Cabin cleaning operation method and device for unmanned loader

Abstract

The invention discloses a cabin cleaning operation method and device for an unmanned loader, and belongs to the technical field of unmanned loaders, and the method comprises the steps: obtaining an internal point cloud map of a cabin, and carrying out the preprocessing of the internal point cloud map of the cabin, and obtaining a preprocessed internal point cloud map of the cabin; based on the preprocessed point cloud map in the cabin, a spading area is obtained by applying an Alpha Shapes algorithm and a connected domain clustering algorithm; and dividing based on the shoveling area to obtain a plurality of shoveling sub-areas, and executing a cabin cleaning operation strategy based on the plurality of shoveling sub-areas until the shoveling tasks of all the areas are completed. Safety and stability of operation can be guaranteed, and reliability and operation efficiency of the loader can be improved.

Description

Technical Field

[0001] The present invention discloses a method and device for cabin cleaning operation of an unmanned loader, belonging to the technical field of unmanned loaders. Background Technique

[0002] Loaders have various functions such as shoveling, loading, and transporting, and can meet the working requirements under different working conditions. However, in complex working conditions, such as bad weather or dangerous environments, manual operation of loaders is likely to lead to safety accidents and threaten the lives of operators. In contrast, unmanned loaders can operate efficiently, reduce labor and energy costs, lower the risk of safety accidents, and at the same time optimize resource utilization and improve the intelligent level of construction.

[0003] In port cabin cleaning operations, the shoveling and unloading work of loaders are mostly repetitive tasks. Manual operation is likely to cause fatigue, and the synchronization and coordination between the loader and the grab during operation are relatively complex. If the coordination is improper, safety problems are likely to occur.

[0004] Currently, the research on the unloading point of loaders mainly focuses on the unloading method for trucks, while the method for selecting the unloading point for cabin cleaning operations has not been fully explored. In existing practices, the selection of the unloading point for loader cabin cleaning operations mainly relies on the operation experience of drivers and lacks systematic theoretical support. Summary of the Invention

[0005] Aiming at the defects of the existing technology, the present invention proposes a method, device and industrial control computer for cabin cleaning operation of an unmanned loader, which solves the problem of selecting the unloading point for existing loader cabin cleaning operations.

[0006] The technical solution of the present invention is as follows:

[0007] According to the first aspect of the embodiment of the present invention, a method for cabin cleaning operation of an unmanned loader is provided, including:

[0008] Obtain the point cloud map inside the cabin, and preprocess the point cloud map inside the cabin to obtain the preprocessed point cloud map inside the cabin;

[0009] Based on the preprocessed point cloud map inside the cabin, apply the Alpha Shapes algorithm and the connected component clustering algorithm to obtain the shoveling area;

[0010] Based on the division of the shoveling area, obtain multiple shoveling sub-areas, and execute the cabin cleaning operation strategy based on the multiple shoveling sub-areas until the shoveling tasks of all areas are completed.

[0011] Further, executing the cabin cleaning operation strategy based on multiple shoveling sub-areas until the shoveling tasks of all areas are completed includes:

[0012] Obtain the point cloud data of the stockpile volume within the current excavation sub-region, and determine whether the point cloud data of the stockpile volume is greater than the stockpile volume threshold:

[0013] Yes, this excavation sub-region is the target working area, and proceed to the next step;

[0014] No, obtain the point cloud data of the stockpile volume within the next excavation sub-region and make a judgment;

[0015] Based on the current excavation sub-region, execute the excavation and unloading operation strategy until the operation of the current excavation sub-region is completed, and drive to the next target working area to repeat the execution of the excavation and unloading operation strategy until the excavation tasks in all areas are completed.

[0016] Furthermore, executing the excavation and unloading operation strategy until the operation of the current excavation sub-region is completed includes:

[0017] Based on the current excavation sub-region, determine the unloading area, and based on the current excavation sub-region and the unloading area, determine the optimal excavation point and the optimal unloading point;

[0018] Perform excavation operations based on the optimal excavation point, and obtain the point cloud data of the stockpile volume within the current excavation sub-region, and determine whether the point cloud data of the stockpile volume within the current excavation sub-region is less than or equal to the stockpile volume threshold:

[0019] Yes, proceed to the next step;

[0020] No, continue to perform excavation operations at the optimal excavation point;

[0021] The loader drives to the optimal unloading point to perform unloading operations until unloading is completed, and the operation of the current excavation sub-region is completed.

[0022] Furthermore, based on the current excavation sub-region and the unloading area, determining the optimal excavation point and the optimal unloading point includes:

[0023] Based on the excavation sub-region, determine the optimal excavation point;

[0024] Based on the unloading area, determine multiple unloading points;

[0025] Obtain the stockpile volumes of multiple unloading points based on multiple unloading points;

[0026] Based on the stockpile volumes of multiple unloading points and the stockpile volume threshold of the unloading point, obtain multiple unloading points that meet the volume threshold;

[0027] Based on multiple unloading points that meet the volume threshold, use the subjective weighting method and the objective weighting method to obtain the optimal unloading position;

[0028] Based on the optimal unloading position and the optimal digging point, the unloading path is obtained by using the Hybrd A* path planning algorithm combined with the simulated annealing algorithm, and the optimal unloading point is obtained based on the unloading path and the optimal unloading position.

[0029] Further, preprocessing is performed on the point cloud map inside the cabin to obtain a preprocessed point cloud map inside the cabin, including:

[0030] For the point cloud map inside the cabin, ground point clouds are sequentially filtered out based on conditional filtering, noise point clouds are removed based on statistical filtering, and downsampling is performed based on voxel filtering to obtain a preprocessed point cloud map inside the cabin.

[0031] Further, based on the preprocessed point cloud map inside the cabin, the Alpha Shapes algorithm and the connected component clustering algorithm are applied to obtain the digging area, including:

[0032] Based on the preprocessed point cloud map inside the cabin, the Alpha Shapes algorithm is used for boundary extraction to obtain the inner and outer boundary contours of the point cloud inside the cabin;

[0033] Based on the inner and outer boundary contours of the point cloud inside the cabin, the connected component clustering algorithm is used to distinguish the boundaries between the cabin and the material pile, obtaining the cabin boundary and the material pile boundary;

[0034] Based on the cabin boundary and the material pile boundary, an outer quadrilateral cabin boundary and an inner quadrilateral material pile boundary are obtained;

[0035] Based on the outer quadrilateral cabin boundary and the inner quadrilateral material pile boundary, the digging area is obtained.

