Automated lithotripsy method, system, device, and storage medium

Abstract

The application discloses an automatic stone crushing method, system, device and storage medium. Point cloud data is acquired by using a laser radar. The position and quantity of stone blocks are determined through division and clustering based on the acquired point cloud data. The coordinates of a crushing point corresponding to each stone block and a crushing direction vector are determined, so that accurate stone crushing parameters can be obtained. The stone crushing device can be controlled by using the stone crushing parameters to complete automatic stone crushing. Compared with an image processing method, the accuracy of crushing point coordinate detection can be effectively ensured, and a crushing direction vector can be constructed, that is, a stone crushing direction is given, so that the effect of automatic stone crushing is further ensured.

Description

Technical Field

[0001] This application relates to the field of mining machinery, and in particular to an automatic stone crushing method, system, device and storage medium. Background Technology

[0002] Secondary ore crushing refers to the process of using the chisel of a breaker hammer to further crush large pieces of ore that cannot be screened out by the grid after primary blasting or crushing. The aim is to reduce the ore particle size to meet the requirements for transportation or mineral processing. Traditionally, crushing is typically accomplished manually using a crushing device. However, with technological advancements, methods based on image detection have been proposed for automated crushing. However, image detection methods usually require the target material to possess certain characteristics, such as shape, texture, and color. The shape of blasted rocks is unstable, and various forms are possible. Therefore, the detection results are highly unstable, leading to poor crushing efficiency. Summary of the Invention

[0003] This application aims to provide an automated stone crushing method, system, apparatus, and storage medium that improves the accuracy of ore crushing.

[0004] An automated stone-breaking method according to a first aspect embodiment of this application includes:

[0005] Acquire the spatial point cloud data of the raster corresponding to the raster in a three-dimensional coordinate system;

[0006] Determine the point cloud data of stones in the grid spatial point cloud data to be tested, wherein the point cloud data of stones represents the geometric features of the stones to be broken;

[0007] A clustering algorithm is performed on the stone point cloud data to obtain multiple stone point cloud clusters;

[0008] A crushing preprocessing strategy is executed for each of the stone point cloud clusters to obtain the coordinates of the crushing point and the crushing direction vector corresponding to each of the stone point cloud clusters.

[0009] Based on the coordinates of the crushing point and the crushing direction vector, the stone crushing device is controlled to complete the crushing process;

[0010] The crushed stone pretreatment strategy includes:

[0011] Determine the center coordinates of the stone point cloud cluster in a three-dimensional spatial coordinate system;

[0012] The coordinates of the breakage point are determined based on the center coordinates, and the coordinates of the breakage point are located within the cluster of stone points.

[0013] Using the coordinates of the broken point as the center and a preset distance threshold as the radius, obtain a set of point clouds for fitting from the cluster of stone point clouds;

[0014] Plane fitting is performed on the point cloud set to obtain the broken foundation plane;

[0015] The normal vector of the fractured foundation plane is determined to obtain the fracture direction vector.

[0016] According to a second aspect embodiment of the present application, the automatic stone crushing system includes a control unit, a lidar electrically connected to the control unit, and a stone crushing device electrically connected to the control unit. The control unit is used to execute the automatic stone crushing method as described in the first aspect embodiment.

[0017] According to the third aspect of the present application, the automatic stone crushing device includes a grid point cloud data acquisition module, which is used to acquire the grid spatial point cloud data of the grid to be measured in a three-dimensional spatial coordinate system.

[0018] The gravel point cloud acquisition module is used to determine the stone point cloud data in the grid spatial point cloud data to be tested, wherein the stone point cloud data represents the geometric features of the stone to be broken.

[0019] The point cloud cluster acquisition module is used to perform a clustering algorithm on the stone point cloud data to obtain multiple stone point cloud clusters;

[0020] The crushed stone parameter acquisition module is used to perform a crushed stone preprocessing strategy on each of the stone point cloud clusters to obtain the coordinates of the crushing point and the crushing direction vector corresponding to each of the stone point cloud clusters.

[0021] The stone crushing execution module is used to control the stone crushing device to complete the crushing based on the coordinates of the crushing point and the crushing direction vector;

[0022] The crushed stone pretreatment strategy includes:

[0023] Determine the center coordinates of the stone point cloud cluster in a three-dimensional spatial coordinate system;

[0024] The coordinates of the breakage point are determined based on the center coordinates, and the coordinates of the breakage point are located within the cluster of stone points.

[0025] Using the coordinates of the broken point as the center and a preset distance threshold as the radius, obtain a set of point clouds for fitting from the cluster of stone point clouds;

[0026] Plane fitting is performed on the point cloud set to obtain the broken foundation plane;

[0027] The normal vector of the fractured foundation plane is determined to obtain the fracture direction vector.

