Calibration method and system of 4D millimeter wave radar, vehicle and equipment

Abstract

The invention discloses a 4D millimeter wave radar calibration method and system, a vehicle and equipment. The calibration method of the 4D millimeter wave radar comprises the following steps: in a vehicle driving process, obtaining detection data of the 4D millimeter wave radar; screening the detection data according to the yaw rate and target information detected by the 4D millimeter wave radar to obtain calibration data; when the data size of the collected calibration data reaches a preset number, obtaining guardrail point cloud data from the calibration data; and obtaining external parameters of the 4D millimeter wave radar according to the target information and the guardrail point cloud data, and calibrating the 4D millimeter wave radar according to the external parameters. The method can automatically complete the calibration of the 4D millimeter wave radar in the daily driving of the vehicle, saves manpower, material resources, time and cost, has the advantages of non-inductive calibration and high calibration precision, and improves the use experience of the vehicle.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a calibration method, system, vehicle and equipment for a 4D millimeter-wave radar. Background Art

[0002] 4D millimeter-wave radar is an emerging obstacle detection sensor in the field of autonomous driving. Its calibration accuracy directly affects the performance of autonomous driving. At present, most 4D millimeter-wave radar calibrations still use the calibration method of 3D millimeter-wave radar. However, 4D millimeter-wave radar has performance far exceeding that of 3D millimeter-wave radar. Therefore, most calibration methods cannot calibrate 4D millimeter-wave radar well.

[0003] Compared with 3D millimeter-wave radar, 4D millimeter-wave radar has a longer detection distance, higher detection accuracy, and increased detection information in the target height dimension. Therefore, higher calibration accuracy is required to fully utilize 4D millimeter-wave radar. The static calibration method generally uses angular anti-equivalent targets, which are placed as required, and optimized and solved by the known target position and the target position returned by the millimeter-wave radar; the dynamic calibration method generally drives a straight distance on a road with guardrails, and uses the information that the guardrail is a straight line to calculate the external parameters of the millimeter-wave radar. However, the static calibration method requires the construction of an angular anti-equivalent target scene, which is time-consuming and labor-intensive, and the accuracy is greatly affected by human factors, and the accuracy of the calibration result is limited. The dynamic calibration method is affected by the driver's driving operation, and the accuracy of the angle calculation is limited. It cannot meet the use requirements of 4D millimeter-wave radar, and generally uses stationary targets for calculation, with limited accuracy. In addition, the existing calibration methods require personnel to spend time alone to calibrate, and sometimes multiple data collections are required, which is inefficient. Summary of the invention

[0004] Based on this, it is necessary to provide a 4D millimeter-wave radar calibration method, system, vehicle and equipment to address the above-mentioned technical problems, which can automatically complete the 4D millimeter-wave radar calibration during the daily driving of the vehicle, saving manpower, material resources and time costs, and has the advantages of non-sensing calibration and high calibration accuracy, thereby improving the vehicle's user experience.

[0005] In a first aspect, a calibration method for a 4D millimeter wave radar is provided, comprising:

[0006] During vehicle driving, the detection data of 4D millimeter wave radar is obtained;

[0007] The detection data is screened according to the yaw rate and the target information detected by the 4D millimeter wave radar to obtain calibration data;

[0008] When the amount of the collected calibration data reaches a predetermined amount, obtaining guardrail point cloud data from the calibration data;

[0009] According to the target information and the guardrail point cloud data, the external parameters of the 4D millimeter-wave radar are obtained, and the 4D millimeter-wave radar is calibrated according to the external parameters.

[0010] In some examples, the detection data is screened according to the yaw rate and the target information detected by the 4D millimeter wave radar to obtain the calibration data, including:

[0011] Obtaining yaw rate data of the detection data within a predetermined window time in the detection data;

[0012] Determine whether changes in the yaw rate data in each direction are less than a limit value;

[0013] If yes, the corresponding detection data is used as candidate calibration data;

[0014] The candidate calibration data is screened according to the target information detected by the 4D millimeter wave radar to obtain calibration data.