[0036] Further, based on the preprocessed point cloud map inside the cabin, the Alpha Shapes algorithm is used for boundary extraction to obtain the inner and outer boundary contours of the point cloud inside the cabin, including:

[0037] After projecting the preprocessed point cloud map inside the cabin onto the xy plane for dimensionality reduction, n points in the point cloud can form n·(n - 1) / 2 line segments;

[0038] The Alpha Shapes algorithm is used to obtain the boundary lines among the n·(n - 1) / 2 line segments, obtaining the inner and outer boundary contours of the point cloud inside the cabin.

[0039] Further, based on the inner and outer boundary contours of the point cloud inside the cabin, the connected component clustering algorithm is used to distinguish the boundaries between the cabin and the material pile, obtaining the cabin boundary and the material pile boundary, including:

[0040] Perform two-dimensional rasterization processing on the inner and outer boundary contours of the point cloud inside the cabin, traverse all the point clouds in sequence, and place the point clouds into the corresponding grids;

[0041] Count the number of point clouds in each grid, binarize the number of point clouds in the grid, and mark the grids with the number of point clouds greater than the threshold as visited;

[0042] Mark the visited and adjacent grids with the same group number, and gather the point clouds contained in the grids under the same number into a point cloud cluster;

[0043] Sort the point cloud clusters according to the number of point clouds to obtain the cabin boundary and the stockpile boundary.

[0044] Furthermore, based on the cabin boundary and the stockpile boundary, obtain the outer quadrilateral cabin boundary and the inner quadrilateral stockpile boundary, including:

[0045] Based on the cabin boundary, traverse all the points on it and find the maximum point and the minimum point to determine the outer quadrilateral cabin boundary;

[0046] Based on the stockpile boundary, use the adaptive boundary fitting algorithm to obtain the inner quadrilateral stockpile boundary.

[0047] According to the second aspect of the embodiments of the present invention, there is provided an unmanned loader cabin cleaning operation device, including:

[0048] A processing module for acquiring a point cloud map inside the cabin and preprocessing the point cloud map inside the cabin to obtain a preprocessed point cloud map inside the cabin;

[0049] A calculation module for applying the Alpha Shapes algorithm and the connected component clustering algorithm based on the preprocessed point cloud map inside the cabin to obtain a digging area;

[0050] An execution module for dividing based on the digging area to obtain a plurality of digging sub-areas, and executing a cabin cleaning operation strategy based on the plurality of digging sub-areas until the digging tasks of all areas are completed.

[0051] The beneficial effects of the present invention are as follows:

[0052] The present invention provides a method, device and industrial control computer for the cabin cleaning operation of an autonomous loading machine. By obtaining the point cloud map inside the cabin, preprocessing the point cloud map inside the cabin to obtain the preprocessed point cloud map inside the cabin, based on the preprocessed point cloud map inside the cabin, applying the Alpha Shapes algorithm and the connected component clustering algorithm to obtain the excavation area, dividing the excavation area into multiple excavation sub-areas, and executing the cabin cleaning operation strategy based on the multiple excavation sub-areas until the excavation tasks of all areas are completed, thereby ensuring the safety and stability of the operation, and also improving the reliability and operation efficiency of the loading machine.

[0053] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present invention. Brief Description of the Drawings

[0054] Figure 1 is a flowchart of a method for the cabin cleaning operation of an autonomous loading machine shown according to an exemplary embodiment.

[0055] Figure 2 is a flowchart of a method for the cabin cleaning operation of an autonomous loading machine shown according to an exemplary embodiment.

[0056] Figure 3 is a schematic installation diagram of the loader lidar in a method for the cabin cleaning operation of an autonomous loading machine shown according to an exemplary embodiment.

[0057] Figure 4 is a schematic diagram of the excavation and unloading area division of a method for selecting the excavation point and unloading point in a method for the cabin cleaning operation of an autonomous loading machine shown according to an exemplary embodiment.

[0058] Figure 5 is a schematic block diagram of the structure of a device for the cabin cleaning operation of an autonomous loading machine shown according to an exemplary embodiment.

[0059] Figure 6 is a schematic block diagram of the structure of an industrial control computer shown according to an exemplary embodiment. Detailed Description of the Embodiment

[0060] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0061] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention.

[0062] In the description of the present invention, it should be noted that unless otherwise clearly specified and defined, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0063] An embodiment of the present invention provides a method for the cabin cleaning operation of an unmanned loader. This method is implemented by an industrial control computer, which can be a desktop computer or a laptop computer, etc. The industrial control computer at least includes a CPU, etc.

[0064] Embodiment 1

[0065] Figure 1 and Figure 2 is a flowchart of a method for the cabin cleaning operation of an unmanned loader shown according to an exemplary embodiment. This method is used in an industrial control computer and includes the following steps:

[0066] Step 101, obtain the point cloud map inside the cabin, and preprocess the point cloud map inside the cabin to obtain the preprocessed point cloud map inside the cabin. The specific steps are as follows:

[0067] Before obtaining the point cloud map inside the cabin, such as Figure 3As shown in the figure, first, an introduction is made to the system to which this method is applied. The system includes an industrial control computer, a lower computer, a first lidar 1, a second lidar 2, a third lidar 3, a fourth lidar 4, and a fifth lidar 5. The industrial control computer is electrically connected to the lower computer, the first lidar 1, the second lidar 2, the third lidar 3, the fourth lidar 4, and the fifth lidar 5 respectively. The first lidar 1, the second lidar 2, the third lidar 3, and the fourth lidar 4 are respectively installed near the edge at the top of the loader cab, and the fifth lidar 5 is installed at the rear end of the loader. The industrial control computer is used to execute the operation method and send instructions to the lower computer, and the lower computer controls the movement of the loader. First, calibrate the first lidar 1, the second lidar 2, the third lidar 3, the fourth lidar 4, and the fifth lidar 5. Through point cloud registration, unify the coordinate systems of the first lidar 1, the second lidar 2, the third lidar 3, and the fifth lidar 5 to the fourth lidar 4 located at the top of the loader cab. Lower the driverless loader into the interior of the cabin to be cleared by a gantry crane, and through its autonomous movement, accumulate the point cloud in the cabin, and finally complete the acquisition of the point cloud map of the interior of the cabin.

