A multi-sensor fusion positioning method and device for a multi-layer tunnel scene, an electronic device, and a storage medium

Abstract

The present application relates to a kind of multi-sensor fusion positioning methods for multilayer roadway scene, comprising: collecting the attitude data of inertial measurement unit in different time periods, the point cloud data of laser radar and UWB beacon data;The point cloud data is introduced into the attitude data in SLAM algorithm, to generate several first global maps in different time periods;Several first global maps are merged to generate a second global map;The second global map is split to generate several topological sub-maps;According to the UWB beacon data, vehicle positioning is obtained.And the device, electronic equipment and storage medium suitable for method.The multi-sensor fusion positioning method for multilayer roadway scene, device, electronic equipment and storage medium provided by the present application solve the problems that field surveying and mapping, instrument measurement manpower cost is larger, not suitable for large-scale underground scene use;Laser radar cannot be started at any position.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of positioning systems, in particular to a multi-sensor fusion positioning method and device for a multi-layer tunnel scene, an electronic device and a storage medium. BACKGROUND

[0002] High-precision positioning technology is not only the key to the safe driving of autonomous vehicles, but also the basis for realizing autonomous navigation of vehicles. Through high-precision positioning technology, autonomous vehicles can accurately know their position on the road, thereby safely avoiding obstacles and accurately performing driving tasks. In the face of multi-layer tunnel scenes in mines, multi-sensor fusion positioning technology faces new challenges.

[0003] In the prior art, when implementing multi-sensor data fusion positioning, the global pose of the ultra-wideband beacon, i.e., the UWB beacon global pose, is often obtained through field mapping and instrument measurement. This method has a large labor cost and is not suitable for large-scale underground scenes. Laser radar is also used to achieve local accurate positioning, but it cannot start at any position.

[0004] Therefore, the prior art has defects and needs to be improved and developed. SUMMARY

[0005] The embodiments of the present application provide a solution to the technical problem that in the prior art, when implementing multi-sensor data fusion positioning, the global pose of the ultra-wideband beacon, i.e., the UWB beacon global pose, is often obtained through field mapping and instrument measurement. This method has a large labor cost and is not suitable for large-scale underground scenes. Laser radar is also used to achieve local accurate positioning, but it cannot start at any position.

[0006] In a first aspect, the embodiments of the present application provide a multi-sensor fusion positioning method for a multi-layer tunnel scene, comprising:

[0007] Collecting attitude data of an inertial measurement unit for detecting a tunnel environment, point cloud data of a laser radar, and UWB beacon data arranged in a tunnel at different time periods and located on a vehicle;

[0008] Import the point cloud data and the attitude data into the SLAM algorithm to generate a plurality of first global maps of different time periods; wherein the method for generating a plurality of first global maps of different time periods comprises: constructing a plurality of layers of point cloud maps according to the point cloud data; labeling a layer number for each layer of the point cloud map according to a tunnel hierarchical relationship; sequentially outputting a last odometry pose of a previous layer of point cloud maps and a first odometry pose of a next layer of point cloud maps in adjacent layer numbers of the point cloud maps; fusing a plurality of layers of point cloud maps to generate the first global map; and importing the last odometry pose of the previous layer of point cloud maps and the first odometry pose of the next layer of point cloud maps in adjacent layer numbers of the point cloud maps into an ICP algorithm to generate the first global map through point-to-plane ICP;

[0009] Merge a plurality of the first global maps to generate a second global map;

[0010] Split the second global map to generate a plurality of topological sub-maps;

[0011] Obtain a vehicle position according to the UWB beacon data.

[0012] Further, the method for merging a plurality of the first global maps to generate a second global map comprises: fusing map segments of overlapping regions in a plurality of the first global maps through a map merging method to generate the second global map.

[0013] Further, the method for obtaining a vehicle accurate position according to the UWB beacon data comprises:

[0014] Obtain a vehicle coarse position according to the UWB beacon data.

[0015] Match the vehicle coarse position, real-time laser radar data of the vehicle, and the second global map to obtain a vehicle position.

