Laser radar calibration method, device and system, electronic equipment and storage medium

Abstract

The invention relates to a laser radar calibration method, device and system, electronic equipment and a storage medium, and is applied to the technical field of laser radars, and the method comprises the steps: obtaining a first GPS coordinate and point cloud data periodically collected by an RTK module in a first vehicle and a to-be-calibrated laser radar in the driving process of the first vehicle; acquiring a second GPS coordinate periodically acquired by an RTK module in the second vehicle in the driving process of the second vehicle; performing target detection on the point cloud data to obtain relative position data of the second vehicle under the laser radar coordinate system; determining absolute position data of the second vehicle according to the initial calibration parameter, the first GPS coordinate and the relative position data of the second vehicle under the laser radar coordinate system; and matching the second GPS coordinate with the absolute position data of the second vehicle by using an iterative nearest point algorithm to optimize the initial calibration parameter and obtain a target calibration parameter. The efficiency and accuracy of laser radar calibration can be improved.

Description

Technical Field

[0001] The present application relates to the field of laser radar technology, and in particular to a laser radar calibration method, device, system, electronic device and storage medium. Background Art

[0002] At present, sensor technology is developing rapidly, and various types of sensors are widely used in fields such as robots and autonomous driving. By integrating multiple positioning sensors, more stable and reliable positioning information can be obtained, improving the robustness of the system. In the high-precision positioning and environmental perception of robots, LiDAR is a commonly used technology. LiDAR emits a laser beam and receives the signal reflected from the target. After comparing and processing it, it can obtain key parameters such as the target's position information, height, and speed.

[0003] In the related art, the laser radar can be calibrated based on a step-by-step iterative algorithm that matches the feature point cloud ICP (Iterative Closest Point). However, the calibration process usually requires multiple steps (data collection, conversion, calculation, verification), has a low degree of automation, requires manual measurement and adjustment, is inefficient and prone to errors. When extracting feature points, the corresponding RTK (Real-time kinematic) data may not be accurate, resulting in low calibration accuracy. Summary of the invention

[0004] In order to solve the above technical problems, the present application provides a laser radar calibration method, device, system, electronic device and storage medium.

[0005] According to a first aspect of the present application, a laser radar calibration method is provided, comprising:

[0006] Acquire first GPS (Global Positioning System) coordinates and point cloud data periodically collected by the RTK module in the first vehicle and the laser radar to be calibrated during the driving of the first vehicle; the relative positions of the RTK module and the laser radar to be calibrated are fixed;

[0007] Acquire the second GPS coordinates periodically collected by the RTK module in the second vehicle during the driving of the second vehicle; the second vehicle is within the detection range of the laser radar to be calibrated, is time synchronized with the first vehicle, and the relative position of the second vehicle to the first vehicle changes;

[0008] Performing target detection on the point cloud data to obtain relative position data of the second vehicle in a laser radar coordinate system;

[0009] Determining the absolute position data of the second vehicle according to the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle in the laser radar coordinate system;

[0010] The second GPS coordinates and the absolute position data of the second vehicle are matched using an iterative closest point algorithm to optimize the initial calibration parameters and obtain target calibration parameters.

[0011] Optionally, performing target detection on the point cloud data to obtain relative position data of the second vehicle in a laser radar coordinate system includes:

[0012] Using multiple target detection algorithms, respectively perform target detection on the point cloud data to obtain relative position data of the second vehicle corresponding to each target detection algorithm in a laser radar coordinate system;

[0013] The determining the absolute position data of the second vehicle according to the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle in the laser radar coordinate system includes:

[0014] Determine the absolute position data of the second vehicle corresponding to each target detection algorithm according to the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle corresponding to each target detection algorithm in the laser radar coordinate system;

[0015] The using of an iterative closest point algorithm to match the second GPS coordinates with the absolute position data of the second vehicle to optimize the initial calibration parameters and obtain target calibration parameters includes:

[0016] The second GPS coordinates are matched with the absolute position data of the second vehicle corresponding to each target detection algorithm by using an iterative closest point algorithm to optimize the initial calibration parameters and obtain target calibration parameters corresponding to each target detection algorithm.

[0017] Optionally, performing target detection on the point cloud data to obtain relative position data of the second vehicle in a laser radar coordinate system includes:

[0018] Dividing the point cloud data into different areas according to the relative positions of the second vehicle and the first vehicle during the driving of the first vehicle and the second vehicle;

[0019] Performing target detection on the point cloud data of each area to obtain relative position data of the second vehicle in each area in a laser radar coordinate system;

[0020] The determining the absolute position data of the second vehicle according to the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle in the laser radar coordinate system includes:

[0021] Determine the absolute position data of the second vehicle in each area according to the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle in each area in the laser radar coordinate system;

[0022] The using of an iterative closest point algorithm to match the second GPS coordinates with the absolute position data of the second vehicle to optimize the initial calibration parameters and obtain target calibration parameters includes:

[0023] The second GPS coordinates are matched with the absolute position data of the second vehicle in each area by using an iterative closest point algorithm to optimize the initial calibration parameters and obtain target calibration parameters in each area.

[0024] Optionally, determining the absolute position data of the second vehicle according to the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle in the laser radar coordinate system includes:

[0025] Performing coordinate conversion on the first GPS coordinates and the relative position data of the second vehicle in the laser radar coordinate system to obtain first position coordinates and relative position data in the target coordinate system respectively;

[0026] Determining absolute position data of the second vehicle in the target coordinate system according to the initial calibration parameters, the first position coordinates in the target coordinate system, and the relative position data in the target coordinate system;

[0027] The matching of the second GPS coordinates and the absolute position data of the second vehicle by using an iterative closest point algorithm includes:

[0028] Performing coordinate conversion on the second GPS coordinates to obtain second position coordinates in the target coordinate system;

[0029] The second position coordinates in the target coordinate system and the absolute position data of the second vehicle in the target coordinate system are matched using an iterative closest point algorithm.