[0068] For the point cloud map of the interior of the cabin, the height of the center of the main lidar from the ground is h. Assuming that the coordinates of a certain point in the point cloud are p(x, y, z), if the coordinate z of the point is less than -h, then it is considered that the point belongs to the ground point cloud and is filtered out. The main purpose of this patent is to solve the problems of shoveling and discharging large-volume material piles around the cabin. For the small material pile in the center of the cabin, the cleaning work is completed by manually remotely controlling the loader. Therefore, the point cloud of the small material pile in the center of the cabin is regarded as noise point cloud and filtered out through statistical filtering method to obtain the preprocessed point cloud map of the interior of the cabin.

[0069] Step 102, based on the preprocessed point cloud map of the interior of the cabin, apply the Alpha Shapes algorithm and the connected component clustering algorithm to obtain the shoveling area. The specific steps are as follows:

[0070] First, based on the preprocessed point cloud map of the interior of the cabin, use the Alpha Shapes algorithm for boundary extraction to obtain the inner and outer boundary contours of the point cloud in the cabin. The specific content includes:

[0071] After projecting the preprocessed point cloud map of the interior of the cabin onto the xy plane for dimensionality reduction, the core task of the Alpha Shapes algorithm is to judge which of these line segments are boundary lines. If a line segment is judged to be a boundary line, then the two endpoints of the line segment will be regarded as boundary points, and these boundary points finally form the boundary contour of the point cloud.

[0072] The specific process of the Alpha Shapes algorithm is as follows:

[0073] 1. Select an arbitrary point p1(x1, y1) within the point cloud. Find a point p2(x2, y2) within a neighborhood with a radius of 2R. Create two circles with a radius of R. The calculation methods for the two centers p3(x3, y3) and p4(x4, y4) are as follows:

[0074]

[0075] Where:

[0076]

[0077] Calculate all other points p in the neighborhood within the point cloud except p1(x1, y1) and p2(x2, y2) i (x i , y i ) to the Euclidean distances d from the two centers p3(x3, y3) and p4(x4, y4). Among all neighborhood points, find the minimum distances d i and d min1 and d min2 to the two centers p3(x3, y3) and p4(x4, y4) respectively;

[0078] If any of the minimum distances d min1 or d min2 is greater than the radius R, then these two points p1(x1, y1) and p2(x2, y2) can be considered as the boundary contours of the point cloud, that is, the inner and outer boundary contours of the point cloud inside the cabin are obtained.

[0079] Secondly, based on the inner and outer boundary contours of the point cloud inside the cabin, use the connected component clustering algorithm to distinguish the boundaries between the cabin and the stockpile, and obtain the cabin boundary and the stockpile boundary. The specific content includes:

[0080] Perform a two-dimensional grid processing on the inner and outer boundary contours of the point cloud inside the cabin. Set the number of grids Num x divided along the X-axis and Num y divided along the Y-axis. Find the maximum and minimum values of the point cloud on the X-axis and Y-axis, denoted as point p min (x min , y max ) and point p max (x max,ymax );

[0081] Traverse all the point clouds in sequence and place the point clouds into the corresponding grids. The currently traversed point cloud is p i (x i , y i , z i ). Let the grid number be (a, b). The calculation method is as follows:

[0082]

[0083] When a and b are not integers, round down.

[0084] Count the number of point clouds Num in each grid. Next, binarize the number of point clouds in the grid. If the number of point clouds Num in the grid is greater than the threshold, the grid is marked as visited; otherwise, it remains unvisited.

[0085] Next, mark the visited and adjacent grids with the same group number. If they are not adjacent, change the number. The set of point clouds contained in the grids under the same number is a point cloud cluster.

[0086] The perimeter of the outer boundary is greater than that of the inner boundary. Therefore, the number of point clouds on the outer boundary is greater than that on the inner boundary. Sort the point cloud clusters by the number of point clouds. The point cloud cluster with the largest number of point clouds is the outer boundary, completing the extraction and distinction of the cabin boundary and the stockpile boundary, and obtaining the cabin boundary and the stockpile boundary.

[0087] Then, based on the cabin boundary and the stockpile boundary, obtain the outer quadrilateral cabin boundary and the inner quadrilateral stockpile boundary. The specific content includes:

[0088] Since the boundary of the cabin shows an obvious quadrilateral distribution, the shape of the cabin can be accurately fitted using AABB (axis-aligned bounding box). First, find the maximum and minimum values of the cabin boundary point cloud on the X-axis and Y-axis, denoted as point p min1 (x min1 , y min1 ) and point p max1 (x max1 , y max1 ). Points p1(x min1 , y min1 ), p2(x max1 , y min1 ), p3(x max1 , y max1 ) and p4(x min1 , y max1 ) are the four corner points of the cabin boundary, and thus the cabin boundary model is obtained.

[0089] In step 5.2), the boundary of the stockpile usually shows an approximately quadrilateral distribution and is also represented by a quadrilateral. If described using AABB (axis-aligned bounding box), it is difficult to accurately reflect the actual contour of the stockpile. At the same time, when using the RANSAC algorithm for boundary extraction, due to its randomness, when fitting the four sides of the stockpile, it is easy to cause two parallel sides to be fitted to the same side, resulting in the inability to correctly identify the boundary of the stockpile. To solve this problem, this application proposes an algorithm for fitting the stockpile boundary, and the specific steps are as follows:

[0090] Find the maximum and minimum values of the stockpile point cloud on the X-axis and Y-axis, denoted as: p min2 (x min2 ,y min2 ) and point p max2 (x max2 ,y max2 ). Based on these values, the maximum boundary range of the stockpile can be determined. Then, set the number of iterations it and set the threshold Δd. The threshold Δd is used to control the distance between the point cloud and the boundary;

[0091] Taking the upper boundary parallel to the X-axis as an example for fitting, assume the initial value of the upper boundary is y = y max2 , and the calculation method of the step size α is:

[0092]

[0093] Then, iteratively update the y t value:

[0094] y t = y t-1 - α (6)

[0095] For each iteration, select inliers on y t and count the number of points N t that meet the conditions. The specific conditions are:

[0096] y t - Δd < y i < y t - Δd (7)

[0097] where y i is the y-coordinate of each point in the stockpile point cloud, and the points that meet this condition are inliers;

[0098] During all iterations, select the y t with the largest number of inliers N t as the upper boundary of the stockpile;

[0099] The calculation methods of other boundaries (lower boundary, left boundary, and right boundary) are similar to that of the upper boundary and will not be elaborated here. For the left and right boundaries, the corresponding maximum and minimum x-coordinate boundaries are also determined by the iterative method. Finally, the four boundaries are set as x = x left , x = x right , y = y up and y = y down .

