An automatic driving vehicle sensor offset diagnosis method and device

Abstract

The application provides an automatic driving vehicle-mounted sensor offset diagnosis method and device, the method comprising: calibrating a target object; obtaining detection results of each vehicle-mounted sensor on at least the position of the target object in multiple different scenes; obtaining detection results of a multi-sensor fusion detection method on at least the position of the target object in multiple different scenes; and diagnosing each sensor based on at least the detection results of each sensor on the position of the target object and the detection results of the multi-sensor fusion detection method on the position of the target object to determine whether there is a target sensor with a position offset. The automatic driving vehicle-mounted sensor offset diagnosis method can quickly and accurately diagnose whether the sensors on the vehicle have an offset.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving for smart devices, and in particular to a method and apparatus for diagnosing the offset of onboard sensors in autonomous driving vehicles. Background Technology

[0002] In open scenarios, autonomous vehicles face complex and ever-changing environments. Currently, single sensors have limited accuracy in target detection, and their false detection and false negative rates are relatively high. To improve the accuracy and reliability of perception of the external environment, multi-sensor fusion solutions are highly recommended.

[0003] In current multi-sensor solutions, once the initial calibration is completed, the calibration effect of the sensors is no longer considered. In the short term, the angle and position of the sensors do not change much, and the offset in the detection of target position, speed, and heading angle is small and not enough to affect the detection effect of multi-sensor fusion. However, as the vehicle runs for a long time, the sensors inevitably encounter severe bumps or other situations that cause sensor offset. This will affect the accuracy of the offset sensor in detecting the position, angle, or other key information of the target object, and at the same time, the detection effect of multi-sensor fusion will also be directly affected.

[0004] Specifically, the sensor offset caused by prolonged bumps or other unnoticed conditions can lead to a deterioration in the overall perception of autonomous vehicles without the driver's knowledge. This manifests as a decrease in the accuracy of detecting the position, heading angle, and speed of obstacles. Troubleshooting this problem is quite difficult, making online diagnostics and early warning of sensor offset essential. Diagnosis allows technicians to understand the sensor offset in real time, promptly alerting relevant personnel to the adverse effects of inaccurate target detection caused by sensor offset, and reducing the time spent troubleshooting problems caused by sensor offset and deteriorating perception. Summary of the Invention

[0005] This invention provides a method and apparatus for diagnosing sensor offset in autonomous driving vehicles, which can quickly and accurately diagnose whether sensors on a vehicle have shifted.

[0006] To address the aforementioned technical problems, embodiments of the present invention provide a method for diagnosing the offset of onboard sensors in autonomous driving vehicles, comprising:

[0007] Target object;

[0008] Obtain the detection results of the target object's position by each vehicle-mounted sensor in multiple different scenarios;

[0009] Obtain detection results of the target object's position based on a multi-sensor fusion detection method in multiple different scenarios;

[0010] The sensors are diagnosed based at least on the detection results of the target object's position by each sensor and the detection results of the target object's position by the multi-sensor fusion detection method, in order to determine whether there are any target sensors with positional shifts.

[0011] As an optional embodiment, obtaining the detection results of the target object's position by each vehicle-mounted sensor under multiple different scenarios includes:

[0012] Obtain at least the lateral distance detection results and longitudinal distance detection results between the target object and the vehicle where each sensor is located under multiple different scenarios from each vehicle-mounted sensor.

[0013] As an optional embodiment, obtaining the detection results of the target object's position based on a multi-sensor fusion detection method in multiple different scenarios includes:

[0014] Obtain at least the lateral distance detection results and longitudinal distance detection results between the target object and the vehicle where each sensor is located under multiple different scenarios based on the multi-sensor fusion detection method.

