceleration, three-axis angular velocity, attitude angle, etc. output by the inertial measurement unit of the vehicle under test during the automatic parking process and the initial vehicle posture information in the recognition result; then, the relative position between the vehicle under test and the virtual parking space is updated in real time by calculating the relative position of the real-time vehicle posture information and the virtual parking space posture information in the recognition result.

[0069] In this embodiment, it is provided how the virtual parking space simulation module specifically updates the relative position between the vehicle to be tested and the virtual parking space in real time, laying a foundation for realizing the closed-loop simulation test of the automatic parking function of the vehicle to be tested under the first scenario data.

[0070] Further, in one embodiment, the combining the relative position and the real-time vehicle body related data to generate the lateral and longitudinal control instructions includes:

[0071] Step 510: Calculate a planned path for automatic parking by combining the relative position and the real-time vehicle body associated data;

[0072] Step 520: Generate lateral and longitudinal control instructions based on the planned path.

[0073] During specific implementation, the planning module in the vehicle to be tested combines the relative position and the real-time body-related data sent by the actuator, uses a path planning algorithm to calculate the planned path for automatic parking, and transmits the planned path to the control module; based on the planned path, PID control, MPC control algorithm, etc. are used to generate lateral and longitudinal control instructions.

[0074] In this embodiment, it is shown how to combine the relative position and real-time vehicle body related data to generate lateral and longitudinal control instructions so that the vehicle under test can automatically park according to the lateral and longitudinal control instructions, thereby realizing a real-vehicle closed-loop simulation test of the automatic parking function of the vehicle under test under the first scenario data.

[0075] Furthermore, in one embodiment, Figure 5 The second flow diagram of the closed-loop simulation test of the automatic parking function provided by an embodiment of the present application. This embodiment uses real data to be fed back in the parking space identification stage to achieve high-performance evaluation of the perception system, solving the problem of low realism of virtual scenes in traditional simulations; uses real vehicles to perform parking operations in the vehicle parking stage, solving the problem of inaccurate simulation accuracy caused by the use of vehicle dynamics models in traditional simulations; and can also achieve simulation tests of various parking spaces such as linear parking spaces and spatial parking spaces.

[0076] Furthermore, in one embodiment, after completing the real vehicle closed-loop simulation test of the automatic parking function of the vehicle to be tested under the first scenario data, the method further includes:

[0077] The test host computer uses the second scene data with standardized format as the current scene data and transmits it to the vehicle under test, and returns to the step of the vehicle under test identifying the virtual parking space in the current scene data, until the actual vehicle closed-loop simulation test of the automatic parking function of the vehicle under test under the second scene data is completed;

[0078] The second scene data is test scene data that is different from the first scene data and is screened from a real road sampling database.

[0079] In specific implementation, after completing the closed-loop simulation test of the automatic parking function of the vehicle to be tested under the first scenario data, the automated test module in the test host computer automatically selects the second scenario data different from the first scenario data from the real road sampling database, and then transmits it to the data processing module. The data processing module standardizes the format of the second test scenario data, and transmits the second scenario data after the format standardization as the current scenario data to the Ethernet communication module. Finally, the Ethernet communication module transmits the current scenario data to the vehicle to be tested, and returns to step 220, and then executes steps 230 and 240 in sequence until the closed-loop simulation test of the automatic parking function of the vehicle to be tested under the second scenario data is completed.

[0080] In this embodiment, after completing the actual vehicle closed-loop simulation test of the automatic parking function of the vehicle to be tested under the first scenario data, the second scenario data is automatically imported, and the actual vehicle closed-loop simulation test of the automatic parking function of the vehicle to be tested under the second scenario data is completed, which can improve the test efficiency.

[0081] In a second aspect, an embodiment of the present application also provides a real vehicle closed-loop simulation test system for an automatic parking function.

[0082] In one embodiment, referring to Figure 6 , Figure 6 This is a functional module diagram of an embodiment of the closed-loop simulation test system for the automatic parking function of the present application. Figure 6 As shown, the automatic parking function real vehicle closed-loop simulation test system 600 includes:

[0083] The test host computer 601 is used to use the first scene data after the format is standardized as the current scene data and transmit it to the vehicle to be tested, wherein the first scene data is the test scene data screened from the real road sampling database; it is also used to update the relative position between the vehicle to be tested and the virtual parking space in real time based on the recognition result and the real-time motion data output by the inertial measurement unit of the vehicle to be tested during the automatic parking process, and transmit the relative position to the vehicle to be tested;

[0084] The vehicle under test 602 is used to identify the virtual parking space in the current scene data, obtain the identification result, and transmit the identification result to the test host computer; it is also used to combine the relative position and the real-time vehicle body related data to generate lateral and longitudinal control instructions to control the vehicle under test to automatically park in the virtual parking space, thereby realizing the real vehicle closed-loop simulation test of the automatic parking function of the vehicle under test under the first scene data.

