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

Abstract

The present application discloses a laser radar calibration method, device, electronic device, and storage medium, wherein the method includes initializing the laser radar to obtain at least a first YAW angle for laser radar calibration; obtaining point cloud data collected by the laser radar according to a preset calibration field, wherein the preset calibration field includes at least an acquisition board, and the acquisition board is located on either side of a lane; obtaining high-precision map data of the area where the preset calibration field is located, wherein the high-precision map data includes lane line data of the lane; determining a second YAW angle based on the matching result of the lane line data and the point cloud data of the acquisition board in the vehicle coordinate system; obtaining a YAW angle error parameter based on the difference between the first YAW angle and the second YAW angle; and calibrating the laser radar based on the YAW angle error parameter. The laser radar calibration method in the present application is simple and easy to use and more in line with actual usage. The present application can dynamically calibrate the laser radar.

Description

Technical Field

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

[0002] With the development of autonomous driving technology, many autonomous vehicles are equipped with lidar as the main perception sensor. By classifying and segmenting the point cloud generated by the lidar, the position, size and other information of targets such as vehicles and pedestrians within the visual range are extracted, providing reliable prior information for subsequent control and local planning.

[0003] Currently, the mainstream lidar calibration is carried out in a dedicated calibration workshop or calibration field, using professional calibration equipment or manual debugging.

[0004] Calibration workshops or calibration sites must be established in specific areas, which is costly. Furthermore, manual calibration has limited accuracy and requires significant manpower. Using specialized calibration equipment is also expensive and subject to installation errors, further impacting calibration accuracy. Summary of the Invention

[0005] The embodiments of the present application provide a laser radar calibration method, device, electronic device, and storage medium to reduce the error of laser calibration.

[0006] The embodiments of this application adopt the following technical solutions:

[0007] In a first aspect, an embodiment of the present application provides a lidar calibration method, wherein the method includes: initializing the lidar to obtain at least a first YAW angle for lidar calibration; obtaining point cloud data collected by the lidar according to a preset calibration field, wherein the preset calibration field includes at least an acquisition board, and the acquisition board is located on either side of the lane; obtaining high-precision map data of the area where the preset calibration field is located, wherein the high-precision map data includes lane line data of the lane; determining a second YAW angle based on a matching result between the lane line data and the point cloud data of the acquisition board in the vehicle coordinate system; obtaining a YAW angle error parameter based on the difference between the first YAW angle and the second YAW angle; and calibrating the lidar based on the YAW angle error parameter.

[0008] In the second aspect, an embodiment of the present application also provides a laser radar calibration device, wherein the device includes: an initialization module, used to initialize the laser radar and obtain at least a first YAW angle for laser radar calibration; a first acquisition module, used to obtain point cloud data collected by the laser radar according to a preset calibration field, wherein the preset calibration field includes at least an acquisition board, and the acquisition board is located on either side of the lane; a second acquisition module, used to obtain high-precision map data of the area where the preset calibration field is located, wherein the high-precision map data includes lane line data of the lane; a matching module, used to determine the second YAW angle based on the matching result of the lane line data and the point cloud data of the acquisition board in the vehicle coordinate system; obtain a YAW angle error parameter based on the difference between the first YAW angle and the second YAW angle; and calibrate the laser radar based on the YAW angle error parameter.

[0009] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor; and a memory arranged to store computer-executable instructions, wherein the executable instructions, when executed, enable the processor to perform the above method.

[0010] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple application programs, the electronic device executes the above method.

[0011] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:

[0012] By establishing a preset calibration field and acquisition board, the YAW angle of the initially calibrated LiDAR is corrected. This correction involves matching the high-precision map with the feature points on the acquisition board. The YAW angle error parameters obtained from this correction are then used to calibrate the LiDAR. Alternatively, the LiDAR can be calibrated using an adaptive method. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0014] Figure 1 This is a flow chart of the laser radar calibration method in the embodiment of the present application;

[0015] Figure 2 This is a schematic diagram of the structure of the laser radar calibration device in an embodiment of the present application;

[0016] Figure 3 Schematic diagram of the calibration field of the laser radar calibration method in the embodiment of the present application;

[0017] Figure 4 This is a structural diagram of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0018] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0019] The inventors discovered that in the related art, the YAW angle after the initial calibration of the lidar still has a large error, and if there is an error of 1 degree in the YAW angle, it will cause an object 100 meters ahead to have a lateral deviation of about 1.7 meters. If it is on a high-speed road, it will cause the autonomous driving vehicle to perform incorrect deceleration, lane change, and other behaviors.