[0016] Further, the method for obtaining a vehicle position according to the UWB beacon data further comprises: updating the position of the vehicle in the topological sub-map according to the attitude data of the inertial measurement unit.

[0017] Further, the method for obtaining a vehicle coarse position according to the UWB beacon data comprises:

[0018] Obtain a P point with a reflection intensity value greater than A according to a reflection intensity of a reflective sticker pasted on the UWB beacon, and the reflective sticker is provided with a label number according to a sequence of vehicles entering a tunnel; wherein the value of A is a critical value for distinguishing the reflective sticker from other reflective objects in the tunnel environment.

[0019] According to the P point, a KD-Tree is used for a nearest neighbor search, n points closest to the P point are obtained, and points in the n points with a distance less than r from the P point are clustered in a set Q; wherein n is a natural number greater than 1, and r is a numerical value of the longest straight line segment on the surface for reflecting light in the reflective sticker;

[0020] If the number of elements in the set Q continues to increase, any point in the set Q other than the P point is selected as a point K, and the above step is repeated until the number of elements in the set Q no longer increases;

[0021] If the number of elements in the set Q no longer increases, the nearest neighbor search is ended, and the point cloud intensity of the reflective sticker is obtained.

[0022] The point cloud intensity of the reflective sticker outputs the three-dimensional coordinates of the center point of the reflective sticker and the label number of the reflective sticker, and obtains the coarse position of the vehicle.

[0023] In a second aspect, the embodiment of the present application provides a multi-sensor fusion positioning device for a multi-layer tunnel scene, comprising:

[0024] A collection module is configured to collect attitude data of an inertial measurement unit located on a vehicle and used for detecting a tunnel environment, point cloud data of a laser radar, and UWB beacon data arranged at equal intervals in a tunnel at different time periods.

[0025] A first generation module is configured to import the point cloud data and the attitude data into a SLAM algorithm to generate a plurality of first global maps at different time periods; wherein the method for generating a plurality of first global maps at different time periods comprises: constructing a plurality of point cloud maps according to the point cloud data; labeling a layer number for each layer of the point cloud maps according to a tunnel hierarchical relationship; sequentially outputting a last odometry pose of an upper layer point cloud map and a first odometry pose of a lower layer point cloud map in point cloud maps with adjacent layer numbers; fusing a plurality of point cloud maps to generate the first global map; and importing the last odometry pose of the upper layer point cloud map and the first odometry pose of the lower layer point cloud map in the point cloud maps with adjacent layer numbers into an ICP algorithm to generate the first global map through point-to-plane ICP.

[0026] A second generation module is configured to merge a plurality of the first global maps to generate a second global map.

[0027] A third generation module is configured to split the second global map to generate a plurality of topological sub-maps.

[0028] An obtaining module is configured to obtain vehicle positioning according to the UWB beacon data.

[0029] In a third aspect, the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the multi-sensor fusion positioning method for a multi-layer tunnel scene.

[0030] In a fourth aspect, the present application provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program, when executed by a processor, implements the multi-sensor fusion positioning method for a multi-layer tunnel scene.

[0031] Advantages:

[0032] From the above scheme, the present application provides a multi-sensor fusion positioning method, device, electronic device and storage medium for a multi-layer tunnel scene. By fusing multi-sensor data, the inertial measurement unit, laser radar and UWB beacon data are fused, and high-precision positioning can be achieved in a multi-layer tunnel complex environment. Through data acquisition and map generation at different time periods, real-time updating of vehicle attitude data, adaptation to changes in tunnel structure in dynamic environments such as mines, enhancement of system flexibility, and guarantee of dynamic response capability and precision of the positioning system. Through systematic design, compared with the traditional method relying on a large amount of manual surveying and mapping, the combination of UWB beacon and multi-sensor greatly reduces the labor and time cost, is suitable for large-scale mine scenes, reduces the cost of manual field surveying and instrument measurement, and improves the applicability of large-scale underground scenes. A variety of sensors and fusion algorithms are used, combined with UWB beacon, laser radar and inertial measurement unit. The system can correct and compensate between multiple sensor data, has stronger anti-interference and error correction capability, enhances the anti-interference capability and robustness of the system in complex environments, and guarantees the stability and reliability of positioning.