[0030] Optionally, dividing the point cloud data into different areas according to the relative position of the second vehicle and the first vehicle during the driving of the first vehicle and the second vehicle includes:

[0031] During the driving of the first vehicle and the second vehicle, the relative positions of the second vehicle and the first vehicle are divided into the following three types: the second vehicle is located in front of the first vehicle, the second vehicle is parallel to the first vehicle, and the second vehicle is located behind the first vehicle;

[0032] Divide the point cloud data into a front area, a parallel area and a rear area according to three division methods of relative positions; or,

[0033] During the driving of the first vehicle and the second vehicle, the relative positions of the second vehicle and the first vehicle are divided into the following four types: the second vehicle is located in front of the first vehicle, the second vehicle is located behind the first vehicle, the second vehicle is located on the left side of the first vehicle, and the second vehicle is located on the right side of the first vehicle;

[0034] According to four division methods of relative positions, the point cloud data is divided into a front area, a rear area, a left area and a right area.

[0035] Optionally, before determining the absolute position data of the second vehicle according to the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle in the laser radar coordinate system, the method further includes:

[0036] The initial calibration parameters are determined according to the relative positions of the RTK module in the first vehicle and the laser radar to be calibrated. The initial calibration parameters include: an initial rotation matrix and an initial translation vector.

[0037] According to a second aspect of the present application, a laser radar calibration device is provided, comprising:

[0038] A first acquisition module is used to acquire first GPS coordinates and point cloud data periodically collected by the RTK module in the first vehicle and the laser radar to be calibrated during the driving process of the first vehicle; the relative positions of the RTK module and the laser radar to be calibrated are fixed;

[0039] A second acquisition module is used to acquire second GPS coordinates periodically collected by the RTK module in the second vehicle during the driving process of the second vehicle; the second vehicle is within the detection range of the laser radar to be calibrated, is time synchronized with the first vehicle, and the relative position with the first vehicle changes;

[0040] A target detection module, used to perform target detection on the point cloud data to obtain relative position data of the second vehicle in a laser radar coordinate system;

[0041] a position determination module, configured to determine the absolute position data of the second vehicle according to the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle in the laser radar coordinate system;

[0042] The target calibration parameter determination module is used to match the second GPS coordinates and the absolute position data of the second vehicle using an iterative closest point algorithm to optimize the initial calibration parameters and obtain target calibration parameters.

[0043] Optionally, the target detection module is specifically used to use multiple target detection algorithms to perform target detection on the point cloud data respectively, and obtain relative position data of the second vehicle corresponding to each target detection algorithm in the laser radar coordinate system;

[0044] The position determination module is specifically used to determine the absolute position data of the second vehicle corresponding to each target detection algorithm according to the initial calibration parameters, the first GPS coordinates and the relative position data corresponding to each target detection algorithm of the second vehicle in the laser radar coordinate system;

[0045] The target calibration parameter determination module is specifically used to use an iterative closest point algorithm to match the second GPS coordinates and the absolute position data of the second vehicle corresponding to each target detection algorithm to optimize the initial calibration parameters and obtain the target calibration parameters corresponding to each target detection algorithm.

[0046] Optionally, the target detection module is specifically used to divide the point cloud data into different areas according to the relative position of the second vehicle and the first vehicle during the driving of the first vehicle and the second vehicle; perform target detection on the point cloud data of each area to obtain the relative position data of the second vehicle in each area in the laser radar coordinate system;

[0047] The position determination module is specifically used to determine the absolute position data of the second vehicle in each area according to the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle in each area in the laser radar coordinate system;

[0048] The target calibration parameter determination module is specifically used to use an iterative closest point algorithm to match the second GPS coordinates and the absolute position data of the second vehicle in each area to optimize the initial calibration parameters and obtain the target calibration parameters in each area.

[0049] Optionally, the position determination module is specifically used to perform coordinate conversion on the first GPS coordinates and the relative position data of the second vehicle in the laser radar coordinate system to obtain the first position coordinates and the relative position data in the target coordinate system respectively; determine the absolute position data of the second vehicle in the target coordinate system according to the initial calibration parameters, the first position coordinates in the target coordinate system and the relative position data in the target coordinate system;

[0050] The target calibration parameter determination module is specifically used to perform coordinate conversion on the second GPS coordinates to obtain the second position coordinates in the target coordinate system; and use an iterative closest point algorithm to match the second position coordinates in the target coordinate system with the absolute position data of the second vehicle in the target coordinate system.

[0051] Optionally, the target detection module is specifically configured to divide the point cloud data into different areas according to the relative position of the second vehicle and the first vehicle during the driving of the first vehicle and the second vehicle through the following steps:

[0052] During the driving of the first vehicle and the second vehicle, the relative positions of the second vehicle and the first vehicle are divided into the following three types: the second vehicle is located in front of the first vehicle, the second vehicle is parallel to the first vehicle, and the second vehicle is located behind the first vehicle;

[0053] Divide the point cloud data into a front area, a parallel area and a rear area according to three division methods of relative positions; or,

[0054] During the driving of the first vehicle and the second vehicle, the relative positions of the second vehicle and the first vehicle are divided into the following four types: the second vehicle is located in front of the first vehicle, the second vehicle is located behind the first vehicle, the second vehicle is located on the left side of the first vehicle, and the second vehicle is located on the right side of the first vehicle;

[0055] According to four division methods of relative positions, the point cloud data is divided into a front area, a rear area, a left area and a right area.

[0056] Optionally, the laser radar calibration device further includes:

[0057] The initial calibration parameter determination module is used to determine the initial calibration parameters according to the relative position of the RTK module in the first vehicle and the laser radar to be calibrated. The initial calibration parameters include: an initial rotation matrix and an initial translation vector.

[0058] According to a third aspect of the present application, a laser radar calibration system is provided, comprising: a first vehicle and a second vehicle, wherein the first vehicle is equipped with an RTK module and a laser radar to be calibrated, and the relative positions of the RTK module and the laser radar to be calibrated are fixed; and the second vehicle is equipped with an RTK module;

[0059] The first vehicle is used to periodically collect first GPS coordinates through the RTK module during the driving of the first vehicle, and to periodically collect point cloud data around the first vehicle through the laser radar to be calibrated during the driving of the first vehicle;

[0060] The second vehicle is used to periodically collect second GPS coordinates through the RTK module during the driving process of the second vehicle, and the second vehicle is in the detection range of the laser radar to be calibrated, is synchronized with the first vehicle in time, and the relative position of the second vehicle to the first vehicle changes;

[0061] The first vehicle is also used to perform target detection on the point cloud data to obtain the relative position data of the second vehicle in the laser radar coordinate system; determine the absolute position data of the second vehicle according to the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle in the laser radar coordinate system; use an iterative closest point algorithm to match the second GPS coordinates and the absolute position data of the second vehicle to optimize the initial calibration parameters and obtain target calibration parameters.

