A driving device positioning method, computer-readable storage medium, and driving device

Abstract

The present invention relates to the field of computer technology, and specifically provides a driving device positioning method, a computer-readable storage medium, and a driving device. To this end, the driving device positioning method of the present invention includes: obtaining multiple point cloud data subsets and grid unit information obtained by pre-gridding the initial global point cloud data according to the spatial position by the server, each point cloud data subset corresponding to a grid unit; obtaining the current position of the driving device and the current point cloud data; determining some grid units for constructing prior point cloud data based on the current position and grid unit information; matching the current point cloud data with the prior point cloud data to obtain the positioning information of the driving device. By obtaining the segmented global point cloud data and constructing the prior point cloud data, this method avoids the full loading of the initial local point cloud data, which is beneficial to reducing memory usage and improving positioning matching efficiency, accuracy, and robustness.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and specifically provides a driving device positioning method, a computer-readable storage medium, and a driving device. Background Art

[0002] With the development of artificial intelligence technology, unmanned vehicles and autonomous driving have received great attention. In the application scenarios of unmanned vehicles and autonomous driving, vehicle positioning and map acquisition play an important role in realizing the autonomous movement of driving equipment.

[0003] When acquiring existing positioning maps, the driving device usually needs to fully load the processed point cloud map. When the data volume is large, there is insufficient memory and memory overflow is prone to occur. In addition, when performing positioning matching based on the point cloud map, the larger data volume usually requires more processor resources, resulting in low positioning matching efficiency, low accuracy, and poor robustness. Summary of the Invention

[0004] The present invention aims to solve the above technical problems, namely, to solve the problems that existing driving equipment positioning requires full loading of point cloud maps, occupies large memory, has low positioning matching efficiency, low accuracy and poor robustness.

[0005] In a first aspect, the present invention provides a driving device positioning method, which is applied to a driving device, comprising:

[0006] Obtaining segmented global point cloud data and grid unit information, wherein the segmented global point cloud data is obtained by pre-gridding the initial global point cloud data according to spatial positions by the server, and the segmented global point cloud data includes multiple point cloud data subsets, each of which corresponds to a grid unit;

[0007] Obtaining a current position of the driving device and current point cloud data at the current position, and determining a target grid cell corresponding to the current position according to the current position and the grid cell information;

[0008] Acquire the point cloud data subset corresponding to the target grid cell and a preset number of surrounding grid cells adjacent to the target grid cell;

[0009] Constructing prior point cloud data based on the point cloud data subset corresponding to the target grid unit and the point cloud data subsets corresponding to the preset number of surrounding grid units;

[0010] The current point cloud data is matched with the prior point cloud data to obtain positioning information of the driving device.

[0011] In some embodiments, the grid unit information includes location information of the grid unit; and the target grid unit is determined from a plurality of the grid units according to the current location and the location information of the grid unit.

[0012] or,

[0013] The grid cell information includes position information of a starting grid cell, a length of the grid cell, a width of the grid cell, and a grid cell number; calculating position information of each of the remaining grid cells except the starting grid cell based on the position information of the starting grid cell, the length of the grid cell, the width of the grid cell, and the grid cell number;

[0014] The target grid unit is determined from the plurality of grid units according to the current position and the position information of each of the grid units.

[0015] In some embodiments, before determining the target grid unit corresponding to the current position according to the current position and the grid unit information, the method further includes:

[0016] Determining whether the driving device is within an area corresponding to the segmented global point cloud data according to the current position;

[0017] If not, re-acquire the current position of the driving device.

[0018] In some embodiments, before determining the target grid unit corresponding to the current position according to the current position and the grid unit information, the method further includes:

[0019] Determining whether to update the historical priori point cloud data based on the current position and the historical target grid unit; the historical target grid unit is the target grid unit determined by the previous positioning of the driving device, and the historical priori point cloud data corresponds to the historical target grid unit;

[0020] If not, determine the positioning information of the driving device according to the current point cloud data and the historical priori point cloud data.

[0021] In some embodiments, the current point cloud data and the prior point cloud data are matched using a normal distribution transformation registration algorithm to obtain positioning information of the driving device.

[0022] In a second aspect, the present invention provides a driving device positioning method, which is applied to a server and includes:

[0023] Obtaining initial global point cloud data of the driving environment of the driving equipment;

[0024] Gridding the initial global point cloud data according to spatial positions to obtain a plurality of point cloud data subsets, using the plurality of point cloud data subsets as segmented global point cloud data, each of the point cloud data subsets corresponding to a grid unit;

[0025] The grid unit information of each grid unit is recorded, and the segmented global point cloud data and the grid unit information are sent to the driving device.