[0085] Furthermore, in one embodiment, the vehicle to be tested is specifically used for:

[0086] Performing perception fusion on the camera video data and the ultrasonic radar data in the first scene data to obtain a perception fusion result;

[0087] The virtual parking space in the first scene data is identified by combining the perception fusion result and the initial vehicle body association data in the first scene data to obtain a parking space identification result.

[0088] Furthermore, in one embodiment, the test host computer is specifically used for:

[0089] Determine the real-time vehicle posture information based on the real-time motion data output by the inertial measurement unit of the vehicle to be tested during the automatic parking process and the initial vehicle posture information in the recognition result;

[0090] The relative position between the vehicle to be tested and the virtual parking space is updated in real time by combining the real-time vehicle posture information and the virtual parking space posture information in the recognition result.

[0091] Furthermore, in one embodiment, the vehicle to be tested is specifically used for:

[0092] Calculating a planned path for automatic parking by combining the relative position and the real-time vehicle body association data;

[0093] Based on the planned path, lateral and longitudinal control instructions are generated.

[0094] Furthermore, in one embodiment, the real-time vehicle body-related data includes vehicle speed, gear position and steering wheel angle; the real-time motion data includes three-axis acceleration, three-axis angular velocity and attitude angle.

[0095] Furthermore, in one embodiment, the test host computer is also used for:

[0096] After completing the real-vehicle closed-loop simulation test of the automatic parking function of the vehicle under test under the first scenario data, the second scenario data with a standardized format is used as the current scenario data and transmitted to the vehicle under test, and the process returns to the step of the vehicle under test identifying the virtual parking space in the current scenario data, until the real-vehicle closed-loop simulation test of the automatic parking function of the vehicle under test under the second scenario data is completed;

[0097] The second scene data is test scene data that is different from the first scene data and is screened from a real road sampling database.

[0098] Among them, the functional implementation of each module in the above-mentioned automatic parking function real vehicle closed-loop simulation test device corresponds to the various steps in the above-mentioned automatic parking function real vehicle closed-loop simulation test method embodiment, and its functions and implementation processes will not be repeated here one by one.

[0099] On the third aspect, an embodiment of the present application provides a real-vehicle closed-loop simulation test device for an automatic parking function. The real-vehicle closed-loop simulation test device for an automatic parking function can be a personal computer (PC), a laptop computer, a server, or other device with data processing capabilities.

[0100] Reference Figure 7 , Figure 7 The hardware structure diagram of the closed-loop simulation test device for the automatic parking function in the embodiment of the present application is shown in FIG. In the embodiment of the present application, the closed-loop simulation test device for the automatic parking function in the present application may include a processor, a memory, a communication interface, and a communication bus.

[0101] The communication bus may be of any type and is used to interconnect the processor, the memory, and the communication interface.

[0102] The communication interface includes input / output (I / O) interface, physical interface and logical interface, etc., which are used to realize the interconnection of devices inside the closed-loop simulation test equipment for the automatic parking function, and the interface used to realize the interconnection between the closed-loop simulation test equipment for the automatic parking function and other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, a fiber optic interface, an ATM interface, etc.; the user device can be a display, a keyboard, etc.

[0103] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0104] The processor may be a general-purpose processor, which may call the closed-loop simulation test program for the automatic parking function stored in the memory and execute the closed-loop simulation test method for the automatic parking function provided in the embodiment of the present application. For example, the general-purpose processor may be a central processing unit (CPU). The method executed when the closed-loop simulation test program for the automatic parking function is called may refer to the various embodiments of the closed-loop simulation test method for the automatic parking function provided in the present application, which will not be described in detail here.

[0105] Those skilled in the art will understand that Figure 7 The hardware structure shown in the figure does not constitute a limitation on the present application, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0106] In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium.

[0107] The computer-readable storage medium of the present application stores a closed-loop simulation test program for an actual vehicle of an automatic parking function, wherein when the closed-loop simulation test program for an actual vehicle of an automatic parking function is executed by a processor, the steps of the closed-loop simulation test method for an actual vehicle of an automatic parking function as described above are implemented.

[0108] Among them, the method implemented when the automatic parking function real vehicle closed-loop simulation test program is executed can refer to the various embodiments of the automatic parking function real vehicle closed-loop simulation test method of the present application, and will not be repeated here.

[0109] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0110] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to different types.

[0111] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a specific way.

[0112] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; the “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0113] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.

[0114] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.