[0062] Optionally, the first vehicle is specifically used to perform target detection on the point cloud data using multiple target detection algorithms, and obtain relative position data of the second vehicle corresponding to each target detection algorithm in a lidar coordinate system; determine the absolute position data of the second vehicle corresponding to each target detection algorithm based on initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle corresponding to each target detection algorithm in a lidar coordinate system; and use an iterative closest point algorithm to match the second GPS coordinates and the absolute position data of the second vehicle corresponding to each target detection algorithm to optimize the initial calibration parameters and obtain target calibration parameters corresponding to each target detection algorithm.

[0063] Optionally, the first vehicle is specifically used to divide the point cloud data into different areas according to the relative position of the second vehicle and the first vehicle during the driving of the first vehicle and the second vehicle; perform target detection on the point cloud data of each area to obtain the relative position data of the second vehicle in each area in the laser radar coordinate system; determine the absolute position data of the second vehicle in each area based on the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle in each area in the laser radar coordinate system; use an iterative closest point algorithm to match the second GPS coordinates and the absolute position data of the second vehicle in each area to optimize the initial calibration parameters and obtain the target calibration parameters in each area.

[0064] Optionally, the first vehicle is specifically used to perform coordinate conversion on the first GPS coordinates and the relative position data of the second vehicle in the lidar coordinate system to obtain the first position coordinates and relative position data in the target coordinate system, respectively; determine the absolute position data of the second vehicle in the target coordinate system according to the initial calibration parameters, the first position coordinates in the target coordinate system and the relative position data in the target coordinate system; perform coordinate conversion on the second GPS coordinates to obtain the second position coordinates in the target coordinate system; and use an iterative closest point algorithm to match the second position coordinates in the target coordinate system with the absolute position data of the second vehicle in the target coordinate system.

[0065] Optionally, the first vehicle is specifically used to divide the point cloud data into different areas according to the relative position of the second vehicle and the first vehicle during the driving of the first vehicle and the second vehicle through the following steps:

[0066] During the driving of the first vehicle and the second vehicle, the relative positions of the second vehicle and the first vehicle are divided into the following three types: the second vehicle is located in front of the first vehicle, the second vehicle is parallel to the first vehicle, and the second vehicle is located behind the first vehicle;

[0067] Divide the point cloud data into a front area, a parallel area and a rear area according to three division methods of relative positions; or,

[0068] During the driving of the first vehicle and the second vehicle, the relative positions of the second vehicle and the first vehicle are divided into the following four types: the second vehicle is located in front of the first vehicle, the second vehicle is located behind the first vehicle, the second vehicle is located on the left side of the first vehicle, and the second vehicle is located on the right side of the first vehicle;

[0069] According to four division methods of relative positions, the point cloud data is divided into a front area, a rear area, a left area and a right area.

[0070] Optionally, the first vehicle is also used to determine the initial calibration parameters according to the relative position of the RTK module in the first vehicle and the laser radar to be calibrated, and the initial calibration parameters include: an initial rotation matrix and an initial translation vector.

[0071] According to a fourth aspect of the present application, an electronic device is provided, comprising: a processor, wherein the processor is used to execute a computer program stored in a memory, wherein the computer program implements the method described in the first aspect when executed by the processor.

[0072] According to a fifth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method described in the first aspect is implemented.

[0073] According to a sixth aspect of the present application, a computer program product is provided. When the computer program product is run on a computer, the computer is enabled to execute the method described in the first aspect.

[0074] Compared with the prior art, the technical solution provided by the embodiments of the present application has the following advantages:

[0075] The first vehicle and the second vehicle are used as calibration tools, and the first vehicle is equipped with an RTK module and a laser radar to be calibrated, and the second vehicle is equipped with an RTK module. During the driving process of the first vehicle and the second vehicle, the laser radar to be calibrated is used to scan and obtain the point cloud data around the first vehicle. The second vehicle is within the detection range of the laser radar to be calibrated, synchronized with the first vehicle in time, and the relative position with the first vehicle changes. Therefore, the point cloud data is subjected to target detection, and the position data of the second vehicle can be detected. According to the position coordinates collected by the RTK module in the first vehicle and the relative position data of the second vehicle detected by the laser radar to be calibrated, the absolute position data of the second vehicle can be calculated. Using the iterative closest point algorithm, the absolute position data is matched with the position coordinates collected by the RTK module in the second vehicle, so as to realize the calibration of the laser radar to be calibrated. The embodiment of the present application uses the vehicle as a calibration tool, which is more practical. Data is collected in real time by the RTK module and the laser radar to be calibrated, and the calibration of the laser radar to be calibrated can be automatically realized through data processing, without manual measurement, and with high efficiency. Since the RTK module and the laser radar to be calibrated are in the real vehicle and fixed in position, there is no problem of recalibration due to the change of the laser radar position. And by synchronizing the time of the second vehicle with the first vehicle and changing the relative position of the second vehicle with the first vehicle, the second vehicle at different positions can be identified to improve the accuracy of calibration. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0077] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0078] Figure 1 A flow chart of a laser radar calibration method in an embodiment of the present application;

[0079] Figure 2 This is another flow chart of the laser radar calibration method in the embodiment of the present application;

[0080] Figure 3 This is another flow chart of the laser radar calibration method in the embodiment of the present application;

[0081] Figure 4A A division method of the relative positions of the second vehicle and the first vehicle in the embodiment of the present application;

[0082] Figure 4B A division method of the relative positions of the second vehicle and the first vehicle in the embodiment of the present application;

[0083] Figure 5 A schematic diagram of the structure of a laser radar calibration device in an embodiment of the present application;

[0084] Figure 6 A schematic diagram of the structure of a laser radar calibration system in an embodiment of the present application;

[0085] Figure 7 A schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0086] In order to more clearly understand the above-mentioned purposes, features and advantages of the present application, the scheme of the present application will be further described below. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0087] In the following description, many specific details are set forth to facilitate a full understanding of the present application, but the present application may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only part of the embodiments of the present application, rather than all of the embodiments.