[0028] A computer-readable storage medium according to a fourth aspect embodiment of the present application stores computer-executable instructions for performing the automatic stone crushing method as described in the first aspect embodiment above.

[0029] This application discloses an automatic stone crushing method, system, apparatus, and storage medium. It utilizes LiDAR to acquire point cloud data. Based on this point cloud data, the location and quantity of stones are determined through processes such as segmentation and clustering. By determining the coordinates of the crushing point and the crushing direction vector corresponding to each stone, accurate crushing parameters can be obtained. These parameters can then be used to control the stone crushing device to complete automatic stone crushing. Compared to image processing methods, this approach effectively ensures the accuracy of crushing point coordinate detection and also constructs the crushing direction vector, thus providing the crushing direction and further guaranteeing the effectiveness of automatic stone crushing.

[0030] Other features and advantages of this application will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing this application. Attached Figure Description

[0031] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which:

[0032] Figure 1 A flowchart of an automatic stone crushing method provided in an embodiment of this application;

[0033] Figure 2 This is a schematic diagram of a lidar and grid arrangement provided in an embodiment of this application;

[0034] Figure 3 A schematic diagram of raster-based point cloud data provided in an embodiment of this application;

[0035] Figure 4 This is a schematic diagram illustrating the construction of intermediate point cloud data by looking up a table, as provided in an embodiment of this application.

[0036] Figure 5 A schematic diagram of pixel grid division provided in an embodiment of this application;

[0037] Figure 6 This is a schematic diagram of a checklist provided in one embodiment of this application.

[0038] Figure label:

[0039] LiDAR 100, grid 200. Detailed Implementation

[0040] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0041] In the description of this application, the use of terms such as "first," "second," etc., is for the purpose of distinguishing technical features only and should not be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated or the order of the technical features indicated.

[0042] In the description of this application, it should be understood that the orientation descriptions, such as up, down, etc., are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application.

[0043] In the description of this application, it should be noted that, unless otherwise explicitly defined, terms such as "setup," "installation," and "connection" should be interpreted broadly, and those skilled in the art can reasonably determine the specific meaning of the above terms in this application in conjunction with the specific content of the technical solution.

[0044] The technical solution of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are some embodiments of this application, not all embodiments.

[0045] See Figure 1 As shown, Figure 1 This is a flowchart of an automatic stone crushing method provided in one embodiment of this application. The automatic stone crushing method includes, but is not limited to, the following steps:

[0046] Acquire the spatial point cloud data of the grid cell corresponding to grid cell 200 in the three-dimensional coordinate system;

[0047] Identify the point cloud data of stones in the raster spatial point cloud data to be tested. The point cloud data of stones represents the geometric features of the stones to be broken.

[0048] A clustering algorithm was performed on the stone point cloud data to obtain multiple stone point cloud clusters;

[0049] A crushing preprocessing strategy is applied to each stone point cloud cluster to obtain the coordinates of the crushing points and the crushing direction vector corresponding to each stone point cloud cluster.

[0050] The crushing device is controlled to complete the crushing process based on the coordinates of the crushing point and the crushing direction vector.

[0051] Among them, the crushed stone pretreatment strategy includes:

[0052] Determine the center coordinates of the stone point cloud cluster in a three-dimensional spatial coordinate system;

[0053] The coordinates of the breakpoint are determined based on the center coordinates, and the breakpoint coordinates are located within the cluster of stone points.

[0054] Using the coordinates of the broken point as the center and a preset distance threshold as the radius, obtain a set of point clouds for fitting from the point cloud cluster of stones;

[0055] Plane fitting is performed on the point cloud set to obtain the broken foundation plane;

[0056] Determine the normal vector of the fractured foundation plane to obtain the fracture direction vector.

[0057] To better describe the automatic stone crushing method of this application embodiment, a brief description of the specific application scenario of this application embodiment is given first. (Reference) Figure 2 The spacing between the horizontal beams and the vertical beams in the grid 200 needs to be designed according to actual requirements and has been determined before the method in this application is executed; therefore, this application does not impose specific constraints. After a blast, the pile of rocks is filtered through the grid 200, and larger rocks remain on the grid 200, requiring subsequent crushing. In this application embodiment, a lidar 100 is used to collect the laser point cloud data of these rocks and the grid 200, and then the crushing parameters are obtained based on the laser point cloud data. In this application embodiment, the lidar 100 is positioned above the grid 200. For ease of computation, the lidar 100 can be positioned directly above and facing the grid 200.

[0058] The automatic stone crushing method of this application embodiment is described below based on the above scenario. It should be noted that the above scenario setting is for better explanation of the embodiments of this application and should not be regarded as a limitation on the protection scope of this application.

