Grid map construction method and device in mine scene, medium and product

Abstract

The invention discloses a grid map construction method and device in a mine scene, a medium and a product. The method comprises the following steps: acquiring first point cloud data acquired by an inertial measurement unit on a mine car, constructing a global point cloud map in a mine scene according to M frames of IMU data and N frames of first point cloud data, acquiring second point cloud data in real time, and locally updating the global point cloud map through the second point cloud data, deleting the ground points from the global point cloud map to obtain an elevation point cloud map, determining whether each point in the elevation point cloud map is a core point or not so as to add adjacent points and the core points in a preset distance range into a point cluster, generating mountain edge data according to the points, which do not exist in any point cluster, in the elevation point cloud map, and sending the mountain edge data to the server; and generating a grid map according to the mountain edge data. Therefore, the high-precision grid map capable of meeting the path planning requirement is constructed in the dynamic mining of the mining area, and the operation efficiency and the operation safety of the mine car are remarkably improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, medium and product for constructing a raster map in a mining scenario. Background Art

[0002] The autonomous driving of unmanned mining vehicles can be technically divided into five modules: perception module, mapping and positioning module, decision module, planning module and control module. The mapping and positioning module is responsible for building and maintaining a map of the vehicle's driving environment and determining the vehicle's position in the map in real time. It provides an accurate positioning and navigation basis for the vehicle, ensuring that the vehicle can drive safely and accurately in the complex and changing mining environment.

[0003] The mapping and positioning module of the existing technology cooperates with the laser radar and the combined navigation system to obtain an accurate estimate of the current position of the mine car. After obtaining the mine car's position, the point cloud data of adjacent frames are extracted and matched through the point cloud matching algorithm. After the position estimation and point cloud data matching, the point cloud data obtained by the laser radar can be spliced ​​together according to the precise position information to form a globally consistent high-precision point cloud map.

[0004] However, in mining scenarios, since the mountain mining face will move with the production process, the point cloud maps in different time dimensions are inconsistent in structure. Therefore, relying solely on the mapping results of the previous cycle will cause the mine car to plan its path based on outdated information, thereby misjudging the drivable area and the edge of the mountain, which will lead to path planning errors during the operation of the mine car, reducing operating efficiency and even causing the risk of accidents. Summary of the invention

[0005] The present application provides a raster map construction method, equipment, medium and product in a mining scenario, which is used to solve the problem that the mine car relies on the mapping results of the previous cycle, resulting in errors in the path planning of the drivable area and the edge of the mountain, which ultimately leads to reduced operation efficiency and even the risk of accidents during the operation of the mine car.

[0006] In a first aspect, the present application provides a method for constructing a grid map in a mine scenario, comprising:

[0007] Acquire M frames of IMU data collected by an inertial measurement unit on the mine car and N frames of first point cloud data collected by a laser radar on the mine car, where M and N are positive integers greater than or equal to 1;

[0008] Constructing a global point cloud map of the mine scene according to the M frames of IMU data and the N frames of the first point cloud data;

[0009] Collecting second point cloud data in real time, and locally updating the global point cloud map through the second point cloud data;

[0010] Deleting ground points from the global point cloud map to obtain an elevation point cloud map;

[0011] For each point in the elevation point cloud map, determine the number of adjacent points within a preset distance range around the point, and determine the point whose number of adjacent points is greater than or equal to a preset threshold of the number of adjacent points as a core point, so as to add the adjacent points within the preset distance range and the core point to a point cluster;

[0012] Mountain edge data are generated according to points in the elevation point cloud map that do not exist in any point cluster, so as to generate a grid map according to the mountain edge data.

[0013] In a possible implementation, deleting ground points from the global point cloud map to obtain an elevation point cloud map includes:

[0014] The process of determining the ground point set is executed multiple times to obtain multiple ground point sets, and the process of determining the ground point set is executed each time to obtain one ground point set;

[0015] Determine a ground point set including the largest number of ground points from multiple ground point sets as a target ground point set, and delete the target ground point set from the global point cloud map to obtain an elevation point cloud map;

[0016] The process of determining the ground point set includes:

[0017] Randomly select three reference points from the global point cloud map to determine a plane passing through the three reference points;

[0018] Calculating the distance between each point in the global point cloud map and the plane;

[0019] A ground point set is generated according to the points in the global point cloud map whose distance is less than or equal to a preset distance threshold.

[0020] In a possible implementation, generating mountain edge data according to points in the elevation point cloud map that do not exist in any point cluster includes:

[0021] The points in the elevation point cloud map that do not exist in any point cluster are regarded as mountain edge points;

[0022] Smoothing the mountain edge points to obtain smoothed mountain edge points;

[0023] Performing a continuity check on the smooth mountain edge points to obtain a continuity check result;

[0024] If the continuity check result indicates that the smooth mountain edge points are continuous, the mountain edge data is generated according to the smooth mountain edge points.

[0025] In a possible implementation, constructing a global point cloud map in the mine scene according to the M frames of IMU data and the N frames of the first point cloud data includes:

[0026] For the first point cloud data of the i-th frame, according to the IMU data collected between the first point cloud data of the i-1-th frame and the first point cloud data of the i-th frame, a first motion parameter between the first point cloud data of the i-1-th frame and the first point cloud data of the i-th frame is calculated as the i-th first motion parameter, the IMU data includes acceleration and angular velocity, the first motion parameter includes: displacement and angle change, and i is a positive integer greater than or equal to 2 and less than or equal to N;

[0027] Matching the first point cloud data of the i-th frame with the first point cloud data of the i-1-th frame to obtain a second motion parameter between the first point cloud data of the i-1-th frame and the first point cloud data of the i-th frame;

[0028] Optimizing the i-th first motion parameter by using the i-th second motion parameter to obtain the i-th target motion parameter;

[0029] According to the i-th target motion parameter, the i-1th mine car posture information is updated to obtain the i-th mine car posture information, and the first mine car posture information is the initial posture information;

[0030] Jointly optimize the N mine car posture information to obtain N optimized mine car posture information;

[0031] According to the N optimized mine car posture information of the N frames of first point cloud data, a global point cloud map is generated from the N first point cloud data.