[0100] Finally, based on the outer quadrilateral cabin boundary and the inner quadrilateral stockpile boundary, the area sandwiched between the outer quadrilateral cabin boundary and the inner quadrilateral stockpile boundary is the excavation area.

[0101] Step 103: Based on the excavation area, divide it into multiple sub-excavation areas, and execute the hold cleaning operation strategy based on the multiple sub-excavation areas until the excavation tasks in all areas are completed. The specific steps are as follows:

[0102] First, based on the excavation area, divide it into multiple sub-excavation areas. The specific content is as follows:

[0103] As Figure 4 shown, in this embodiment, the excavation area is divided into 8 sub-excavation areas. Among them, the distance between the first sub-excavation area 1, the second sub-excavation area 2 and the third sub-excavation area 3, the fourth sub-excavation area 4 is the length of the shorter side of the stockpile boundary, and the distance between the fifth sub-excavation area 5, the sixth sub-excavation area 6 and the seventh sub-excavation area 7, the eighth sub-excavation area 8 is the length of the longer side of the stockpile boundary. By comparison, it can be found that the workload of the first sub-excavation area 1, the second sub-excavation area 2 and the third sub-excavation area 3 and the fourth sub-excavation area 4 is significantly less than that of the fifth sub-excavation area 5, the sixth sub-excavation area 6, the seventh sub-excavation area 7 and the eighth sub-excavation area 8. This is because when operating in the fifth sub-excavation area 5, the sixth sub-excavation area 6, the seventh sub-excavation area 7 and the eighth sub-excavation area 8, the front and rear movable range of the loader is relatively large, and relatively speaking, the operation difficulty is lower; while when operating in the first sub-excavation area 1, the second sub-excavation area 2, the third sub-excavation area 3 and the fourth sub-excavation area 4, the movable range of the loader is smaller, and it is easy to collide with the stockpile, resulting in an increase in the operation difficulty. In order to improve work efficiency, it is recommended to give priority to investing resources and energy in the tasks that are easier to complete, reduce the proportion of high-difficulty tasks, so as to ensure the smooth progress of the work. Therefore, the division of the excavation area is considered based on this to optimize the overall operation process. Let the coordinates of a certain point in the cabin be (x, y). The ranges of each excavation area are as follows:

[0104] The first sub-excavation area 1:

[0105]

[0106] The second sub-excavation area 2:

[0107]

[0108] The third sub-excavation area 3:

[0109]

[0110] The fourth sub-excavation area 4:

[0111]

[0112] The fifth sub-excavation area 5:

[0113]

[0114] Sixth excavation sub-region 6:

[0115]

[0116] Seventh excavation sub-region 7:

[0117]

[0118] Eighth excavation sub-region 8:

[0119]

[0120] Further, an unloading operation strategy is executed based on multiple excavation sub-regions until the excavation tasks in all regions are completed. The specific content includes:

[0121] Obtain the pile volume point cloud data in the current excavation sub-region, and determine whether the pile volume point cloud data is greater than the pile volume threshold:

[0122] Yes, this excavation sub-region is the target working area, and proceed to the next step;

[0123] No, obtain the pile volume point cloud data in the next excavation sub-region and make a judgment;

[0124] Based on the current excavation sub-region, execute the excavation and unloading operation strategy until the operation in the current excavation sub-region is completed, and drive to the next target working area to repeat the execution of the excavation and unloading operation strategy until the excavation tasks in all regions are completed.

[0125] The above execution of the excavation and unloading operation strategy until the operation in the current excavation sub-region is completed. The specific content includes:

[0126] Based on the current excavation sub-region, determine the unloading area. Taking the first excavation sub-region 1 as an example, determine the unloading area corresponding to the first excavation sub-region 1. As Figure 4 shown, the safety distance d1 refers to the distance from the upper boundary of the unloading area to the upper boundary of the pile. The purpose of designing d1 is to prevent the upper boundary of the pile from exceeding the hatch, so as to ensure that the grab can smoothly grab the pile in the unloading area.

[0127] The calculation method of the ordinate of the lower boundary of the unloading area is as follows:

[0128] y unload_up = y up - d1 (16)

[0129] When the first excavation sub-region 1 of the loader approaches the pile of materials in the second excavation sub-region 2, in order to prevent the loader from accidentally excavating the pile of materials in the unloading area during the process of moving towards the excavation point, a safety distance d2 needs to be set. Its function is to ensure that the bucket will not accidentally touch or excavate the pile of materials in the unloading area during the movement, thus avoiding affecting the unloading operation. Let the width of the bucket be W bucket , then the safety distance d2 can be set as:

[0130]

[0131] That is, the safety distance d2 is equal to half of the bucket width. This design can ensure that during the operation of the loader, there is enough spacing between the bucket and the unloading area when the bucket approaches area 1, thus avoiding misoperation.

[0132] In order to ensure that the loader can drive into the unloading area at any angle for unloading and the materials can all fall into the unloading area, the maximum circumscribed circle diameter of the bucket is selected as the width of the unloading area. Specifically, for the maximum circumscribed circle diameter, the calculation method of the maximum circumscribed circle diameter d3 is as follows:

[0133]

[0134] Where: L bucket is the length of the bottom of the bucket, and W bucket is the width of the bucket.

[0135] Through this calculation method, it can be ensured that when the loader drives into the unloading area at any angle, the materials in the bucket will be completely unloaded within the unloading area. The specific calculation method is as follows:

[0136] 1. The distance D from the lower boundary of the unloading area to the lower boundary of the pile of materials down Calculation:

[0137] D down = d5 + d6 + d7 + d8 (19)

[0138] 2. Calculation of the ordinate of the lower boundary of the unloading area:

[0139] y unload_down = y down + D down - d3 / 2 (20)

[0140] Where: y down is the ordinate of the lower boundary of the pile of materials, and d3 is the maximum circumscribed circle diameter of the bucket.

[0141] 3. Calculate d5:

[0142] d5 = d4·sin40° (21)

[0143] Where:

[0144] When the loader is discharging, d4 is the distance from the vehicle articulation center to the bucket center. When in the first excavation sub-region 1, the average value of θ in the excavation point S(x, y, θ) is 90°. The common operation path of the loader is a V-shaped operation path. The angle between the discharge point and the working face is 50° - 55°. Let the angle between d4 and the horizontal direction be 40°.