[0015] As an optional embodiment, it also includes:

[0016] After the target object is initially calibrated, the normalized difference X between the lateral distance detection results of the vehicle and the detection results obtained by each sensor during the period of stable tracking of the target object is determined. d Normalized difference Y of longitudinal distance detection results d And the normalized difference X between the lateral distance detection result and the vehicle detected during the stable tracking of the target object based on the multi-sensor fusion detection method. d Normalized difference Y of longitudinal distance detection results d ;

[0017] Based on the obtained X d Value, the Y d The values ​​are calculated as the average values ​​corresponding to each sensor during the stable tracking period. and average value

[0018] As an optional embodiment, it also includes:

[0019] Determine the normalized difference X between the lateral distance detection results of the target object and the vehicle obtained by each sensor within the target period. d1 Normalized difference Y of longitudinal distance detection results d1And the normalized difference X between the target object and the vehicle in the target period, obtained by the multi-sensor fusion detection method. d1 Normalized difference Y of longitudinal distance detection results d1 ;

[0020] Based on the obtained X d1 Value, the Y d1 The values ​​are calculated as the average values ​​corresponding to each sensor during the stable tracking period. and average value

[0021] As an optional embodiment, it also includes:

[0022] Based on the preset fusion strategy corresponding to each sensor, multiple offset thresholds corresponding to each sensor are calculated and determined.

[0023] As an optional embodiment, the step of diagnosing each sensor based at least on the detection results of the target object's position by each sensor and the detection results of the target object's position based on the multi-sensor fusion detection method, to determine whether there is a target sensor with a positional shift, includes:

[0024] Based on the average values ​​of each of the aforementioned sensors and average and the average values ​​corresponding to each of the aforementioned sensors. and average Calculate the difference;

[0025] The difference is compared with the corresponding sensor offset threshold.

[0026] The target sensor is determined based on the comparison results, wherein the difference corresponding to the target sensor exceeds the corresponding offset threshold.

[0027] As an optional embodiment, it also includes:

[0028] Determine the offset of each sensor;

[0029] The offset of each sensor is displayed.

[0030] As an optional embodiment, it also includes:

[0031] An alarm is output when the target sensor is identified.

[0032] Another embodiment of the present invention also provides an autonomous driving vehicle-mounted sensor offset diagnostic device, comprising:

[0033] The calibration module is used to calibrate the target object;

[0034] The first acquisition module is used to acquire the detection results of the position of the target object by each vehicle-mounted sensor in multiple different scenarios;

[0035] The second acquisition module is used to acquire the detection results of the position of the target object based on the multi-sensor fusion detection method in multiple different scenarios;

[0036] The calculation module is used to diagnose each sensor based at least on the detection results of the target object's position by each sensor and the detection results of the target object's position based on the multi-sensor fusion detection method, so as to determine whether there is a target sensor with a positional shift.

[0037] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings.

[0038] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0039] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0040] Figure 1 This is a flowchart of the autonomous driving vehicle-mounted sensor offset diagnosis method in an embodiment of the present invention.

[0041] Figure 2 This is a schematic diagram showing the arrangement of various sensors on the vehicle in an embodiment of the present invention.

[0042] Figure 3 This is a structural block diagram of the autonomous driving vehicle-mounted sensor offset diagnostic device in an embodiment of the present invention. Detailed Implementation

[0043] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings, but these are not intended to limit the scope of the invention.

[0044] It should be understood that various modifications can be made to the embodiments disclosed herein. Therefore, the following description should not be considered as limiting, but merely as an example of embodiments. Other modifications within the scope and spirit of this disclosure will be apparent to those skilled in the art.

[0045] The accompanying drawings, which are included in and form part of this specification, illustrate embodiments of the present disclosure and, together with the general description of the disclosure given above and the detailed description of the embodiments given below, serve to explain the principles of the disclosure.

[0046] These and other features of the invention will become apparent from the following description of preferred forms of embodiments given as non-limiting examples, with reference to the accompanying drawings.