[0020] To address the above-mentioned shortcomings, the present application provides a lidar calibration method, which provides an adaptive dynamic calibration method.

[0021] The following describes in detail the technical solutions provided by various embodiments of the present application in conjunction with the accompanying drawings.

[0022] The present application embodiment provides a laser radar calibration method, such as Figure 1 As shown, a schematic flow chart of a laser radar calibration method according to an embodiment of the present application is provided, wherein the method comprises at least the following steps S110 to S160:

[0023] Step S110: Initialize the laser radar and obtain at least the first YAW angle calibrated by the laser radar.

[0024] For lidar, initial calibration can be performed using methods known in related technologies. This involves initializing the lidar to obtain the first yaw angle for lidar calibration. In addition to the yaw angle, initial calibration can also determine parameters such as pitch angle, roll angle, x_offset, and y_offset. However, this application primarily focuses on the yaw angle.

[0025] Step S120: acquiring point cloud data collected by the laser radar according to a preset calibration field, wherein the preset calibration field at least includes a collection plate, and the collection plate is located on either side of the lane.

[0026] The point cloud data collected by the LiDAR is acquired using a special acquisition board in a pre-set calibration field. The acquisition board can be located on either side of the lane, or on both sides of the lane.

[0027] Preferably, the autonomous vehicle can be driven forward in a preset calibration field. For example, two collection panels (reflectors / reflectors) can be placed on the left and right sides of two lane lines, with the long sides aligning with the nearest lane line.

[0028] like Figure 3 As shown, by selecting the acquisition board, you can set the driving route of the autonomous vehicle, that is, set a straight driving route parallel to the lane lines on both sides. The route length can be set to 200 meters, of which the starting point of forward driving is about 100 meters away from the center of the acquisition board (A or B), and the starting point of reverse driving is about 100 meters away from the center of the acquisition board (A or B).

[0029] Step S130: Obtain high-precision map data of the area where the preset calibration location is located, wherein the high-precision map data includes lane line data of the lane.

[0030] At the same time, it is also necessary to obtain high-precision map data for the area where the preset calibration site is located. It is understood that this high-precision map data must at least include lane line data. Lane line data is needed as a reference for the following matching.

[0031] Step S140 : determining a second YAW angle based on a matching result between the lane line data and the point cloud data of the acquisition board in the vehicle coordinate system.

[0032] The vehicle coordinate system is a two-dimensional coordinate system. The second YAW angle is determined based on the matching result of the lane line data and the point cloud data of the acquisition board in the vehicle coordinate system.

[0033] It can be understood that the second YAW angle includes multiple moments, or each moment includes the second YAW angle.

[0034] Step S150: Obtain a YAW angle error parameter according to a difference between the first YAW angle and the second YAW angle.

[0035] The YAW angle error parameter may be obtained based on the difference between the first YAW angle and the second YAW angle.

[0036] Preferably, the autonomous driving vehicle can be allowed to drive in the reverse direction in a previously preset calibration field, and the YAW angle error parameters at multiple moments can be calculated again.

[0037] Step S160: calibrate the laser radar according to the YAW angle error parameter.

[0038] The laser radar is calibrated according to the YAW angular error parameter (which can be an average value or a dynamically changing value) to obtain an optimized laser radar calibration result.

[0039] In one embodiment of the present application, the acquisition boards include at least two, and the two acquisition boards are relatively arranged on both sides of the lane. The second YAW angle is determined according to the matching results of the lane line data and the point cloud data of the acquisition boards in the vehicle coordinate system, including: segmenting the corresponding first point cloud data according to the two acquisition boards; projecting the first point cloud data to the vehicle coordinate system and extracting the point cloud data of the target boundary; in the process of matching the point cloud data of the target boundary with the lane line data, adjusting the YAW angle to change the position of the point cloud data of the target boundary so that the point cloud data of the target boundary coincides with the lane line data; and determining the second YAW angle according to the result of the coincident position.