[0033] It should be understood that all combinations of the foregoing concepts and additional concepts described in greater detail below (provided such concepts are not mutually inconsistent) are contemplated as being part of the inventive subject matter.

[0034] The foregoing and other aspects, embodiments and features of the present teachings can be better understood from the following detailed description taken in conjunction with the accompanying drawings. Additional features of the present teachings will be described or will become apparent in the course of the following detailed description. BRIEF DESCRIPTION OF DRAWINGS

[0035] The drawings are not drawn to scale. In the drawings, like reference numerals can be used to denote like parts throughout the various figures. In order to make the drawings more clear, not every component can be labeled in every drawing. Embodiments of various aspects of the present application will now be described, by way of example only, with reference to the drawings in which:

[0036] Figure 1 A multi-sensor fusion positioning method flow chart for a multi-layer tunnel scene for an embodiment of the present application.

[0037] Figure 2 A method flow chart for generating a first global map for several different time periods for an embodiment of the present application.

[0038] Figure 3 A partial method flow chart for obtaining a coarse position of a vehicle for an embodiment of the present application. DETAILED DESCRIPTION

[0039] In order to make the purposes, technical solutions, and advantages of embodiments of the present application clearer, the technical solutions of embodiments of the present application will be described clearly and completely below with reference to the drawings of embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the described embodiments of the present application, all other embodiments obtained by persons of ordinary skill in the art without creative effort fall within the scope of the present application. Unless otherwise defined, technical terms or scientific terms used herein should be understood as their common meanings to those skilled in the art of the present application.

[0040] The terms “first”, “second”, and similar terms used in the patent application specification and claims of the present application do not denote any order, quantity, or importance, but are used to distinguish different components. Similarly, unless the context clearly indicates otherwise, the singular forms “a”, “an”, and “the” do not denote quantity restrictions, but denote the presence of at least one. The terms “comprise”, “include”, and similar terms mean that the elements or objects appearing before “comprise” or “include” cover the features, integers, steps, operations, elements, and / or components listed after “comprise” or “include”, and do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or sets thereof. “Up”, “down”, “left”, “right”, and the like are used only to indicate relative positional relationships, and when the absolute positions of the described objects change, the relative positional relationships can also change accordingly.

[0041] In the prior art, when realizing multi-sensor data fusion positioning, the global pose of an ultra-wideband beacon, i.e., the global pose of the UWB beacon, is often obtained through field mapping and instrument measurement, which is of large labor cost and is not suitable for large-scale underground scene use; there is also a method of using a laser radar to realize local accurate positioning, but it cannot realize starting at any position.

[0042] Therefore, embodiments of the present application provide a multi-sensor fusion positioning method for a multi-layer tunnel scene, referring to Figure 1 , comprising:

[0043] Step S102: collecting attitude data of an inertial measurement unit located on a vehicle and used for detecting a tunnel environment, point cloud data of a laser radar, and UWB beacon data arranged in the tunnel in different time periods;

[0044] Step S104: importing the point cloud data and the attitude data into a SLAM algorithm to generate a plurality of first global maps in different time periods;

[0045] Step S106: merging the plurality of first global maps to generate a second global map;

[0046] Step S108: splitting the second global map to generate a plurality of topological sub-maps;

[0047] Step S110: obtaining vehicle positioning according to the UWB beacon data.

[0048] If the tunnel is divided into multiple sections, the relative positions of the UWB beacons in each section of the tunnel remain constant, such as height and spatial position, and each UWB beacon can be clearly scanned by the laser radar to improve the accuracy of later labeling and positioning calculation. By fusing the data of the inertial measurement unit, the laser radar and the UWB beacon, the accuracy and reliability of positioning can be improved. One of the significant features of technical fusion is to improve the accuracy and real-time performance. The laser radar provides rich environmental information and accurate distance measurement, the inertial measurement unit provides fast motion state feedback, and the UWB provides an initial position value at any position. The combination of the three makes the embodiments of the present application be able to start high-frequency positioning at any position and realize real-time high-precision positioning.