[0015] In some examples, the step of screening the candidate calibration data according to the target information detected by the 4D millimeter wave radar to obtain the calibration data includes:

[0016] According to the target information, the number of targets and the target positions are obtained;

[0017] Determining whether the target quantity and target position meet predetermined criteria;

[0018] If yes, the candidate calibration data is used as the calibration data.

[0019] In some examples, when the amount of collected calibration data reaches a predetermined amount, obtaining guardrail point cloud data from the calibration data includes:

[0020] Determining whether the amount of collected calibration data reaches a predetermined amount;

[0021] If yes, setting the 4D millimeter-wave radar to a state to be calibrated;

[0022] When the calibration conditions are met, the remaining point cloud data other than the guardrail point cloud data are removed from the calibration data to obtain the guardrail point cloud data.

[0023] In some examples, obtaining external parameters of the 4D millimeter-wave radar according to the target information and the guardrail point cloud data, and calibrating the 4D millimeter-wave radar according to the external parameters includes:

[0024] Convert the guardrail point cloud data into two dimensions and perform linear fitting to obtain the yaw angle;

[0025] Calculate the roll angle and pitch angle based on the target information;

[0026] According to the yaw angle, roll angle and pitch angle corresponding to each frame of calibration data, the external parameters of the 4D millimeter wave radar are obtained, and the 4D millimeter wave radar is calibrated according to the external parameters.

[0027] In some examples, obtaining the external parameters of the 4D millimeter-wave radar according to the yaw angle, roll angle, and pitch angle corresponding to each frame of calibration data, and calibrating the 4D millimeter-wave radar according to the external parameters includes:

[0028] Minimize the cumulative error based on the yaw angle, roll angle and pitch angle corresponding to each frame of calibration data;

[0029] The minimized cumulative error is solved to obtain a final result at each angle, and the 4D millimeter-wave radar is calibrated according to the final result.

[0030] In some examples, this also includes:

[0031] The calibration result of the 4D millimeter-wave radar is verified by the perception results of other sensors or other known position targets.

[0032] In a second aspect, a 4D millimeter wave radar calibration system is provided, comprising:

[0033] The acquisition module is used to obtain the detection data of the 4D millimeter-wave radar during the vehicle's driving process;

[0034] A calibration data screening module, used to screen the detection data according to the yaw rate and the target information detected by the 4D millimeter wave radar to obtain calibration data;

[0035] A point cloud screening module, used to obtain guardrail point cloud data from the calibration data when the amount of collected calibration data reaches a predetermined amount;

[0036] A calibration module is used to obtain external parameters of the 4D millimeter-wave radar according to the target information and the guardrail point cloud data, and calibrate the 4D millimeter-wave radar according to the external parameters.

[0037] In a third aspect, a vehicle is provided, comprising: a calibration system for the 4D millimeter-wave radar according to the second aspect.

[0038] In a fourth aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the calibration method of the 4D millimeter-wave radar of the first aspect and any possible implementation method of the first aspect are implemented.

[0039] According to the embodiment of the present application, during the driving process of the vehicle, the detection data of the 4D millimeter wave radar is obtained, and then, according to the yaw rate and the target information detected by the 4D millimeter wave radar, the detection data is screened to obtain the calibration data, and when the amount of the collected calibration data reaches a predetermined amount, the guardrail point cloud data is obtained from the calibration data, and finally, according to the target information and the guardrail point cloud data, the external parameters of the 4D millimeter wave radar are obtained, and the 4D millimeter wave radar is calibrated according to the external parameters. When the position of the 4D millimeter wave radar changes due to bumps and collisions during the use of the vehicle, the 4D millimeter wave radar can be recalibrated at any time, which has the advantage of high real-time performance. In addition, there is no need for personnel to spend time to calibrate the 4D millimeter wave radar separately, and data collection and calibration can be automatically completed according to its own state during daily driving. The 4D millimeter wave radar calibration can be automatically completed during the daily driving of the vehicle, saving manpower, material resources and time costs, with the advantages of non-sensing calibration, and high calibration accuracy, thereby improving the use experience of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0041] Figure 1 A flowchart of a calibration method for a 4D millimeter-wave radar provided in an embodiment of the present application;

[0042] Figure 2 A flowchart of a specific implementation of a calibration method for a 4D millimeter-wave radar provided in an embodiment of the present application;

[0043] Figure 3 A structural block diagram of a 4D millimeter wave radar calibration system provided in an embodiment of the present application;

[0044] Figure 4 A structural block diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] The present application is further described in detail below in conjunction with the embodiments and drawings. It is to be understood that the specific embodiments described herein are only used to explain the relevant application, rather than to limit the application. It is also necessary to explain that, for ease of description, only the parts related to the application are shown in the drawings.