[0040] During specific implementation, in order to better collect point cloud data, the acquisition boards include at least two, and the two acquisition boards are relatively arranged on both sides of the lane.

[0041] Based on the two acquisition boards, corresponding first point cloud data is segmented and then projected into the vehicle coordinate system to extract the target boundary point cloud data. During the matching process between the target boundary point cloud data and the lane line data, the YAW angle is adjusted to change the position of the target boundary point cloud data. In other words, since only the YAW angle error is considered, the optimization term during matching can be set to the YAW angle. By continuously changing the YAW value, the position of the long side point cloud of the acquisition board can be further changed until the point cloud and lane line overlap to the highest degree. This allows the target boundary point cloud data to overlap with the lane line data. Based on the overlapped position, the second YAW angle is determined.

[0042] In one embodiment of the present application, obtaining the YAW angle error parameter based on the difference between the first YAW angle and the second YAW angle includes: driving forward on the target lane, obtaining the second YAW angle corresponding to the Kth moment; driving backward on the target lane, obtaining the second YAW angle corresponding to the Nth moment; obtaining the YAW angle error parameter based on the second YAW angle corresponding to the K moment and the second YAW angle corresponding to the N moment, wherein K and N are natural numbers, the error value conforms to the normal distribution and the average value is used as the YAW angle error parameter.

[0043] In a specific implementation, the error between the second YAW angle at time K and the second YAW angle at time N is used as the YAW angle error parameter. Preferably, the error values conform to a normal distribution, and the average value is used as the YAW angle error parameter. Generally, for the sake of generality, multiple forward and reverse driving can be performed. Based on the principle of large numbers, the YAW angle errors obtained statistically conform to a normal distribution, and the average value is the YAW angle error.

[0044] In one embodiment of the present application, the point cloud data of the target boundary includes point cloud data of the long side on the acquisition board, and the long side coincides with the lane line in the preset calibration field.

[0045] In specific implementations, the point cloud data for the long side is the point cloud data that overlaps with the lane lines in the preset calibration field. Since high-precision map data is acquired, the matching result between the lane line data provided in the HD map and the point cloud data can affect the position of the long side point cloud data. This means that the second YAW angle is adjusted until the point cloud and lane line overlap is maximized. Furthermore, the adjusted second YAW angle is then subtracted from the first YAW angle, thereby dynamically updating the YAW angle error parameter.

[0046] In one embodiment of the present application, the point cloud data collected by the laser radar is obtained according to a preset calibration field, wherein the preset calibration field includes at least an acquisition board, and the acquisition board is located on either side of the lane, including: segmenting the point cloud data recognized by the laser radar at the current moment according to the current position and orientation of the vehicle, the initial rough calibration parameters of the laser radar, and a preset error range.

[0047] In specific implementation, taking the above two acquisition boards as an example, for example, the point cloud recognized by the lidar at time K is processed to separate the point cloud data of the two acquisition boards. The segmentation can be performed based on the current position and orientation of the vehicle, the initial rough calibration parameters of the lidar, and the set error range.

[0048] It should be noted that the segmentation process is well known to those skilled in the art and will not be described in detail here.

[0049] In one embodiment of the present application, the obtaining of high-precision map data of the area where the preset calibration location is located, wherein the high-precision map data includes lane line data of the lane, further includes: determining whether the offline high-precision map data of the area where the preset calibration location is located is updated; if it is determined that the offline high-precision map data of the area where the preset calibration location is located is not updated, updating the lane line data according to the point cloud data collected by the lidar.

[0050] In specific implementations, for offline high-precision map data, before matching, a determination is made as to whether the offline high-precision map data for the area where the preset calibration location is located has been updated. If it is determined that the offline high-precision map data for the area where the preset calibration location is located has not been updated, the lane line data is updated based on the point cloud data collected by the lidar (currently collected or older than the offline historical version). Because the lidar is calibrated through dynamic adjustment of the YAW angle error parameters, the point cloud data collected by the lidar is more accurate than the previous high-precision map data.