[0059] The point cloud data of the stones collected by the lidar 100 is in the lidar 100 coordinate system. Therefore, it is necessary to first transform this point cloud data into a three-dimensional spatial coordinate system, that is, to obtain the point cloud data of the grid to be measured. The xy plane of the above-mentioned three-dimensional spatial coordinate system is on the same plane as the surface of the grid 200. The origin can be set on the grid 200 or at any position outside the grid 200. For the convenience of calculation, it will be set at a vertex of the grid 200, such as the lower right vertex.

[0060] The obtained point cloud data of the grid space to be tested includes the point cloud data of grid 200 and the stone. At this time, it is necessary to extract the point cloud data of the stone that only contains the stone, because the existence of the point cloud data corresponding to grid 200 will interfere with the subsequent determination of the spatial state of the stone.

[0061] The extracted stone point cloud data are not correlated with each other. Therefore, clustering algorithms can be used to process the stone point cloud data, resulting in multiple stone point cloud clusters, each corresponding to an individual stone. The DBSCAN clustering algorithm can be used; by applying DBSCAN based on connectivity, the point cloud can be clustered into independent clusters. It should be noted that there are many clustering algorithms available, and other algorithms can be selected according to actual needs.

[0062] After obtaining multiple stone point cloud clusters, a crushing preprocessing strategy needs to be performed on each stone point cloud cluster to determine the coordinates of the crushing point and the crushing direction vector corresponding to each stone point cloud cluster.

[0063] The above-mentioned stone crushing pretreatment strategy first obtains the center coordinates by determining the center positions of multiple point clouds in the stone point cloud cluster. Considering that the determined center coordinates may not necessarily fall on the stone, it is necessary to use the center coordinates to determine the coordinates of the breaking point on the stone. The breaking point coordinates can be selected from the point closest to the center coordinates, and the breaking point coordinates are the striking points of the subsequent stone crushing device.

[0064] After determining the coordinates of the crushing point, it is necessary to further determine the striking direction of the crushing device. At this time, the coordinates of the crushing point are used to determine the crushing foundation plane within a small range. By obtaining the normal vector of the crushing foundation plane, the crushing direction vector can be determined.

[0065] The aforementioned fractured foundation plane can be obtained by directly acquiring a set of planar point clouds with the fracture point coordinates as the center and a preset distance threshold as the radius, and then performing planar fitting.

[0066] By obtaining the coordinates of the breaking point and the breaking direction vector corresponding to each stone cluster, the striking point and striking direction for each stone are obtained. At this point, the stone crushing device can be controlled to complete the crushing process based on the coordinates of the breaking point and the breaking direction vector. It should be noted that when there are multiple stones, they can be crushed one by one in a "Z" shaped sequence, or any other sequence can be selected according to requirements.

[0067] In the automatic stone crushing method of this application embodiment, point cloud data is acquired using a lidar 100. Based on the acquired point cloud data, the position and quantity of stones are determined through processes such as segmentation and clustering. By determining the coordinates of the crushing point and the crushing direction vector corresponding to each stone, accurate stone crushing parameters can be obtained. These parameters can then be used to control the stone crushing device to complete automatic stone crushing. Compared with image processing methods, this method can effectively ensure the accuracy of crushing point coordinate detection and also construct the crushing direction vector, thus providing the stone crushing direction and further ensuring the effectiveness of automatic stone crushing.

[0068] In some embodiments, the acquisition of the point cloud data of the grid space corresponding to the grid 200 in the three-dimensional spatial coordinate system includes:

[0069] Acquire the laser point cloud data of the grid 200 to be measured collected by the lidar 100, wherein the lidar 100 is arranged above the grid 200;

[0070] The test grid spatial point cloud data of the laser point cloud data to be tested in the three-dimensional spatial coordinate system is obtained according to the first coordinate transformation relationship obtained in advance. The first coordinate transformation relationship represents the spatial position relationship between any point in the three-dimensional spatial coordinate system and the coordinate system of the laser radar 100.

[0071] The laser point cloud data of the grid 200 collected by the lidar 100 can be directly obtained by the lidar 100 arranged above the grid 200.

[0072] The first coordinate transformation relationship mentioned above is the transformation relationship between the three-dimensional spatial coordinate system and the LiDAR 100 coordinate system. By using the first coordinate transformation relationship, the coordinates of any point cloud in the LiDAR 100 coordinate system can be converted into coordinates in the three-dimensional spatial coordinate system. Thus, the test grid spatial point cloud data can be obtained from the test laser point cloud data, which facilitates the application of some subsequent algorithms.