[0145] 4. Calculate d6

[0146] d6 = d9·sin40° (22)

[0147] Where: d9 is the minimum turning radius of the loader, provided by the design parameters of the loader; d7 is the length of the rear body of the loader, usually provided by the design specifications of the vehicle; d8 is the safety distance from the lower boundary of the discharge area to the rear body of the loader.

[0148] Based on the excavation sub-region, determine the optimal excavation point, send the excavation point to the lower computer, and start the excavation work. Based on the discharge area, determine multiple discharge points. By introducing the "excavation-discharge ratio" to determine the number of discharge points, the magnitude of the "excavation-discharge ratio" can be expressed by the following formula:

[0149]

[0150] Where L unload is the length of the discharge area, that is, the length from the upper boundary to the lower boundary of the discharge area.

[0151] Each discharge point can determine a discharge range. The discharge range is a circle with d3 as the diameter. When the loader is discharging, as long as the center of the bucket coincides with the discharge point, regardless of the discharge path, it can ensure that the material accurately enters the discharge range.

[0152] When λ is less than 1.0, that is, the bucket width of the loader is greater than the length of the discharge area. Considering the operation safety, unloading operation cannot be carried out at this time, so the number of discharge points is 0;

[0153] When λ is in the interval [1.0, 1.5], the bucket width of the loader is less than the length of the discharge area. Therefore, 1 discharge point can be set, and the discharge point is located at the middle position of the dischargeable area of the dump truck box;

[0154] When λ is in the interval (1.5, 2.5], 2 discharge points can be set at this time. The discharge range circle determined by the first discharge point is tangent to the upper boundary of the discharge area, and the discharge range circle determined by the second discharge point is tangent to the lower boundary of the discharge area;

[0155] When the value of λ is in the interval (2.5, 3.5], 3 discharge points can be set at this time. Based on the 2 discharge points, 1 more discharge point is added at the middle position of the discharge area.

[0156] And so on. As λ increases, more discharge points can be continuously set. Finally, multiple discharge points U(x, y, θ) in the discharge area are determined, where θ is unknown.

[0157] Next, the optimal discharge point is selected, and the specific content is as follows:

[0158] First, the selection of the optimal discharge position needs to comprehensively consider five factors, namely the distance between the discharge point and the excavation point, the volume of the material pile at the discharge point, the distance between the currently selected discharge point and the previous discharge point, the difficulty for the loader to reach the discharge point, and whether the volume of the material pile reaches the threshold. The influence of each factor is described in detail below:

[0159] The distance between the discharge point and the excavation point: The distance between the discharge point and the excavation point is directly related to the transportation distance and operation time. If the discharge point is too far from the excavation point, the transportation time increases and the efficiency decreases. Generally, the discharge point with a shorter distance can improve the operation efficiency and reduce the transportation cost.

[0160] The volume of the material pile at the discharge point: The loader should preferably select the discharge point with a larger volume of the material pile, because a larger material pile can reach the threshold of the material pile volume at the discharge point faster, reducing the dispersion of material accumulation. Generally, a discharge point with a larger volume of the material pile means that the material accumulation is more concentrated, and the grab bucket can grab more materials more efficiently, ensuring the full-bucket rate of the grab bucket, reducing the number of grabs, thus shortening the operation time and improving the overall work efficiency. For the grab bucket operator, selecting a larger discharge point usually means that the operation of frequently adjusting the position or discharging can be reduced, making the operation smoother, concentrating on efficient loading, and thus reducing the operation difficulty.

[0161] The distance between the currently selected discharge point and the previous discharge point: The currently selected discharge point should preferably consider the point closer to the previous discharge point, which can effectively avoid the problem of material accumulation dispersion, thus ensuring that the full-bucket rate of the grab bucket is not affected. The discharge point with a shorter distance can reduce the driving time of the loader in the no-load state, thus avoiding frequent path planning and position adjustment, which usually take a lot of time and reduce the operation efficiency.

[0162] Difficulty for the loader to reach the unloading point: During the path planning process, the loader usually needs to pass through the outer unloading point to enter the inner unloading point. Since the outer unloading point usually has a relatively spacious space and is easily accessible. However, such a choice may cause the loader to be interfered by the accumulation of outer materials or obstacles during driving, and may even prevent it from smoothly entering the inner unloading point. In addition, when the loader enters the inner unloading point, the complexity of path planning further increases, especially when the material pile is high and irregularly stacked. In order to bypass the outer unloading point or the accumulation, the loader must design a more complex driving route, not only avoiding obstacles but also ensuring the path is unobstructed. This complex path planning increases the difficulty of the operation and also raises the risk during the operation.

[0163] Whether the volume of the material pile reaches the threshold: When the volume of the material pile at a certain unloading point reaches the set volume threshold, the loader will not be able to continue unloading to this unloading point. This is because the material pile exceeding the threshold may become unstable and there is a risk of collapse.

[0164] Therefore, based on multiple unloading points, multiple material pile volumes of the unloading points are obtained, and the calculation method of the material pile volume of the unloading point is as follows:

[0165] Assume that a certain unloading point is U(x,y), and extract the point cloud within the range with (x,y) as the center and d3 as the diameter;

[0166] Rasterize the extracted point cloud, put each point into the corresponding grid, and the length and width of the grid are L grid and W grid ;

[0167] Calculate the height of the point cloud of each grid, specifically the average value of the coordinates of all points in each grid on the Z-axis, and the result is H i ;

[0168] The volume V of each grid i , and the calculation method is as follows:

[0169] V i = L grid ×W grid ×(H i -H ground ) (24)

[0170] Where:

[0171] H ground is the ground height;

[0172] Finally, calculate the volume V of the material pile in the entire area, accumulate the volumes V of all grids i to obtain the final result, and based on the material pile volumes of multiple unloading points and the material pile volume threshold of the unloading point, obtain multiple unloading points that meet the volume threshold.

[0173] Based on multiple discharge points that meet the volume threshold, the subjective weighting method and the objective weighting method are used to obtain the optimal discharge position.