[0047] It should also be understood that although the invention has been described with reference to some specific examples, those skilled in the art can certainly implement many other equivalent forms of the invention, which have the features described in the claims and are therefore all within the scope of protection defined herein.

[0048] The above and other aspects, features and advantages of this disclosure will become more apparent when taken in conjunction with the accompanying drawings and in view of the following detailed description.

[0049] Specific embodiments of the present disclosure are described thereafter with reference to the accompanying drawings; however, it should be understood that the disclosed embodiments are merely examples of the present disclosure and can be implemented in various ways. Well-known and / or repeated functions and structures are not described in detail to avoid unnecessary or redundant details that could obscure the present disclosure. Therefore, the specific structural and functional details disclosed herein are not intended to be limiting, but merely to serve as the basis and representative basis for the claims to teach those skilled in the art to use the present disclosure in a variety of substantially any suitable detailed structures.

[0050] This specification may use the phrases “in one embodiment,” “in another embodiment,” “in yet another embodiment,” or “in still another embodiment,” all of which may refer to one or more of the same or different embodiments according to this disclosure.

[0051] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0052] like Figure 1 As shown, this embodiment of the invention provides a method for diagnosing the offset of onboard sensors in autonomous driving vehicles, including:

[0053] Target object;

[0054] Obtain the detection results of the target object's position by each vehicle-mounted sensor in multiple different scenarios;

[0055] Obtain the detection results of the target object's position based on a multi-sensor fusion detection method in multiple different scenarios;

[0056] The detection results of the target object's position by each sensor are used as a basis for diagnosis, based at least on the detection results of the target object's position by the multi-sensor fusion detection method, to determine whether there are any target sensors with positional deviations.

[0057] For example, a vehicle with autonomous driving capabilities has multiple sensors. Testers can manually calibrate the target object, or the vehicle's onboard system can randomly calibrate the target object during driving; the specific calibration method is not unique. The target object can be a stationary object or a moving vehicle. After initial target object calibration, the system obtains detection results from each sensor in multiple different scenarios, such as different driving scenarios including different road sections, driving environments, and weather conditions, showing the target object's position at least once. Simultaneously, the system obtains detection results from the same multiple different scenarios—that is, scenarios identical to those experienced by the sensors—showing the same target object's position detected at least once, based on a multi-sensor fusion detection method. Having obtained the two detection results from different methods, the system diagnoses each sensor based on both the individual sensor's target object position detection results and the multi-sensor fusion detection method's results, to determine if any target sensors have experienced positional shifts.

[0058] This embodiment uses the above method to diagnose sensor position shifts caused by prolonged vehicle operation, bumps, or other unnoticed factors. It promptly detects target sensors with position shifts, and the overall diagnostic process is simple, fast, and highly accurate. This effectively prevents the overall perception performance of autonomous vehicles from deteriorating due to sensor position shifts without human knowledge, including reduced detection accuracy when detecting the position, heading angle, and speed of obstacles. It reduces the difficulty for users or technicians to troubleshoot vehicle anomalies, allowing users and other personnel to understand sensor shifts in real time and reducing the time spent troubleshooting vehicle problems.

[0059] Furthermore, in this embodiment, the detection results of the target object's position by each vehicle-mounted sensor under multiple different scenarios are obtained, including:

[0060] Obtain at least the lateral distance detection results and longitudinal distance detection results between the target object and the vehicle where each sensor is located under multiple different scenarios.

[0061] Furthermore, the detection results of at least the target object's position based on the multi-sensor fusion detection method are obtained in multiple different scenarios, including:

[0062] The method obtains at least the lateral distance detection results and longitudinal distance detection results between the target object and the vehicle where each sensor is located in multiple different scenarios based on the multi-sensor fusion detection method.

[0063] That is, by using sensors and fusion methods, the lateral and longitudinal distances between the target and the vehicle are detected respectively.

