Laser radar self-checking method and device for autonomous vehicle

Abstract

The invention discloses a laser radar self-checking method and device for an automatic driving vehicle, which are used for solving the technical problems of how to design and optimize a self-checking algorithm of a vehicle state and how to improve the response speed and accuracy of a system to an abnormal state. Performing hardware self-inspection on the laser radar of the automatic driving vehicle, and starting the automatic driving vehicle when the hardware self-inspection is passed; carrying out pos change judgment on the running automatic driving vehicle, and obtaining a first sensor parameter through plane fitting when judging that the automatic driving vehicle runs in a straight line; judging whether the laser radar has position fluctuation or not according to the first sensor parameter, and if not, tracking the vehicle detected at the front end; when a preset tracking judgment condition is met, acquiring laser point cloud data of the tracked vehicle, and calculating a second sensor parameter based on the laser point cloud data; and performing parameter verification on the second sensor parameter, and when the parameter verification meets a preset threshold condition, completing comprehensive self-inspection for the laser radar.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to a LiDAR self-testing method for autonomous vehicles, a LiDAR self-testing device for autonomous vehicles, an electronic device, and a storage medium. Background Technology

[0002] In Level 4 autonomous vehicle operation, the vehicle's autonomous driving system needs to possess a high degree of intelligence and autonomy to ensure safe operation in complex urban road environments. However, this high degree of autonomy also places extremely high demands on the system's stability and reliability. Especially when faced with emergencies or system malfunctions, the vehicle must be able to react promptly to avoid danger.

[0003] In the operation of autonomous vehicles, automatic vehicle status detection is a crucial aspect of ensuring safety. Vehicles need to monitor the status of their sensors, the health of their control systems, and the operation of their actuators in real time so that timely measures can be taken in case of anomalies.

[0004] However, existing autonomous driving systems still face certain technical challenges in vehicle status self-checking. Some systems rely on redundancy design and fault-tolerance mechanisms. But these mechanisms can still miss or misjudge situations in actual operation. Once an abnormal state of the vehicle is not detected in time during operation, it could very likely lead to a serious accident.

[0005] Therefore, how to design and optimize the self-checking algorithm for vehicle status, and how to improve the system's response speed and accuracy to abnormal states, are urgent problems to be solved in the current development of L4 autonomous vehicle technology. Summary of the Invention

[0006] This invention provides a LiDAR self-testing method for autonomous vehicles, a LiDAR self-testing device for autonomous vehicles, an electronic device, and a storage medium, which are used to solve or partially solve the technical problem of how to design and optimize the self-testing algorithm for vehicle status, and improve the system's response speed and accuracy to abnormal states.

[0007] This invention provides a self-testing method for lidar in autonomous vehicles, the method comprising:

[0008] Perform a hardware self-test on the LiDAR of the autonomous vehicle, and start the autonomous vehicle when the hardware self-test passes;

[0009] The pos change of the autonomous vehicle in motion is judged. When it is determined that the autonomous vehicle is traveling in a straight line, the first sensor parameters are obtained by plane fitting.

[0010] Based on the parameters of the first sensor, determine whether the lidar has experienced position fluctuations. If not, then track the vehicle detected by the front end.

[0011] When the preset tracking judgment conditions are met, the laser point cloud data of the tracked vehicle is acquired, and the parameters of the second sensor are calculated based on the laser point cloud data.

[0012] The parameters of the second sensor are verified. When the parameter verification meets the preset threshold conditions, a comprehensive self-test for the lidar is completed.

[0013] Optionally, the hardware self-test for the LiDAR of the autonomous vehicle includes:

[0014] Acquire open areas detected by different types of sensors in autonomous vehicles;

[0015] The flatness is obtained by detecting the point cloud state of the open area using lidar.

[0016] When the flatness meets the preset flatness threshold, it is determined that the lidar has passed the hardware self-test.