[0051] In one embodiment of the present application, it also includes: a step of dynamically calibrating the laser radar: adjusting the YAW angular error parameters of the laser radar in real time based on multiple sets of vehicle data recognized by the visual sensor and pre-loaded high-precision map data to make the vehicle travel in the target lane, wherein the multiple sets of vehicle data are used as markers corresponding to the point cloud data collected by the laser radar.

[0052] In practice, in addition to the static calibration method described above, the lidar can also be calibrated dynamically. This involves adjusting the lidar's YAW angle error parameters in real time based on multiple sets of vehicle data identified by the visual sensor (as identifiers) and pre-loaded high-precision map data (providing high-precision lane markings). The result of the dynamic calibration is determined by the adjustment of the YAW angle error parameters.

[0053] It should be noted that the multiple sets of vehicle data are used as landmark sets corresponding to the point cloud data collected by the lidar.

[0054] The present application also provides a laser radar calibration device 200, such as Figure 2 As shown, a schematic diagram of the structure of a laser radar calibration device in an embodiment of the present application is provided. The laser radar calibration device 200 includes at least: an initialization module 210, a first acquisition module 220, a second acquisition module 230, a matching module 240, a difference calculation module 250, and a calibration module 260, wherein:

[0055] Initialization module 210, used to initialize the laser radar and obtain at least a first YAW angle calibrated by the laser radar;

[0056] A first acquisition module 220 is configured to acquire point cloud data collected by the laser radar according to a preset calibration field, wherein the preset calibration field includes at least an acquisition board, and the acquisition board is located on either side of the lane;

[0057] A second acquisition module 230 is configured to acquire high-precision map data of the area where the preset calibration location is located, wherein the high-precision map data includes lane line data of the lane;

[0058] A matching module 240 is configured to determine a second YAW angle based on a matching result between the lane line data and the point cloud data of the acquisition board in the vehicle coordinate system;

[0059] a difference calculation module 250 for obtaining a YAW angle error parameter according to a difference between the first YAW angle and the second YAW angle;

[0060] The calibration module 260 is used to calibrate the laser radar according to the YAW angle error parameter.

[0061] In one embodiment of the present application, the initialization module 210 is specifically configured to perform initial calibration of the lidar using methods known in the relevant art. Specifically, after initializing the lidar, the first yaw angle (YAW) of the lidar calibration is obtained. In addition to the YAW angle, initial calibration can also calibrate parameters such as the pitch angle, roll angle, x_offset, and y_offset. However, this application primarily focuses on the YAW angle.

[0062] In one embodiment of the present application, the first acquisition module 220 is specifically configured to acquire point cloud data collected by the LiDAR based on a special acquisition board in a preset calibration field. The acquisition board can be located on either side of the lane, or on both sides of the lane.

[0063] Preferably, the autonomous vehicle can be driven forward in a preset calibration field. For example, two collection panels (reflectors / reflectors) can be placed on the left and right sides of two lane lines, with the long sides aligning with the lane lines.

[0064] like Figure 3 As shown, the driving route of the autonomous driving vehicle can be set, that is, a straight driving route parallel to the lane lines on both sides can be set, and the length can be set to 200 meters, of which the starting point of the forward driving is about 100 meters away from the collection board, and the starting point of the reverse driving is about 100 meters away from the collection board.

[0065] In one embodiment of the present application, the second acquisition module 230 is specifically configured to: simultaneously acquire high-precision map data within the area of the preset calibration site. It is understood that this high-precision map data must at least include lane line data. The lane line data is used as a reference for the following matching.

[0066] In one embodiment of the present application, the matching module 240 is specifically used to: the vehicle coordinate system is a two-dimensional coordinate system, and the second YAW angle is determined based on the matching result of the lane line data and the point cloud data of the acquisition board in the vehicle coordinate system.

[0067] It can be understood that the second YAW angle includes multiple moments, or each moment includes the second YAW angle.

[0068] In one embodiment of the present application, the difference calculation module 250 is specifically configured to obtain the YAW angle error parameter according to the difference between the first YAW angle and the second YAW angle.

[0069] Preferably, the autonomous driving vehicle can be allowed to drive in the reverse direction in a previously preset calibration field, and the YAW angle error parameters at multiple moments can be calculated again.

[0070] In one embodiment of the present application, the calibration module 260 is specifically used to calibrate the laser radar according to the YAW angular error parameter (which may be an average value or a dynamically changing value) to obtain an optimized laser radar calibration result.