[0064] Furthermore, the method in this embodiment also includes:

[0065] After the initial target calibration, the normalized difference X between the lateral distance detection results of each sensor and the vehicle during the period of stable tracking of the target is determined. d Normalized difference Y of longitudinal distance detection results d And the normalized difference X between the lateral distance detection results of the target and the vehicle obtained during stable tracking of the target using a multi-sensor fusion detection method. d Normalized difference Y of longitudinal distance detection results d ;

[0066] Based on the obtained X d Value, Y d The values ​​are calculated as the average values ​​of each sensor during the stable tracking period. and average value That is, based on the obtained X d Value, calculate the average value of the corresponding sensor. According to the obtained Y d The value is calculated based on the average value of the corresponding sensor.

[0067] In addition, the method in this embodiment also includes:

[0068] Determine the normalized difference X between the lateral distance detection results of the target object and the vehicle obtained by each sensor within the target period. d1 Normalized difference Y of longitudinal distance detection results d1 And the normalized difference X between the target object and the vehicle detected by the multi-sensor fusion detection method within the target period. d1 Normalized difference Y of longitudinal distance detection results d1 ;

[0069] Based on the obtained X d1 Value, Y d1 The values ​​are calculated as the average values ​​of each sensor during the stable tracking period. and average value

[0070] That is, also based on the obtained X d1 Value, calculate the average value of the corresponding sensor. According to the obtained Y d1 The value is calculated based on the average value of the corresponding sensor. The specific duration of the aforementioned fixed cycle is variable and can be determined based on factors such as the actual vehicle performance, autonomous driving capabilities, and the number of sensors.

[0071] Furthermore, the method in this embodiment also includes:

[0072] Based on the preset fusion strategy corresponding to each sensor, multiple offset thresholds corresponding to each sensor are calculated and determined.

[0073] For example, the offset threshold D for each sensor is calculated based on the preset fusion strategy for each sensor in the fusion algorithm. T .

[0074] Furthermore, in this embodiment, at least based on the detection results of the target object's position by each sensor and the detection results of the target object's position based on the multi-sensor fusion detection method, the sensors are diagnosed to determine whether there are any target sensors with positional shifts, including:

[0075] The difference is calculated based on the average value and average value of each corresponding sensor, and the average value and average value of each corresponding sensor.

[0076] The difference is compared with the corresponding sensor offset threshold;

[0077] The target sensor is determined based on the comparison results, where the difference between the target sensor and the target sensor exceeds the corresponding offset threshold.

[0078] For example, comparing the longitudinal and lateral distance detection results obtained after the initial calibration. and Corresponding to data collected periodically and The differences are compared with the corresponding offset thresholds for the same sensor. At least one sensor with a difference exceeding the threshold is identified as the target sensor, indicating a significant positional shift. Differences within the threshold also result in a smaller positional shift for the corresponding sensor, which can be adjusted or left unadjusted. Differences less than the threshold indicate no sensor shift. Furthermore, if the sensor's detected value and the fusion method's detected value are greater than the corresponding sensor offset threshold, the sensor cannot participate in the fusion process; otherwise, it can. In other words, sensors with large positional shifts cannot participate in the fusion process; only sensors with no or small positional shifts can participate.

[0079] Optionally, the method in this embodiment further includes:

[0080] Determine the offset of each sensor;

[0081] Displays the offset of each sensor.

[0082] and / or

[0083] An alarm is output when the target sensor is identified.

[0084] For example, the positional offset or offset level of each sensor can be determined, and then the positional offset or offset level of each sensor can be output on the vehicle's display screen, such as large offset, small offset, or no offset. Furthermore, when a target sensor with a large positional offset is identified, the vehicle's horn can be controlled to output a warning sound, or an alarm message can be displayed on the screen, or both a warning sound and an alarm message can be output simultaneously. This alarm message may include information such as which sensor has experienced a large positional offset and requires immediate adjustment by the user or technician.