[0174] Among them, the determination of the index weights for discharge point selection under AHP:

[0175] According to the factors that determine the selection of discharge points, a hierarchical structure model is constructed: the target layer A is the loading machine discharge operation efficiency, the criterion layer B1 is the distance between the discharge point and the excavation point, B2 is the volume of the material pile at the discharge point, B3 is the distance between the currently selected discharge point and the previous discharge point, and B4 is the difficulty for the loading machine to reach the discharge point;

[0176] Based on the evaluation of experienced drivers, the relative importance of each evaluation index is obtained. Among them, B3 is more important than B4, B2 is more important than B3, and B1 is more important than B2. An A-B i matrix is constructed, and consistency testing and relative index weight calculation are performed;

[0177] After constructing the judgment matrix, we need to test its consistency to ensure the logical rationality of each evaluation. And calculate the maximum eigenvalue λ max of the matrix, calculate the consistency index CI and the consistency ratio CR. If the CR value is less than 0.1, the consistency of the judgment matrix is acceptable;

[0178] The judgment matrix is decomposed using the maximum eigenvalue to obtain the eigenvector. The eigenvector represents the relative importance weights of each criterion layer index. Then, the eigenvector is normalized so that the sum of all weights is 1, and the weights W α for discharge point selection under AHP are obtained:

[0179] W α ={w α1 , w α2 , w α3 , w α4} (25)

[0180] Determination of the index weights for discharge point selection under the entropy method:

[0181] A set of discharge point data is measured in advance, with a total of m indicators and n samples. A decision matrix X is constructed, where each element x ij represents the score of the i-th sample on the j-th indicator;

[0182] Since the measurement units and directions of each indicator are not unified, it is necessary to standardize the original data to construct a decision matrix Y. Usually, the following method is used:

[0183] Positive indicator:

[0184]

[0185] Negative index:

[0186]

[0187] Calculate the proportion of the index under each sample in the total of this index:

[0188]

[0189] Calculate the entropy value of each index:

[0190]

[0191] Calculate the weight W of the index for selecting the unloading point under the entropy method β , the calculation method is as follows:

[0192]

[0193] Obtain the weight W of the index for selecting the unloading point under the entropy method β :

[0194] W β = {w β1 , w β2 , w β3 , w β4} (31)

[0195] After obtaining the weights of the indexes for selecting the unloading point under AHP and the entropy method, calculate the comprehensive weight, and the calculation method is as follows:

[0196]

[0197] Finally, calculate the evaluation score E of each excavation point:

[0198] E = w1·F1 + w2·F2 + w3·F3 + w4·F4 (33)

[0199] Where w1, w2, w3, and w4 are the respective weights, and F1, F2, F3, and F4 are the distance from the unloading point to the excavation point, the volume of the material pile at the unloading point, the distance from the currently selected unloading point to the previous unloading point, and the difficulty for the loader to reach the unloading point. Calculate the evaluation score E of each unloading point, and select the unloading point with the highest evaluation score E as the optimal unloading position.

[0200] Based on the optimal unloading position and the optimal excavation point, use the Hybrid A* path planning algorithm combined with the simulated annealing algorithm to obtain the unloading path, and based on the unloading path and the optimal unloading position, obtain the optimal unloading point. The specific steps are as follows:

[0201] Given the known optimal digging point S(x, y, θ), the common operation path of the loader is a V-shaped operation path, and the angle between the unloading point and the working face is 50° - 55°. Taking the digging area 1 as an example, the initial unloading angle is set as θ - 50°. The optimal unloading angle may be within a certain range of the initial setting. Therefore, search for the optimal unloading angle within the range of [θ - 60°, θ - 40°].

[0202] Within the given angle range, we need to evaluate the quality of the path by calculating the path lengths corresponding to different unloading angles, and use the simulated annealing algorithm combined with the Hybrd A* path planning algorithm to find the optimal solution within the range:

[0203] Set the initial solution θ0, that is, the initially set unloading angle. Usually, choose θ0 = θ - 50°, and use the Hybrd A* path planning algorithm to plan the path between the optimal unloading position and the optimal digging point, and calculate the path length. Set the initial temperature and the temperature reduction rate;

[0204] Generate a new angle θ' by randomly perturbing around the current angle. The amplitude of the perturbation usually depends on the current temperature;

[0205] Calculate the path length corresponding to the new solution θ'. If the path length of the new solution is shorter, accept the new solution unconditionally; if the path length of the new solution is longer, it can be accepted with a certain probability;

[0206] As time goes by, the temperature gradually decreases. When the temperature drops to a certain threshold, the algorithm terminates, and the optimal unloading angle is obtained. Based on the unloading path, the optimal unloading angle, and the optimal unloading position, the optimal unloading point is obtained.

[0207] Perform digging operations based on the optimal digging point, and obtain the point cloud data of the stockpile volume within the current digging sub-area. Judge whether the point cloud data of the stockpile volume within the current digging sub-area is less than or equal to the stockpile volume threshold:

[0208] Yes, execute the next step;

[0209] No, continue to perform digging operations at the optimal digging point;

[0210] The loader travels to the optimal unloading point to perform unloading operations until unloading is completed, and the operation of the current digging sub-area is completed.

[0211] This application obtains the point cloud map inside the cabin, preprocesses the point cloud map inside the cabin to obtain the preprocessed point cloud map inside the cabin, applies the AlphaShapes algorithm and the connected component clustering algorithm based on the preprocessed point cloud map inside the cabin to obtain the excavation area, divides the excavation area to obtain multiple excavation sub-areas, and executes the cabin cleaning operation strategy based on the multiple excavation sub-areas until the excavation tasks of all areas are completed, thereby ensuring the safety and stability of the operation and improving the reliability and operation efficiency of the loader.

[0212] Embodiment 2

[0213] Figure 5 It is a structural schematic block diagram of a device for the cabin cleaning operation of an unmanned loader shown according to an exemplary embodiment. The device includes:

[0214] A processing module 210, configured to obtain the point cloud map inside the cabin and preprocess the point cloud map inside the cabin to obtain the preprocessed point cloud map inside the cabin;

[0215] A calculation module 220, configured to apply the AlphaShapes algorithm and the connected component clustering algorithm based on the preprocessed point cloud map inside the cabin to obtain the excavation area;

[0216] An execution module 230, configured to divide based on the excavation area to obtain multiple excavation sub-areas, and execute the cabin cleaning operation strategy based on the multiple excavation sub-areas until the excavation tasks of all areas are completed.