[0017] Optionally, the step of judging the pos change of the autonomous vehicle in motion, and obtaining the first sensor parameters through plane fitting when it is determined that the autonomous vehicle is traveling in a straight line, includes:

[0018] The laser radar is used to collect laser point clouds of the autonomous vehicle in motion, and the collected laser point clouds are then framed to obtain framed point cloud data.

[0019] The pos is calculated based on the extracted point cloud data, and the driving route is determined based on the pos calculation result.

[0020] When the driving route determination result indicates that the autonomous vehicle is driving in a straight line, the first sensor parameters are obtained through plane fitting calculation.

[0021] Optionally, the first sensor parameters include pitch angle, roll angle, and position offset tz; the step of determining whether the lidar experiences position fluctuations based on the first sensor parameters includes:

[0022] The pitch angle, roll angle, and position offset tz are compared with the corresponding reference parameter values ​​in the database.

[0023] When the deviations of the pitch angle, the roll angle, and the position offset tz from the corresponding reference parameter values ​​in the database are all less than their respective preset deviation thresholds, it is determined that the lidar has not experienced position fluctuations.

[0024] Optionally, acquiring the laser point cloud data of the tracking vehicle when the preset tracking judgment conditions are met includes:

[0025] When the lidar detects that a set number of vehicles appear stably in a continuous preset frame in front of the autonomous vehicle, it acquires the lidar point cloud data of the continuously appearing vehicles.

[0026] Optionally, calculating the second sensor parameters based on the laser point cloud data includes:

[0027] Registration calculations are performed based on the laser point cloud data to obtain the parameters of the second sensor.

[0028] Optionally, the second sensor parameters include the yaw angle, position offset tx, and position offset ty; the parameter verification of the second sensor parameters, and when the parameter verification meets a preset threshold condition, completing a comprehensive self-test for the lidar, includes:

[0029] The yaw angle, the position offset tx, and the position offset ty are compared with the corresponding reference parameter values ​​in the database.

[0030] When the deviations of the yaw angle, the position offset tx, and the position offset ty from the corresponding reference parameter values ​​in the database are all less than their respective preset deviation thresholds, a comprehensive self-test for the lidar is completed.

[0031] The present invention also provides a self-testing device for lidar in autonomous vehicles, comprising:

[0032] The hardware self-test unit is used to perform a hardware self-test on the LiDAR of the autonomous vehicle. When the hardware self-test passes, the autonomous vehicle is started.

[0033] The pos change judgment unit is used to judge the pos change of the autonomous vehicle in motion. When it is determined that the autonomous vehicle is driving in a straight line, the first sensor parameters are obtained by plane fitting.

[0034] The position fluctuation judgment unit is used to determine whether the lidar has experienced position fluctuation based on the parameters of the first sensor. If not, the vehicle detected by the front end is tracked.

[0035] The second sensor parameter calculation unit is used to acquire the laser point cloud data of the tracked vehicle when the preset tracking judgment conditions are met, and to calculate the second sensor parameters based on the laser point cloud data.

[0036] The parameter verification unit is used to verify the parameters of the second sensor. When the parameter verification meets the preset threshold conditions, the unit completes the comprehensive self-test for the lidar.

[0037] The present invention also provides an electronic device, the device comprising a processor and a memory:

[0038] The memory is used to store program code and transmit the program code to the processor;

[0039] The processor is used to execute the lidar self-test method for autonomous vehicles as described in any of the preceding claims, according to the instructions in the program code.

[0040] The present invention also provides a computer-readable storage medium for storing program code for executing the lidar self-test method for an autonomous vehicle as described in any of the preceding claims.