[0046] It should be noted that, in the absence of conflict, the embodiments of the present application, that is, the features of the embodiments, can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0047] The following describes in detail the calibration method, system, vehicle and equipment of the 4D millimeter wave radar according to the embodiments of the present application in conjunction with the accompanying drawings.

[0048] Figure 1 FIG. 4 is a flow chart of a calibration method for a 4D millimeter wave radar according to an embodiment of the present application. Figure 1 As shown, the calibration method of the 4D millimeter wave radar according to the embodiment of the present application includes the following steps:

[0049] S101: During vehicle driving, detection data of a 4D millimeter wave radar is obtained.

[0050] In a specific example, a vehicle can use the on-board 4D millimeter-wave radar to scan and detect on a daily driving road where the road surface is flat, straight, there are guardrails such as metal guardrails in the middle or at the edge of the road, and there are vehicles of different distances on the road, thereby obtaining detection data of the 4D millimeter-wave radar under the driving conditions.

[0051] Specifically, combined Figure 2 As shown, when the vehicle's autonomous driving domain controller is manually triggered by the user or the algorithm verification fails, it receives a request for 4D millimeter-wave radar calibration. At this time, the 4D millimeter-wave radar is placed in a pending calibration state. Then, the autonomous driving domain controller will continue to cache a certain historical frame of 4D millimeter-wave radar data, i.e., the detection data of the 4D millimeter-wave radar, in real time during the vehicle's driving. At this time, the system is in a calibration data acquisition state.

[0052] S102: Filter the detection data according to the yaw rate and the target information detected by the 4D millimeter wave radar to obtain calibration data.

[0053] In one embodiment of the present application, Figure 2 As shown, according to the yaw rate and the target information detected by the 4D millimeter-wave radar, the detection data is screened to obtain calibration data, including: obtaining the yaw rate data of the detection data within a predetermined window time in the detection data; judging whether the change of the yaw rate data in each direction is less than a limited value; if so, taking the corresponding detection data as alternative calibration data; according to the target information detected by the 4D millimeter-wave radar, the alternative calibration data is screened to obtain calibration data.

[0054] In the above example, the alternative calibration data is screened according to the target information detected by the 4D millimeter-wave radar to obtain calibration data, including: obtaining the number of targets and target positions according to the target information; judging whether the number of targets and target positions meet predetermined standards; if so, using the alternative calibration data as the calibration data.

[0055] Specifically, the yaw_rate data of the vehicle within a certain window time is automatically calculated. If the change of yaw_rate in each direction is less than the limit value, the data segment is marked as candidate calibration data.

[0056] The target information output in the 4D millimeter wave data of the candidate calibration is confirmed. If the number and position of the targets meet the definition, the data segment is used as the calibration data. If not, the data segment is discarded.

[0057] S103: When the amount of the collected calibration data reaches a predetermined amount, guardrail point cloud data is obtained from the calibration data.

[0058] In one embodiment of the present application, when the amount of collected calibration data reaches a predetermined amount, guardrail point cloud data is obtained from the calibration data, including: determining whether the amount of collected calibration data reaches a predetermined amount; if so, setting the 4D millimeter-wave radar to a state to be calibrated; when the calibration conditions are met, removing the remaining point cloud data other than the guardrail point cloud data from the calibration data to obtain the guardrail point cloud data.

[0059] For example: after detecting that the amount of collected data meets the specified calibration data amount, data collection is stopped and the 4D millimeter-wave radar is placed in a calibration calculation state.

[0060] S104: Obtaining external parameters of the 4D millimeter-wave radar according to the target information and the guardrail point cloud data, and calibrating the 4D millimeter-wave radar according to the external parameters.