[0032] In a possible implementation, matching the i-th frame and the i-1-th frame includes:

[0033] For any one of the i-th frame of first point cloud data and the i-1-th frame of first point cloud data, dividing the frame of first point cloud data into a plurality of scan lines, each of the scan lines including a plurality of points in the frame of first point cloud data;

[0034] For each point in each of the scan lines, calculating the curvature of the point;

[0035] Determine a point whose curvature is greater than or equal to a preset curvature threshold as a feature point;

[0036] Match the feature points in the first point cloud data of the i-th frame with the feature points in the first point cloud data of the i-1-th frame.

[0037] In a possible implementation, according to N optimized mine car posture information of N frames of first point cloud data, generating a global point cloud map from the N first point cloud data includes:

[0038] Determine a static object point in each frame of first point cloud data, wherein the static object point is a point other than a dynamic object point;

[0039] According to the N optimized mine car posture information, convert the N static object points in the first point cloud data into a world coordinate system;

[0040] The static object points in the world coordinate system are spliced ​​to obtain the global point cloud map.

[0041] In a possible implementation, locally updating the global point cloud map using the second point cloud data includes:

[0042] Extracting a first key point from the global point cloud map, and extracting a second key point from the second point cloud data;

[0043] Acquire a first key geometric feature around each of the first key points, and acquire a second key geometric feature around each of the second key points;

[0044] Matching the first key geometric feature with the second key geometric feature to obtain a first matching degree, and taking a point cloud submap corresponding to a second key geometric feature whose first matching degree is greater than or equal to a preset matching degree threshold in the second point cloud data as a target point cloud submap;

[0045] The second point cloud data and the target point cloud submap are matched to obtain a second matching degree, and the target point cloud submap corresponding to the second matching degree is updated by the second point cloud data when the second matching degree is greater than or equal to a preset matching degree threshold.

[0046] In a second aspect, the present application provides a grid map construction device in a mining scenario, comprising:

[0047] An acquisition module is used to acquire M frames of IMU data collected by an inertial measurement unit on the mine car and N frames of first point cloud data collected by a laser radar on the mine car, where M and N are positive integers greater than or equal to 1;

[0048] A processing module, used for constructing a global point cloud map of the mine scene according to the M frames of IMU data and the N frames of the first point cloud data;

[0049] The processing module is further used to collect second point cloud data in real time, and locally update the global point cloud map through the second point cloud data;

[0050] The processing module is further used to delete ground points from the global point cloud map to obtain an elevation point cloud map;

[0051] The processing module is further used to determine, for each point in the elevation point cloud map, the number of adjacent points within a preset distance range around the point, and determine a point whose number of adjacent points is greater than or equal to a preset threshold of the number of adjacent points as a core point, so as to add the adjacent points within the preset distance range and the core point to a point cluster;

[0052] The processing module is also used to generate mountain edge data according to points in the elevation point cloud map that do not exist in any point cluster, so as to generate a grid map according to the mountain edge data.

[0053] In a grid map construction device in a mine scenario provided by this application:

[0054] A processing module, configured to execute the process of determining a ground point set multiple times to obtain multiple ground point sets, wherein each time the process of determining a ground point set is executed, one ground point set is obtained;

[0055] The processing module is further used to determine a ground point set including the largest number of ground points from the multiple ground point sets as a target ground point set, and delete the target ground point set from the global point cloud map to obtain an elevation point cloud map;

[0056] The process of determining the ground point set includes:

[0057] The processing module is further used to randomly select three reference points from the global point cloud map to determine a plane passing through the three reference points;

[0058] The processing module is further used to calculate the distance between each point in the global point cloud map and the plane;

[0059] The processing module is also used to generate a ground point set based on the points in the global point cloud map whose distance is less than or equal to a preset distance threshold.

[0060] In a grid map construction device in a mine scenario provided by this application:

[0061] The processing module is further used to take points in the elevation point cloud map that do not exist in any point cluster as mountain edge points;

[0062] The processing module is further used to smooth the mountain edge points to obtain smoothed mountain edge points;

[0063] The processing module is also used to perform continuity check on the edge points of the smooth mountain to obtain a continuity check result;

[0064] If the continuity check result indicates that the smooth mountain edge points are continuous, the processing module is used to generate the mountain edge data according to the smooth mountain edge points.

[0065] In a grid map construction device in a mine scenario provided by this application:

[0066] A processing module, for calculating, for the first point cloud data of the i-th frame, a first motion parameter between the first point cloud data of the i-1th frame and the first point cloud data of the i-th frame according to the IMU data collected between the first point cloud data of the i-1th frame and the first point cloud data of the i-th frame, as the i-th first motion parameter, the IMU data including acceleration and angular velocity, the first motion parameter including: displacement and angle change, and i is a positive integer greater than or equal to 2 and less than or equal to N;

[0067] The processing module is further used to match the first point cloud data of the i-th frame with the first point cloud data of the i-1-th frame to obtain a second motion parameter between the first point cloud data of the i-1-th frame and the first point cloud data of the i-th frame;

[0068] The processing module is further configured to optimize the i-th first motion parameter by using the i-th second motion parameter to obtain the i-th target motion parameter;

[0069] The processing module is further used to update the i-1th mine car posture information according to the i-th target motion parameter to obtain the i-th mine car posture information, and the first mine car posture information is the initial posture information;

[0070] The processing module is also used to jointly optimize the N mine car posture information to obtain N optimized mine car posture information;

[0071] The processing module is also used to generate a global point cloud map from the N optimized mine car posture information of the N frames of first point cloud data.

