A vehicle-mounted radar detection angle anomaly detection method and device, a vehicle, and a medium

Abstract

The application provides a vehicle-mounted radar detection angle anomaly detection method, device, automobile and medium, comprising: acquiring point cloud data collected by a vehicle-mounted radar and preprocessing the collected point cloud data; determining a radar self-checking angle of the vehicle-mounted radar based on the preprocessed point cloud data, and comparing the radar self-checking angle with a preset abnormal angle threshold and a radar initial adaptive angle in sequence; when the radar self-checking angle is greater than the preset abnormal angle threshold and a difference between the radar self-checking angle and the radar initial adaptive angle is greater than a preset angle difference threshold, determining that the detection angle of the vehicle-mounted radar is abnormal, and setting the vehicle-mounted radar to continuously monitor the radar self-checking angle in a current ignition cycle, and not updating the radar initial adaptive angle to the radar self-checking angle. The application effectively avoids frequent false alarms of radar angle out-of-tolerance caused by road bumps and sudden deformation (recoverable) of a bumper.

Description

Technical Field

[0001] This invention relates to the field of vehicle-mounted radar detection angle anomaly detection technology, and in particular to a method, device, vehicle, and medium for vehicle-mounted radar detection angle anomaly detection. Background Technology

[0002] Automotive millimeter-wave radar is installed at the front, front corners, or rear corners of a vehicle. It emits 76GHz–79GHz continuously modulated millimeter waves via antennas and receives reflected signals from targets. By analyzing the reflected signals, the distance, relative speed, and azimuth of the target can be calculated. Millimeter-wave radars installed at different locations can extract information about surrounding vehicles during driving, thus ensuring safe driving. However, on bumpy roads, after a severe impact, or when the bumper is deformed, the adaptive test results of the radar's installation angle may momentarily deviate significantly, causing a self-check angle error. Normal operation only resumes after a stable target or smooth road surface is encountered. During this malfunction, the radar is unusable, easily leading to user complaints and a perceived lack of radar functionality. Especially in scenarios involving bumpy roads, sudden collisions, or sudden bumper deformation, the radar's monitoring angle may exceed tolerances, resulting in frequent false alarms due to out-of-tolerance radar angle readings. Summary of the Invention

[0003] The purpose of this invention is to propose a method, device, vehicle, and medium for detecting abnormal radar detection angles, and to solve the technical problem of how to avoid frequent false alarms of radar angle deviation caused by recoverable deformation when there are abnormal radar deviation angles.

[0004] On the one hand, a method for detecting abnormal detection angles of vehicle-mounted radar is provided, including:

[0005] Acquire point cloud data collected by vehicle-mounted radar and preprocess the collected point cloud data;

[0006] The radar self-test angle of the vehicle-mounted radar is determined based on the preprocessed point cloud data. The radar self-test angle is then compared sequentially with a preset abnormal angle threshold and the radar initial adaptation angle. The radar self-test angle represents the angle result monitored in real time when the radar is working, and the radar initial adaptation angle represents the angle when the radar is initially installed.

[0007] When the radar self-test angle is greater than a preset abnormal angle threshold and the difference between the radar self-test angle and the radar initial adaptation angle is greater than a preset angle difference threshold, the detection angle of the vehicle radar is determined to be abnormal, and the vehicle radar is set to continuously monitor the radar self-test angle in the current ignition cycle, without updating the radar initial adaptation angle to the radar self-test angle.

[0008] Preferably, it further includes:

[0009] When the radar self-test angle is greater than the preset abnormal angle threshold and the difference between the radar self-test angle and the radar initial adaptation angle is less than the preset angle difference threshold, the vehicle radar angle is determined to be out of tolerance, and the radar initial adaptation angle is set to be updated to the radar self-test angle.

[0010] Preferably, it further includes:

[0011] When the radar self-test angle is less than a preset abnormal angle threshold and the difference between the radar self-test angle and the radar initial adaptation angle is less than a preset angle difference threshold, the radar initial adaptation angle is updated to the radar self-test angle.

[0012] Preferably, it further includes:

[0013] When the radar self-test angle is less than the preset abnormal angle threshold and the difference between the radar self-test angle and the radar initial adaptation angle is greater than the preset angle difference threshold, the vehicle radar is set to continuously monitor the radar self-test angle within the current ignition cycle and not update the radar initial adaptation angle to the radar self-test angle.