[0041] As can be seen from the above technical solutions, the present invention has the following advantages:

[0042] A self-testing method for LiDAR in autonomous vehicles is proposed. First, a hardware self-test is performed on the LiDAR of the autonomous vehicle. If the hardware self-test passes, the autonomous vehicle is started. This hardware self-test allows for the determination of whether sensor anomalies are caused by hardware problems, achieving a preliminary self-test for the LiDAR. Next, position change judgment is performed on the moving autonomous vehicle. When the autonomous vehicle is determined to be traveling in a straight line, the first sensor parameters are obtained through plane fitting. Based on the first sensor parameters, it is determined whether the LiDAR exhibits position fluctuations. If not, the vehicle detected by the front end is tracked. Combining the position change judgment and the first sensor parameters obtained through plane fitting, this method is used to determine whether the LiDAR is currently experiencing position fluctuations, eliminating anomalies caused by position fluctuations and completing a second self-test for the LiDAR. When the preset tracking judgment conditions are met, the laser point cloud data of the tracked vehicle is acquired, and the parameters of the second sensor are calculated based on the laser point cloud data. The parameters of the second sensor are verified, and when the parameter verification meets the preset threshold conditions, a comprehensive self-check for the lidar is completed. Thus, by combining the calculation of the second sensor parameters with the front-end vehicle tracking detection, and verifying the parameters based on the second sensor parameters, it is further determined whether there are deviations in the lidar parameters outside the allowable error range, thereby realizing a comprehensive self-check for the lidar, ensuring the safe operation of the lidar, and improving the system's response speed and accuracy to abnormal states. Attached Figure Description

[0043] 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, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 A flowchart illustrating the steps of a self-testing method for a lidar system in an autonomous vehicle.

[0045] Figure 2 This is a schematic diagram of the overall process of a self-testing method for LiDAR in an autonomous vehicle.

[0046] Figure 3 This is a structural block diagram of a LiDAR self-testing device for an autonomous vehicle. Detailed Implementation

[0047] This invention provides a LiDAR self-testing method for autonomous vehicles, a LiDAR self-testing device for autonomous vehicles, an electronic device, and a storage medium, which are used to solve or partially solve the technical problem of how to design and optimize the self-testing algorithm for vehicle status, and improve the system's response speed and accuracy to abnormal states.

[0048] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0049] To enable those skilled in the art to better understand the technical solutions provided in the embodiments of the present invention, some of the technical features involved in the solutions are briefly described first:

[0050] Position calculation refers to the processing and calculation of position information. In this invention, the pose and trajectory of the autonomous vehicle are calculated based on sensor data collected by LiDAR.

[0051] Pitch angle: describes the tilt angle of a vehicle or sensor in a vertical plane.

[0052] roll angle: describes the tilt angle of a vehicle or sensor on a horizontal plane.

[0053] tz: Describes the positional offset of the vehicle or sensor on the Z-axis (vertical direction).

[0054] These parameters are primarily used in autonomous driving systems for sensor localization, vehicle attitude estimation, and calculation of the three-dimensional position of target objects. By accurately measuring and calculating these parameters, the system can better understand the surrounding environment and the vehicle's own state, thereby making more precise driving decisions.

[0055] yaw angle: The rotation angle around the Z-axis, indicating the direction of vehicle steering.

[0056] tx: Position offset in the X-axis direction, indicating the change in the vehicle's position in the east-west or left-right direction.

[0057] ty: Position offset in the Y-axis direction, indicating the change in the vehicle's position in the north-south or front-back direction.

[0058] These parameters are used in autonomous driving systems to describe the vehicle's attitude and position, enabling the system to achieve functions such as accurate positioning, path planning, and obstacle avoidance.

[0059] As an example, in the operation of autonomous vehicles, automatic vehicle status detection is a crucial aspect of ensuring safety. Vehicles need to monitor the status of their sensors, the health of their control systems, and the operation of their actuators in real time so that timely measures can be taken in case of anomalies.

[0060] However, existing autonomous driving systems still face certain technical challenges in vehicle status self-checking. Some systems rely on redundancy design and fault-tolerance mechanisms. But these mechanisms can still miss or misjudge situations in actual operation. Once an abnormal state of the vehicle is not detected in time during operation, it could very likely lead to a serious accident.

[0061] Therefore, how to design and optimize the self-checking algorithm for vehicle status, and how to improve the system's response speed and accuracy to abnormal states, are urgent problems to be solved in the current development of L4 autonomous vehicle technology.