[0072] In a grid map construction device in a mine scenario provided by this application:

[0073] A processing module, for dividing any one of the i-th frame of first point cloud data and the i-1-th frame of first point cloud data into a plurality of scan lines, each of which includes a plurality of points in the frame of first point cloud data;

[0074] The processing module is further used to calculate the curvature of each point in each of the scan lines;

[0075] The processing module is further used to determine the point whose curvature is greater than or equal to a preset curvature threshold as a feature point;

[0076] The processing module is also used to match the feature points in the first point cloud data of the i-th frame with the feature points in the first point cloud data of the i-1-th frame.

[0077] In a grid map construction device in a mine scenario provided by this application:

[0078] The processing module is further used to determine static object points in each frame of the first point cloud data, wherein the static object points are points other than the dynamic object points;

[0079] The processing module is further used to convert the static object points in the N first point cloud data into a world coordinate system according to the N optimized mine car posture information;

[0080] The processing module is also used to splice the static object points in the world coordinate system to obtain the global point cloud map.

[0081] In a grid map construction device in a mine scenario provided by this application:

[0082] The processing module is further used to extract a first key point from the global point cloud map, and to extract a second key point from the second point cloud data;

[0083] The acquisition module is further used to acquire a first key geometric feature around each of the first key points, and to acquire a second key geometric feature around each of the second key points;

[0084] The processing module is further used to match the first key geometric feature with the second key geometric feature to obtain a first matching degree, and use the point cloud submap corresponding to the second key geometric feature whose first matching degree is greater than or equal to a preset matching degree threshold in the second point cloud data as a target point cloud submap;

[0085] The processing module is also used to match the second point cloud data with the target point cloud submap to obtain a second matching degree, and update the target point cloud submap corresponding to the second matching degree when the second matching degree is greater than or equal to a preset matching degree threshold through the second point cloud data.

[0086] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0087] The memory stores computer-executable instructions;

[0088] The processor executes the computer-executable instructions stored in the memory to implement a grid map construction method in a mining scenario as described in any one of the first aspects.

[0089] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement a grid map construction method in a mining scenario as described in any one of the first aspects.

[0090] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements a method for constructing a grid map in a mining scenario as described in any one of the first aspects.

[0091] The present application provides a grid map construction method, device, medium and product in a mining scenario. First, M frames of IMU data collected by an inertial measurement unit on a mining car and N frames of first point cloud data collected by a laser radar on the mining car are obtained. A global point cloud map in the mining scenario is constructed according to the M frames of IMU data and the N frames of first point cloud data. Second point cloud data is collected in real time, and the global point cloud map is locally updated through the second point cloud data. Ground points are deleted from the global point cloud map to obtain an elevation point cloud map. For each point in the elevation point cloud map, the number of adjacent points within a preset distance range around the point is determined, and a point whose number of adjacent points is greater than or equal to a preset threshold value of the number of adjacent points is determined as a core point, so that the adjacent points within the preset distance range and the core point are added to a point cluster, and mountain edge data is generated according to points in the elevation point cloud map that do not exist in any point cluster, so as to generate a grid map according to the mountain edge data. Compared with the prior art, relying solely on the mapping results of the previous cycle will cause the mine car to plan its path based on outdated information, thereby misjudging the drivable area and the edge of the mountain, which will lead to path planning errors during the operation of the mine car, reducing operation efficiency and even causing the risk of accidents. The present application constructs a global map of the mining scene, and then collects a second point cloud map in real time. The global point cloud map is locally updated through the second point cloud map, thereby avoiding path planning misleading due to changes in the mountain mining surface. Then, mountain edge data is generated, and a raster map is generated based on the mountain edge data. This is a key step in accurately distinguishing between drivable areas and non-drivable areas. Refined edge recognition helps the mine car to better understand its operating environment and avoid collisions with obstacles such as mountains. BRIEF DESCRIPTION OF THE DRAWINGS

[0092] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0093] Figure 1 A schematic diagram of a flow chart of a first embodiment of a method for constructing a grid map in a mining scenario provided in an embodiment of the present application;

[0094] Figure 2A schematic diagram of a flow chart of a second embodiment of a method for constructing a grid map in a mining scenario provided in an embodiment of the present application;

[0095] Figure 3 A schematic diagram of a flow chart of a third embodiment of a method for constructing a grid map in a mining scenario provided in an embodiment of the present application;

[0096] Figure 4 A grid map construction device in a mining scenario provided in an embodiment of the present application;

[0097] Figure 5 A schematic diagram of the structure of an electronic device embodiment 1 provided in an embodiment of the present application.

[0098] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0099] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0100] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0101] In the prior art, mapping and positioning uses the cooperation of laser radar and integrated navigation system to obtain an accurate estimate of the current position of the mine car, and then extracts and matches the point cloud data of adjacent frames according to the point cloud matching algorithm. After the position estimation and point cloud data matching, the point cloud data obtained by the laser radar can be spliced ​​together according to the precise position information to form a globally consistent high-precision point cloud map. In the mining scene, as the operation progresses, the mountain mining surface will move with the production process. Therefore, relying only on the mapping results of the previous cycle will cause the mine car to plan its path based on outdated information, which will lead to errors in path planning during the operation of the mine car, reducing the operation efficiency and even leading to the risk of accidents.

[0102] Based on this, the inventive concept of this application is to provide a grid map construction method in a mining scenario, by constructing a global map and performing real-time local updates on the global map during the operation process, thereby ensuring the accuracy and timeliness of the map information, thereby improving the operating efficiency of the mine car during the operation process and avoiding the risk of accidents.

[0103] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0104] Figure 1 A schematic diagram of a flow chart of a first embodiment of a method for constructing a grid map in a mining scenario provided in an embodiment of the present application;

[0105] S101: Acquire M frames of IMU data collected by an inertial measurement unit on the mine car and N frames of first point cloud data collected by a laser radar on the mine car, where M and N are positive integers greater than or equal to 1.