[0014] Preferably, the preprocessing of the collected point cloud data includes:

[0015] Obtain the target detection range of the vehicle-mounted radar, wherein the signal strength corresponding to the data point in the point cloud data of the target detection range is greater than a specified strength;

[0016] The point cloud data within the target detection range is determined as the preprocessed point cloud data.

[0017] On the other hand, a vehicle-mounted radar detection angle anomaly detection device is also provided to implement the vehicle-mounted radar detection angle anomaly detection method, including:

[0018] The data acquisition module is used to acquire point cloud data collected by the vehicle radar and to preprocess the acquired point cloud data.

[0019] The radar self-test module is used to determine the radar self-test angle of the vehicle radar based on the preprocessed point cloud data, and compare the radar self-test angle with the preset abnormal angle threshold and the radar initial adaptation angle in sequence; the radar self-test angle represents the angle result monitored in real time when the radar is working, and the radar initial adaptation angle represents the angle when the radar is initially installed.

[0020] When the radar self-test angle is greater than a preset abnormal angle threshold and the difference between the radar self-test angle and the radar initial adaptation angle is greater than a preset angle difference threshold, the detection angle of the vehicle radar is determined to be abnormal, and the vehicle radar is set to continuously monitor the radar self-test angle in the current ignition cycle, without updating the radar initial adaptation angle to the radar self-test angle.

[0021] Preferably, the radar self-test module is further configured to update the radar initial adaptation angle to the radar self-test angle when the radar self-test angle is greater than a preset abnormal angle threshold and the difference between the radar self-test angle and the radar initial adaptation angle is less than a preset angle difference threshold, or when the radar self-test angle is less than a preset abnormal angle threshold and the difference between the radar self-test angle and the radar initial adaptation angle is less than a preset angle difference threshold.

[0022] Preferably, the radar self-test module is further configured to, when the radar self-test angle is less than a preset abnormal angle threshold and the difference between the radar self-test angle and the radar initial adaptation angle is greater than a preset angle difference threshold, set the vehicle radar to continuously monitor the radar self-test angle within the current ignition cycle and not update the radar initial adaptation angle to the radar self-test angle.

[0023] On the other hand, a vehicle is also provided, including:

[0024] One or more processors;

[0025] Memory;

[0026] Detection components;

[0027] One or more computer programs, wherein the one or more computer programs are stored in the memory and configured to be executed by the one or more processors, the one or more computer programs being configured to perform the vehicle-mounted radar detection angle anomaly detection method.

[0028] On the other hand, a computer-readable storage medium is also provided, wherein computer program instructions are stored in the computer-readable storage medium, and the computer program instructions can be called by a processor to execute the vehicle-mounted radar detection angle anomaly detection method.

[0029] In summary, implementing the embodiments of the present invention has the following beneficial effects:

[0030] The present invention provides a method, device, vehicle, and medium for detecting abnormal radar detection angles. When the radar self-test angle is greater than a preset abnormal angle threshold and the difference between the radar self-test angle and the radar initial adaptation angle is greater than a preset angle difference threshold, it can be determined that the current radar angle deviation is not caused by normal aging of the installation position. In this case, the radar's initial adaptation angle is not updated, which can effectively avoid frequent false alarms of radar angle deviation caused by road bumps or sudden deformation of the bumper (which can be recovered). This avoids such recoverable faults that cause the radar to malfunction, allowing the system to work normally and reducing customer complaints. Attached Figure Description

[0031] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, obtaining other drawings based on these drawings without creative effort still falls within the scope of the present invention.

[0032] Figure 1 This is a schematic diagram of the main process of a vehicle-mounted radar detection angle anomaly detection method in an embodiment of the present invention.

[0033] Figure 2 This is a logical schematic diagram of a method for detecting abnormal angles of vehicle-mounted radar in an embodiment of the present invention. Detailed Implementation

[0034] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings.

[0035] like Figure 1 and Figure 2 The diagram shown is a schematic representation of an embodiment of a method for detecting anomalies in the detection angle of a vehicle-mounted radar provided by the present invention. In this embodiment, the method includes the following steps:

[0036] Step S1: Acquire point cloud data collected by the vehicle-mounted radar and preprocess the collected point cloud data. Understandably, the radar detects reference point cloud data, which may include detection information of objects in the external environment (e.g., vehicles on the side and rear of the vehicle, roadside railings, lampposts) within the detection range of the vehicle. After collection, check the point cloud quality of the reference object, and monitor the peak value of the point cloud under specific conditions in combination with the horizontal angle fluctuation range of the point cloud, filtering out some sudden change test angle results, thereby improving the accuracy of angle detection.