[0061] In a specific example, the external parameters of the 4D millimeter-wave radar are obtained according to the target information and the guardrail point cloud data, and the 4D millimeter-wave radar is calibrated according to the external parameters, including: two-dimensionalizing the guardrail point cloud data and performing straight line fitting to obtain the yaw angle; calculating the roll angle and the pitch angle according to the target information; obtaining the external parameters of the 4D millimeter-wave radar according to the yaw angle, roll angle and pitch angle corresponding to each frame of calibration data, and calibrating the 4D millimeter-wave radar according to the external parameters.

[0062] In the above example, the external parameters of the 4D millimeter-wave radar are obtained according to the yaw angle, roll angle and pitch angle corresponding to each frame of calibration data, and the 4D millimeter-wave radar is calibrated according to the external parameters, including: minimizing the cumulative error according to the yaw angle, roll angle and pitch angle corresponding to each frame of calibration data; solving the minimized cumulative error to obtain the final results of each angle, and calibrating the 4D millimeter-wave radar according to the final results.

[0063] Specifically, when the system is idle, apply to process 4D millimeter wave data for calibration, and the system will enter the calibration calculation state. If the system receives other mode requests at this time, it will immediately exit the calibration calculation state and return to the calibration calculation state, and enter the calibration calculation state again when it is idle next time.

[0064] After the calibration is completed, the update result is restarted to put the 4D millimeter wave radar into the calibration completed state.

[0065] 4D millimeter wave radar calibration data processing: According to the target information output by the 4D millimeter wave, the target point cloud in the point cloud data is removed, the remaining guardrail point cloud data is two-dimensionalized, and Ransac is used for linear fitting to obtain the yaw angle:

[0066]

[0067] According to the target information output by 4D millimeter wave, the roll angle and pitch angle of 4D millimeter wave are calculated:

[0068]

[0069] Multi-frame data combination optimization:

[0070] Process each frame of data in multiple segments as above to minimize the cumulative error:

[0071]

[0072] The final results of each angle can be obtained by solving through optimization methods such as Gauss-Newton or LM, thus completing the calibration of the 4D millimeter-wave radar.

[0073] After the 4D millimeter wave radar is calibrated, the calibration result of the 4D millimeter wave radar is verified through the perception results of other sensors or other known position targets. That is, the calibration result can be verified through the perception results of other sensors or other known position targets to verify whether the calibration is accurate and reliable.

[0074] According to the calibration method of the 4D millimeter wave radar in the embodiment of the present application, during the driving process of the vehicle, the detection data of the 4D millimeter wave radar is obtained, and then, according to the yaw rate and the target information detected by the 4D millimeter wave radar, the detection data is screened to obtain the calibration data, and when the amount of the collected calibration data reaches a predetermined amount, the guardrail point cloud data is obtained from the calibration data, and finally, according to the target information and the guardrail point cloud data, the external parameters of the 4D millimeter wave radar are obtained, and the 4D millimeter wave radar is calibrated according to the external parameters. When the position of the 4D millimeter wave radar changes due to bumps and collisions during the use of the vehicle, the 4D millimeter wave radar can be recalibrated at any time, which has the advantage of high real-time performance. In addition, there is no need for personnel to spend time to calibrate the 4D millimeter wave radar separately, and data collection and calibration can be automatically completed according to its own state during daily driving. The 4D millimeter wave radar calibration can be automatically completed during the daily driving of the vehicle, saving manpower, material resources and time costs, with non-sensing calibration, and has the advantages of high calibration accuracy, thereby improving the use experience of the vehicle.

[0075] Figure 3 FIG. 1 is a structural block diagram of a 4D millimeter wave radar calibration system according to an embodiment of the present application. Figure 3 As shown, a calibration system for a 4D millimeter wave radar according to an embodiment of the present application includes: an acquisition module 310, a calibration data screening module 320, a point cloud screening module 330 and a calibration module 340, wherein:

[0076] The acquisition module 310 is used to obtain the detection data of the 4D millimeter wave radar during the vehicle driving process;

[0077] The calibration data screening module 320 is used to screen the detection data according to the yaw rate and the target information detected by the 4D millimeter wave radar to obtain calibration data;

[0078] The point cloud screening module 330 is used to obtain the guardrail point cloud data from the calibration data when the amount of the collected calibration data reaches a predetermined amount;

[0079] The calibration module 340 is used to obtain the external parameters of the 4D millimeter wave radar according to the target information and the guardrail point cloud data, and calibrate the 4D millimeter wave radar according to the external parameters.