[0106] In the embodiment of the present application, an inertial measurement unit and a laser radar are installed on the mine car to collect IMU data and first point cloud data respectively, and then M frames of IMU data collected by the inertial measurement unit and N frames of first point cloud data collected by the laser radar are obtained, where M and N are both positive integers greater than or equal to 1. In addition, the first point cloud data is dedistorted to correct the point cloud deformation caused by the movement of the mine car.

[0107] S102: Construct a global point cloud map in a mine scene according to the M frames of IMU data and the N frames of first point cloud data.

[0108] In an embodiment of the present application, in order to correct the deformation of the point cloud data caused by the movement of the mine car, a global point cloud map of the mine scene is constructed based on M frames of IMU data and N frames of first point cloud data.

[0109] S103: Collect second point cloud data in real time, and locally update the global point cloud map using the second point cloud data.

[0110] In an embodiment of the present application, the second point cloud data is collected in real time and the global point cloud map is locally updated using the second point cloud data.

[0111] S104: Deleting ground points from the global point cloud map to obtain an elevation point cloud map.

[0112] In an embodiment of the present application, a specific implementation method of deleting ground points from a global point cloud map to obtain an elevation point cloud map is:

[0113] The process of determining the ground point set is executed multiple times to obtain multiple ground point sets, and one ground point set is obtained each time the process of determining the ground point set is executed.

[0114] In the embodiment of the present application, the process of determining the ground point set is performed multiple times to obtain multiple ground point sets, each of which includes multiple points in the global point cloud map. Each time the process of determining the ground point set is performed, a ground point set can be obtained.

[0115] A ground point set with the largest number of ground points is determined from multiple ground point sets as a target ground point set, and the target ground point set is deleted from the global point cloud map to obtain an elevation point cloud map.

[0116] In the embodiment of the present application, the obtained multiple ground point sets are compared in terms of the number of ground points they include, the ground point set with the largest number of ground points is determined as the target ground point set, and the target ground point set is deleted from the global point cloud map to obtain a point cloud map. Optionally, in order to obtain a more refined elevation point cloud map, the global point cloud map after deleting the target ground point set from the global point cloud map can be subjected to elevation filtering, that is, when the distance between the point in the global point cloud map and the plane of the target ground point set is greater than or equal to the preset height threshold, it is deleted, and finally a more refined elevation point cloud map is obtained.

[0117] The process of determining the ground point set includes:

[0118] Three reference points are randomly selected from the global point cloud map to determine a plane passing through the three reference points.

[0119] In an embodiment of the present application, three reference points are randomly selected from the global point cloud map, and the plane of the three reference points is determined by the three randomly selected reference points.

[0120] Calculate the distance between each point in the global point cloud map and the plane.

[0121] In an embodiment of the present application, the distance between each point in the global point cloud map and the obtained plane is calculated.

[0122] Generate a ground point set based on the points in the global point cloud map whose distance is less than or equal to the preset distance threshold.

[0123] In the embodiment of the present application, based on the calculated distance between each point in the global point cloud map and the obtained plane, it is determined whether the distance is less than or equal to the preset distance threshold. Points in the global point cloud map whose distance is less than or equal to the preset distance threshold are screened out as a ground point set.

[0124] S105: For each point in the elevation point cloud map, determine the number of adjacent points within a preset distance range around the point, and determine the point whose number of adjacent points is greater than or equal to a preset threshold value of the number of adjacent points as a core point, so as to add the adjacent points and the core points within the preset distance range into a point cluster.

[0125] In an embodiment of the present application, a preset distance range is first determined. For each point in the elevation point cloud map, the number of neighboring points within the preset distance range is calculated, and the point whose number of neighboring points is greater than or equal to the preset neighboring point number threshold is determined as the core point, and the core point and its surrounding neighboring points within the preset distance range are added to a point cluster.

[0126] S106: Generate mountain edge data according to points in the elevation point cloud map that do not exist in any point cluster, so as to generate a grid map according to the mountain edge data.

[0127] In an embodiment of the present application, it is determined whether a point in the elevation point cloud map is in the point cluster determined in the above step, mountain edge data is generated for the point that does not exist in any point cluster, and a raster map is generated based on the mountain edge data.

[0128] In the above step S106, a specific implementation method of generating mountain edge data according to points in the elevation point cloud map that do not exist in any point cluster is:

[0129] Points in the elevation point cloud map that do not exist in any point cluster are regarded as mountain edge points.

[0130] In an embodiment of the present application, points in the elevation point cloud map that do not exist in any point cluster are identified as mountain edge points, that is, points that do not belong to core points and points that are not adjacent to core points are identified as mountain edge points.

[0131] The mountain edge points are smoothed to obtain smooth mountain edge points.

[0132] In the embodiment of the present application, since the mountain edge points directly extracted from the elevation point cloud map are irregular, smoothing is performed to reduce noise and irregularity. Optionally, an interpolation method can be used to smooth the mountain edge points, for example, linear interpolation, spline interpolation, and other interpolation methods are used to smooth the mountain edge points.

[0133] Perform continuity check on the edge points of the smooth mountain and obtain the continuity check result.

[0134] In the embodiment of the present application, the continuity check is performed on the smoothed mountain edge points to ensure that the smoothed mountain edge points at this time constitute a continuous mountain edge. Optionally, the continuity check can be implemented by calculating the distance and angle between two adjacent points in the smoothed mountain edge points, that is, when the distance between two adjacent points in the smoothed mountain edge points is less than a preset distance threshold, and when the angle between two adjacent points in the smoothed mountain edge points is less than a preset angle threshold, it indicates that the smoothed mountain edge points are continuous.

[0135] If the continuity check result indicates that the smooth mountain edge points are continuous, mountain edge data are generated based on the smooth mountain edge points.

[0136] In the embodiment of the present application, if the result of the continuity check on the smooth mountain edge points is that the smooth mountain edge points are continuous, the mountain edge data is generated according to the smooth mountain edge points.