[0037] In a specific embodiment, the preprocessing of the collected point cloud data includes: obtaining the target detection range of the vehicle-mounted radar, wherein the signal strength corresponding to the data points in the point cloud data within the target detection range is greater than a specified strength; and determining the point cloud data within the target detection range as the preprocessed point cloud data. In this embodiment, by eliminating low-precision point cloud data, calculation errors caused by the data processing results are avoided. Therefore, the data processing results obtained from point cloud data with higher data precision are better than the data processing results obtained directly from the point cloud data.

[0038] Step S2: Based on the preprocessed point cloud data, determine the radar self-test angle of the vehicle-mounted radar. Compare the radar self-test angle sequentially with a preset abnormal angle threshold and the radar initial adaptation angle. The radar self-test angle represents the angle result monitored in real-time during radar operation, while the radar initial adaptation angle represents the angle attitude of the radar upon initial installation. Understandably, based on the determined point cloud data, multiple sets of angle calculation sample values ​​are numerically sorted, outliers are removed, and the average value is taken to output the final angle calculation result, i.e., the radar self-test angle. Then, sequentially determine whether the radar self-test angle is less than the preset abnormal angle threshold (set to 5 degrees in this embodiment) and whether the difference between the radar self-test angle and the radar initial adaptation angle is greater than 3 degrees. First, determine whether the radar self-test angle is greater than 5 degrees to confirm that the current radar operating environment has undergone a sudden change due to external factors, causing the radar to detect an anomaly. A normal self-test angle is within 5 degrees. Further determining whether the difference between the radar self-test angle and the radar initial adaptation angle is greater than 3 degrees is to eliminate false alarms, and combining the two determinations can clearly distinguish between false alarms and non-false alarms.

[0039] Step S3: When the radar self-test angle is greater than a preset abnormal angle threshold and the difference between the radar self-test angle and the radar initial adaptation angle is greater than a preset angle difference threshold, the detection angle of the vehicle radar is determined to be abnormal. The vehicle radar is then set to continuously monitor the radar self-test angle within the current ignition cycle, without updating the radar initial adaptation angle to the radar self-test angle. Understandably, the first step is to determine whether the radar self-test angle is greater than the preset abnormal angle threshold. When the radar self-test angle is greater than 5 degrees and the radar self-test angle is more than 3 degrees greater than the radar initial angle, it can be determined to be an abnormal situation. Within the current ignition cycle, the radar self-test angle is continuously re-monitored, without directly updating it to the radar initial adaptation angle. It should be noted that this mainly confirms whether there has been an abnormal abrupt change between the radar's initial attitude and the real-time detected radar self-test angle. For example, if the angle difference between the initial value and the detected value within a single cycle is greater than 3 degrees, it can be determined that the current radar is either operating on a bumpy road or experiencing a sudden bumper deformation. By ensuring that the initial angle is not updated within the current ignition cycle, the temporary angle deviation false alarms during bumps or deformation can be effectively reduced.

[0040] In a specific embodiment, in other cases, such as when the radar self-test angle is greater than a preset abnormal angle threshold and the difference between the radar self-test angle and the radar initial adaptation angle is less than a preset angle difference threshold, the vehicle radar angle is determined to be out of tolerance, and the radar initial adaptation angle is updated to the radar self-test angle. That is, if the radar self-test angle is greater than 5 degrees and the radar self-test angle is less than 3 degrees compared to the radar initial angle, it can be preliminarily determined that the radar attitude is incorrect, and further inspection of the assembly status is required.

[0041] Specifically, when the radar self-test angle is less than a preset abnormal angle threshold and the difference between the radar self-test angle and the radar initial adaptation angle is less than a preset angle difference threshold, the radar initial adaptation angle is updated to the radar self-test angle. That is, at this time, the radar self-test angle is less than 5° and the difference between it and the radar initial adaptation angle is less than 3°, so it is only necessary to update the radar initial adaptation angle to the radar self-test angle.