[0049] Data acquisition at different time periods can reflect dynamic changes in the environment and improve the accuracy of the global map. Combining data acquisition from inertial measurement units, lidar, and UWB beacons enables multi-sensor data fusion, ensuring stable vehicle positioning in complex tunnel environments. Data acquisition at different time periods and SLAM algorithm processing ensure the system's adaptability to dynamic environments. The multi-sensor fusion positioning method for multi-level tunnel scenarios provided by this invention is applicable to complex multi-level tunnel scenarios. It integrates data from multiple sensors such as lidar, inertial measurement units, and UWB, and through fine processing and deep fusion of this data, achieves high-frequency positioning functionality that can be initiated at any location.

[0050] In some embodiments, refer to Figure 2 Methods for importing point cloud data and pose data into the SLAM algorithm to generate first global maps for several different time periods include:

[0051] Step S1041: Construct a point cloud map with several layers based on the point cloud data;

[0052] Step S1042: Mark the layer number for each layer of point cloud map according to the roadway hierarchy;

[0053] Step S1043: Output the last odometry pose of the upper layer point cloud map and the first odometry pose of the lower layer point cloud map in the adjacent layer point cloud maps in sequence.

[0054] Step S1044: Merge several layers of point cloud maps to generate the first global map;

[0055] Step S1045: Import the last odometry pose of the previous layer point cloud map and the first odometry pose of the next layer point cloud map from the adjacent layer point cloud map into the ICP algorithm to generate the first global map through point-to-surface ICP.

[0056] By fusing hierarchical relationship annotation and odometry pose, effective fusion of point cloud maps at different levels can be achieved, generating an accurate first global map. Unlike conventional point-to-point ICP methods, we calculate the distance from points in the source point cloud to the surface formed by the target point cloud, and use the ICP algorithm to achieve point-to-surface matching, which can improve the accuracy of map stitching and reduce error accumulation. Multi-layer point cloud maps are generated using LiDAR point cloud data, and combined with odometry pose and hierarchical information, the global continuity and consistency of the map are ensured, thereby improving positioning accuracy.

[0057] In some embodiments, the method of merging several first global maps to generate a second global map includes: merging map segments of overlapping areas in several first global maps using a map merging method to generate a second global map.

[0058] By the map segment fusion of the overlapping area, the continuity and accuracy of the map can be further improved, and a complete second global map is generated. By merging the first global map generated in multiple time periods, the problem of incomplete map generated by single SLAM algorithm is solved, ensuring that the coverage of the global map is wider, and the positioning result is more stable and accurate.

[0059] In some embodiments, the method of obtaining the accurate position of the vehicle according to the UWB beacon data comprises:

[0060] According to the UWB beacon data, the coarse position of the vehicle is obtained; the coarse position of the vehicle, the real-time lidar data of the vehicle, and the second global map are matched to obtain the vehicle positioning.

[0061] The UWB beacon data is used to quickly obtain the coarse position of the vehicle, providing a basis for subsequent accurate positioning. By matching the lidar data and the global map, the vehicle positioning is further refined, ensuring the accuracy and reliability of the positioning. The combination of UWB beacon and lidar data realizes efficient conversion from coarse positioning to accurate positioning. The UWB beacon provides coarse position information, which is combined with lidar point cloud and global map to further improve the positioning accuracy.

[0062] In some embodiments, the method of obtaining the vehicle positioning according to the UWB beacon data further comprises: updating the positioning of the vehicle in the topological sub-map according to the attitude data of the inertial measurement unit.

[0063] The attitude data of the inertial measurement unit can be used to correct the positioning of the vehicle in the topological sub-map in real time, reduce the cumulative error, and improve the accuracy of dynamic positioning. In addition to the UWB beacon data, the attitude data of the inertial measurement unit is used to dynamically correct the vehicle position, compensate for errors in the sensor fusion process, and make the positioning more accurate. Since the frequency of lidar is low, there will be a positioning drift when the vehicle makes a sharp turn. At this time, the high-frequency odometer pose data is used for interpolation to update the current position of the vehicle, obtaining higher frequency positioning information such as coordinate points and heading, for subsequent navigation algorithms. In the face of complex environment, it has adaptability. Since the underground environment is complex, there will often be a phenomenon of map superposition at the same z-axis coordinate. The division of topological map is to split some special scenes, such as overlapping and interleaved maps, and switch the map positioning according to the scene, which can reduce the positioning pressure. In the environment of multi-layer tunnel, the map and positioning function are provided, which provides data support for downstream navigation tasks. When the vehicle moves to the junction of two topological maps, the second scene map is switched, and so on to complete the positioning of the whole scene.