[0080] According to the calibration system of the 4D millimeter wave radar of the embodiment of the present application, during the driving process of the vehicle, the detection data of the 4D millimeter wave radar is obtained, and then, according to the yaw rate and the target information detected by the 4D millimeter wave radar, the detection data is screened to obtain the calibration data, and when the amount of the collected calibration data reaches a predetermined amount, the guardrail point cloud data is obtained from the calibration data, and finally, according to the target information and the guardrail point cloud data, the external parameters of the 4D millimeter wave radar are obtained, and the 4D millimeter wave radar is calibrated according to the external parameters. When the position of the 4D millimeter wave radar changes due to bumps and collisions during the use of the vehicle, the 4D millimeter wave radar can be recalibrated at any time, which has the advantage of high real-time performance. In addition, there is no need for personnel to spend time to calibrate the 4D millimeter wave radar separately, and data collection and calibration can be automatically completed according to its own state during daily driving. The 4D millimeter wave radar calibration can be automatically completed during the daily driving of the vehicle, saving manpower, material resources and time costs, with non-sensing calibration, and has the advantages of high calibration accuracy, thereby improving the use experience of the vehicle.

[0081] For the specific definition of the calibration system of the 4D millimeter-wave radar, please refer to the definition of the calibration method of the 4D millimeter-wave radar mentioned above, which will not be repeated here. The various modules of the calibration system of the above-mentioned 4D millimeter-wave radar can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0082] In one embodiment, a computer device is provided. Figure 4 This is a block diagram of the computer device provided in the embodiment of the present application, refer to Figure 4 The computer device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the aforementioned 4D millimeter wave radar calibration method embodiment is implemented. For example, the following is performed: during vehicle driving, the detection data of the 4D millimeter wave radar is obtained;

[0083] The detection data is screened according to the yaw rate and the target information detected by the 4D millimeter wave radar to obtain calibration data;

[0084] When the amount of the collected calibration data reaches a predetermined amount, obtaining guardrail point cloud data from the calibration data;

[0085] According to the target information and the guardrail point cloud data, the external parameters of the 4D millimeter-wave radar are obtained, and the 4D millimeter-wave radar is calibrated according to the external parameters.

[0086] The embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and the processor implements the aforementioned 4D millimeter wave radar calibration method embodiment when executing the computer program. For example, during the vehicle driving process, the detection data of the 4D millimeter wave radar is obtained;

[0087] The detection data is screened according to the yaw rate and the target information detected by the 4D millimeter wave radar to obtain calibration data;

[0088] When the amount of the collected calibration data reaches a predetermined amount, obtaining guardrail point cloud data from the calibration data;

[0089] According to the target information and the guardrail point cloud data, the external parameters of the 4D millimeter-wave radar are obtained, and the 4D millimeter-wave radar is calibrated according to the external parameters.

[0090] The present application embodiment provides a computer program product, which includes instructions. When the instructions are executed, the method described in the embodiment of the present application is executed. For example, it can be executed Figure 1 The various steps of the calibration method of the 4D millimeter wave radar shown are, for example, performed as follows: during vehicle driving, obtaining detection data of the 4D millimeter wave radar;

[0091] The detection data is screened according to the yaw rate and the target information detected by the 4D millimeter wave radar to obtain calibration data;

[0092] When the amount of the collected calibration data reaches a predetermined amount, obtaining guardrail point cloud data from the calibration data;

[0093] According to the target information and the guardrail point cloud data, the external parameters of the 4D millimeter-wave radar are obtained, and the 4D millimeter-wave radar is calibrated according to the external parameters.

[0094] Those of ordinary skill in the art can understand that all or part of the processes in the methods for implementing the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0095] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0096] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent application shall be subject to the attached claims.