[0085] Specifically, in order to better illustrate the above method of this embodiment, the following detailed description is provided in conjunction with specific embodiments:

[0086] For example, the configuration of multiple sensors on a vehicle includes:

[0087] Three lidar units, including two forward-facing 32-line lidar units and one 16-line backward-facing lidar unit;

[0088] Four smart cameras, including three front-facing main cameras and one rear-facing camera;

[0089] Five millimeter-wave radars, including one forward-facing and four lateral millimeter-wave radars.

[0090] The test vehicle is 6 meters long, 2.6 meters wide, and 3 meters high. The preferred installation method is shown in the diagram. The vehicle's longitudinal direction is X-axis. Figure 2 The direction of the vehicle is indicated by the diagram, with upward movement being positive and downward movement being negative; the horizontal direction of the vehicle is indicated by the diagram, with leftward movement being positive and rightward movement being negative.

[0091] Furthermore, taking the measurement results of a certain forward-facing camera as an example for analysis, we obtain the longitudinal distance detection result X of the camera during the stable tracking time period of a certain stable tracking target. 相机 The longitudinal distance detection result X of the fusion method 融合 The X-axis of the camera is calculated. d Value, statistically, the stable tracking target X within the stable tracking period. d The mean A x .

[0092] X d =((X) 融合 -X相机 )) / X 融合

[0093]

[0094] Analogous to the above method of solving the normalized difference Y of the detection results in the Y direction using parameters related to the X direction. d The average value A y The solution is as follows:

[0095] Y d =((Y) 融合 -Y 相机 )) / Y 融合

[0096]

[0097] The above A x and A y This is considered as the sensor's offset in the x and y directions. Compare the offsets A in the X and Y directions respectively. x and the corresponding offset threshold x-axis value, A y The value in the y-direction of the corresponding offset threshold is used. If the offset is greater than the threshold, a warning is issued; if it is less than the threshold, the offset is displayed.

[0098] The above method only describes how to calculate the offset of a specific forward-facing camera. Similarly, the offsets of the LiDAR and millimeter-wave radar in the forward and lateral directions can be calculated and real-time alerts provided. This embodiment obtains the current offset status of each sensor in the vehicle by comparing the initial calibration deviation with the current sensor deviation, and issues alerts and warnings to improve the vehicle's self-diagnostic capabilities. Furthermore, it can provide the offset of each sensor in real time, reducing the troubleshooting time for problems such as deteriorated perception caused by sensor offset; it also reminds relevant personnel to perform checks to prevent adverse effects caused by inaccurate target detection due to sensor offset, thereby improving the safety of autonomous vehicles.

[0099] like Figure 3 As shown, another embodiment of the present invention also provides an autonomous driving vehicle-mounted sensor offset diagnostic device, comprising:

[0100] The calibration module is used to calibrate the target object;

[0101] The first acquisition module is used to acquire the detection results of the position of the target object by each vehicle sensor in multiple different scenarios;

[0102] The second acquisition module is used to acquire the detection results of the position of the target object based on the multi-sensor fusion detection method in multiple different scenarios;

[0103] The calculation module is used to diagnose each sensor based at least on the detection results of the target position by each sensor and the detection results of the target position based on the multi-sensor fusion detection method, so as to determine whether there is a target sensor with positional displacement.

[0104] As an optional embodiment, obtaining the detection results of the target object's position by each vehicle-mounted sensor under multiple different scenarios includes:

[0105] Obtain at least the lateral distance detection results and longitudinal distance detection results between the target object and the vehicle where each sensor is located under multiple different scenarios from each vehicle-mounted sensor.

[0106] As an optional embodiment, obtaining the detection results of the target object's position based on a multi-sensor fusion detection method in multiple different scenarios includes:

[0107] Obtain at least the lateral distance detection results and longitudinal distance detection results between the target object and the vehicle where each sensor is located under multiple different scenarios based on the multi-sensor fusion detection method.