[0026] In some embodiments, after acquiring the initial global point cloud data of the driving environment of the driving device and before meshing the initial global point cloud data according to spatial positions, the method further includes:

[0027] The initial global point cloud data is downsampled using a voxel filtering algorithm, so as to perform grid division based on the downsampled initial global point cloud data.

[0028] In some embodiments, obtaining initial global point cloud data of the driving environment of the driving device includes:

[0029] Acquire multi-frame point cloud data of the driving environment of the driving device;

[0030] Registering the multi-frame point cloud data to obtain the initial global point cloud data;

[0031] or,

[0032] Acquiring multi-frame point cloud data, inertial measurement data, and global positioning system data of the driving environment of the driving device;

[0033] The initial global point cloud data is acquired by fusing the multi-frame point cloud data, the inertial measurement data, and the global positioning system data.

[0034] In a third aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, any one of the above-mentioned driving device positioning methods is implemented.

[0035] In a fourth aspect, the present invention provides a driving device, which includes a driving device body, a memory and a controller, wherein the memory stores a computer program, and when the computer program is executed by the controller, any one of the above-mentioned driving device positioning methods is implemented.

[0036] When the above technical solution is adopted, the present invention, when applied to a driving device, can obtain segmented global point cloud data and grid cell information. The segmented global point cloud data is obtained by pre-gridding the initial global point cloud data according to spatial position on a server. The segmented global point cloud data includes multiple point cloud data subsets, each corresponding to a grid cell. The present invention also obtains the current position of the driving device and the current point cloud data at the current position, determines the target grid cell corresponding to the current position based on the current position and the grid cell information, obtains the point cloud data subsets corresponding to the target grid cell and a preset number of surrounding grid cells adjacent to the target grid cell, constructs prior point cloud data based on the point cloud data subset corresponding to the target grid cell and the point cloud data subsets corresponding to the preset number of surrounding grid cells, and matches the current point cloud data with the prior point cloud data to obtain positioning information for the driving device. By obtaining the segmented global point cloud data, grid cell information, and constructing the prior point cloud data, the present method avoids loading the entire initial global point cloud data, thereby reducing memory usage and improving positioning matching efficiency, accuracy, and robustness. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The preferred embodiments of the present invention are described below with reference to the accompanying drawings, in which:

[0038] Figure 1 1 is a flow chart of a driving device positioning method applied to a server provided by an embodiment of the present invention;

[0039] Figure 2 It is the initial global point cloud map provided by the present invention;

[0040] Figure 3 It is a top view of the initial global point cloud map after grid division provided by the present invention;

[0041] Figure 4 is a flow chart of a driving device positioning method applied to a server provided by another embodiment of the present invention;

[0042] Figure 5 A driving device positioning method applied to a driving device is provided in an embodiment of the present invention;

[0043] Figure 6 It is a flowchart of a driving device positioning method applied to a driving device provided by another embodiment of the present invention. DETAILED DESCRIPTION

[0044] Some embodiments of the present invention are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0045] When acquiring existing positioning maps, the driving device usually needs to fully load the processed point cloud map. When the data volume is large, there is insufficient memory and memory overflow is prone to occur. In addition, when performing positioning matching based on the point cloud map, the larger data volume usually requires more processor resources, resulting in low positioning matching efficiency, low accuracy, and poor robustness.

[0046] In view of this, the present invention provides a method for positioning a driving device. A server pre-grids initial global point cloud data of the driving device's driving environment based on spatial position to obtain segmented global point cloud data. The segmented global point cloud data includes multiple point cloud data subsets, each corresponding to a grid cell. The server records grid cell information for each grid cell and transmits the segmented global point cloud data and grid cell information to the driving device. The driving device then obtains its current position and collects its current point cloud data at that position. Based on the current position and grid cell information, it determines a subset of grid cells. Prior point cloud data is constructed based on the point cloud data subsets corresponding to the subset of grid cells, and matching positioning is performed based on the current point cloud data and the prior point cloud data. This method avoids loading the entire initial global point cloud data, which helps improve positioning matching efficiency, accuracy, and robustness.