[0088] See also Figure 1 , Figure 1 This is a flow chart of a laser radar calibration method in an embodiment of the present application, which may include the following steps:

[0089] Step S102, obtaining the first GPS coordinates and point cloud data periodically collected by the RTK module in the first vehicle and the laser radar to be calibrated during the driving process of the first vehicle.

[0090] The first vehicle (i.e., the real-value vehicle) is equipped with an RTK module and a laser radar to be calibrated. The RTK module can provide centimeter-level high-precision position information and output the position and attitude data of the RTK module in the world coordinate system in real time. It supports multi-band reception, has the ability to resist multipath interference, and ensures stability. The laser radar to be calibrated has a high scanning frequency and a large field of view, which is suitable for data acquisition in complex scenes. The high-precision industrial-grade laser radar that has completed factory calibration can provide multi-beam point cloud acquisition capabilities.

[0091] In the embodiment of the present application, the first vehicle can be controlled to travel according to a preset first trajectory. During the travel of the first vehicle, the RTK module periodically collects the first GPS coordinates, and the laser radar to be calibrated periodically collects point cloud data around the first vehicle. The data collection frequency of the RTK module is relatively high, for example, 100HZ, and the collection frequency of the laser radar to be calibrated is relatively low, for example, 10HZ. Since the sampling frequency (10HZ) of the laser radar to be matched is much lower than the sampling frequency (100HZ) of the RTK module, the timestamp detected by the laser radar to be calibrated of the first vehicle can be used as a reference to select the GPS coordinates collected by the RTK module in the first vehicle that are closest to the timestamp, that is, the first GPS coordinates.

[0092] The relative position of the RTK module and the laser radar to be calibrated is fixed. In this way, the relative position of the world coordinate system where the RTK module is located and the radar coordinate system where the laser radar to be calibrated is located is also fixed. According to the GPS coordinates collected by the RTK module, the coordinates of the laser radar to be calibrated can be determined.

[0093] Step S104, obtaining the second GPS coordinates periodically collected by the RTK module in the second vehicle during the driving process of the second vehicle.

[0094] Similarly, the second vehicle (i.e., the calibration tool vehicle) is also equipped with an RTK module, which can control the second vehicle to travel along the preset second trajectory, and the second vehicle is synchronized with the first vehicle in time. During the driving process of the second vehicle, the RTK module periodically collects the second GPS coordinates. Based on the timestamp detected by the laser radar to be calibrated of the first vehicle, the GPS coordinates collected by the RTK module in the second vehicle closest to the timestamp are selected, i.e., the second GPS coordinates.

[0095] The second vehicle is within the detection range of the laser radar to be calibrated. In this way, the second vehicle can be detected from the point cloud data collected by the laser radar to be calibrated, and the position coordinates of the second vehicle can be determined. According to the calculated position coordinates of the second vehicle and the second GPS coordinates collected by the RTK module, the calibration of the laser radar to be calibrated can be achieved through point cloud matching. The relative position of the second vehicle to the first vehicle changes, and the point cloud data collected by the laser radar to be calibrated can include point cloud data of the second vehicle in different directions.

[0096] Step S106, performing target detection on the point cloud data to obtain the relative position data of the second vehicle in the laser radar coordinate system.

[0097] The target detection algorithm is used to perform target detection on the point cloud data, and the category information of each detection frame and the pose information of each detection frame are output, so that the position data of the second vehicle can be obtained. Since the point cloud data collected by the laser radar to be calibrated can include the point cloud data of the second vehicle in different directions, the position data of the second vehicle in different directions can be detected. The relative position data of the second vehicle refers to the position data in the laser radar coordinate system.

[0098] Step S108, determining the absolute position data of the second vehicle according to the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle in the laser radar coordinate system.

[0099] The initial calibration parameters refer to the calibration parameters obtained by calibrating the RTK module in the first vehicle and the laser radar to be calibrated. Optionally, the initial calibration parameters can be determined according to the relative position of the RTK module in the first vehicle and the laser radar to be calibrated, and the initial calibration parameters include: an initial rotation matrix and an initial translation vector. For example, a three-coordinate measuring instrument can be used to measure the posture of the laser radar to be calibrated and the RTK module, and the rotation matrix and the translation vector can be recorded.

[0100] The first GPS coordinates record the coordinates of the RTK module. Therefore, the coordinates of the laser radar to be calibrated can be determined based on the initial calibration parameters and the first GPS coordinates. Furthermore, the absolute position data of the second vehicle can be determined based on the coordinates of the laser radar to be calibrated and the relative position data of the second vehicle in the laser radar coordinate system.

[0101] Since the first GPS coordinates and the second GPS coordinates are coordinates in the world coordinate system, and the relative position data are coordinates in the radar coordinate system, the two are in different coordinate systems, and the subsequent point cloud matching using the iterative closest point algorithm needs to be in the same coordinate system. Therefore, the calculated position coordinates of the second vehicle and the position coordinates of the second vehicle obtained by the RTK module can be converted to the same coordinate system through coordinate conversion.

[0102] Optionally, coordinate conversion is performed on the first GPS coordinates and the relative position data of the second vehicle in the laser radar coordinate system to obtain the first position coordinates and the relative position data in the target coordinate system, respectively. The target coordinate system can be a UTM (Universal Transverse Mercator Grid System) coordinate system, a Gaussian coordinate system, or a world coordinate system.

[0103] It should be noted that when the target coordinate system is the UTM coordinate system or the Gaussian coordinate system, since both the UTM coordinate system and the Gaussian coordinate system are plane coordinate systems, the Z-axis coordinate can be added after the coordinate conversion. For the second vehicle detected by the laser radar to be calibrated, the detection result includes the Z-axis coordinate in meters, which can be used directly. The GPS coordinates output by the RTK module include altitude coordinates and can also be used. It should be noted that since the detection frame output by the laser radar to be calibrated is a 3D detection frame, the output is the coordinates of a certain point (the center point of the 3D detection frame or the upper center point, etc.), therefore, after the coordinate conversion, the Z-axis coordinate corresponding to the added detection result and the Z-axis coordinate corresponding to the GPS coordinate can be kept consistent.

[0104] After the coordinate conversion is performed, the absolute position data of the second vehicle in the target coordinate system is determined according to the initial calibration parameters, the first position coordinates in the target coordinate system, and the relative position data in the target coordinate system.

[0105] Step S110, using an iterative closest point algorithm, matching the second GPS coordinates with the absolute position data of the second vehicle to optimize the initial calibration parameters and obtain target calibration parameters.