[0062] Further analysis revealed two main reasons for the malfunction of the lidar sensor. First, the sensor itself may have a quality issue. Second, the installation location may have shifted due to various factors.

[0063] Therefore, one of the core inventive points of this invention is to propose a self-testing method for LiDAR in autonomous vehicles, addressing the aforementioned shortcomings. First, a hardware self-test determines whether sensor anomalies are caused by hardware problems, achieving a preliminary self-test for the LiDAR. Next, by combining position change judgment and plane fitting to obtain first sensor parameters, the method determines whether the LiDAR is experiencing position fluctuations, eliminating anomalies caused by position fluctuations and completing a second self-test for the LiDAR. Further, by combining front-end vehicle tracking and detection to calculate second sensor parameters, and based on these second sensor parameters, parameter verification is performed to further determine whether the LiDAR parameters have deviations outside the allowable error range, achieving a comprehensive self-test for the LiDAR, ensuring safe operation of the LiDAR, and improving the system's response speed and accuracy to abnormal states.

[0064] Reference Figure 1The diagram illustrates a flowchart of a self-testing method for a lidar system in an autonomous vehicle according to an embodiment of the present invention, which may specifically include the following steps:

[0065] Step 101: Perform a hardware self-test on the LiDAR of the autonomous vehicle. When the hardware self-test passes, start the autonomous vehicle.

[0066] First, a hardware self-test must be performed on the LiDAR. Only after the hardware self-test passes should the next step of the self-test be performed to avoid sensor malfunctions caused by hardware issues. The self-test principle of the LiDAR is as follows: first, acquire an open area provided by other modes; then, detect the point cloud state. If the flatness α meets a preset threshold, it can be considered that the LiDAR has no hardware problems.

[0067] "Open areas defined by other modalities" refers to areas around the vehicle or in the environment where there are no obstacles, vehicles, pedestrians, or other objects, as detected by different types of sensors (i.e., other modalities). Here, "modality" refers to the type of sensor or data format, such as cameras, LiDAR, radar, and ultrasonic sensors.

[0068] In a specific implementation, the hardware self-test of the LiDAR in an autonomous vehicle can be performed as follows: acquiring open areas detected by different types of sensors in the autonomous vehicle; performing point cloud state detection on the open areas using the LiDAR to obtain flatness; and determining that the LiDAR has passed the hardware self-test when the flatness meets a preset flatness threshold.

[0069] Step 102: Detect the pos change of the autonomous vehicle in motion. When it is determined that the autonomous vehicle is traveling in a straight line, obtain the first sensor parameters through plane fitting.

[0070] After the vehicle starts, the point cloud data of frames 1, n+1, 2n+1, ..., 3n+1, ... are first archived. If the calculated position (pos) indicates that the vehicle's travel path is a straight line, then the vehicle is considered to be traveling in a straight line on a flat road surface. Next, a plane fitting calculation is performed. Through the LiDAR pos calculation, the first sensor parameters, including pitch angle, roll angle, and position offset (tz), can be obtained.

[0071] In the specific implementation, the position change of the autonomous vehicle in motion is judged. When it is determined that the autonomous vehicle is traveling in a straight line, the first sensor parameters are obtained through plane fitting. This can be done by: collecting laser point cloud data of the autonomous vehicle in motion using LiDAR, and extracting frames from the collected laser point cloud data to obtain extracted point cloud data; calculating the position based on the extracted point cloud data, and judging the driving route based on the position calculation result; when the driving route judgment result indicates that the autonomous vehicle is traveling in a straight line, the first sensor parameters are obtained through plane fitting calculation.

[0072] Step 103: Determine whether the position of the lidar fluctuates based on the parameters of the first sensor. If not, track the vehicle detected by the front end.

[0073] After the first sensor parameters are calculated, these parameters are compared with reference parameter values ​​(or default values) in the database. If the deviation between each sensor parameter and its corresponding reference parameter value is less than a preset deviation threshold, it is considered that the radar has not experienced positional fluctuations. At this point, the vehicle detected by the autonomous vehicle's foreground can be tracked.