[0064] In some embodiments, referring to Figure 3According to the UWB beacon data, the method for obtaining the coarse position of the vehicle comprises the following steps: obtaining a P point with a reflection intensity value greater than A according to the reflection intensity of the reflective sticker pasted on the UWB beacon, and the reflective sticker is provided with a label number in the order of the vehicle entering the lane; wherein the value of A is a critical value for distinguishing the reflective sticker from the remaining reflective objects in the lane environment; according to the P point, the nearest neighbor search is performed by using a KD-Tree to obtain n points closest to the P point, and the points with a distance less than r from the P point in the n points are clustered in a set Q; wherein n is a natural number greater than 1, and r is the value of the longest straight line segment on the surface for reflection in the reflective sticker; if the number of elements in the set Q continues to increase, an arbitrary point in the set Q except the P point is selected as a point K, and the above step is repeated until the number of elements in the set Q does not increase any more; if the number of elements in the set Q does not increase any more, the nearest neighbor search is ended, the point cloud intensity of the reflective sticker is obtained, and the three-dimensional coordinates of the center point of the reflective sticker and the label number of the reflective sticker are output, so as to obtain the coarse position of the vehicle.

[0065] The light intensity of the reflective sticker is detected, so that the coarse position of the vehicle can be quickly and reliably determined. The KD-Tree algorithm is used for nearest neighbor search, so that the speed and accuracy of coarse positioning are improved. The reflective sticker is used in combination with light intensity to perform preliminary vehicle position identification, and the KD-Tree algorithm is used to optimize position search, so that the positioning efficiency in a complex UWB beacon arrangement scene is improved. In the point cloud map positioning, the UWB is introduced, the point cloud of the position of the UWB beacon is output by clustering based on the point cloud intensity in the preliminary mapping, and the coordinates and number of the UWB beacon in the point cloud map are output, so that the processing speed of the coordinates of the UWB beacon in the point cloud map is greatly improved by introducing the reflective sticker with high light intensity and the clustering method based on the point cloud intensity, and the processing workload is reduced. In extremely harsh environments, if the positioning is lost, the position of the vehicle is calculated according to the coordinates of the UWB, the positioning is calibrated, and the stability and adaptability of the entire positioning system to the environment are significantly improved.

[0066] Another embodiment of the present application also provides a multi-sensor fusion positioning device for a multi-layer lane scene, comprising:

[0067] The acquisition module is used for acquiring the attitude data of the inertial measurement unit, the point cloud data of the laser radar and the UWB beacon data arranged at equal intervals in the lane at different time periods and used for detecting the lane environment on the vehicle;

[0068] The first generation module is used for importing the point cloud data and the attitude data into the SLAM algorithm to generate a plurality of first global maps of different time periods, wherein the method for generating the plurality of first global maps of different time periods comprises the following steps: constructing a plurality of layers of point cloud maps according to the point cloud data; marking a layer number for each layer of point cloud map according to a tunnel hierarchical relationship; sequentially outputting a last odometry pose of a previous layer of point cloud map and a first odometry pose of a next layer of point cloud map in the point cloud maps of adjacent layer numbers; fusing the plurality of layers of point cloud maps to generate the first global map; and importing the last odometry pose of the previous layer of point cloud map and the first odometry pose of the next layer of point cloud map in the point cloud maps of adjacent layer numbers into the ICP algorithm to generate the first global map through point-to-plane ICP.

[0069] The second generation module is used for merging the plurality of first global maps to generate a second global map.

[0070] The third generation module is used for splitting the second global map to generate a plurality of topological sub-maps.