[0073] In some embodiments, the first coordinate transformation relationship is obtained by the following steps:

[0074] Acquire point cloud data from grid 200 collected by lidar 100;

[0075] Construct a three-dimensional spatial coordinate system based on the plane containing grid 200;

[0076] Determine the three-dimensional coordinates of multiple first corner points on grid 200 in a three-dimensional spatial coordinate system, and the different positions of the multiple first corner points on grid 200;

[0077] Obtain the corner radar coordinates of multiple first corner points in the lidar 100 coordinate system;

[0078] The first coordinate transformation relationship is obtained based on the three-dimensional coordinates of the first corner point and the radar coordinates of the corner point corresponding to multiple first corner points.

[0079] The point cloud data constructed by the above grid can be directly collected by the lidar 100 when no stones have been removed from the grid 200.

[0080] The xy plane of the above three-dimensional spatial coordinate system is on the same plane as the surface of grid 200. The origin can be set on grid 200 or at any position outside grid 200. For ease of calculation, it will be set at a vertex of grid 200, such as the lower right vertex.

[0081] The aforementioned multiple first corner points can be selected at different positions in grid 200, which allows for sufficient spatial distance between the multiple corner points, thus improving the accuracy of the obtained first coordinate transformation relationship.

[0082] For any corner point, the corner radar coordinates in the 100 coordinate system and the three-dimensional coordinates of the first corner point in the three-dimensional coordinate system can be directly obtained. After obtaining multiple sets of corresponding coordinates, the first coordinate transformation relationship can be constructed. The specific construction process can be based on the least squares method, or other algorithms that can construct the transformation relationship can be selected.

[0083] In some embodiments, determining stone point cloud data in the grid spatial point cloud data to be tested includes:

[0084] The spatial point cloud data of the grid to be tested is filtered and denoised to obtain the intermediate point cloud data of the grid to be tested.

[0085] In the point cloud data of the grid to be measured, identify the first point cloud data projected onto grid 200 and the second point cloud data projected off grid 200;

[0086] The height of the first point cloud data is determined, and the height of the third point cloud data is obtained if it is greater than the preset height threshold.

[0087] Stone point cloud data is obtained based on the third point cloud data and the second point cloud data.

[0088] The above-mentioned raster spatial point cloud data to be tested contains certain interference. Therefore, filtering and noise reduction are used to remove some abnormal data, thereby obtaining the intermediate point cloud data of the raster to be tested.

[0089] After obtaining the point cloud data of the center of the grid to be tested, the first point cloud data projected onto the grid 200 and the second point cloud data projected onto the grid 200 can be determined. The second point cloud data projected onto the grid 200 can be determined as a stone point cloud. The first point cloud data projected onto the grid 200 area needs to be further judged.

[0090] Based on the actual situation, the first point cloud data projected onto the grid 200 area needs further height determination. Point clouds with a certain height are identified as stone point clouds, while point clouds that are basically close to the grid 200 can be identified as the grid 200 itself. These point clouds that exceed the preset height threshold can be recorded as the third point cloud data.

[0091] The third point cloud data, together with the second point cloud data, constitutes the stone point cloud data. At this point, the stone point cloud data may include point clouds corresponding to multiple stones.

[0092] In some embodiments, determining the first point cloud data projected onto the grid 200 and the second point cloud data projected not onto the grid 200 in the intermediate point cloud data of the grid to be measured includes:

[0093] According to the pre-acquired checklist, a lookup operation is performed on the intermediate point cloud data of the grid to be tested to obtain the lookup results. The checklist includes the grid arrangement status corresponding to each position in the detection area where grid 200 is located. The detection area is bounded by the outer periphery of grid 200.

[0094] Based on the table lookup results, the first point cloud data projected onto grid 200 and the second point cloud data projected onto grid 200 are determined.

[0095] To determine whether the projection is within the 200 grid area, a checklist can be used directly, which can greatly reduce the computation time.

[0096] The checklist contains the grid layout status for each location within the 200-grid boundary. For details, please refer to... Figure 5 , Figure 5 The area shown is where grid 200 is located, and this area has been divided into multiple smaller grids. The size of the smaller grids can be constructed by taking into account the width of each horizontal and vertical beam in the grid 200 frame, ultimately resulting in the following: Figure 6 The results shown indicate that the areas marked with "0" are the horizontal and vertical beams, which are on grid 200, while the areas marked with "1" are outside grid 200.

[0097] In some embodiments, the checklist is obtained by the following steps:

[0098] Acquire point cloud data from grid 200 collected by lidar 100;

[0099] Based on the pre-acquired first coordinate transformation relationship, the raster point cloud data is transformed to the three-dimensional spatial coordinate system to obtain the lookup table point cloud data. The first coordinate transformation relationship represents the spatial positional relationship between any point in the three-dimensional spatial coordinate system and the coordinate system of the lidar 100 where the lidar 100 is located.

[0100] The point cloud data constructed by looking up the table is subjected to pass-through filtering to obtain intermediate point cloud data constructed by looking up the table.