[0071] It can be understood that the above-mentioned laser radar calibration device can implement each step of the laser radar calibration method provided in the aforementioned embodiment. The relevant explanations about the laser radar calibration method are applicable to the laser radar calibration device and will not be repeated here.

[0072] Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 4 At the hardware level, the electronic device includes a processor and, optionally, an internal bus, a network interface, and memory. The memory may include internal memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for its services.

[0073] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0074] The memory is used to store programs. Specifically, the program may include program code, which includes computer operating instructions. The memory may include internal memory and non-volatile memory, and provides instructions and data to the processor.

[0075] The processor reads the corresponding computer program from the non-volatile memory into the internal memory and then runs it, forming a lidar calibration device at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0076] Initialize the lidar and get at least the first YAW angle calibrated by the lidar;

[0077] Acquiring point cloud data collected by the laser radar according to a preset calibration field, wherein the preset calibration field includes at least a collection plate, and the collection plate is located on either side of the lane;

[0078] Obtaining high-precision map data of the area where the preset calibration location is located, wherein the high-precision map data includes lane line data of the lane;

[0079] Determining a second YAW angle based on a matching result between the lane line data and the point cloud data of the acquisition board in the vehicle coordinate system;

[0080] Obtaining a YAW angle error parameter according to a difference between the first YAW angle and the second YAW angle;

[0081] The laser radar is calibrated according to the YAW angle error parameter.

[0082] The above application Figure 1 The method performed by the lidar calibration device disclosed in the illustrated embodiment can be applied to or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits in the processor or by software instructions. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in conjunction with the embodiments of this application can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method.

[0083] The electronic device may also perform Figure 1 The method for executing the laser radar calibration device in Figure 1 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0084] The embodiment of the present application also provides a computer-readable storage medium, which stores one or more programs, wherein the one or more programs include instructions, which, when executed by an electronic device including multiple application programs, can enable the electronic device to execute Figure 1 The method performed by the laser radar calibration device in the embodiment shown is specifically used to perform:

[0085] Initialize the lidar and get at least the first YAW angle calibrated by the lidar;

[0086] Acquiring point cloud data collected by the laser radar according to a preset calibration field, wherein the preset calibration field includes at least a collection plate, and the collection plate is located on either side of the lane;

[0087] Obtaining high-precision map data of the area where the preset calibration location is located, wherein the high-precision map data includes lane line data of the lane;

[0088] Determining a second YAW angle based on a matching result between the lane line data and the point cloud data of the acquisition board in the vehicle coordinate system;

[0089] Obtaining a YAW angle error parameter according to a difference between the first YAW angle and the second YAW angle;

[0090] The laser radar is calibrated according to the YAW angle error parameter.

[0091] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0092] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0093] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0094] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0095] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0096] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0097] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0098] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0099] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0100] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A laser radar calibration method, wherein: The method comprises: Initialize the lidar and get at least the first YAW angle calibrated by the lidar; Acquiring point cloud data collected by the laser radar according to a preset calibration field, wherein the preset calibration field includes at least a collection plate, and the collection plate is located on either side of the lane; Obtaining high-precision map data of the area where the preset calibration location is located, wherein the high-precision map data includes lane line data of the lane; The obtaining of high-precision map data of the area where the preset calibration location is located, wherein the high-precision map data includes lane line data of a lane, further comprises: Determine whether the offline high-precision map data of the area where the preset calibration location is located is updated; If it is determined that the offline high-precision map data of the area where the preset calibration location is located has not been updated, updating the lane line data according to the point cloud data collected by the lidar; Determining a second YAW angle based on a matching result between the lane line data and the point cloud data of the acquisition board in the vehicle coordinate system; Obtaining a YAW angle error parameter according to a difference between the first YAW angle and the second YAW angle; Calibrate the laser radar according to the YAW angular error parameter; The invention also includes the steps of dynamically calibrating the laser radar: Based on the multiple sets of vehicle data identified by the visual sensor and the pre-loaded high-precision map data, the YAW angle error parameters of the lidar are adjusted in real time to make the vehicle travel within the target lane. The multiple sets of vehicle data are used as markers corresponding to the point cloud data collected by the lidar. The error values conform to the normal distribution and the average value is used as the YAW angle error parameter.