[0071] The obtaining module is used for obtaining vehicle positioning according to UWB beacon data.

[0072] Another embodiment of the present application further provides an electronic device, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, and the computer program is executed by the processor to implement the multi-sensor fusion positioning method for the multi-layer tunnel scene.

[0073] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc. The processor is the control center of the data processing device of the gateway, and connects each part of the data processing device of the gateway through various interfaces and lines.

[0074] Another embodiment of the present application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the multi-sensor fusion positioning method for the multi-layer tunnel scene.

[0075] The memory can include a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs required by at least one function; and the data storage area can store data created by the processor and the like. In addition, the memory is preferably but not limited to a high-speed random access memory, for example, can also be a non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some embodiments, the memory can also optionally include a memory disposed remotely with respect to the processor, which can be connected to the processor through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0076] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by a computer program instructing related hardware, which can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiment methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD), etc. The storage medium can also include a combination of the above-mentioned types of memories.

[0077] In summary, by using the multi-sensor fusion positioning method and device for multi-layer tunnel scene, electronic equipment and storage medium provided by the application, through multi-sensor data fusion, the inertial measurement unit, lidar and UWB beacon data are fused, high-precision positioning can be realized in a multi-layer tunnel complex environment; through data acquisition and map generation at different time periods, real-time updating of vehicle attitude data, adaptation to changes in tunnel structure in dynamic environments such as mines, enhancement of system flexibility, and guarantee of dynamic response capability and precision of the positioning system; through systematic scheme design, compared with the traditional method relying on a large amount of manual surveying and mapping, the combination of UWB beacon and multi-sensor greatly reduces the labor and time cost, is suitable for large-scale mine scene, reduces the cost of manual field surveying and instrument measurement, and improves the applicability of large-scale underground scene; a variety of sensors and fusion algorithms are adopted, combined with UWB beacon, lidar and inertial measurement unit, the system can correct and compensate between multiple sensor data, has stronger anti-interference and error correction capability, enhances the anti-interference capability and robustness of the system in complex environment, and guarantees the stability and reliability of positioning.

[0078] In a complex multi-layer tunnel environment, high-frequency positioning function without specific initial position is realized, through technical scheme fusion of laser radar, inertial measurement unit and ultra-wide band and possible increase more sensor data, through the depth fusion of these data, the comprehensive understanding and accurate positioning to the environment are realized. Compared with the existing technology, the scheme of the application improves the positioning accuracy and real-time performance significantly by virtue of its unique sensor fusion strategy. Laser radar provides rich environmental information and accurate distance measurement, inertial measurement unit provides fast motion state feedback, and UWB provides position initial value at any position, the combination of the three makes the scheme can start high-frequency positioning at any position, realizes real-time high-precision positioning. Especially in the environment of multi-layer tunnel, the traditional positioning technology often faces serious challenges, such as signal shielding, multipath effect and other problems. However, the scheme of the application effectively overcomes these problems by taking advantage of multiple sensors, and realizes high-precision positioning in such a complex environment.

[0079] Although the present application has been disclosed with reference to the preferred embodiments above, it is not intended to limit the present application. Those skilled in the art without departing from the spirit and scope of the present application can make various modifications and improvements. Therefore, the protection scope of the present application shall be subject to the scope defined by the claims.

Claims

1. A multi-sensor fusion positioning method for a multi-layer roadway scene, characterized in that, The method comprises: collecting attitude data of an inertial measurement unit located on a vehicle and used for detecting a tunnel environment, point cloud data of a laser radar, and UWB beacon data arranged in the tunnel at different time periods; importing the point cloud data and the attitude data into a SLAM algorithm to generate a first global map at different time periods; wherein the method of generating the first global map at different time periods comprises: constructing a plurality of layers of point cloud maps according to the point cloud data; labeling a layer number for each layer of the point cloud maps according to a tunnel hierarchical relationship; sequentially outputting a last odometry pose of a previous layer point cloud map and a first odometry pose of a next layer point cloud map in the point cloud maps of adjacent layer numbers; fusing the plurality of layers of point cloud maps to generate the first global map; and importing the last odometry pose of the previous layer point cloud map and the first odometry pose of the next layer point cloud map in the point cloud maps of adjacent layer numbers into an ICP algorithm to generate the first global map through point-to-plane ICP; merging a plurality of the first global maps to generate a second global map; splitting the second global map to generate a plurality of topological sub-maps; obtaining a vehicle position according to the UWB beacon data.