[0101] Based on the lookup table, intermediate point cloud data is constructed to obtain raster point cloud 2D data;

[0102] A checklist is obtained based on the two-dimensional data of the grid point cloud. The checklist includes the grid arrangement status corresponding to each position in the detection area where grid 200 is located. The grid arrangement status is used to characterize whether any point on grid 200 is on grid 200. The detection area is bounded by the outer perimeter of grid 200.

[0103] refer to Figure 3 When constructing the check table, point cloud data needs to be collected when no object is placed on grid 200 to obtain grid construction point cloud data of grid 200; then, the grid construction point cloud data is converted into table construction point cloud data in three-dimensional spatial coordinate system using the already constructed first coordinate transformation relationship, as shown in the figure.

[0104] Next, a filtering operation is performed on grid 200 to remove point cloud data outside the boundaries of grid 200 and point cloud data not located on the horizontal and vertical beams, resulting in intermediate point cloud data constructed by looking up a table. Figure 4 .

[0105] The purpose of the checklist is to improve computational efficiency. Therefore, this embodiment does not construct a three-dimensional checklist, but directly constructs a two-dimensional checklist. The two-dimensional raster point cloud data can be obtained by directly compressing the intermediate point cloud data constructed from the checklist. Specifically, the compression process can be completed by directly setting the Z coordinate value of all points to 0.

[0106] Next, the 2D raster point cloud data is divided into smaller grids. Assigning values ​​to these smaller grids yields the checklist. For details, please refer to [link / reference needed]. Figure 5 First, the L0*W0 region can be divided into a pixel grid. Create a range of cells, each s0*s0 in size, and denote this range as R0. Simultaneously, create... First, create an array Arr0 of size 1. Then, label the point cloud within the region of the raster point cloud 2D data, using multiple polygons to encompass the point cloud of the raster region 200, denoted as R1. Finally, set all cells in R0 that intersect with R1 to 0, denoted as array Arr1. (Refer to...) Figure 6 At this time, any point P n (x n ,y n ,z n This allows for table lookup, retrieving values ​​from the Arr1 array. If the position is 1, then the point cloud does not fall directly above or below grid 200; otherwise, if the position is 0, then it falls directly above or below grid 200.

[0107] In some embodiments, a clustering algorithm is performed on the stone point cloud data to obtain multiple stone point cloud clusters, including:

[0108] A clustering algorithm was performed on the stone point cloud data to obtain multiple candidate point cloud clusters;

[0109] A filtering operation is performed on multiple candidate point cloud clusters whose number of points is less than a preset threshold, resulting in multiple stone point cloud clusters.

[0110] After performing a clustering algorithm on the stone point cloud data, multiple candidate point cloud clusters are obtained. These clusters may contain very few points due to various influences during the point cloud acquisition process and the clustering process itself. These clusters are actually error data; that is, there should be no very small stones on a grid of 200. Therefore, it is necessary to remove the clusters with fewer points to obtain the remaining stone point cloud clusters.

[0111] In some embodiments, controlling the stone crushing device to complete the crushing process based on the coordinates of the crushing point and the crushing direction vector includes:

[0112] Based on the pre-acquired second coordinate transformation relationship and the coordinates of the crushing point and the crushing direction vector corresponding to each stone point cloud cluster, the stone crushing device is controlled to complete the crushing in the base coordinate system of the robotic arm. The second coordinate transformation relationship represents the spatial position transformation relationship between any point in the three-dimensional spatial coordinate system and the base coordinate system of the robotic arm.

[0113] The stone crushing device consists of a robotic arm and a stone crushing hammer. By controlling the movement of the robotic arm, the striking point and direction of the stone crushing hammer can be adjusted, thereby completing the stone crushing.

[0114] The robotic arm operates in a base coordinate system, while the calculated coordinates of the crushing point and the crushing direction vector correspond to a three-dimensional coordinate system. Therefore, to better enable the robotic arm to control the crushing hammer and complete the crushing, the coordinates of the crushing point and the crushing direction vector need to be transformed into the robotic arm's base coordinate system before the crushing control can be completed. This transformation process is directly accomplished using the pre-acquired second coordinate transformation relationship.

[0115] The second coordinate transformation relationship mentioned above is the transformation relationship between the three-dimensional spatial coordinate system and the robot arm base coordinate system. Using the second coordinate transformation relationship, the coordinates of any point cloud in the three-dimensional spatial coordinate system can be converted into the coordinates in the robot arm base coordinate system.

[0116] In some embodiments, the second coordinate transformation relationship is obtained by the following steps:

[0117] Determine the three-dimensional coordinates of multiple second corner points on grid 200, and the different positions of the multiple second corner points on grid 200;

[0118] Obtain the corner coordinates of multiple second corner points in the robot arm's base coordinate system;

[0119] The second coordinate transformation relationship is obtained based on the three-dimensional coordinates of the second corner points and the coordinates of the corner point robotic arm.