[0074] Based on the preceding discussion, the first sensor parameters include the pitch angle, roll angle, and position offset (tz). Therefore, in the specific implementation, determining whether the LiDAR exhibits positional fluctuations based on these first sensor parameters can be achieved by comparing the pitch angle, roll angle, and position offset (tz) with their respective reference parameter values ​​in the database. If the deviations between these values ​​and their respective reference parameter values ​​are all less than their preset deviation thresholds, it is determined that the LiDAR has not exhibited positional fluctuations.

[0075] Step 104: When the preset tracking judgment conditions are met, acquire the laser point cloud data of the tracking vehicle, and calculate the second sensor parameters based on the laser point cloud data;

[0076] When tracking vehicles detected by the front end, assuming that K vehicles appear stably in consecutive γ frames, the laser point cloud data of these vehicles are loaded, and registration calculations are performed based on these data to obtain the second sensor parameters, namely yaw angle, position offset tx and position offset ty, for database comparison to achieve parameter verification.

[0077] In a specific implementation, when the preset tracking judgment conditions are met, the laser point cloud data of the tracked vehicle is obtained. This can be achieved by: when the lidar detects that a preset number of vehicles appear stably in a continuous preset frame in front of the autonomous vehicle, the laser point cloud data of the continuously appearing vehicles is obtained.

[0078] Furthermore, the second sensor parameters are calculated based on the laser point cloud data. Specifically, this can be done by performing registration calculations based on the laser point cloud data to obtain the second sensor parameters.

[0079] Step 105: Perform parameter verification on the second sensor parameters. When the parameter verification meets the preset threshold conditions, complete the comprehensive self-test for the lidar.

[0080] After the second sensor parameters are calculated, these parameters are compared with the reference parameter values ​​(or default values) in the database to complete the parameter verification of the yaw angle, tx, and ty directions. When the deviation between each sensor parameter and the corresponding reference parameter value is less than the preset deviation threshold, the comprehensive self-test of the lidar is completed.

[0081] Based on the preceding discussion, the second sensor parameters include the yaw angle, position offset tx, and position offset ty. In the specific implementation, parameter verification of the second sensor parameters is performed. When the parameter verification meets the preset threshold conditions, a comprehensive self-test for the LiDAR is completed. This can be achieved by comparing the yaw angle, position offset tx, and position offset ty with the corresponding reference parameter values ​​in the database. When the deviations between the yaw angle, position offset tx, and position offset ty and the corresponding reference parameter values ​​in the database are all less than their respective preset deviation thresholds, a comprehensive self-test for the LiDAR is completed.

[0082] Furthermore, after comprehensive evaluation, if the calculated parameter values ​​(pitch angle, roll angle, position offset tz, yaw angle, position offset tx, and position offset ty) meet the parameter update thresholds, then these calculated parameter values ​​replace the corresponding reference values ​​in the database to achieve automatic updating of vehicle parameters. If the thresholds are not met, it indicates a significant deviation in the currently calculated parameter values, suggesting a possible sensor malfunction. In this case, an alarm or notification can be issued to allow maintenance personnel to promptly address the anomaly and terminate the self-test process.

[0083] This invention proposes a self-testing method for a LiDAR in an autonomous vehicle. First, a hardware self-test is performed on the LiDAR of the autonomous vehicle. If the hardware self-test passes, the autonomous vehicle is started. This hardware self-test allows determination of whether sensor anomalies are caused by hardware problems, achieving a preliminary self-test for the LiDAR. Next, position change judgment is performed on the moving autonomous vehicle. When the autonomous vehicle is determined to be traveling in a straight line, first sensor parameters are obtained through plane fitting. Based on these first sensor parameters, it is determined whether the LiDAR exhibits position fluctuations. If not, the vehicle detected at the front end is tracked. Thus, combining the position change judgment and the first sensor parameters obtained through plane fitting, it is used to determine whether the LiDAR is currently experiencing position fluctuations, eliminating anomalies caused by position fluctuations, and completing a second self-test for the LiDAR. When the preset tracking judgment conditions are met, the laser point cloud data of the tracked vehicle is acquired, and the parameters of the second sensor are calculated based on the laser point cloud data. The parameters of the second sensor are verified, and when the parameter verification meets the preset threshold conditions, a comprehensive self-check for the lidar is completed. Thus, by combining the calculation of the second sensor parameters with the front-end vehicle tracking detection, and verifying the parameters based on the second sensor parameters, it is further determined whether there are deviations in the lidar parameters outside the allowable error range, thereby realizing a comprehensive self-check for the lidar, ensuring the safe operation of the lidar, and improving the system's response speed and accuracy to abnormal states.