[0106] Correspondingly, the second GPS coordinates can also be converted to obtain the second position coordinates in the target coordinate system. The second position coordinates in the target coordinate system and the absolute position data of the second vehicle in the target coordinate system are matched using the iterative closest point algorithm. The details are as follows:

[0107] Assume that p i represents the absolute position data of the second vehicle in the target coordinate system, that is, the position coordinates obtained by calculation, q i Represents the second position coordinate in the target coordinate system, that is, the position coordinate output by RTK. p is transformed by rigid body transformation T i Convert to Rp i +t, T includes: rotation matrix R and translation vector t. According to the formula: Minimize the sum of squared Euclidean distances between two point clouds E(R,t), where N represents the number of points.

[0108] The optimal rotation matrix R and translation vector t are solved by SVD (singular value decomposition). Through iterative calculation, the rotation matrix R and translation vector t that satisfy the Euclidean distance less than the set threshold are obtained. The initial calibration parameters are multiplied by the parameters obtained by the above trajectory matching to obtain the final calibration parameters (including the final rotation matrix and translation vector). After calibrating the laser radar to be calibrated with the final calibration parameters, the coordinates finally output by the target detection algorithm can be used as the GPS coordinates of the true value.

[0109] The laser radar calibration method of the embodiment of the present application uses the vehicle as a calibration tool, which is more practical. The RTK module and the laser radar to be calibrated collect data in real time, and the calibration of the laser radar to be calibrated can be automatically realized through data processing, without manual measurement, and the efficiency is high. Since the RTK module and the laser radar to be calibrated are in the real vehicle and the position is fixed, there is no problem of recalibration due to the change of the laser radar position. And by synchronizing the time of the second vehicle with the first vehicle and changing the relative position of the second vehicle with the first vehicle, the second vehicle in different positions can be identified to improve the accuracy of the calibration.

[0110] LiDAR-based target detection algorithms include Point-based, Voxel-based, Point-Voxel-based, and Multi-view-based. There are errors between the detection results and the real coordinates obtained by different target detection algorithms. Considering the differences between different target detection algorithms, the corresponding calibration parameters can be calculated for different target detection algorithms to improve the accuracy of LiDAR calibration. Figure 2 , Figure 2 This is another flow chart of the laser radar calibration method in the embodiment of the present application, which may include the following steps:

[0111] Step S202, obtaining the first GPS coordinates and point cloud data periodically collected by the RTK module in the first vehicle and the laser radar to be calibrated during the driving of the first vehicle; the relative positions of the RTK module and the laser radar to be calibrated are fixed.

[0112] Step S204, obtaining the second GPS coordinates periodically collected by the RTK module in the second vehicle during the driving process of the second vehicle; the second vehicle is within the detection range of the laser radar to be calibrated, is time synchronized with the first vehicle, and its relative position with the first vehicle changes.

[0113] Step S206, using multiple target detection algorithms, respectively perform target detection on the point cloud data to obtain relative position data of the second vehicle corresponding to each target detection algorithm in the laser radar coordinate system.

[0114] In this step, different target detection algorithms are used to perform target detection on the point cloud data. Since the errors of different target detection algorithms are different, the relative position data of the second vehicle detected by different target detection algorithms are also different. Accordingly, the target calibration parameters finally obtained in the following step S210 will also be different.

[0115] Step S208, determining the absolute position data of the second vehicle corresponding to each target detection algorithm based on the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle corresponding to each target detection algorithm in the laser radar coordinate system.

[0116] Step S210, using an iterative closest point algorithm, matching the second GPS coordinates with the absolute position data of the second vehicle corresponding to each target detection algorithm to optimize initial calibration parameters and obtain target calibration parameters corresponding to each target detection algorithm.

[0117] Figure 2 Example and Figure 1 For the same parts as the embodiments, please refer to Figure 1 The description in the embodiments is sufficient and will not be repeated here.

[0118] In the embodiment of the present application, considering the influence of different target detection algorithms on the detection results, the target calibration parameters corresponding to the different target detection algorithms are calculated respectively, so as to improve the calibration accuracy.

[0119] For the target detection algorithm, the position of the second vehicle relative to the first vehicle is different, and the point cloud scanned by the laser radar to be calibrated in the first vehicle will also be different. For example, when the second vehicle is in front of the first vehicle, the point cloud scanned by the radar is mainly the middle and rear end of the second vehicle. When the second vehicle is on the left and right sides of the first vehicle, the point cloud scanned by the radar is mainly the side of the second vehicle. When the second vehicle is on the rear side of the first vehicle, the point cloud scanned by the radar is mainly the middle and front end of the second vehicle. Therefore, the point cloud features obtained in different areas are somewhat different. In addition, the distance between the second vehicle and the first vehicle is different, and the point cloud features are also somewhat different. In summary, the relative positions of the first vehicle and the second vehicle are different, and the error between the obtained detection results and the true results is not fixed. Therefore, the point cloud data can be divided into different areas according to the relative position of the second vehicle and the first vehicle, and the target calibration parameters corresponding to different areas are calculated respectively.

[0120] See also Figure 3 , Figure 3 This is another flow chart of the laser radar calibration method in the embodiment of the present application, which may include the following steps:

[0121] Step S302, obtaining the first GPS coordinates and point cloud data periodically collected by the RTK module in the first vehicle and the laser radar to be calibrated during the driving of the first vehicle; the relative positions of the RTK module and the laser radar to be calibrated are fixed.

[0122] Step S304, obtaining the second GPS coordinates periodically collected by the RTK module in the second vehicle during the driving process of the second vehicle; the second vehicle is within the detection range of the laser radar to be calibrated, is time synchronized with the first vehicle, and its relative position with the first vehicle changes.

[0123] Step S306 , dividing the point cloud data into different areas according to the relative position of the second vehicle and the first vehicle during the driving of the first vehicle and the second vehicle.

[0124] See also Figure 4A , during the driving of the first vehicle and the second vehicle, the relative positions of the second vehicle and the first vehicle can be divided into the following three types: the second vehicle is located in front of the first vehicle, the second vehicle is parallel to the first vehicle, and the second vehicle is located behind the first vehicle. According to the three division methods of relative positions, the point cloud data is divided into the front area, the parallel area, and the rear area.