[0047] See also Figure 1 As shown, Figure 1 : is a flow chart of a driving device positioning method applied to a server provided by the present invention, which may include:

[0048] Step S11: Acquire initial global point cloud data of the driving environment of the driving device;

[0049] Step S12: Gridding the initial global point cloud data according to the spatial position to obtain multiple point cloud data subsets, and using the multiple point cloud data subsets as the segmented global point cloud data, each point cloud data subset corresponds to a grid unit;

[0050] Step S13: Record the grid cell information of each grid cell, and send the segmented global point cloud data and grid cell information to the driving device.

[0051] In some embodiments, step S11 may specifically include:

[0052] Acquire multi-frame point cloud data of the driving environment of the driving equipment;

[0053] Multi-frame point cloud data are registered to obtain initial global point cloud data.

[0054] Among them, multi-frame point cloud data of the driving environment of the driving equipment collected by the laser radar can be obtained.

[0055] In some embodiments, the NDT (Normal Distributions Transform) Mapping algorithm can be used to align the multi-frame point cloud data, so that the multi-frame point cloud data can be spliced ​​into an initial global point cloud map in a unified coordinate system, such as Figure 2 As shown in Figure 3, the initial global point cloud data is obtained.

[0056] In other embodiments, in order to improve the accuracy of the initial global point cloud data, step S11 may also be specifically as follows:

[0057] Acquire multi-frame point cloud data, inertial measurement data, and global positioning system data of the driving environment of the driving equipment;

[0058] Initial global point cloud data is obtained by fusing multi-frame point cloud data, inertial measurement data and global positioning system data.

[0059] Among them, multi-frame point cloud data of the driving environment of the driving device collected by LiDAR can be obtained. Inertial measurement data collected by an Inertial Measurement Unit (IMU) can be obtained, where the inertial measurement data can include three-axis attitude angles and acceleration. Global Positioning System data (GPS), i.e., position data, provided by the Global Positioning System (GPS), can be obtained.

[0060] The NDT (Normal Distributions Transform) Mapping algorithm can be used to align multi-frame point cloud data, so that the multi-frame point cloud data can be spliced ​​into a global point cloud map in a unified coordinate system. By fusing inertial measurement data and global positioning system data, the displacement matrix and rotation matrix of the point cloud in the global point cloud map are further optimized based on the fusion results of the inertial measurement data and the global positioning system data. Among them, the specific implementation method of fusing inertial measurement data and global positioning system data and further optimizing the displacement matrix and rotation matrix of the point cloud in the global point cloud map based on the fusion results can be implemented using existing technologies in the field and will not be described in detail here.

[0061] In some embodiments, step S12 can be specifically to set the length and width of the grid unit; in a plane parallel to the ground, the initial global point cloud data is divided according to the length and width of the grid unit to obtain multiple point cloud data subsets, and the multiple point cloud data subsets are used as the segmented global point cloud data, and each point cloud data subset corresponds to a grid unit.

[0062] You can select any grid cell as the starting grid cell, and number each grid cell m_n in the order from left to right in the horizontal direction and from top to bottom in the vertical direction, indicating the grid cell in the mth row and nth column. For details, see Figure 3 shown.

[0063] In some embodiments, the grid unit information may include position information of a starting grid unit, a length of the grid unit, a width of the grid unit, and a grid unit number.

[0064] In other embodiments, the position information of each grid cell may be directly calculated after the initial global point cloud data is gridded in step S12, and the position information of each grid cell may be directly recorded in step S13.

[0065] Among them, see Figure 3 As shown, the coordinates of the upper left vertex of the grid cell numbered 1_1 can be obtained. For the remaining grid cells, the coordinates of each vertex of the remaining grid cells can be determined based on the grid cell numbers, lengths, and widths of the remaining grid cells, thereby obtaining the position information of each grid cell.

[0066] In some embodiments, sending the segmented global point cloud data and grid cell information to the driving device in step S13 can be specifically as follows: for grid cells with point clouds, generating a point cloud file based on the grid cell information of the grid cell and a subset of point cloud data corresponding to the grid cell, and multiple grid cells can obtain multiple point cloud files; and compressing the multiple point cloud files and sending them to the driving device.

[0067] In some other embodiments, the initial point cloud data may also be filtered. For details, see Figure 4 As shown, Figure 4 FIG. 1 is a flow chart of a driving device positioning method applied to a server provided in another embodiment of the present invention, which may include:

[0068] Step S41: Acquire initial global point cloud data of the driving environment of the driving device;

[0069] Step S42: downsampling the initial global point cloud data using a voxel filtering algorithm;

[0070] Step S43: gridding the downsampled initial global point cloud data according to the spatial position to obtain multiple point cloud data subsets, and using the multiple point cloud data subsets as the segmented global point cloud data, each point cloud data subset corresponds to a grid unit;

[0071] Step S44: Record the grid cell information of each grid cell, and send the segmented global point cloud data and grid cell information to the driving device.