Claims

1. A 4D millimeter wave radar calibration method, characterized in that: include: During vehicle driving, the detection data of 4D millimeter wave radar is obtained; The detection data is screened according to the yaw rate and the target information detected by the 4D millimeter wave radar to obtain calibration data; When the amount of the collected calibration data reaches a predetermined amount, obtaining guardrail point cloud data from the calibration data; According to the target information and the guardrail point cloud data, the external parameters of the 4D millimeter-wave radar are obtained, and the 4D millimeter-wave radar is calibrated according to the external parameters.

2. The 4D millimeter wave radar calibration method according to claim 1, characterized in that: The detection data is screened according to the yaw rate and the target information detected by the 4D millimeter wave radar to obtain calibration data, including: Obtaining yaw rate data of the detection data within a predetermined window time in the detection data; Determine whether changes in the yaw rate data in each direction are less than a limit value; If yes, the corresponding detection data is used as candidate calibration data; The candidate calibration data is screened according to the target information detected by the 4D millimeter wave radar to obtain calibration data.

3. The calibration method of 4D millimeter wave radar according to claim 2, characterized in that: The step of screening the candidate calibration data according to the target information detected by the 4D millimeter wave radar to obtain the calibration data includes: According to the target information, the number of targets and the target positions are obtained; Determining whether the target quantity and target position meet predetermined criteria; If yes, the candidate calibration data is used as the calibration data.

4. The calibration method of 4D millimeter wave radar according to claim 1, characterized in that: When the amount of the collected calibration data reaches a predetermined amount, obtaining guardrail point cloud data from the calibration data includes: Determining whether the amount of collected calibration data reaches a predetermined amount; If yes, setting the 4D millimeter-wave radar to a state to be calibrated; When the calibration conditions are met, the remaining point cloud data other than the guardrail point cloud data are removed from the calibration data to obtain the guardrail point cloud data.

5. The calibration method of 4D millimeter wave radar according to claim 1, characterized in that: The method of obtaining external parameters of the 4D millimeter-wave radar according to the target information and the guardrail point cloud data, and calibrating the 4D millimeter-wave radar according to the external parameters includes: Convert the guardrail point cloud data into two dimensions and perform linear fitting to obtain the yaw angle; Calculate the roll angle and pitch angle based on the target information; According to the yaw angle, roll angle and pitch angle corresponding to each frame of calibration data, the external parameters of the 4D millimeter wave radar are obtained, and the 4D millimeter wave radar is calibrated according to the external parameters.

6. The calibration method of 4D millimeter wave radar according to claim 5, characterized in that: The method of obtaining the external parameters of the 4D millimeter-wave radar according to the yaw angle, roll angle and pitch angle corresponding to each frame of calibration data, and calibrating the 4D millimeter-wave radar according to the external parameters includes: Minimize the cumulative error based on the yaw angle, roll angle and pitch angle corresponding to each frame of calibration data; The minimized cumulative error is solved to obtain a final result at each angle, and the 4D millimeter-wave radar is calibrated according to the final result.

7. The 4D millimeter wave radar calibration method according to any one of claims 1 to 6, characterized in that: Also includes: The calibration result of the 4D millimeter-wave radar is verified by the perception results of other sensors or other known position targets.

8. A 4D millimeter wave radar calibration system, characterized in that: include: The acquisition module is used to obtain the detection data of the 4D millimeter-wave radar during the vehicle's driving process; A calibration data screening module, used to screen the detection data according to the yaw rate and the target information detected by the 4D millimeter wave radar to obtain calibration data; A point cloud screening module, used to obtain guardrail point cloud data from the calibration data when the amount of collected calibration data reaches a predetermined amount; A calibration module is used to obtain external parameters of the 4D millimeter-wave radar according to the target information and the guardrail point cloud data, and calibrate the 4D millimeter-wave radar according to the external parameters.

9. A vehicle, characterized in that: include: The calibration system of the 4D millimeter-wave radar according to claim 8.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the calibration method of the 4D millimeter-wave radar according to any one of claims 1-7 is implemented.

Images