2. The method according to claim 1, wherein: The acquisition boards include at least two, and the two acquisition boards are disposed opposite to each other on both sides of the lane. The second YAW angle is determined based on the matching result of the lane line data and the point cloud data of the acquisition boards in the vehicle coordinate system, including: Segmenting the point cloud data according to the positions of the two acquisition boards to obtain corresponding first point cloud data; Projecting the first point cloud data to the vehicle coordinate system and extracting point cloud data of the target boundary; In the process of matching the point cloud data of the target boundary with the lane line data, adjusting the YAW angle to change the position of the point cloud data of the target boundary so that the point cloud data of the target boundary coincides with the lane line data; The second YAW angle is determined according to the result of adjusting to the overlapping position.

3. The method according to claim 2, wherein: The obtaining of a YAW angle error parameter according to a difference between the first YAW angle and the second YAW angle includes: Drive forward on the target lane to obtain the second YAW angle corresponding to the Kth moment; Driving in the target lane in the opposite direction, the second YAW angle corresponding to the Nth moment is obtained; A YAW angle error parameter is obtained according to the second YAW angle corresponding to the Kth moment and the second YAW angle corresponding to the Nth moment, where K and N are natural numbers, and an average value of the YAW angle error parameters at multiple moments is used as the YAW angle error parameter.

4. The method according to claim 2, wherein: The point cloud data of the target boundary includes point cloud data of the long side on the acquisition board, and the long side coincides with a portion of a lane line in a preset calibration field.

5. The method according to claim 1, wherein: The step of obtaining point cloud data collected by the laser radar according to a preset calibration field, wherein the preset calibration field includes at least a collection plate, and the collection plate is located on either side of the lane, including: The point cloud data recognized by the laser radar at the current moment is segmented according to the current position and orientation of the vehicle, the initial rough calibration parameters of the laser radar, and a preset error range.

6. A laser radar calibration device, wherein: The device comprises: An initialization module is used to initialize the laser radar and obtain at least the first YAW angle calibrated by the laser radar; A first acquisition module is configured to acquire point cloud data collected by the laser radar according to a preset calibration field, wherein the preset calibration field includes at least an acquisition board, and the acquisition board is located on either side of the lane; A second acquisition module is configured to acquire high-precision map data of the area where the preset calibration location is located, wherein the high-precision map data includes lane line data of the lane; The obtaining of high-precision map data of the area where the preset calibration location is located, wherein the high-precision map data includes lane line data of a lane, further comprises: Determine whether the offline high-precision map data of the area where the preset calibration location is located is updated; If it is determined that the offline high-precision map data of the area where the preset calibration location is located has not been updated, updating the lane line data according to the point cloud data collected by the lidar; The obtaining of high-precision map data of the area where the preset calibration location is located, wherein the high-precision map data includes lane line data of a lane, further comprises: Determine whether the offline high-precision map data of the area where the preset calibration location is located is updated; If it is determined that the offline high-precision map data of the area where the preset calibration location is located has not been updated, updating the lane line data according to the point cloud data collected by the lidar; a matching module, configured to determine a second YAW angle based on a matching result between the lane line data and the point cloud data of the acquisition board in a vehicle coordinate system; a difference calculation module, configured to obtain a YAW angle error parameter according to a difference between the first YAW angle and the second YAW angle; A calibration module, configured to calibrate the laser radar according to the YAW angular error parameter; Also includes: Based on the multiple sets of vehicle data identified by the visual sensor and the pre-loaded high-precision map data, the YAW angle error parameters of the lidar are adjusted in real time to make the vehicle travel within the target lane. The multiple sets of vehicle data are used as markers corresponding to the point cloud data collected by the lidar. The error values conform to the normal distribution and the average value is used as the YAW angle error parameter.

7. An electronic device comprising: processor; as well as A memory arranged to store computer-executable instructions, which, when executed, cause the processor to perform the method of any one of claims 1 to 5.

8. A computer-readable storage medium storing one or more programs, wherein when the one or more programs are executed by an electronic device including a plurality of application programs, the electronic device executes the method according to any one of claims 1 to 5.

Images