[0072] Among them, steps S41, S43 and S44 can be implemented in the same manner as steps S11-S13, and are not described here for the sake of brevity. For details, please refer to the above description.

[0073] Among them, when the voxel filtering algorithm is used to downsample the initial global point cloud data, a cube can be set to wrap the initial global point cloud data; according to the set resolution, the cube is divided into multiple small cubes; for each small cube, the center of mass of the small cube is calculated, and the data of the point corresponding to the center of mass is used to replace all the point cloud data in the small cube, or, when there is no corresponding point for the calculated center of mass, the data of the point close to the center of mass is used to replace all the point cloud data in the small cube, so that the point cloud data can be reduced by downsampling.

[0074] See also Figure 5 As shown, Figure 5 A driving device positioning method applied to a driving device provided by an embodiment of the present invention may include:

[0075] Step S51: obtaining segmented global point cloud data and grid unit information. The segmented global point cloud data is obtained by the server pre-gridding the initial global point cloud data according to spatial positions. The segmented global point cloud data includes multiple point cloud data subsets, each point cloud data subset corresponding to a grid unit.

[0076] Step S52: obtaining the current position of the driving device and the current point cloud data at the current position, and determining the target grid cell corresponding to the current position according to the current position and the grid cell information;

[0077] Step S53: obtaining a point cloud data subset corresponding to the target grid cell and a preset number of surrounding grid cells adjacent to the target grid cell;

[0078] Step S54: constructing prior point cloud data based on the point cloud data subset corresponding to the target grid cell and the point cloud data subsets corresponding to a preset number of surrounding grid cells;

[0079] Step S55: Match the current point cloud data with the prior point cloud data to obtain the positioning information of the driving device.

[0080] In some embodiments, obtaining the current location of the driving device in step S52 may specifically be obtaining the current location of the driving device using GPS.

[0081] In some embodiments, the grid cell information may include location information of the grid cell, and determining the target grid cell corresponding to the current position based on the current position and the grid cell information in step S52 may specifically be determining the target grid cell from multiple grid cells based on the current position and the location information of the grid cell. The target grid cell is the grid cell where the current position is located.

[0082] In other embodiments, the grid cell information may include the position information of the starting grid cell, the length of the grid cell, the width of the grid cell, and the grid cell number; in step S52, determining the target grid cell corresponding to the current position based on the current position and the grid cell information may specifically be:

[0083] Calculate the position information of all grid cells except the starting grid cell according to the position information of the starting grid cell, the length of the grid cell, the width of the grid cell, and the grid cell number;

[0084] A target grid cell is determined from the plurality of grid cells according to the current position and the position information of each grid cell.

[0085] In some embodiments, step S53 may specifically determine eight surrounding grid cells adjacent to the target grid cell from multiple grid cells, and obtain a point cloud data subset corresponding to the target grid cell and the eight surrounding grid cells adjacent to the target grid cell. This ensures that the point cloud features near the current position and the surrounding point cloud features are included, making the positioning matching more accurate and improving the robustness and accuracy of positioning. As an example, Figure 3 As shown, when the target grid unit is determined to be 4_4, the surrounding grid units numbered 3_3, 3_4, 3_5, 4_3, 4_5, 5_3, 5_4 and 5_5 can be loaded simultaneously.

[0086] It should be noted that the preset number of loaded peripheral grid units can be set according to the positioning accuracy requirement and the length and width of the set grid unit, wherein the preset number can be a positive integer greater than or equal to zero.

[0087] In an embodiment of the present invention, by executing step S54, prior point cloud data is constructed based on the target grid unit determined from multiple grid units and a preset number of surrounding grid units, which can effectively reduce the loaded point cloud data and thus help improve the positioning matching efficiency.

[0088] In some embodiments, step S55 may specifically be to use a Normal Distribution Transform Matching (NDT Matching) algorithm to match the current point cloud data with the prior point cloud data to obtain the positioning information of the driving device.

[0089] See also Figure 6 As shown, Figure 6 FIG. 1 is a flow chart of a method for positioning a driving device applied to a driving device provided by another embodiment of the present invention, which may include:

[0090] Step S61: Obtaining segmented global point cloud data and grid unit information. The segmented global point cloud data is obtained by the server pre-gridding the initial global point cloud data according to spatial positions. The segmented global point cloud data includes multiple point cloud data subsets, each point cloud data subset corresponding to a grid unit.