[0125] Alternatively, see Figure 4B During the driving of the first vehicle and the second vehicle, the relative positions of the second vehicle and the first vehicle are divided into the following four types: the second vehicle is located in front of the first vehicle, the second vehicle is located behind the first vehicle, the second vehicle is located on the left side of the first vehicle, and the second vehicle is located on the right side of the first vehicle; according to the four division methods of relative positions, the point cloud data are divided into the front area, the rear area, the left area and the right area.

[0126] Step S308, performing target detection on the point cloud data of each area to obtain the relative position data of the second vehicle in each area in the laser radar coordinate system.

[0127] Step S310, determining the absolute position data of the second vehicle in each area according to the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle in each area in the laser radar coordinate system.

[0128] Step S312, using an iterative closest point algorithm, matching the second GPS coordinates with the absolute position data of the second vehicle in each area to optimize the initial calibration parameters and obtain target calibration parameters in each area.

[0129] Figure 3 Example and Figure 1 For the same parts as the embodiments, please refer to Figure 1 The description in the embodiments is sufficient and will not be repeated here.

[0130] In the embodiment of the present application, considering that the accuracy of detection results corresponding to different areas is different under the same target detection algorithm, the target calibration parameters corresponding to different target areas are calculated respectively, so as to improve the calibration accuracy.

[0131] The present application also provides a laser radar calibration device. Figure 5 , the laser radar calibration device 500 includes:

[0132] The first acquisition module 502 is used to acquire the first GPS coordinates and point cloud data periodically collected by the RTK module in the first vehicle and the laser radar to be calibrated during the driving process of the first vehicle; the relative positions of the RTK module and the laser radar to be calibrated are fixed;

[0133] The second acquisition module 504 is used to acquire the second GPS coordinates periodically collected by the RTK module in the second vehicle during the driving process of the second vehicle; the second vehicle is in the detection range of the laser radar to be calibrated, is time synchronized with the first vehicle, and the relative position with the first vehicle changes;

[0134] The target detection module 506 is used to perform target detection on the point cloud data to obtain the relative position data of the second vehicle in the laser radar coordinate system;

[0135] A position determination module 508, for determining the absolute position data of the second vehicle according to the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle in the laser radar coordinate system;

[0136] The target calibration parameter determination module 510 is used to match the second GPS coordinates and the absolute position data of the second vehicle using an iterative closest point algorithm to optimize the initial calibration parameters and obtain the target calibration parameters.

[0137] Optionally, the target detection module 506 is specifically used to use multiple target detection algorithms to perform target detection on the point cloud data respectively, and obtain relative position data of the second vehicle corresponding to each target detection algorithm in the laser radar coordinate system;

[0138] The position determination module 508 is specifically used to determine the absolute position data of the second vehicle corresponding to each target detection algorithm according to the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle corresponding to each target detection algorithm in the laser radar coordinate system;

[0139] The target calibration parameter determination module 510 is specifically used to use an iterative closest point algorithm to match the second GPS coordinates and the absolute position data of the second vehicle corresponding to each target detection algorithm to optimize the initial calibration parameters and obtain the target calibration parameters corresponding to each target detection algorithm.

[0140] Optionally, the target detection module 506 is specifically used to divide the point cloud data into different areas according to the relative position of the second vehicle and the first vehicle during the driving of the first vehicle and the second vehicle; perform target detection on the point cloud data of each area to obtain the relative position data of the second vehicle in each area in the laser radar coordinate system;

[0141] The position determination module 508 is specifically used to determine the absolute position data of the second vehicle in each area according to the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle in each area in the laser radar coordinate system;

[0142] The target calibration parameter determination module 510 is specifically used to match the second GPS coordinates and the absolute position data of the second vehicle in each area using an iterative closest point algorithm to optimize the initial calibration parameters and obtain the target calibration parameters in each area.

[0143] Optionally, the position determination module 508 is specifically used to perform coordinate conversion on the first GPS coordinates and the relative position data of the second vehicle in the laser radar coordinate system to obtain the first position coordinates and the relative position data in the target coordinate system respectively; determine the absolute position data of the second vehicle in the target coordinate system according to the initial calibration parameters, the first position coordinates in the target coordinate system and the relative position data in the target coordinate system;

[0144] The target calibration parameter determination module 510 is specifically used to perform coordinate conversion on the second GPS coordinates to obtain second position coordinates in the target coordinate system; and use an iterative closest point algorithm to match the second position coordinates in the target coordinate system with the absolute position data of the second vehicle in the target coordinate system.

[0145] Optionally, the target detection module 506 is specifically configured to divide the point cloud data into different areas according to the relative position of the second vehicle and the first vehicle during the driving of the first vehicle and the second vehicle through the following steps:

[0146] During the driving of the first vehicle and the second vehicle, the relative positions of the second vehicle and the first vehicle are divided into the following three types: the second vehicle is located in front of the first vehicle, the second vehicle is parallel to the first vehicle, and the second vehicle is located behind the first vehicle;

[0147] According to the three division methods of relative position, the point cloud data is divided into the front area, the parallel area and the rear area; or,

[0148] During the driving of the first vehicle and the second vehicle, the relative positions of the second vehicle and the first vehicle are divided into the following four types: the second vehicle is located in front of the first vehicle, the second vehicle is located behind the first vehicle, the second vehicle is located on the left side of the first vehicle, and the second vehicle is located on the right side of the first vehicle;

[0149] According to the four division methods of relative position, the point cloud data is divided into the front area, the back area, the left area and the right area.

[0150] Optionally, the laser radar calibration device 500 further includes:

[0151] The initial calibration parameter determination module is used to determine the initial calibration parameters according to the relative position of the RTK module in the first vehicle and the laser radar to be calibrated. The initial calibration parameters include: an initial rotation matrix and an initial translation vector.

[0152] The specific details of each module or unit in the above device have been described in detail in the corresponding method, so they will not be repeated here.