[0084] For better explanation, refer to Figure 2 This diagram illustrates the overall flow of a LiDAR self-test method for an autonomous vehicle according to an embodiment of the present invention. It should be noted that this embodiment only provides a brief description of the general flow of the LiDAR self-test for an autonomous vehicle. The specific implementation process of each step can be understood by referring to the relevant content in the foregoing embodiments, and will not be elaborated upon here. It is understood that the present invention does not impose any limitations on this.

[0085] Step 201: Perform a hardware self-test on the LiDAR of the autonomous vehicle and determine whether the hardware self-test passes; if not, end the process; if yes, start the autonomous vehicle.

[0086] Step 202: Detect the position change of the autonomous vehicle in motion and determine whether the autonomous vehicle is traveling in a straight line; if not, end the process; if so, obtain the pitch angle, roll angle and position offset tz through plane fitting.

[0087] Step 203: Determine whether the LiDAR is experiencing positional fluctuations based on the pitch angle, roll angle, and position offset (tz). If yes, end the process; otherwise, track the vehicle detected by the front end.

[0088] Step 204: Determine whether the vehicle tracking meets the preset tracking judgment conditions; if not, end the process; if yes, obtain the laser point cloud data of the tracked vehicle, and calculate the yaw angle, position offset tx and position offset ty based on the laser point cloud data;

[0089] Step 205: Perform parameter verification on the yaw angle, position offset tx, and position offset ty, and determine whether the parameter verification meets the preset threshold conditions; if not, end the process; if yes, complete the comprehensive self-test for the LiDAR.

[0090] Step 206: Determine whether the calculated pitch angle, roll angle, position offset tz, yaw angle, position offset tx, and position offset ty meet the update parameter thresholds; if not, issue an alarm and end the process; if yes, automatically update the vehicle parameters.

[0091] Reference Figure 3 The diagram illustrates a structural block diagram of a lidar self-testing device for an autonomous vehicle according to an embodiment of the present invention, which may specifically include:

[0092] The hardware self-test unit 301 is used to perform a hardware self-test on the LiDAR of the autonomous vehicle. When the hardware self-test passes, the autonomous vehicle is started.

[0093] The pos change judgment unit 302 is used to judge the pos change of the autonomous vehicle in motion. When it is determined that the autonomous vehicle is driving in a straight line, the first sensor parameters are obtained by plane fitting.

[0094] The position fluctuation judgment unit 303 is used to determine whether the lidar has a position fluctuation based on the first sensor parameters. If not, it tracks the vehicle detected by the front end.

[0095] The second sensor parameter calculation unit 304 is used to acquire the laser point cloud data of the tracked vehicle when the preset tracking judgment conditions are met, and to calculate the second sensor parameters based on the laser point cloud data.

[0096] The parameter verification unit 305 is used to verify the parameters of the second sensor. When the parameter verification meets the preset threshold conditions, a comprehensive self-test for the lidar is completed.

[0097] In one optional embodiment, the hardware self-test unit 301 includes:

[0098] The open area acquisition unit is used to acquire open areas detected by different types of sensors in autonomous vehicles.

[0099] A point cloud state detection unit is used to detect the point cloud state of the open area using a lidar to obtain the flatness.