2. The multi-sensor fusion positioning method for a multi-layer roadway scene according to claim 1, characterized in that, The method of merging a plurality of the first global maps to generate a second global map comprises: fusing map segments of overlapping regions in a plurality of the first global maps through a map merging method to generate the second global map.

3. The multi-sensor fusion positioning method for multi-layer roadway scenes according to claim 1, characterized in that, The method of obtaining a vehicle accurate position according to the UWB beacon data comprises: obtaining a vehicle coarse position according to the UWB beacon data; matching the vehicle coarse position, real-time laser radar data of the vehicle, and the second global map to obtain a vehicle position.

4. The multi-sensor fusion positioning method for multi-layer roadway scenes according to claim 3, characterized in that, The method of obtaining a vehicle position according to the UWB beacon data further comprises: updating the position of the vehicle in the topological sub-maps according to the attitude data of the inertial measurement unit.

5. The multi-sensor fusion positioning method for multi-layer roadway scenes according to claim 3, characterized in that, The method of obtaining a vehicle coarse position according to the UWB beacon data comprises: obtaining a P point with a reflection intensity value greater than A according to a reflection intensity of a reflective sticker pasted on the UWB beacon, wherein the reflective sticker is provided with a label number according to a sequence in which the vehicle enters the tunnel; wherein the value of A is a critical value for distinguishing the reflective sticker from other reflective objects in the tunnel environment; performing a nearest neighbor search on the P point using a KD-Tree to obtain n points closest to the P point, and clustering points in the n points with a distance less than r from the P point in a set Q; wherein n is a natural number greater than 1, and r is a value of a longest straight line segment on a reflective surface of the reflective sticker; if the number of elements in the set Q continues to increase, selecting an arbitrary point other than the P point in the set Q as a point K, and repeating the previous step until the number of elements in the set Q no longer increases; if the number of elements in the set Q no longer increases, ending the nearest neighbor search, and obtaining a point cloud intensity of the reflective sticker; the point cloud intensity of the reflective sticker outputs a three-dimensional coordinate of a center point of the reflective sticker and a label number of the reflective sticker, and obtains the vehicle coarse position.

6. A multi-sensor fusion positioning device for multi-level tunnel scenarios, characterized in that, The method comprises: The collection module is configured to collect attitude data of an inertial measurement unit located on the vehicle and used to detect a mine environment, point cloud data of a laser radar, and UWB beacon data of equally spaced UWB beacons arranged in the mine at different time periods; The first generation module is configured to import the point cloud data and the attitude data into a SLAM algorithm to generate a first global map at different time periods; The method of generating the first global map at different time periods includes: constructing a plurality of layers of point cloud maps according to the point cloud data; labeling a layer number for each layer of the point cloud maps according to a mine hierarchical relationship; sequentially outputting a last odometry pose of a previous layer of point cloud maps and a first odometry pose of a next layer of point cloud maps in the point cloud maps with adjacent layer numbers; fusing the plurality of layers of point cloud maps to generate the first global map; and importing the last odometry pose of the previous layer of point cloud maps and the first odometry pose of the next layer of point cloud maps in the point cloud maps with adjacent layer numbers into an ICP algorithm to generate the first global map through point-to-plane ICP; The second generation module is configured to merge the first global maps to generate a second global map; The third generation module is configured to split the second global map to generate a plurality of topological sub-maps; The obtaining module is configured to obtain vehicle positioning according to the UWB beacon data.

7. An electronic device, comprising: The computer program is executed by the processor to implement the multi-sensor fusion positioning method for a multi-layer mine scene according to any one of claims 1-5.

8. A computer-readable storage medium storing a computer program, the computer-readable storage medium comprising: The computer program is executed by the processor to implement the multi-sensor fusion positioning method for a multi-layer mine scene according to any one of claims 1-5.

Images