[0091] Step S62: Acquire the current position of the driving device and the current point cloud data at the current position;

[0092] Step S63: determining whether the driving device is within the area corresponding to the segmented global point cloud data based on the current position;

[0093] If not, return to step S62 to reacquire the current position information of the driving device; if yes, execute step S64;

[0094] Step S64: determining whether to update the historical priori point cloud data based on the current position and the historical target grid unit; the historical target grid unit is the target grid unit determined by the previous positioning of the driving device, and the historical priori point cloud data corresponds to the historical target grid unit;

[0095] If no, execute step S65; if yes, execute steps S66-S69;

[0096] Step S65: If not, determine the positioning information of the driving device based on the current point cloud data and the historical prior point cloud data;

[0097] Step S66: determining a target grid cell corresponding to the current position according to the current position and the grid cell information;

[0098] Step S67: obtaining a point cloud data subset corresponding to the target grid cell and a preset number of surrounding grid cells adjacent to the target grid cell;

[0099] Step S68: constructing prior point cloud data based on the point cloud data subset corresponding to the target grid cell and the point cloud data subsets corresponding to a preset number of surrounding grid cells;

[0100] Step S69: Match the current point cloud data with the prior point cloud data to obtain the positioning information of the driving device.

[0101] Among them, steps S61, S62 and S66-S69 can be implemented in the same manner as steps S51-S55. For the sake of brevity, they are not repeated here. For details, please refer to the description above.

[0102] In some embodiments, step S63 can be specifically to obtain the position coordinates of the driving device at the current position, and determine whether the driving device is currently in the area corresponding to the segmented global point cloud data based on the position coordinates of the driving device; if so, execute step S64; if not, return to execute step S62, and loop through steps S62 and S63 until the driving device enters the area corresponding to the segmented global point cloud data.

[0103] In some embodiments, step S64 may specifically determine whether the current position is within the area corresponding to the historical target grid unit. If so, there is no need to update the historical priori point cloud data; if not, the historical priori point cloud data needs to be updated.

[0104] In other embodiments, when it is determined that the current position is not within the area corresponding to the historical target grid unit, it is further determined whether the current position is within the buffer zone corresponding to the historical target grid unit, so as to determine whether the historical prior point cloud data needs to be updated based on the determination result. In some embodiments, determining whether the current position is within the buffer zone corresponding to the historical target grid unit can be specifically as follows: obtaining the position information of the historical target grid unit determined by the previous positioning of the driving device, wherein the position information of the historical target grid unit can be represented by its four vertex coordinates, so that the border of the historical target grid unit can be determined; determining whether the distance between the current position and the border of the historical target grid unit is less than a preset distance threshold; if so, it can be determined that the current position is within the buffer zone corresponding to the historical target grid unit determined by the previous positioning of the driving device, wherein the buffer zone is an area within the preset distance threshold from the border of the historical target grid unit.

[0105] When it is determined that the current position is within the buffer corresponding to the historical target grid cell determined by the driving device during the previous positioning, step S65 is executed to continue using the historical prior point cloud data determined by the previous positioning without updating the prior point cloud data. When the current position is not within the historical target grid cell and is not within the buffer corresponding to the historical target grid cell, steps S66-S69 may be executed to update the historical prior point cloud data based on the current position, and then match positioning based on the updated prior point cloud data. In some embodiments, when it is determined that the historical prior point cloud data needs to be updated based on the current position, the point cloud data subset corresponding to the invalid grid cell may also be deleted to avoid occupying storage resources.

[0106] It will be understood by those skilled in the art that all or part of the processes in the methods for implementing the above embodiments of the present invention may also be accomplished by instructing related hardware through a computer program. The computer program may be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of each of the above method embodiments may be implemented. The computer program includes computer program code, which may be in source code form, object code form, executable file, or some intermediate form. The computer-readable storage medium may include any entity or device, medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electric carrier signal, telecommunication signal, and software distribution medium, etc., which may carry the computer program code.

[0107] Another aspect of the present invention further provides a computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements the driving device positioning method described in any of the aforementioned embodiments applied to a server, or implements the driving device positioning method described in any of the aforementioned embodiments applied to a driving device. The computer-readable storage medium may be a storage device formed by various electronic devices. Optionally, in embodiments of the present invention, the computer-readable storage medium is a non-transitory computer-readable storage medium.