[0137] In an embodiment of the present application, first, M frames of IMU data collected by the inertial measurement unit on the mine car and N frames of first point cloud data collected by the laser radar on the mine car are obtained, and a global point cloud map of the mine scene is constructed according to the M frames of IMU data and the N frames of first point cloud data, and the second point cloud data is collected in real time, and the global point cloud map is locally updated through the second point cloud data, and the ground points are deleted from the global point cloud map to obtain an elevation point cloud map. For each point in the elevation point cloud map, the number of adjacent points within a preset distance range around the point is determined, and the point whose number of adjacent points is greater than or equal to a preset threshold value of the number of adjacent points is determined as a core point, so that the adjacent points and core points within the preset distance range are added to a point cluster, and mountain edge data is generated according to the points in the elevation point cloud map that do not exist in any point cluster, so as to generate a raster map according to the mountain edge data. Compared with the prior art, relying solely on the mapping results of the previous cycle will cause the mine car to plan its path based on outdated information, thereby misjudging the drivable area and the edge of the mountain, which will lead to path planning errors during the operation of the mine car, reducing operation efficiency and even causing the risk of accidents. The present application constructs a global map of the mining scene, and then collects a second point cloud map in real time. The global point cloud map is locally updated through the second point cloud map, thereby avoiding path planning misleading due to changes in the mountain mining surface. Then, mountain edge data is generated, and a raster map is generated based on the mountain edge data. This is a key step in accurately distinguishing between drivable areas and non-drivable areas. Refined edge recognition helps the mine car to better understand its operating environment and avoid collisions with obstacles such as mountains.

[0138] Figure 2 A flowchart of a second embodiment of a method for constructing a grid map in a mining scenario provided in an embodiment of the present application is shown in FIG. Figure 2 As shown in the above Figure 1Based on the illustrated embodiment, a specific implementation of step S102 is as follows:

[0139] S201: For the first point cloud data of the i-th frame, according to the IMU data collected between the first point cloud data of the i-1-th frame and the first point cloud data of the i-th frame, calculate the first motion parameter between the first point cloud data of the i-1-th frame and the first point cloud data of the i-th frame as the i-th first motion parameter, the IMU data includes acceleration and angular velocity, the first motion parameter includes: displacement and angle change, i is a positive integer greater than or equal to 2 and less than or equal to N.

[0140] In an embodiment of the present application, the acquired M frames of IMU data and N frames of first point cloud data are fused. For the i-th frame of first point cloud data, the first motion parameter between the i-1-th frame of first point cloud data and the i-th frame of first point cloud data is calculated based on the IMU data collected between the i-1-th frame of first point cloud data and the i-th frame of first point cloud data as the i-th first motion parameter.

[0141] For example, the inertial measurement unit will collect one frame of IMU data every 10 milliseconds, and the laser radar will collect one frame of the first point cloud data every 100 milliseconds. The IMU data collected between the first point cloud data of the i-1th frame and the first point cloud data of the i-th frame is extracted, that is, the time interval between the first point cloud data of the i-1th frame and the i-th frame is 100 milliseconds, and all IMU data within the 100 millisecond time interval are extracted. IMU data includes acceleration and angular velocity. The acceleration in the IMU data collected between the i-1th frame and the i-th frame is integrated to obtain the displacement in the i-th first motion parameter; the angular velocity in the IMU data collected between the i-1th frame and the i-th frame is integrated to obtain the angular velocity change in the i-th first motion parameter.

[0142] S202: Match the first point cloud data of the i-th frame with the first point cloud data of the i-1-th frame to obtain a second motion parameter between the first point cloud data of the i-1-th frame and the first point cloud data of the i-th frame.

[0143] In an embodiment of the present application, by matching the first point cloud data of the i-th frame with the first point cloud data of the i-1th frame, the second motion parameter between the first point cloud data of the i-1th frame and the first point cloud data of the i-th frame is obtained, that is, as the i-th second motion parameter, wherein the second motion parameter includes a displacement and an angle change.

[0144] In the above step S202, a specific implementation method of matching the i-th frame and the i-1-th frame is:

[0145] For any one of the i-th frame of first point cloud data and the (i-1)-th frame of first point cloud data, the frame of first point cloud data is divided into a plurality of scan lines, each scan line including a plurality of points in the frame of first point cloud data.

[0146] In an embodiment of the present application, optionally, the laser radar is a 32-line laser radar, and the scan lines are formed when the laser radar scans in the horizontal direction, emitting laser beams one by one at fixed angle intervals and receiving reflected signals. Each scan line represents a two-dimensional point sequence, in which each point contains its position information in three-dimensional space. These scan lines together constitute the point cloud data of the three-dimensional environment observed by the laser radar. The 32-line laser radar is composed of 32 scan lines. Each frame of the first point cloud data includes 32 scan lines, each scan line includes multiple points in the first point cloud data of the frame, and the points in the first point cloud data of each scan line in the i-th frame are obtained, and the points in the first point cloud data of each scan line in the i-1-th frame are obtained.

[0147] For each point in each scan line, calculate the curvature of the point.

[0148] In the embodiment of the present application, each point in each scan line can be regarded as a two-dimensional point sequence. For each point in each scan line in the first point cloud data of the i-1th frame, the curvature of the point is calculated; for each point in each scan line in the first point cloud data of the i-th frame, the curvature of the point is calculated.

[0149] Points whose curvature is greater than or equal to a preset curvature threshold are determined as feature points.

[0150] In the embodiment of the present application, for the curvature of a point in each scan line in the i-1 frame data, it is determined whether its curvature is greater than or equal to a set curvature threshold, and if it is greater than or equal to the set curvature threshold, it is determined as a feature point in the first point cloud data of the i-1 frame. Similarly, for the curvature of a point in each scan line in the i frame data, it is determined whether its curvature is greater than or equal to a set curvature threshold, and if it is greater than or equal to the set curvature threshold, it is determined as a feature point in the first point cloud data of the i frame.