[0108] As an optional embodiment, it also includes:

[0109] After the target object is initially calibrated, the normalized difference X between the lateral distance detection results of the vehicle and the detection results obtained by each sensor during the period of stable tracking of the target object is determined. d Normalized difference Y of longitudinal distance detection results d And the normalized difference X between the lateral distance detection result and the vehicle detected during the stable tracking of the target object based on the multi-sensor fusion detection method. d Normalized difference Y of longitudinal distance detection results d ;

[0110] Based on the obtained X d Value, the Y d The values ​​are calculated as the average values ​​corresponding to each sensor during the stable tracking period. and average value

[0111] As an optional embodiment, it also includes:

[0112] Determine the normalized difference X between the lateral distance detection results of the target object and the vehicle obtained by each sensor within the target period. d1 Normalized difference Y of longitudinal distance detection results d1 And the normalized difference X between the target object and the vehicle in the target period, obtained by the multi-sensor fusion detection method.d1 Normalized difference Y of longitudinal distance detection results d1 ;

[0113] Based on the obtained X d1 Value, the Y d1 The values ​​are calculated as the average values ​​corresponding to each sensor during the stable tracking period. and average value

[0114] As an optional embodiment, it also includes:

[0115] Based on the preset fusion strategy corresponding to each sensor, multiple offset thresholds corresponding to each sensor are calculated and determined.

[0116] As an optional embodiment, the step of diagnosing each sensor based at least on the detection results of the target object's position by each sensor and the detection results of the target object's position based on the multi-sensor fusion detection method, to determine whether there is a target sensor with a positional shift, includes:

[0117] Based on the average values ​​of each of the aforementioned sensors and average and the average values ​​corresponding to each of the aforementioned sensors. and average Calculate the difference;

[0118] The difference is compared with the corresponding sensor offset threshold.

[0119] The target sensor is determined based on the comparison results, wherein the difference corresponding to the target sensor exceeds the corresponding offset threshold.

[0120] As an optional embodiment, it also includes:

[0121] Determine the offset of each sensor;

[0122] The offset of each sensor is displayed.

[0123] As an optional embodiment, it also includes:

[0124] An alarm is output when the target sensor is identified.

[0125] Another embodiment of this application also provides an electronic device, including:

[0126] One or more processors;

[0127] Memory, configured to store one or more programs;

[0128] When the one or more programs are executed by the one or more processors, the one or more processors shall implement the methods described above.

[0129] One embodiment of this application also provides a storage medium storing a computer program that, when executed by a processor, implements the method described above. It should be understood that the various solutions in this embodiment have the corresponding technical effects in the above method embodiments, and will not be repeated here.

[0130] This application also provides a computer program product tangibly stored on a computer-readable medium and including computer-readable instructions that, when executed, cause at least one processor to perform methods as described in the embodiments above. It should be understood that the various solutions in this embodiment have the corresponding technical effects in the above method embodiments, which will not be repeated here.

[0131] It should be noted that the computer storage medium of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. Computer-readable media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access storage media (RAM), read-only storage media (ROM), erasable programmable read-only storage media (EPROM or flash memory), optical fibers, portable compact disk read-only storage media (CD-ROM), optical storage media, magnetic storage media, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program configured for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, antenna, optical fiber, RF, etc., or any suitable combination thereof.

[0132] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0133] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0134] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0135] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0136] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

[0137] The above embodiments are merely exemplary embodiments of the present invention and are not intended to limit the present invention. The scope of protection of the present invention is defined by the claims. Those skilled in the art can make various modifications or equivalent substitutions to the present invention within its spirit and scope of protection, and such modifications or equivalent substitutions should also be considered to fall within the scope of protection of the present invention.