[0153] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0154] The present application also provides a laser radar calibration system. Figure 6 , the laser radar calibration system 600 includes: a first vehicle 610 and a second vehicle 620, the first vehicle 610 is equipped with an RTK module and a laser radar to be calibrated, and the relative positions of the RTK module and the laser radar to be calibrated are fixed; the second vehicle 620 is equipped with an RTK module;

[0155] The first vehicle 610 is configured to periodically collect first GPS coordinates by using an RTK module while the first vehicle is traveling, and periodically collect point cloud data around the first vehicle by using a laser radar to be calibrated while the first vehicle is traveling;

[0156] The second vehicle 620 is used to periodically collect the second GPS coordinates through the RTK module during the driving process of the second vehicle. The second vehicle is in the detection range of the laser radar to be calibrated, is synchronized with the first vehicle in time, and the relative position of the second vehicle to the first vehicle changes;

[0157] The first vehicle 610 is also used to perform target detection on the point cloud data to obtain the relative position data of the second vehicle in the laser radar coordinate system; determine the absolute position data of the second vehicle according to the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle in the laser radar coordinate system; use the iterative closest point algorithm to match the second GPS coordinates and the absolute position data of the second vehicle to optimize the initial calibration parameters and obtain the target calibration parameters.

[0158] Optionally, the first vehicle 610 is specifically used to use multiple target detection algorithms to perform target detection on point cloud data respectively, and obtain relative position data of the second vehicle corresponding to each target detection algorithm in the lidar coordinate system; determine the absolute position data of the second vehicle corresponding to each target detection algorithm according to the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle corresponding to each target detection algorithm in the lidar coordinate system; use an iterative nearest point algorithm to match the second GPS coordinates and the absolute position data of the second vehicle corresponding to each target detection algorithm to optimize the initial calibration parameters and obtain the target calibration parameters corresponding to each target detection algorithm.

[0159] Optionally, the first vehicle 610 is specifically used to divide the point cloud data into different areas according to the relative position of the second vehicle and the first vehicle during the driving of the first vehicle and the second vehicle; perform target detection on the point cloud data of each area to obtain the relative position data of the second vehicle in each area in the laser radar coordinate system; determine the absolute position data of the second vehicle in each area according to the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle in each area in the laser radar coordinate system; use an iterative nearest point algorithm to match the second GPS coordinates and the absolute position data of the second vehicle in each area to optimize the initial calibration parameters and obtain the target calibration parameters in each area.

[0160] Optionally, the first vehicle 610 is specifically used to perform coordinate conversion on the first GPS coordinates and the relative position data of the second vehicle in the lidar coordinate system to obtain first position coordinates and relative position data in the target coordinate system, respectively; determine the absolute position data of the second vehicle in the target coordinate system according to initial calibration parameters, the first position coordinates in the target coordinate system and the relative position data in the target coordinate system; perform coordinate conversion on the second GPS coordinates to obtain second position coordinates in the target coordinate system; and use an iterative closest point algorithm to match the second position coordinates in the target coordinate system with the absolute position data of the second vehicle in the target coordinate system.

[0161] Optionally, the first vehicle is specifically configured to divide the point cloud data into different areas according to the relative positions of the second vehicle and the first vehicle during the driving of the first vehicle and the second vehicle through the following steps:

[0162] During the driving of the first vehicle and the second vehicle, the relative positions of the second vehicle and the first vehicle are divided into the following three types: the second vehicle is located in front of the first vehicle, the second vehicle is parallel to the first vehicle, and the second vehicle is located behind the first vehicle;

[0163] According to the three division methods of relative position, the point cloud data is divided into the front area, the parallel area and the rear area; or,

[0164] During the driving of the first vehicle and the second vehicle, the relative positions of the second vehicle and the first vehicle are divided into the following four types: the second vehicle is located in front of the first vehicle, the second vehicle is located behind the first vehicle, the second vehicle is located on the left side of the first vehicle, and the second vehicle is located on the right side of the first vehicle;

[0165] According to the four division methods of relative position, the point cloud data is divided into the front area, the back area, the left area and the right area.

[0166] Optionally, the first vehicle is further used to determine initial calibration parameters according to the relative position of the RTK module in the first vehicle and the laser radar to be calibrated, and the initial calibration parameters include: an initial rotation matrix and an initial translation vector.

[0167] An embodiment of the present application also provides an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the above-mentioned laser radar calibration method in this example implementation.

[0168] Reference Figure 7 , Figure 7 This is a schematic diagram of the structure of an electronic device in an embodiment of the present application. The specific embodiment of the present application does not limit the specific implementation of the electronic device.

[0169] like Figure 7 As shown, the electronic device may include: a processor 702 , a communication interface 704 , a memory 706 , and a communication bus 708 .

[0170] The processor 702 , the communication interface 704 , and the memory 706 communicate with each other via a communication bus 708 .

[0171] The communication interface 704 is used to communicate with other electronic devices or servers.

[0172] The processor 702 is used to execute the program 710, and specifically can execute the relevant steps in the above method embodiment.

[0173] Specifically, the program 710 may include program codes, which include computer operation instructions.

[0174] The processor 702 may be a central processing unit, or a specific integrated circuit, or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the smart device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0175] The memory 706 is used to store the program 710. The memory 706 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0176] Program 710 can be specifically used to enable processor 702 to execute the steps in the above-mentioned laser radar calibration method embodiment.

[0177] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding process descriptions in the aforementioned method embodiments and will not be repeated here.

[0178] A computer-readable storage medium is also provided in an embodiment of the present application, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned laser radar calibration method is implemented.

[0179] It should be noted that the computer-readable storage medium shown in the present application may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, radio frequency, etc., or any suitable combination of the above.

[0180] In an embodiment of the present application, a computer program product is also provided. When the computer program product is run on a computer, the computer executes the above-mentioned laser radar calibration method.

[0181] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0182] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A laser radar calibration method, characterized in that: include: Acquire the first global positioning system GPS coordinates and point cloud data periodically collected by the real-time differential positioning RTK module in the first vehicle and the laser radar to be calibrated during the driving process of the first vehicle; the relative positions of the RTK module and the laser radar to be calibrated are fixed; Acquire the second GPS coordinates periodically collected by the RTK module in the second vehicle during the driving of the second vehicle; the second vehicle is within the detection range of the laser radar to be calibrated, is time synchronized with the first vehicle, and the relative position of the second vehicle to the first vehicle changes; Performing target detection on the point cloud data to obtain relative position data of the second vehicle in a laser radar coordinate system; Determining the absolute position data of the second vehicle according to the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle in the laser radar coordinate system; The second GPS coordinates and the absolute position data of the second vehicle are matched using an iterative closest point algorithm to optimize the initial calibration parameters and obtain target calibration parameters.