[0120] The xy plane of the above three-dimensional spatial coordinate system is on the same plane as the surface of grid 200. The origin can be set on grid 200 or at any position outside grid 200. For ease of calculation, it will be set at a vertex of grid 200, such as the lower right vertex.

[0121] The aforementioned multiple second corner points can be selected at different positions in grid 200, which allows for sufficient spatial distance between the multiple corner points, thus improving the accuracy of the obtained second coordinate transformation relationship.

[0122] For any corner point, the coordinates of the corner point in the base coordinate system and the 3D coordinates of the second corner point in the 3D coordinate system can be directly obtained. After obtaining multiple sets of corresponding coordinates, the second coordinate transformation relationship can be constructed. Specifically, the least squares method can be used for this construction process, or other algorithms capable of constructing the transformation relationship can be selected.

[0123] Here is a brief description of how to obtain the corner robot arm coordinates. By controlling the end-effector vertex of the robot arm to move to a certain position that needs to be transformed on grid 200, and recording the forward solution of the robot arm, we can obtain the expression of the position that needs to be transformed in the robot arm's base coordinate system, that is, obtain the corner robot arm coordinates.

[0124] In some embodiments, determining the center coordinates of the stone point cloud cluster in a three-dimensional spatial coordinate system includes:

[0125] The mean value of multiple point clouds in the stone point cloud cluster is calculated to obtain the center coordinates in the three-dimensional spatial coordinate system.

[0126] The center coordinates can be obtained by calculating the average values ​​of the x, y, and z dimensions of multiple point clouds in each point cloud cluster.

[0127] In some embodiments, determining the coordinates of the break point based on the center coordinates includes:

[0128] Determine the nearest point cloud data to the center coordinates within the stone point cloud cluster;

[0129] The spatial coordinates corresponding to the most recent point cloud data are determined as the coordinates of the breakpoint.

[0130] The calculated center coordinates may not necessarily coincide with a point cloud in the stone point cloud cluster, and there is a certain probability that they will fall directly outside the stone. However, when breaking stones, the striking point must be on the stone. Therefore, the spatial coordinates corresponding to the point cloud closest to the center coordinates will be determined as the breaking point coordinates.

[0131] In some embodiments, the preset distance threshold is obtained by the following steps:

[0132] Obtain the detection distance between the plane containing the lidar 100 and the grid 200;

[0133] Obtain the angular detection resolution of the LiDAR 100;

[0134] The preset distance threshold is obtained based on the detection distance and angular detection resolution.

[0135] If the preset distance threshold is too small, it will be impossible to fit a suitable plane. If the preset distance threshold is too large, the fitted plane may also be biased. In this embodiment, the setting of the preset distance threshold fully considers the detection distance and the angle detection resolution, so as to avoid the situation where the preset distance threshold is too large or too small.

[0136] Specifically, you can refer to the following formula:

[0137]

[0138] In the formula, γ0 is the preset distance threshold, and L d β represents the distance to the 100-grid 200-plane of the LiDAR, and β represents the angular resolution of the LiDAR 100. In some embodiments, an empirical value can be directly taken, β = 3 * γ0, to obtain a preset distance threshold.

[0139] This application also provides an automatic stone crushing system. The automatic stone crushing device includes a control unit, a lidar 100 electrically connected to the control unit, and a stone crushing device electrically connected to the control unit. The control unit is used to execute the automatic stone crushing method described above. Because the automatic stone crushing method described above is executed, the system possesses the beneficial effects brought about by the automatic stone crushing method described above.

[0140] The automatic stone crushing method provided in this application can be executed by an automatic stone crushing device. This application uses an automatic stone crushing device executing the automatic stone crushing method as an example to illustrate the automatic stone crushing iterative device provided in this application.

[0141] The automatic stone crushing device includes:

[0142] The 200-grid point cloud data acquisition module is used to acquire the spatial point cloud data of the grid to be measured corresponding to the 200 grid in the three-dimensional spatial coordinate system.

[0143] The gravel point cloud acquisition module is used to determine the stone point cloud data in the grid spatial point cloud data to be tested. The stone point cloud data represents the geometric features of the stone to be broken.

[0144] The point cloud cluster acquisition module is used to perform clustering algorithms on the stone point cloud data to obtain multiple stone point cloud clusters;

[0145] The crushed stone parameter acquisition module is used to perform crushed stone preprocessing strategies on each stone point cloud cluster to obtain the coordinates of the crushing point and the crushing direction vector corresponding to each stone point cloud cluster.

[0146] The stone crushing execution module is used to control the stone crushing device to complete the crushing process based on the coordinates of the crushing point and the crushing direction vector.