[0151] Match the feature points in the first point cloud data of the i-th frame with the feature points in the first point cloud data of the i-1-th frame.

[0152] In an embodiment of the present application, the feature points in the first point cloud data of the i-th frame and the feature points in the first point cloud data of the i-1th frame are matched, and finally the second motion parameters between the first point cloud data of the i-1th frame and the first point cloud data of the i-th frame are obtained, wherein the second motion parameters include displacement and angle change.

[0153] S203: Optimize the i-th first motion parameter by using the i-th second motion parameter to obtain the i-th target motion parameter.

[0154] In the embodiment of the present application, the i-th first motion parameter is optimized by the i-th second motion parameter to obtain the i-th target motion parameter. Optionally, a Kalman filter algorithm is used to optimize the i-th first motion parameter by the i-th second motion parameter, the second motion parameter is used as a high-frequency, low-precision motion estimate, and the first motion parameter provides low-frequency, high-precision relative position information. The two are combined through the Kalman filter algorithm to balance accuracy and real-time performance.

[0155] S204: updating the i-1th mine car posture information according to the i-th target motion parameter to obtain the i-th mine car posture information, and the first mine car posture information is the initial posture information.

[0156] In the embodiment of the present application, optionally, the i-1th mine car posture information is updated according to the i-th target motion parameter through coordinate transformation and matrix operation, etc., to obtain the i-th mine car posture information. The first mine car posture information is the initial posture information, and the first mine car posture information is updated using the second target motion parameter to obtain the second mine car posture information; the second mine car posture information is updated according to the third target motion parameter to obtain the third mine car posture information; and so on, the i-1th mine car posture information is updated according to the i-th target motion parameter to obtain the i-th mine car posture information; finally, N mine car posture information is obtained.

[0157] S205: Jointly optimize the N mine car posture information to obtain N optimized mine car posture information.

[0158] In an embodiment of the present application, the obtained N mine car posture information is jointly optimized, and a backend graph optimization algorithm is used, such as a graph optimization algorithm, to jointly optimize the obtained N mine car posture information to obtain N optimized mine car posture information. The graph optimization algorithm considers the constraint relationship between all frame point cloud data, and optimizes the posture of each mine car by minimizing the error function, thereby obtaining globally consistent and high-precision mine car posture information.

[0159] S206: Generate a global point cloud map from the N first point cloud data according to the N optimized mine car posture information of the N frames of first point cloud data.

[0160] In an embodiment of the present application, a specific implementation method of generating a global point cloud map from N first point cloud data according to N optimized mine car posture information of N frames of first point cloud data is:

[0161] A static object point in the first point cloud data of each frame is determined, where the static object point is a point other than the dynamic object point.

[0162] In the embodiment of the present application, the static object points in each frame of the first point cloud data are first determined, and the static object points are points other than the dynamic object points. That is, by determining the dynamic object points, by excluding the dynamic object points in each frame of the first point cloud data, the static object points in each frame of the first point cloud data are further determined. The dynamic object points are points where the motion parameters in the first point cloud data of adjacent frames change.

[0163] According to the N optimized mine car posture information, the static object points in the N first point cloud data are converted into the world coordinate system.

[0164] In the embodiment of the present application, based on N optimized mine car posture information, the static object points in the N first point cloud data are first converted into the world coordinate system.

[0165] Static object points in the world coordinate system are stitched together to obtain a global point cloud map.

[0166] In an embodiment of the present application, static object points in the world coordinate system are spliced ​​to ultimately obtain a global point cloud map.

[0167] In an embodiment of the present application, for the first point cloud data of the i-th frame, according to the IMU data collected between the first point cloud data of the i-1th frame and the first point cloud data of the i-th frame, the first motion parameter between the first point cloud data of the i-1th frame and the first point cloud data of the i-th frame is calculated, as the i-th first motion parameter, the IMU data includes acceleration and angular velocity, the first motion parameter includes: displacement and angle change, i is a positive integer greater than or equal to 2 and less than or equal to N, the i-th frame first point cloud data and the i-1th frame first point cloud data are matched, and the second motion parameter between the i-1th frame first point cloud data and the i-th frame first point cloud data is obtained. Motion parameters, optimize the i-th first motion parameter through the i-th second motion parameter to obtain the i-th target motion parameter, update the i-1-th mine car posture information according to the i-th target motion parameter to obtain the i-th mine car posture information, the first mine car posture information is the initial posture information, and the N mine car posture information are jointly optimized to obtain N optimized mine car posture information. According to the N optimized mine car posture information of the N frames of the first point cloud data, the N first point cloud data are used to generate a global point cloud map. By constructing a global point cloud map, the comprehensiveness and accuracy of map construction are improved, and a foundation is laid for subsequent local map updates.

[0168] Figure 3 A flowchart of a third embodiment of a method for constructing a grid map in a mining scenario provided in an embodiment of the present application is shown in FIG. Figure 3 As shown in the above Figure 1 or Figure 2Based on the embodiment shown, a specific implementation method of locally updating the global point cloud map through the second point cloud data in step S103 is:

[0169] S301: extracting a first key point from a global point cloud map, and extracting a second key point from second point cloud data.

[0170] In an embodiment of the present application, optionally, the first key point is extracted from the global point cloud map and the second key point is extracted from the second point cloud data through an ISS (Intrinsic Shape Signatures) algorithm.

[0171] S302: Acquire a first key geometric feature around each first key point, and acquire a second key geometric feature around each second key point.

[0172] In the embodiment of the present application, the first key geometric features around each first key point are obtained through the descriptor, and the second key geometric features around each second key point are obtained through the descriptor.