[0217] This application obtains the point cloud map inside the cabin, preprocesses the point cloud map inside the cabin to obtain the preprocessed point cloud map inside the cabin, applies the AlphaShapes algorithm and the connected component clustering algorithm based on the preprocessed point cloud map inside the cabin to obtain the excavation area, divides the excavation area to obtain multiple excavation sub-areas, and executes the cabin cleaning operation strategy based on the multiple excavation sub-areas until the excavation tasks of all areas are completed, thereby ensuring the safety and stability of the operation and improving the reliability and operation efficiency of the loader.

[0218] Embodiment 3

[0219] Figure 6 It is a structural block diagram of an industrial control computer provided by an embodiment of the present application. The industrial control computer can be the industrial control computer in the above embodiment. The industrial control computer 300 can be a portable mobile industrial control computer, such as: a smart phone, a tablet computer. The industrial control computer 300 may also be called other names such as a user device, a portable industrial control computer, etc.

[0220] Generally, the industrial control computer 300 includes: a processor 301 and a memory 302.

[0221] The processor 301 may include one or more processing cores, such as a quad-core processor, an octa-core processor, etc. The processor 301 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), or PLA (Programmable Logic Array). The processor 301 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the wake state, also known as the CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 301 may be integrated with a GPU (Graphics Processing Unit), and the GPU is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 301 may further include an AI (Artificial Intelligence) processor, which is used to process computational operations related to machine learning.

[0222] The memory 302 may include one or more computer-readable storage media, which may be tangible and non-transitory. The memory 302 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices and flash storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 302 is used to store at least one instruction, and the at least one instruction is used to be executed by the processor 301 to implement a method for the cleaning operation of an unmanned loader provided in this application.

[0223] In some embodiments, the industrial control computer 300 may also optionally include: a peripheral device interface 303 and at least one peripheral device. Specifically, the peripheral device includes at least one of a radio frequency circuit 304, a touch display screen 305, a camera 306, an audio circuit 307, a positioning component 308, and a power supply 309.

[0224] The peripheral device interface 303 may be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 301 and the memory 302. In some embodiments, the processor 301, the memory 302, and the peripheral device interface 303 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 301, the memory 302, and the peripheral device interface 303 may be implemented on separate chips or circuit boards, and this embodiment does not limit this.

[0225] The radio frequency circuit 304 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 304 communicates with the communication network and other communication devices through electromagnetic signals. The radio frequency circuit 304 converts electrical signals into electromagnetic signals for transmission, or converts the received electromagnetic signals into electrical signals. Optionally, the radio frequency circuit 304 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, and so on. The radio frequency circuit 304 can communicate with other industrial computers through at least one wireless communication protocol. The wireless communication protocol includes but is not limited to: the World Wide Web, a metropolitan area network, an intranet, various generations of mobile communication networks (2G, 3G, 4G, and 5G), a wireless local area network, and / or a WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 304 may further include a circuit related to NFC (Near Field Communication), which is not limited in this application.

[0226] The touch display screen 305 is used to display a UI (User Interface). The UI may include graphics, text, icons, videos, and any combination thereof. The touch display screen 305 also has the ability to collect touch signals on or above the surface of the touch display screen 305. The touch signals can be input to the processor 301 as control signals for processing. The touch display screen 305 is used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there may be one touch display screen 305, which is set on the front panel of the industrial computer 300; in other embodiments, there may be at least two touch display screens 305, which are respectively set on different surfaces of the industrial computer 300 or in a folded design; in still other embodiments, the touch display screen 305 may be a flexible display screen, which is set on the curved surface or the folding surface of the industrial computer 300. Even, the touch display screen 305 can also be set into an irregular non-rectangular shape, that is, a special-shaped screen. The touch display screen 305 can be prepared from materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0227] The camera component 306 is used to collect images or videos. Optionally, the camera component 306 includes a front camera and a rear camera. Generally, the front camera is used to implement video calls or selfies, and the rear camera is used to take photos or videos. In some embodiments, there are at least two rear cameras, which can be any one of a main camera, a depth camera, and a wide-angle camera, so as to implement the function of background blurring by fusing the main camera and the depth camera, and implement panoramic shooting and VR (Virtual Reality) shooting functions by fusing the main camera and the wide-angle camera. In some embodiments, the camera component 306 may further include a flash. The flash can be a single-color temperature flash or a two-color temperature flash. The two-color temperature flash refers to the combination of a warm light flash and a cold light flash, which can be used for light compensation under different color temperatures.

[0228] The audio circuit 307 is used to provide an audio interface between the user and the industrial computer 300. The audio circuit 307 may include a microphone and a speaker. The microphone is used to collect sound waves of the user and the environment, and convert the sound waves into electrical signals and input them to the processor 301 for processing, or input them to the radio frequency circuit 304 to achieve voice communication. For the purpose of stereo collection or noise reduction, there may be multiple microphones, which are respectively arranged at different parts of the industrial computer 300. The microphone can also be an array microphone or an omnidirectional collection microphone. The speaker is used to convert the electrical signals from the processor 301 or the radio frequency circuit 304 into sound waves. The speaker can be a traditional thin film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert electrical signals into sound waves audible to humans, but also convert electrical signals into sound waves inaudible to humans for uses such as ranging. In some embodiments, the audio circuit 307 may further include a headphone jack.

[0229] The positioning component 308 is used to locate the current geographical location of the industrial computer 300 to achieve navigation or LBS (Location-Based Service). The positioning component 308 can be a positioning component based on the US GPS (Global Positioning System), China's Beidou system, or Russia's Galileo system.

[0230] The power supply 309 is used to supply power to each component in the industrial computer 300. The power supply 309 can be alternating current, direct current, a disposable battery, or a rechargeable battery. When the power supply 309 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery charged through a wired line, and a wireless rechargeable battery is a battery charged through a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0231] In some embodiments, the industrial control computer 300 further includes one or more sensors 310. The one or more sensors 310 include, but are not limited to: an acceleration sensor 311, a gyroscope sensor 312, a pressure sensor 313, a fingerprint sensor 314, an optical sensor 315, and a proximity sensor 316.

[0232] The acceleration sensor 311 can detect the magnitudes of accelerations on the three coordinate axes of the coordinate system established with the industrial control computer 300. For example, the acceleration sensor 311 can be used to detect the components of the gravitational acceleration on the three coordinate axes. The processor 301 can control the touch display screen 305 to display the user interface in a landscape view or a portrait view according to the gravitational acceleration signal collected by the acceleration sensor 311. The acceleration sensor 311 can also be used for collecting game or user movement data.