[0147] Among them, the crushed stone pretreatment strategy includes:

[0148] Determine the center coordinates of the stone point cloud cluster in a three-dimensional spatial coordinate system;

[0149] The coordinates of the breakpoint are determined based on the center coordinates, and the breakpoint coordinates are located within the cluster of stone points.

[0150] Using the coordinates of the broken point as the center and a preset distance threshold as the radius, obtain a set of point clouds for fitting from the point cloud cluster of stones;

[0151] Plane fitting is performed on the point cloud set to obtain the broken foundation plane;

[0152] Determine the normal vector of the fractured foundation plane to obtain the fracture direction vector.

[0153] Furthermore, one embodiment of this application provides a computer-readable storage medium storing computer-executable instructions that are executed by a processor or control module, causing the processor to perform the automatic stone crushing method in the above embodiments, for example, the method described above.

[0154] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which may include computer storage media or non-transitory media and communication media or transient media. As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc DVD or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0155] The embodiments of this application have been described in detail above with reference to the accompanying drawings. However, this application is not limited to the above embodiments. Within the scope of knowledge possessed by those skilled in the art, various changes can be made without departing from the spirit of this application.

Claims

1. An automatic stone crushing method, characterized in that, The automatic stone crushing method includes: Acquire the spatial point cloud data of the raster corresponding to the raster in a three-dimensional coordinate system; Determine the stone point cloud data in the grid spatial point cloud data to be tested, wherein the stone point cloud data characterizes the geometric features of the stone to be broken; A clustering algorithm is performed on the stone point cloud data to obtain multiple stone point cloud clusters; A crushing preprocessing strategy is executed on each of the stone point cloud clusters to obtain the coordinates of the crushing points and the crushing direction vector corresponding to each of the stone point cloud clusters. Based on the coordinates of the crushing point and the crushing direction vector, the stone crushing device is controlled to complete the crushing process; The crushed stone pretreatment strategy includes: Determine the center coordinates of the stone point cloud cluster in a three-dimensional spatial coordinate system; The coordinates of the breakage point are determined based on the center coordinates, and the coordinates of the breakage point are located within the cluster of stone points. Using the coordinates of the broken point as the center and a preset distance threshold as the radius, obtain a set of point clouds for fitting from the cluster of stone point clouds; Plane fitting is performed on the point cloud set to obtain the broken foundation plane; Determine the normal vector of the crushing foundation plane to obtain the crushing direction vector; The step of determining the stone point cloud data in the grid spatial point cloud data to be tested includes: The spatial point cloud data of the grid under test is filtered and denoised to obtain the intermediate point cloud data of the grid under test. In the point cloud data of the grid to be measured, determine the first point cloud data projected on the grid and the second point cloud data not projected on the grid. The height of the first point cloud data is determined, and the height of the third point cloud data is obtained if it is greater than a preset height threshold. Stone point cloud data is obtained based on the third point cloud data and the second point cloud data; The determination of the first point cloud data projected onto the grid and the second point cloud data not projected onto the grid in the intermediate point cloud data of the grid to be measured includes: A lookup operation is performed on the intermediate point cloud data of the grid to be tested according to the pre-acquired checklist to obtain the lookup result. The checklist includes the grid arrangement status corresponding to each position in the detection area where the grid is located. The detection area is bounded by the outer perimeter of the grid. Based on the lookup results, determine the first point cloud data projected onto the grid and the second point cloud data not projected onto the grid. The checklist is obtained through the following steps: Construct point cloud data from the grids collected by the lidar; The grid-constructed point cloud data is transformed to a three-dimensional spatial coordinate system according to the pre-acquired first coordinate transformation relationship to obtain lookup table-constructed point cloud data. The first coordinate transformation relationship represents the spatial positional relationship between any point in the three-dimensional spatial coordinate system and the coordinate system of the lidar where the lidar is located. The point cloud data constructed by the lookup table is subjected to pass-through filtering to obtain intermediate point cloud data constructed by the lookup table; Based on the table lookup, intermediate point cloud data is constructed to obtain raster point cloud two-dimensional data; A check table is obtained based on the two-dimensional data of the grid point cloud. The check table includes the grid arrangement state corresponding to each position in the detection area where the grid is located. The grid arrangement state is used to characterize whether any point on the grid is on the grid. The detection area is bounded by the outer perimeter of the grid.

2. The automatic stone crushing method according to claim 1, characterized in that, The acquisition of the spatial point cloud data of the raster corresponding to the raster in the three-dimensional coordinate system includes: Acquire the laser point cloud data of the grid to be measured by the lidar, wherein the lidar is arranged above the grid; The laser point cloud data to be tested is obtained in the three-dimensional spatial coordinate system based on the first coordinate transformation relationship obtained in advance. The first coordinate transformation relationship represents the spatial positional relationship between any point in the three-dimensional spatial coordinate system and the coordinate system of the lidar where the lidar is located.