[0100] The hardware self-test judgment unit is used to determine that the lidar passes the hardware self-test when the flatness meets the preset flatness threshold.

[0101] In one optional embodiment, the pos change determination unit 302 includes:

[0102] The frame-sampling point cloud data acquisition unit is used to acquire laser point clouds from the autonomous vehicle in motion using the lidar, and to extract frames from the acquired laser point clouds to obtain frame-sampling point cloud data.

[0103] The pos calculation unit is used to perform pos calculation based on the extracted point cloud data and to determine the driving route based on the pos calculation result.

[0104] The first sensor parameter calculation unit is used to obtain the first sensor parameters by plane fitting when the driving route judgment result indicates that the autonomous vehicle is driving in a straight line.

[0105] In one optional embodiment, the first sensor parameters include pitch angle, roll angle, and position offset tz; the position fluctuation judgment unit 303 is specifically used for:

[0106] The pitch angle, roll angle, and position offset tz are compared with the corresponding reference parameter values ​​in the database.

[0107] When the deviations of the pitch angle, the roll angle, and the position offset tz from the corresponding reference parameter values ​​in the database are all less than their respective preset deviation thresholds, it is determined that the lidar has not experienced position fluctuations.

[0108] In one optional embodiment, the second sensor parameter calculation unit 304 includes:

[0109] The laser point cloud data acquisition unit is used to acquire the laser point cloud data of the continuously appearing vehicles when the lidar detects that a continuous preset number of vehicles have appeared stably in the front-end preset frames of the autonomous driving vehicle.

[0110] In one optional embodiment, the second sensor parameter calculation unit 304 is specifically used for:

[0111] Registration calculations are performed based on the laser point cloud data to obtain the parameters of the second sensor.

[0112] In one optional embodiment, the second sensor parameters include the yaw angle, position offset tx, and position offset ty; the parameter verification unit 305 is specifically used for:

[0113] The yaw angle, the position offset tx, and the position offset ty are compared with the corresponding reference parameter values ​​in the database.

[0114] When the deviations of the yaw angle, the position offset tx, and the position offset ty from the corresponding reference parameter values ​​in the database are all less than their respective preset deviation thresholds, a comprehensive self-test for the lidar is completed.

[0115] As the device embodiment is basically similar to the method embodiment, it is described in a relatively simple way. For relevant details, please refer to the description of the method embodiment above.

[0116] It should be noted that, in order to enable those skilled in the art to better distinguish data of the same type but with different actual meanings, the embodiments of the present invention use "first" and "second" to distinguish and describe some technical features. "First" and "second" are only used to distinguish data and have no other special meaning. It is understood that the present invention does not impose any limitations on them.

[0117] This invention also provides an electronic device, which includes a processor and a memory:

[0118] The memory is used to store program code and transfer the program code to the processor;

[0119] The processor is used to execute the lidar self-test method for autonomous vehicles according to the instructions in the program code of any embodiment of the present invention.

[0120] This invention also provides a computer-readable storage medium for storing program code for executing the LiDAR self-test method for an autonomous vehicle according to any embodiment of this invention.

[0121] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0122] In the embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or units through some interfaces, and may be electrical, mechanical, or other forms.

[0123] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0124] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0125] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0126] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A self-testing method for lidar in an autonomous vehicle, characterized in that, include: Perform a hardware self-test on the LiDAR of the autonomous vehicle, and start the autonomous vehicle when the hardware self-test passes; The pos change of the autonomous vehicle in motion is judged. When it is determined that the autonomous vehicle is traveling in a straight line, the first sensor parameters are obtained by plane fitting. Based on the parameters of the first sensor, determine whether the lidar has experienced position fluctuations. If not, then track the vehicle detected by the front end. When the preset tracking judgment conditions are met, the laser point cloud data of the tracked vehicle is acquired, and the parameters of the second sensor are calculated based on the laser point cloud data. The parameters of the second sensor are verified. When the parameter verification meets the preset threshold conditions, a comprehensive self-test for the lidar is completed.