Claims

1. A method for diagnosing the offset of onboard sensors in an autonomous driving vehicle, characterized in that, include: Target object; Obtain the detection results of the target object's position by each vehicle-mounted sensor in multiple different scenarios; Obtain detection results of the target object's position based on a multi-sensor fusion detection method in multiple different scenarios; The detection results of the target object's position by each sensor, and the detection results of the target object's position by the multi-sensor fusion detection method, are used to diagnose each sensor to determine whether there is a target sensor with a positional shift. This also includes: After the target object is initially calibrated, the normalized difference X between the lateral distance detection results of the target object and the vehicle detected by each sensor during stable tracking of the target object is determined. d Normalized difference Y of longitudinal distance detection results d And the normalized difference X between the lateral distance detection result and the vehicle detected during the stable tracking of the target object based on the multi-sensor fusion detection method. d Normalized difference Y of longitudinal distance detection results d ; Based on the obtained X d Value, the Y d The values ​​are calculated as the average values ​​corresponding to each sensor during the stable tracking period. and average ; Also includes: Determine the normalized difference X between the lateral distance detection results of the target object and the vehicle obtained by each sensor within the target period. d1 Normalized difference Y of longitudinal distance detection results d1 And the normalized difference X between the target object and the vehicle in the target period, obtained by the multi-sensor fusion detection method. d1 Normalized difference Y of longitudinal distance detection results d1 ; Based on the obtained X d1 Value, the Y d1 The values ​​are calculated as the average values ​​corresponding to each sensor during the stable tracking period. and average ; Also includes: Based on the preset fusion strategy corresponding to each sensor, multiple offset thresholds corresponding to each sensor are calculated and determined. The step of diagnosing each sensor based at least on the detection results of the target object's position by each sensor, and based on the detection results of the target object's position by the multi-sensor fusion detection method, to determine whether there is a target sensor with a positional shift, includes: Based on the average values ​​of each of the aforementioned sensors and average and the average value corresponding to each of the aforementioned sensors. and average Calculate the difference; The difference is compared with the corresponding sensor offset threshold. The target sensor is determined based on the comparison results, wherein the difference corresponding to the target sensor exceeds the corresponding offset threshold. Among them, X d =((X 融合 -X 相机 )) X 融合 Y d =((Y 融合 -Y 相机 )) Y 融合 X 相机 X represents the camera's lateral distance detection result. 融合 For the lateral distance detection results of the fusion method, Y 相机 Y represents the camera's longitudinal distance detection result. 融合 This represents the longitudinal distance detection results from the fusion method.

2. The method according to claim 1, characterized in that, The process of obtaining the detection results of the target object's position by each vehicle-mounted sensor under multiple different scenarios includes: Obtain at least the lateral distance detection results and longitudinal distance detection results between the target object and the vehicle where each sensor is located under multiple different scenarios from each vehicle-mounted sensor.

3. The method according to claim 2, characterized in that, The acquisition of detection results of the target object's position based on a multi-sensor fusion detection method in multiple different scenarios includes: Obtain at least the lateral distance detection results and longitudinal distance detection results between the target object and the vehicle where each sensor is located under multiple different scenarios based on the multi-sensor fusion detection method.

4. The method according to claim 1, characterized in that, Also includes: Determine the offset of each sensor; The offset of each sensor is displayed.

5. The method according to claim 4, characterized in that, Also includes: An alarm is output when the target sensor is identified.

6. An autonomous driving vehicle-mounted sensor offset diagnostic device, characterized in that, For implementing the autonomous driving vehicle-mounted sensor offset diagnosis method as described in any one of claims 1-5, the apparatus comprises: The calibration module is used to calibrate the target object; The first acquisition module is used to acquire the detection results of the position of the target object by each vehicle-mounted sensor in multiple different scenarios; The second acquisition module is used to acquire the detection results of the position of the target object based on the multi-sensor fusion detection method in multiple different scenarios; The calculation module is used to diagnose each sensor based at least on the detection results of the target object's position by each sensor and the detection results of the target object's position based on the multi-sensor fusion detection method, so as to determine whether there is a target sensor with a positional shift.

Images