[0042] More specifically, when the radar self-test angle is less than a preset abnormal angle threshold and the difference between the radar self-test angle and the radar initial adaptation angle is greater than a preset angle difference threshold, the vehicle radar is configured to continuously monitor the radar self-test angle within the current ignition cycle and not update the radar initial adaptation angle to the radar self-test angle. That is, when the radar self-test angle is less than 5° and the difference between it and the radar initial adaptation angle is greater than 3°, the vehicle radar is also configured to continuously monitor the radar self-test angle within the current ignition cycle and not update the radar initial adaptation angle to the radar self-test angle.

[0043] In one embodiment, the present invention also provides a vehicle-mounted radar detection angle anomaly detection device to implement the vehicle-mounted radar detection angle anomaly detection method, comprising:

[0044] The data acquisition module is used to acquire point cloud data collected by the vehicle radar and to preprocess the acquired point cloud data.

[0045] The radar self-test module is used to determine the radar self-test angle of the vehicle radar based on the preprocessed point cloud data, and compare the radar self-test angle with the preset abnormal angle threshold and the radar initial adaptation angle in sequence; the radar self-test angle represents the angle result monitored in real time when the radar is working, and the radar initial adaptation angle represents the angle when the radar is initially installed.

[0046] When the radar self-test angle is greater than a preset abnormal angle threshold and the difference between the radar self-test angle and the radar initial adaptation angle is greater than a preset angle difference threshold, the detection angle of the vehicle radar is determined to be abnormal, and the vehicle radar is set to continuously monitor the radar self-test angle in the current ignition cycle, without updating the radar initial adaptation angle to the radar self-test angle.

[0047] In a specific embodiment, the radar self-test module is further configured to update the radar initial adaptation angle to the radar self-test angle when the radar self-test angle is greater than a preset abnormal angle threshold and the difference between the radar self-test angle and the radar initial adaptation angle is less than a preset angle difference threshold, or when the radar self-test angle is less than a preset abnormal angle threshold and the difference between the radar self-test angle and the radar initial adaptation angle is less than a preset angle difference threshold.

[0048] The radar self-test module is further configured to, when the radar self-test angle is less than a preset abnormal angle threshold and the difference between the radar self-test angle and the radar initial adaptation angle is greater than a preset angle difference threshold, set the vehicle radar to continuously monitor the radar self-test angle within the current ignition cycle and not update the radar initial adaptation angle to the radar self-test angle.

[0049] The present invention also provides a vehicle, characterized in that it comprises:

[0050] One or more processors;

[0051] Memory;

[0052] Detection components;

[0053] One or more computer programs, wherein the one or more computer programs are stored in the memory and configured to be executed by the one or more processors, the one or more computer programs being configured to perform the vehicle-mounted radar detection angle anomaly detection method.

[0054] The present invention also provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores computer program instructions, which can be called by a processor to execute the vehicle-mounted radar detection angle anomaly detection method.

[0055] It should be noted that the apparatus described in the above embodiments corresponds to the method described in the above embodiments. Therefore, the parts of the apparatus described in the above embodiments that are not described in detail can be obtained by referring to the content of the method described in the above embodiments, and will not be repeated here.

[0056] It is understood that further details regarding the steps involved in the aforementioned automobile and computer-readable storage media can be found in the aforementioned limitations on the method for detecting anomalies in the detection angle of vehicle radar, and will not be repeated here.

[0057] In summary, implementing the embodiments of the present invention has the following beneficial effects:

[0058] The present invention provides a method, device, vehicle, and medium for detecting abnormal radar detection angles. When the radar self-test angle is greater than 5° and deviates from the initial adaptation angle by more than 3°, it can be determined that the current radar angle deviation is not caused by normal aging of the installation position. In this case, the radar's initial adaptation angle is not updated, which can effectively avoid frequent false alarms of radar angle deviation caused by road bumps or sudden deformation of the bumper (which can be recovered). This avoids such recoverable faults that cause the radar to malfunction, allowing the system to work normally and reducing customer complaints.