2. The method according to claim 1, characterized in that The performing target detection on the point cloud data to obtain relative position data of the second vehicle in the laser radar coordinate system includes: Using multiple target detection algorithms, respectively perform target detection on the point cloud data to obtain relative position data of the second vehicle corresponding to each target detection algorithm in a laser radar coordinate system; The determining the absolute position data of the second vehicle according to the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle in the laser radar coordinate system includes: Determine the absolute position data of the second vehicle corresponding to each target detection algorithm according to the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle corresponding to each target detection algorithm in the laser radar coordinate system; The using of an iterative closest point algorithm to match the second GPS coordinates with the absolute position data of the second vehicle to optimize the initial calibration parameters and obtain target calibration parameters includes: The second GPS coordinates are matched with the absolute position data of the second vehicle corresponding to each target detection algorithm by using an iterative closest point algorithm to optimize the initial calibration parameters and obtain target calibration parameters corresponding to each target detection algorithm.

3. The method according to claim 1, characterized in that The performing target detection on the point cloud data to obtain relative position data of the second vehicle in the laser radar coordinate system includes: Dividing the point cloud data into different areas according to the relative positions of the second vehicle and the first vehicle during the driving of the first vehicle and the second vehicle; Performing target detection on the point cloud data of each area to obtain relative position data of the second vehicle in each area in a laser radar coordinate system; The determining the absolute position data of the second vehicle according to the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle in the laser radar coordinate system includes: Determine the absolute position data of the second vehicle in each area according to the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle in each area in the laser radar coordinate system; The using of an iterative closest point algorithm to match the second GPS coordinates with the absolute position data of the second vehicle to optimize the initial calibration parameters and obtain target calibration parameters includes: The second GPS coordinates are matched with the absolute position data of the second vehicle in each area by using an iterative closest point algorithm to optimize the initial calibration parameters and obtain target calibration parameters in each area.

4. The method according to claim 1, characterized in that: The determining the absolute position data of the second vehicle according to the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle in the laser radar coordinate system includes: Performing coordinate conversion on the first GPS coordinates and the relative position data of the second vehicle in the laser radar coordinate system to obtain first position coordinates and relative position data in the target coordinate system respectively; Determining absolute position data of the second vehicle in the target coordinate system according to the initial calibration parameters, the first position coordinates in the target coordinate system, and the relative position data in the target coordinate system; The matching of the second GPS coordinates and the absolute position data of the second vehicle by using an iterative closest point algorithm includes: Performing coordinate conversion on the second GPS coordinates to obtain second position coordinates in the target coordinate system; The second position coordinates in the target coordinate system and the absolute position data of the second vehicle in the target coordinate system are matched using an iterative closest point algorithm.

5. The method according to claim 3, characterized in that: The dividing the point cloud data into different areas according to the relative position of the second vehicle and the first vehicle during the driving of the first vehicle and the second vehicle includes: During the driving of the first vehicle and the second vehicle, the relative positions of the second vehicle and the first vehicle are divided into the following three types: the second vehicle is located in front of the first vehicle, the second vehicle is parallel to the first vehicle, and the second vehicle is located behind the first vehicle; Divide the point cloud data into a front area, a parallel area and a rear area according to three division methods of relative positions; or, During the driving of the first vehicle and the second vehicle, the relative positions of the second vehicle and the first vehicle are divided into the following four types: the second vehicle is located in front of the first vehicle, the second vehicle is located behind the first vehicle, the second vehicle is located on the left side of the first vehicle, and the second vehicle is located on the right side of the first vehicle; According to four division methods of relative positions, the point cloud data is divided into a front area, a rear area, a left area and a right area.

6. The method according to claim 1, characterized in that Before determining the absolute position data of the second vehicle according to the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle in the laser radar coordinate system, the method further includes: The initial calibration parameters are determined according to the relative positions of the RTK module in the first vehicle and the laser radar to be calibrated. The initial calibration parameters include: an initial rotation matrix and an initial translation vector.

7. A laser radar calibration device, characterized in that: The device comprises: A first acquisition module is used to acquire first global positioning system GPS coordinates and point cloud data periodically collected by a real-time differential positioning RTK module in the first vehicle and the laser radar to be calibrated during the driving process of the first vehicle; the relative positions of the RTK module and the laser radar to be calibrated are fixed; A second acquisition module is used to acquire second GPS coordinates periodically collected by the RTK module in the second vehicle during the driving process of the second vehicle; the second vehicle is within the detection range of the laser radar to be calibrated, is time synchronized with the first vehicle, and the relative position with the first vehicle changes; A target detection module, used to perform target detection on the point cloud data to obtain relative position data of the second vehicle in a laser radar coordinate system; a position determination module, configured to determine the absolute position data of the second vehicle according to the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle in the laser radar coordinate system; The target calibration parameter determination module is used to match the second GPS coordinates and the absolute position data of the second vehicle using an iterative closest point algorithm to optimize the initial calibration parameters and obtain target calibration parameters.

8. A laser radar calibration system, characterized in that: The system comprises: a first vehicle and a second vehicle, wherein the first vehicle is equipped with a real-time differential positioning RTK module and a laser radar to be calibrated, and the relative positions of the RTK module and the laser radar to be calibrated are fixed; and the second vehicle is equipped with an RTK module; The first vehicle is used to periodically collect first global positioning system GPS coordinates through the RTK module during the driving of the first vehicle, and to periodically collect point cloud data around the first vehicle through the laser radar to be calibrated during the driving of the first vehicle; The second vehicle is used to periodically collect second GPS coordinates through the RTK module during the driving process of the second vehicle, and the second vehicle is in the detection range of the laser radar to be calibrated, is synchronized with the first vehicle in time, and the relative position of the second vehicle to the first vehicle changes; The first vehicle is also used to perform target detection on the point cloud data to obtain the relative position data of the second vehicle in the laser radar coordinate system; determine the absolute position data of the second vehicle according to the initial calibration parameters, the first GPS coordinates and the relative position data of the second vehicle in the laser radar coordinate system; use an iterative closest point algorithm to match the second GPS coordinates and the absolute position data of the second vehicle to optimize the initial calibration parameters and obtain target calibration parameters.

9. An electronic device, characterized in that: include: A processor, wherein the processor is used to execute a computer program stored in a memory, wherein the computer program, when executed by the processor, implements the method according to any one of claims 1 to 6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images