[0108] In another aspect of the present invention, a driving device is provided, which may include a driving device body, a memory and a controller, wherein a computer program is stored in the memory. When the computer program is executed by the controller, the driving device positioning method described in any of the above embodiments applied to the server is implemented, or the driving device positioning method described in any of the above embodiments applied to the driving device is implemented.

[0109] In some embodiments, the driving device may further include a laser radar and an inertial measurement sensor disposed on the driving device body.

[0110] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

Claims

1. A driving equipment positioning method, characterized in that: Applied to driving equipment, including: Obtaining segmented global point cloud data and grid unit information, wherein the segmented global point cloud data is obtained by pre-gridding the initial global point cloud data according to spatial positions by the server, and the segmented global point cloud data includes multiple point cloud data subsets, each of which corresponds to a grid unit; Obtaining a current position of the driving device and current point cloud data at the current position, and determining a target grid cell corresponding to the current position according to the current position and the grid cell information; Acquire the point cloud data subset corresponding to the target grid cell and a preset number of surrounding grid cells adjacent to the target grid cell; Constructing prior point cloud data based on the point cloud data subset corresponding to the target grid unit and the point cloud data subsets corresponding to the preset number of surrounding grid units; The current point cloud data is matched with the prior point cloud data to obtain positioning information of the driving device.

2. The method according to claim 1, characterized in that The grid unit information includes location information of the grid unit; determining the target grid unit from the plurality of grid units according to the current location and the location information of the grid unit; or, The grid cell information includes position information of a starting grid cell, a length of the grid cell, a width of the grid cell, and a grid cell number; calculating position information of each of the remaining grid cells except the starting grid cell based on the position information of the starting grid cell, the length of the grid cell, the width of the grid cell, and the grid cell number; The target grid unit is determined from the plurality of grid units according to the current position and the position information of each of the grid units.

3. The method according to claim 1, characterized in that Before determining the target grid unit corresponding to the current position according to the current position and the grid unit information, the method further includes: Determining whether the driving device is within an area corresponding to the segmented global point cloud data according to the current position; If not, re-acquire the current position of the driving device.

4. The method according to claim 1, wherein Before determining the target grid unit corresponding to the current position according to the current position and the grid unit information, the method further includes: Determining whether to update the historical priori point cloud data based on the current position and the historical target grid unit; the historical target grid unit is the target grid unit determined by the previous positioning of the driving device, and the historical priori point cloud data corresponds to the historical target grid unit; If not, determine the positioning information of the driving device according to the current point cloud data and the historical priori point cloud data.

5. The method according to any one of claims 1 to 4, characterized in that The current point cloud data and the prior point cloud data are matched using a normal distribution transformation registration algorithm to obtain positioning information of the driving device.

6. A driving equipment positioning method, characterized in that: Applicable to servers, including: Obtaining initial global point cloud data of the driving environment of the driving equipment; Gridding the initial global point cloud data according to spatial positions to obtain a plurality of point cloud data subsets, using the plurality of point cloud data subsets as segmented global point cloud data, each of the point cloud data subsets corresponding to a grid unit; Record the grid unit information of each grid unit, and send the segmented global point cloud data and the grid unit information to a driving device, so that the driving device performs the driving device positioning method according to any one of claims 1 to 5.

7. The method according to claim 6, characterized in that After acquiring the initial global point cloud data of the driving environment of the driving device and before meshing the initial global point cloud data according to spatial positions, the method further includes: The initial global point cloud data is downsampled using a voxel filtering algorithm, so as to perform grid division based on the downsampled initial global point cloud data.

8. The method according to claim 6 or 7, characterized in that The obtaining of initial global point cloud data of the driving environment of the driving device includes: Acquire multi-frame point cloud data of the driving environment of the driving device; Registering the multi-frame point cloud data to obtain the initial global point cloud data; or, Acquiring multi-frame point cloud data, inertial measurement data, and global positioning system data of the driving environment of the driving device; The initial global point cloud data is acquired by fusing the multi-frame point cloud data, the inertial measurement data, and the global positioning system data.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the driving device positioning method described in any one of claims 1 to 5 or the driving device positioning method described in any one of claims 6 to 8 is implemented.

10. A driving device, characterized in that: The invention comprises a driving device body, a memory and a controller, wherein the memory stores a computer program, and when the computer program is executed by the controller, the driving device positioning method described in any one of claims 1 to 5 or the driving device positioning method described in any one of claims 6 to 8 is implemented.

Images