[0173] Specifically, a descriptor is a mathematical representation used to describe local geometric shapes or feature points. After extracting the first key point from the global point cloud map, the ISS algorithm calculates the descriptor of the surrounding area of ​​the first key point to obtain the first key geometric feature. Similarly, after extracting the second key point from the second point cloud data, the ISS algorithm calculates the descriptor of the surrounding area of ​​the second key point to obtain the second key geometric feature.

[0174] S303: Match the first key geometric feature and the second key geometric feature to obtain a first matching degree, and use the point cloud submap corresponding to the second key geometric feature whose first matching degree is greater than or equal to a preset matching degree threshold in the second point cloud data as the target point cloud submap.

[0175] In the embodiment of the present application, optionally, a K-dimensional tree (KD tree) is constructed to efficiently match the first key geometric feature and the second key geometric feature to obtain a first matching degree, and the point cloud submap corresponding to the second key geometric feature whose first matching degree is greater than or equal to a preset matching degree threshold in the second point cloud data is used as the target point cloud submap. More optionally, when matching, a method using a spatial partitioning data structure can be used to accelerate the matching process. Specifically, a coarse matching is first performed using key geometric features, and then points with a higher matching degree are further finely matched by comparing the spatial positions of key points.

[0176] S304: Match the second point cloud data with the target point cloud submap to obtain a second matching degree, and update the target point cloud submap corresponding to the second matching degree when the second matching degree is greater than or equal to a preset matching degree threshold using the second point cloud data.

[0177] In the embodiment of the present application, the key points extracted from the second point cloud data are used to find the nearest neighbor and the second nearest neighbor of each key point in the target point cloud map, and the ratio of the nearest neighbor distance and the second nearest neighbor distance of each key point is calculated as the second matching degree. If the calculated second matching degree is greater than or equal to the preset matching degree threshold, the corresponding target point cloud submap is integrated into the global point cloud map, and the global point cloud map is locally updated.

[0178] In an embodiment of the present application, a first key point is extracted from a global point cloud map, and a second key point is extracted from a second point cloud data, a first key geometric feature around each first key point is obtained, and a second key geometric feature around each second key point is obtained, the first key geometric feature and the second key geometric feature are matched to obtain a first matching degree, and a point cloud submap corresponding to a second key geometric feature whose first matching degree is greater than or equal to a preset matching degree threshold in the second point cloud data is used as a target point cloud submap, the second point cloud data and the target point cloud submap are matched to obtain a second matching degree, and the target point cloud submap corresponding to the second matching degree greater than or equal to the preset matching degree threshold is updated through the second point cloud data. By locally updating the global point cloud map, the map can be updated in real time during the operation process to avoid path planning misleading due to changes in the mountain mining surface, thereby improving operation efficiency.

[0179] Figure 4 A grid map construction device in a mine scenario provided in an embodiment of the present application. A grid map construction device in a mine scenario provided in the present application comprises: an acquisition module 41 and a processing module 42; wherein:

[0180] The acquisition module 41 is used to acquire M frames of IMU data collected by the inertial measurement unit on the mine car and N frames of first point cloud data collected by the laser radar on the mine car, where M and N are positive integers greater than or equal to 1; the processing module 42 is used to construct a global point cloud map in the mine scene based on the M frames of IMU data and the N frames of first point cloud data; the processing module 42 is also used to collect the second point cloud data in real time, and locally update the global point cloud map through the second point cloud data; the processing module 42 is also used to delete the ground points from the global point cloud map to obtain the elevation point cloud map; the processing module 42 is also used to determine the number of adjacent points within a preset distance range around each point in the elevation point cloud map, and determine the point whose number of adjacent points is greater than or equal to the preset neighboring point number threshold as the core point, so as to add the adjacent points and core points within the preset distance range to a point cluster; the processing module 52 is also used to generate mountain edge data based on points in the elevation point cloud map that do not exist in any point cluster, so as to generate a raster map based on the mountain edge data.

[0181] Figure 5 A schematic diagram of the structure of an electronic device embodiment 1 provided in the present application. Figure 5 The electronic device provided in this embodiment includes: at least one processor 51 and a memory 52. ​​The processor 51 and the memory 52 are connected via a bus 53.

[0182] The specific implementation process of the processor 51 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0183] In the above Figure 5 In the illustrated embodiment, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0184] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0185] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0186] The present application also provides a computer-readable storage medium on which computer-executable instructions are stored. When a processor executes the computer-executable instructions, a grid map construction method in a mining scenario as described above is implemented.

[0187] The computer-readable storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The computer-readable storage medium may be any available medium that can be accessed by a general or special purpose computer.

[0188] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0189] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0190] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0191] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0192] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0193] The present application also provides a computer program product, including a computer program. When the computer program is executed by a processor, it is used to implement the above-mentioned grid map construction method in a mining scenario.

[0194] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0195] It should be further noted that, although the various steps in the flowchart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0196] It should be understood that the above-mentioned device embodiments are only illustrative, and the device of the present application can also be implemented in other ways. For example, the division of units / modules in the above-mentioned embodiments is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units, modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed.

[0197] In addition, unless otherwise specified, each functional unit / module in each embodiment of the present application may be integrated into one unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The above-mentioned integrated unit / module may be implemented in the form of hardware or in the form of a software program module.

[0198] If the integrated unit / module is implemented in the form of hardware, the hardware may be a digital circuit, an analog circuit, etc. The physical implementation of the hardware structure includes but is not limited to transistors, memristors, etc. If not specifically stated, the processor may be any appropriate hardware processor, such as a CPU, a GPU, an FPGA, a DSP, an ASIC, etc. If not specifically stated, the storage unit may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc.