3. The automatic stone crushing method according to claim 1, characterized in that, The step of controlling the stone crushing device to complete the crushing based on the coordinates of the crushing point and the crushing direction vector includes: Based on the pre-acquired second coordinate transformation relationship and the coordinates of the crushing point corresponding to each stone point cloud cluster and the crushing direction vector, the stone crushing device is controlled to complete the crushing in the robotic arm base coordinate system. The second coordinate transformation relationship represents the spatial position transformation relationship between any point in the three-dimensional spatial coordinate system and the robotic arm base coordinate system.

4. The automatic stone crushing method according to claim 1, characterized in that, Determining the coordinates of the break point based on the center coordinates includes: Determine the nearest point cloud data in the stone point cloud cluster that is closest to the center coordinates; The spatial coordinates corresponding to the nearest point cloud data are determined as the coordinates of the breakpoint.

5. An automatic stone crushing system, characterized in that, The automatic stone crushing system includes a control unit, a lidar electrically connected to the control unit, and a stone crushing device electrically connected to the control unit. The control unit is used to execute the automatic stone crushing method as described in any one of claims 1 to 4.

6. An automatic stone crushing device, characterized in that, The automatic stone crushing device includes: The raster point cloud data acquisition module is used to acquire the spatial point cloud data of the raster to be measured in a three-dimensional spatial coordinate system. The gravel point cloud acquisition module is used to determine the stone point cloud data in the grid spatial point cloud data to be tested, wherein the stone point cloud data represents the geometric features of the stone to be broken. The point cloud cluster acquisition module is used to perform a clustering algorithm on the stone point cloud data to obtain multiple stone point cloud clusters; The crushed stone parameter acquisition module is used to perform a crushed stone preprocessing strategy on each of the stone point cloud clusters to obtain the crushing point coordinates and crushing direction vectors corresponding to each of the stone point cloud clusters. The stone crushing execution module is used to control the stone crushing device to complete the crushing based on the coordinates of the crushing point and the crushing direction vector; The crushed stone pretreatment strategy includes: Determine the center coordinates of the stone point cloud cluster in a three-dimensional spatial coordinate system; The coordinates of the breakage point are determined based on the center coordinates, and the coordinates of the breakage point are located within the cluster of stone points. Using the coordinates of the broken point as the center and a preset distance threshold as the radius, obtain a set of point clouds for fitting from the cluster of stone point clouds; Plane fitting is performed on the point cloud set to obtain the broken foundation plane; Determine the normal vector of the crushing foundation plane to obtain the crushing direction vector; The step of determining the stone point cloud data in the grid spatial point cloud data to be tested includes: The spatial point cloud data of the grid under test is filtered and denoised to obtain the intermediate point cloud data of the grid under test. In the point cloud data of the grid to be measured, determine the first point cloud data projected on the grid and the second point cloud data not projected on the grid. The height of the first point cloud data is determined, and the height of the third point cloud data is obtained if it is greater than a preset height threshold. Stone point cloud data is obtained based on the third point cloud data and the second point cloud data; The determination of the first point cloud data projected onto the grid and the second point cloud data not projected onto the grid in the intermediate point cloud data of the grid to be measured includes: A lookup operation is performed on the intermediate point cloud data of the grid to be tested according to the pre-acquired checklist to obtain the lookup result. The checklist includes the grid arrangement status corresponding to each position in the detection area where the grid is located. The detection area is bounded by the outer perimeter of the grid. Based on the lookup results, determine the first point cloud data projected onto the grid and the second point cloud data not projected onto the grid. The checklist is obtained through the following steps: Construct point cloud data from the grids collected by the lidar; The grid-constructed point cloud data is transformed to a three-dimensional spatial coordinate system according to the pre-acquired first coordinate transformation relationship to obtain lookup table-constructed point cloud data. The first coordinate transformation relationship represents the spatial positional relationship between any point in the three-dimensional spatial coordinate system and the coordinate system of the lidar where the lidar is located. The point cloud data constructed by the lookup table is subjected to pass-through filtering to obtain intermediate point cloud data constructed by the lookup table; Based on the table lookup, intermediate point cloud data is constructed to obtain raster point cloud two-dimensional data; A check table is obtained based on the two-dimensional data of the grid point cloud. The check table includes the grid arrangement state corresponding to each position in the detection area where the grid is located. The grid arrangement state is used to characterize whether any point on the grid is on the grid. The detection area is bounded by the outer perimeter of the grid.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions for causing a computer to perform the automated stone crushing method as described in any one of claims 1 to 4.

Images