[0115] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A closed-loop simulation test method for an automatic parking function, characterized in that: Applied to a real vehicle closed-loop simulation test system for an automatic parking function, the real vehicle closed-loop simulation test system for the automatic parking function comprises a test host computer and a vehicle to be tested, and the real vehicle closed-loop simulation test method for the automatic parking function comprises: The test host computer uses the first scene data in a standardized format as the current scene data and transmits it to the vehicle to be tested, wherein the first scene data is the test scene data selected from the real road sampling database; The vehicle to be tested identifies the virtual parking space in the current scene data, obtains the identification result, and transmits the identification result to the test host computer; The test host computer updates the relative position between the vehicle under test and the virtual parking space in real time based on the recognition result and the real-time motion data output by the inertial measurement unit of the vehicle under test during the automatic parking process, and transmits the relative position to the vehicle under test; The vehicle under test generates lateral and longitudinal control instructions in combination with the relative position and real-time vehicle body associated data to control the vehicle under test to automatically park in the virtual parking space, thereby realizing a closed-loop simulation test of the automatic parking function of the vehicle under test under the first scenario data.

2. The closed-loop simulation test method for the automatic parking function of a real vehicle according to claim 1, characterized in that: The identifying of the virtual parking space in the current scene data to obtain the identification result includes: Performing perception fusion on the camera video data and the ultrasonic radar data in the first scene data to obtain a perception fusion result; The virtual parking space in the first scene data is identified by combining the perception fusion result and the initial vehicle body association data in the first scene data to obtain a parking space identification result.

3. The closed-loop simulation test method for the automatic parking function of a real vehicle according to claim 1, characterized in that: The method of updating the relative position between the vehicle to be tested and the virtual parking space in real time based on the recognition result and the real-time motion data output by the inertial measurement unit of the vehicle to be tested during the automatic parking process includes: Determine the real-time vehicle posture information based on the real-time motion data output by the inertial measurement unit of the vehicle to be tested during the automatic parking process and the initial vehicle posture information in the recognition result; The relative position between the vehicle to be tested and the virtual parking space is updated in real time by combining the real-time vehicle posture information and the virtual parking space posture information in the recognition result.

4. The closed-loop simulation test method for the automatic parking function of a real vehicle according to claim 1, characterized in that: The step of combining the relative position and the real-time vehicle body related data to generate lateral and longitudinal control instructions includes: Calculating a planned path for automatic parking by combining the relative position and the real-time vehicle body association data; Based on the planned path, lateral and longitudinal control instructions are generated.

5. The closed-loop simulation test method for the automatic parking function of a real vehicle according to claim 1, characterized in that: The real-time vehicle body-related data includes vehicle speed, gear position and steering wheel angle; the real-time motion data includes three-axis acceleration, three-axis angular velocity and attitude angle.

6. The closed-loop simulation test method for the automatic parking function of a real vehicle according to claim 1, characterized in that: After completing the real vehicle closed-loop simulation test of the automatic parking function of the vehicle to be tested under the first scenario data, the method further includes: The test host computer uses the second scene data with standardized format as the current scene data and transmits it to the vehicle under test, and returns to the step of the vehicle under test identifying the virtual parking space in the current scene data, until the actual vehicle closed-loop simulation test of the automatic parking function of the vehicle under test under the second scene data is completed; The second scene data is test scene data that is different from the first scene data and is screened from a real road sampling database.

7. A closed-loop simulation test system for an automatic parking function, characterized in that: The automatic parking function real vehicle closed-loop simulation test system comprises: The test host computer is used to use the first scene data after the format is standardized as the current scene data and transmit it to the vehicle to be tested, wherein the first scene data is the test scene data screened from the real road sampling database; it is also used to update the relative position between the vehicle to be tested and the virtual parking space in real time based on the recognition result and the real-time motion data output by the inertial measurement unit of the vehicle to be tested during the automatic parking process, and transmit the relative position to the vehicle to be tested; The vehicle under test is used to identify the virtual parking space in the current scene data, obtain the identification result, and transmit the identification result to the test host computer; it is also used to combine the relative position and the real-time vehicle body related data to generate lateral and longitudinal control instructions to control the vehicle under test to automatically park in the virtual parking space, thereby realizing the real vehicle closed-loop simulation test of the automatic parking function of the vehicle under test under the first scene data.

8. The automatic parking function real vehicle closed-loop simulation test system as claimed in claim 7, characterized in that: The vehicle to be tested is specifically used for: Performing perception fusion on the camera video data and the ultrasonic radar data in the first scene data to obtain a perception fusion result; The virtual parking space in the first scene data is identified by combining the perception fusion result and the initial vehicle body association data in the first scene data to obtain a parking space identification result.

9. A closed-loop simulation test device for an automatic parking function, characterized in that: The automatic parking function real-vehicle closed-loop simulation test equipment includes a processor, a memory, and an automatic parking function real-vehicle closed-loop simulation test program stored in the memory and executable by the processor, wherein when the automatic parking function real-vehicle closed-loop simulation test program is executed by the processor, the steps of the automatic parking function real-vehicle closed-loop simulation test method as described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a closed-loop simulation test program for an actual vehicle of an automatic parking function, wherein when the closed-loop simulation test program for an actual vehicle of an automatic parking function is executed by a processor, the steps of the closed-loop simulation test method for an actual vehicle of an automatic parking function as described in any one of claims 1 to 6 are implemented.

Images