[0199] If the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0200] In the above embodiments, the description of each embodiment has its own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0201] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0202] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for constructing a grid map in a mine scene, characterized in that: include: Acquire M frames of IMU data collected by an inertial measurement unit on the mine car and N frames of first point cloud data collected by a laser radar on the mine car, where M and N are positive integers greater than or equal to 1; Constructing a global point cloud map of the mine scene according to the M frames of IMU data and the N frames of the first point cloud data; Collecting second point cloud data in real time, and locally updating the global point cloud map through the second point cloud data; Deleting ground points from the global point cloud map to obtain an elevation point cloud map; For each point in the elevation point cloud map, determine the number of adjacent points within a preset distance range around the point, and determine the point whose number of adjacent points is greater than or equal to a preset threshold of the number of adjacent points as a core point, so as to add the adjacent points within the preset distance range and the core point to a point cluster; Mountain edge data are generated according to points in the elevation point cloud map that do not exist in any point cluster, so as to generate a grid map according to the mountain edge data.

2. The method according to claim 1, characterized in that: The step of deleting ground points from the global point cloud map to obtain an elevation point cloud map includes: The process of determining the ground point set is executed multiple times to obtain multiple ground point sets, and the process of determining the ground point set is executed each time to obtain one ground point set; Determine a ground point set including the largest number of ground points from multiple ground point sets as a target ground point set, and delete the target ground point set from the global point cloud map to obtain an elevation point cloud map; The process of determining the ground point set includes: Randomly select three reference points from the global point cloud map to determine a plane passing through the three reference points; Calculating the distance between each point in the global point cloud map and the plane; A ground point set is generated according to the points in the global point cloud map whose distance is less than or equal to a preset distance threshold.

3. The method according to claim 1, characterized in that The step of generating mountain edge data according to points in the elevation point cloud map that do not exist in any point cluster includes: The points in the elevation point cloud map that do not exist in any point cluster are regarded as mountain edge points; Smoothing the mountain edge points to obtain smoothed mountain edge points; Performing a continuity check on the smooth mountain edge points to obtain a continuity check result; If the continuity check result indicates that the smooth mountain edge points are continuous, the mountain edge data is generated according to the smooth mountain edge points.

4. The method according to claim 1, characterized in that: The step of constructing a global point cloud map in the mine scene according to the M frames of IMU data and the N frames of the first point cloud data includes: For the first point cloud data of the i-th frame, according to the IMU data collected between the first point cloud data of the i-1-th frame and the first point cloud data of the i-th frame, a first motion parameter between the first point cloud data of the i-1-th frame and the first point cloud data of the i-th frame is calculated as the i-th first motion parameter, the IMU data includes acceleration and angular velocity, the first motion parameter includes: displacement and angle change, i is a positive integer greater than or equal to 2 and less than or equal to N; Matching the first point cloud data of the i-th frame with the first point cloud data of the i-1-th frame to obtain a second motion parameter between the first point cloud data of the i-1-th frame and the first point cloud data of the i-th frame; Optimizing the i-th first motion parameter by using the i-th second motion parameter to obtain the i-th target motion parameter; According to the i-th target motion parameter, the i-1th mine car posture information is updated to obtain the i-th mine car posture information, and the first mine car posture information is the initial posture information; Jointly optimize the N mine car posture information to obtain N optimized mine car posture information; According to the N optimized mine car posture information of the N frames of first point cloud data, a global point cloud map is generated from the N first point cloud data.

5. The method according to claim 4, characterized in that The matching of the i-th frame and the i-1-th frame includes: For any one of the i-th frame of first point cloud data and the i-1-th frame of first point cloud data, dividing the frame of first point cloud data into a plurality of scan lines, each of the scan lines including a plurality of points in the frame of first point cloud data; For each point in each of the scan lines, calculating the curvature of the point; Determine a point whose curvature is greater than or equal to a preset curvature threshold as a feature point; Match the feature points in the first point cloud data of the i-th frame with the feature points in the first point cloud data of the i-1-th frame.

6. The method according to claim 4, characterized in that The step of generating a global point cloud map from the N pieces of N optimized mine car posture information of the N frames of first point cloud data comprises: Determine a static object point in each frame of first point cloud data, wherein the static object point is a point other than a dynamic object point; According to the N optimized mine car posture information, convert the N static object points in the first point cloud data into a world coordinate system; The static object points in the world coordinate system are spliced ​​to obtain the global point cloud map.

7. The method according to any one of claims 1 to 6, characterized in that The locally updating the global point cloud map by using the second point cloud data includes: Extracting a first key point from the global point cloud map, and extracting a second key point from the second point cloud data; Acquire a first key geometric feature around each of the first key points, and acquire a second key geometric feature around each of the second key points; Matching the first key geometric feature with the second key geometric feature to obtain a first matching degree, and taking a point cloud submap corresponding to a second key geometric feature whose first matching degree is greater than or equal to a preset matching degree threshold in the second point cloud data as a target point cloud submap; The second point cloud data and the target point cloud submap are matched to obtain a second matching degree, and the target point cloud submap corresponding to the second matching degree is updated by the second point cloud data when the second matching degree is greater than or equal to a preset matching degree threshold.

8. A grid map construction device in a mine scene, characterized in that: include: An acquisition module is used to acquire M frames of IMU data collected by an inertial measurement unit on the mine car and N frames of first point cloud data collected by a laser radar on the mine car, where M and N are positive integers greater than or equal to 1; A processing module, used for constructing a global point cloud map of the mine scene according to the M frames of IMU data and the N frames of the first point cloud data; The processing module is further used to collect second point cloud data in real time, and locally update the global point cloud map through the second point cloud data; The processing module is further used to delete ground points from the global point cloud map to obtain an elevation point cloud map; The processing module is further used to determine, for each point in the elevation point cloud map, the number of adjacent points within a preset distance range around the point, and determine a point whose number of adjacent points is greater than or equal to a preset threshold of the number of adjacent points as a core point, so as to add the adjacent points within the preset distance range and the core point to a point cluster; The processing module is also used to generate mountain edge data according to points in the elevation point cloud map that do not exist in any point cluster, so as to generate a grid map according to the mountain edge data.

9. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

11. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 7 when being executed by a processor.

Images