2. The self-testing method for lidar in autonomous vehicles according to claim 1, characterized in that, The hardware self-test for the LiDAR of the autonomous vehicle includes: Acquire open areas detected by different types of sensors in autonomous vehicles; The flatness is obtained by detecting the point cloud state of the open area using lidar. When the flatness meets the preset flatness threshold, it is determined that the lidar has passed the hardware self-test.

3. The self-testing method for lidar in autonomous vehicles according to claim 1, characterized in that, The step of judging the position change of the autonomous vehicle in motion, and when it is determined that the autonomous vehicle is traveling in a straight line, obtaining the first sensor parameters through plane fitting, includes: The laser radar is used to collect laser point clouds of the autonomous vehicle in motion, and the collected laser point clouds are then framed to obtain framed point cloud data. The pos is calculated based on the extracted point cloud data, and the driving route is determined based on the pos calculation result. When the driving route determination result indicates that the autonomous vehicle is driving in a straight line, the first sensor parameters are obtained through plane fitting calculation.

4. The self-testing method for lidar in autonomous vehicles according to claim 3, characterized in that, The first sensor parameters include pitch angle, roll angle, and position offset (tz); determining whether the lidar experiences position fluctuations based on the first sensor parameters includes: The pitch angle, roll angle, and position offset tz are compared with the corresponding reference parameter values ​​in the database. When the deviations of the pitch angle, the roll angle, and the position offset tz from the corresponding reference parameter values ​​in the database are all less than their respective preset deviation thresholds, it is determined that the lidar has not experienced position fluctuations.

5. The self-testing method for lidar in autonomous vehicles according to claim 1, characterized in that, When the preset tracking judgment conditions are met, the acquisition of laser point cloud data of the tracking vehicle includes: When the lidar detects that a set number of vehicles appear stably in a continuous preset frame in front of the autonomous vehicle, it acquires the lidar point cloud data of the continuously appearing vehicles.

6. The self-testing method for lidar in autonomous vehicles according to claim 1, characterized in that, The calculation of the second sensor parameters based on the laser point cloud data includes: Registration calculations are performed based on the laser point cloud data to obtain the parameters of the second sensor.

7. The self-testing method for lidar of an autonomous vehicle according to any one of claims 1 to 6, characterized in that, The second sensor parameters include the yaw angle, position offset tx, and position offset ty; the parameter verification of the second sensor parameters, when the parameter verification meets the preset threshold conditions, completes the comprehensive self-test for the lidar, including: The yaw angle, the position offset tx, and the position offset ty are compared with the corresponding reference parameter values ​​in the database. When the deviations of the yaw angle, the position offset tx, and the position offset ty from the corresponding reference parameter values ​​in the database are all less than their respective preset deviation thresholds, a comprehensive self-test for the lidar is completed.

8. A self-testing device for lidar in an autonomous vehicle, characterized in that, include: The hardware self-test unit is used to perform a hardware self-test on the LiDAR of the autonomous vehicle. When the hardware self-test passes, the autonomous vehicle is started. The pos change judgment unit is used to judge the pos change of the autonomous vehicle in motion. When it is determined that the autonomous vehicle is driving in a straight line, the first sensor parameters are obtained by plane fitting. The position fluctuation judgment unit is used to determine whether the lidar has experienced position fluctuation based on the parameters of the first sensor. If not, the vehicle detected by the front end is tracked. The second sensor parameter calculation unit is used to acquire the laser point cloud data of the tracked vehicle when the preset tracking judgment conditions are met, and to calculate the second sensor parameters based on the laser point cloud data. The parameter verification unit is used to verify the parameters of the second sensor. When the parameter verification meets the preset threshold conditions, the unit completes the comprehensive self-test for the lidar.

9. An electronic device, characterized in that, The device includes a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is configured to execute the lidar self-test method for autonomous vehicles according to any one of claims 1-7, based on the instructions in the program code.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store program code for executing the lidar self-testing method for an autonomous vehicle according to any one of claims 1-7.

Images