[0059] The above description discloses only preferred embodiments of the present invention and should not be construed as limiting the scope of the present invention. Therefore, equivalent variations made in accordance with the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for detecting anomalies in the detection angle of a vehicle-mounted radar, characterized in that, include: Acquire point cloud data collected by vehicle-mounted radar and preprocess the collected point cloud data; The radar self-test angle of the vehicle-mounted radar is determined based on the preprocessed point cloud data. The radar self-test angle is then compared sequentially with a preset abnormal angle threshold and the radar initial adaptation angle. The radar self-test angle represents the angle result monitored in real time when the radar is working, and the radar initial adaptation angle represents the angle when the radar is initially installed. The radar self-test angle is calculated by sorting multiple sets of angle measurement sample values ​​based on the preprocessed point cloud data, removing outliers, and taking the average value to output the final angle calculation result. When the radar self-test angle is greater than a preset abnormal angle threshold and the difference between the radar self-test angle and the radar initial adaptation angle is greater than a preset angle difference threshold, the detection angle of the vehicle radar is determined to be abnormal, and the vehicle radar is set to continuously monitor the radar self-test angle in the current ignition cycle, without updating the radar initial adaptation angle to the radar self-test angle.

2. The method as described in claim 1, characterized in that, Also includes: When the radar self-test angle is greater than the preset abnormal angle threshold and the difference between the radar self-test angle and the radar initial adaptation angle is less than the preset angle difference threshold, the vehicle radar angle is determined to be out of tolerance, and the radar initial adaptation angle is set to be updated to the radar self-test angle.

3. The method as described in claim 2, characterized in that, Also includes: When the radar self-test angle is less than a preset abnormal angle threshold and the difference between the radar self-test angle and the radar initial adaptation angle is less than a preset angle difference threshold, the radar initial adaptation angle is updated to the radar self-test angle.

4. The method as described in claim 2, characterized in that, Also includes: When the radar self-test angle is less than the preset abnormal angle threshold and the difference between the radar self-test angle and the radar initial adaptation angle is greater than the preset angle difference threshold, the vehicle radar is set to continuously monitor the radar self-test angle within the current ignition cycle and not update the radar initial adaptation angle to the radar self-test angle.

5. The method as described in claim 1, characterized in that, The preprocessing of the collected point cloud data includes: Obtain the target detection range of the vehicle-mounted radar, wherein the signal strength corresponding to the data point in the point cloud data of the target detection range is greater than a specified strength; The point cloud data within the target detection range is determined as the preprocessed point cloud data.

6. A vehicle-mounted radar detection angle anomaly detection device, used to implement the method as described in any one of claims 1-5, characterized in that, include: The data acquisition module is used to acquire point cloud data collected by the vehicle radar and to preprocess the acquired point cloud data. The radar self-test module is used to determine the radar self-test angle of the vehicle-mounted radar based on preprocessed point cloud data. The radar self-test angle is compared sequentially with a preset abnormal angle threshold and the radar initial adaptation angle. The radar self-test angle represents the angle result monitored in real time when the radar is working, and the radar initial adaptation angle represents the angle when the radar is initially installed. The radar self-test angle is calculated by sorting multiple sets of angle measurement sample values ​​based on preprocessed point cloud data, removing outliers, and taking the average value to output the final angle calculation result. When the radar self-test angle is greater than a preset abnormal angle threshold and the difference between the radar self-test angle and the radar initial adaptation angle is greater than a preset angle difference threshold, the detection angle of the vehicle radar is determined to be abnormal, and the vehicle radar is set to continuously monitor the radar self-test angle in the current ignition cycle, without updating the radar initial adaptation angle to the radar self-test angle.

7. The apparatus as claimed in claim 6, characterized in that, The radar self-test module is further configured to update the radar initial adaptation angle to the radar self-test angle when the radar self-test angle is greater than a preset abnormal angle threshold and the difference between the radar self-test angle and the radar initial adaptation angle is less than a preset angle difference threshold, or when the radar self-test angle is less than a preset abnormal angle threshold and the difference between the radar self-test angle and the radar initial adaptation angle is less than a preset angle difference threshold.

8. The apparatus as claimed in claim 7, characterized in that, The radar self-test module is further configured to, when the radar self-test angle is less than a preset abnormal angle threshold and the difference between the radar self-test angle and the radar initial adaptation angle is greater than a preset angle difference threshold, set the vehicle radar to continuously monitor the radar self-test angle within the current ignition cycle and not update the radar initial adaptation angle to the radar self-test angle.

9. A vehicle, characterized in that, include: One or more processors; Memory; Detection components; One or more computer programs, wherein the one or more computer programs are stored in the memory and configured to be executed by the one or more processors, the one or more computer programs being configured to perform the method as described in any one of claims 1 to 5.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that can be invoked by a processor to perform the method as described in any one of claims 1 to 5.

Images