[0233] The gyroscope sensor 312 can detect the body direction and rotation angle of the industrial control computer 300. The gyroscope sensor 312 can cooperate with the acceleration sensor 311 to collect the 3D (3 Dimensions) actions of the user on the industrial control computer 300. Based on the data collected by the gyroscope sensor 312, the processor 301 can implement the following functions: motion sensing (such as changing the UI according to the user's tilt operation), image stabilization during shooting, game control, and inertial navigation.

[0234] The pressure sensor 313 can be disposed on the side frame of the industrial control computer 300 and / or the lower layer of the touch display screen 305. When the pressure sensor 313 is disposed on the side frame of the industrial control computer 300, it can detect the holding signal of the user on the industrial control computer 300, and perform left / right hand recognition or shortcut operations according to the holding signal. When the pressure sensor 313 is disposed on the lower layer of the touch display screen 305, it can control the operable controls on the UI interface according to the pressure operation of the user on the touch display screen 305. The operable controls include at least one of a button control, a scroll bar control, an icon control, and a menu control.

[0235] The fingerprint sensor 314 is used to collect the fingerprint of the user to identify the user's identity according to the collected fingerprint. When the identified user identity is a trusted identity, the processor 301 authorizes the user to perform relevant sensitive operations, and the sensitive operations include unlocking the screen, viewing encrypted information, downloading software, making payments, and changing settings, etc. The fingerprint sensor 314 can be disposed on the front, back, or side of the industrial control computer 300. When there are physical buttons or a manufacturer logo on the industrial control computer 300, the fingerprint sensor 314 can be integrated with the physical buttons or the manufacturer logo.

[0236] The optical sensor 315 is used to collect the ambient light intensity. In one embodiment, the processor 301 can control the display brightness of the touch display screen 305 according to the ambient light intensity collected by the optical sensor 315. Specifically, when the ambient light intensity is high, the display brightness of the touch display screen 305 is increased; when the ambient light intensity is low, the display brightness of the touch display screen 305 is decreased. In another embodiment, the processor 301 can also dynamically adjust the shooting parameters of the camera assembly 306 according to the ambient light intensity collected by the optical sensor 315.

[0237] The proximity sensor 316, also known as the distance sensor, is usually arranged on the front of the industrial control computer 300. The proximity sensor 316 is used to collect the distance between the user and the front of the industrial control computer 300. In one embodiment, when the proximity sensor 316 detects that the distance between the user and the front of the industrial control computer 300 is gradually decreasing, the processor 301 controls the touch display screen 305 to switch from the lit state to the off state; when the proximity sensor 316 detects that the distance between the user and the front of the industrial control computer 300 is gradually increasing, the processor 301 controls the touch display screen 305 to switch from the off state to the lit state.

[0238] Those skilled in the art can understand that Figure 6 the structure shown in does not constitute a limitation on the industrial control computer 300, and may include more or fewer components than shown in the figure, or combine some components, or adopt different component arrangements.

[0239] Embodiment 4

[0240] In an exemplary embodiment, a computer-readable storage medium is further provided, on which a computer program is stored, and when the program is executed by a processor, it implements a method for cleaning the cabin of an unmanned loader as provided in all the inventive embodiments of the present application.

[0241] Any combination of one or more computer-readable media can be adopted. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (a non-exhaustive list) of the computer-readable storage medium include: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device.

[0242] A computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take various forms, including—but not limited to—electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device.

[0243] The program code contained on a computer-readable medium may be transmitted using any appropriate medium, including—but not limited to—wireless, wire, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0244] Computer program code for performing the operations of the present invention may be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0245] Embodiment Five

[0246] In an exemplary embodiment, there is also provided an application program product including one or more instructions that can be executed by a processor 301 of the above device to complete the above method for clearing a cabin of an unmanned loader.

[0247] Although the embodiments of the present invention have been disclosed as above, they are not limited to the applications listed in the specification and embodiments. It can be fully applied to various fields suitable for the present invention. For those skilled in the art, additional modifications can be easily implemented. Therefore, without departing from the general concept defined by the claims and the equivalent scope, the present invention is not limited to the specific details and the illustrated and described examples here.

Claims

1. A method for the cabin cleaning operation of an unmanned loader, characterized in that, Including: Obtain the point cloud map inside the cabin, and preprocess the point cloud map inside the cabin to obtain the preprocessed point cloud map inside the cabin; Based on the preprocessed point cloud map inside the cabin, apply the Alpha Shapes algorithm and the connected component clustering algorithm to obtain the excavation area; Based on the division of the excavation area, obtain multiple excavation sub-areas, and execute the cabin cleaning operation strategy based on the multiple excavation sub-areas until the excavation tasks of all areas are completed.

2. The method for the cabin cleaning operation of an autonomous loader according to claim 1, wherein, Executing the cabin cleaning operation strategy based on multiple excavation sub-areas until the excavation tasks of all areas are completed, including: Obtain the point cloud data of the stockpile volume inside the current excavation sub-area, and judge whether the point cloud data of the stockpile volume is greater than the stockpile volume threshold: Yes, this excavation sub-area is the target working area, and execute the next step; No, obtain the point cloud data of the stockpile volume inside the next excavation sub-area and make a judgment; Based on the current excavation sub-area, execute the excavation and unloading operation strategy until the operation of the current excavation sub-area is completed, and drive to the next target working area to repeat the execution of the excavation and unloading operation strategy until the excavation tasks of all areas are completed.

3. The method for the unmanned loader to clear the cabin according to claim 2, characterized in that, Executing the excavation and unloading operation strategy until the operation of the current excavation sub-area is completed, including: Based on the current excavation sub-area, determine the unloading area, and based on the current excavation sub-area and the unloading area, determine the optimal excavation point and the optimal unloading point; Perform excavation operations based on the optimal excavation point, and obtain the point cloud data of the stockpile volume inside the current excavation sub-area, and judge whether the point cloud data of the stockpile volume inside the current excavation sub-area is less than or equal to the stockpile volume threshold: Yes, execute the next step; No, continue to perform excavation operations at the optimal excavation point; The loader drives to the optimal unloading point to perform unloading operations until unloading is completed, and the operation of the current excavation sub-area is completed.

4. The method for cleaning the cabin of an unmanned loader according to claim 3, characterized in that, Based on the current excavation sub-area and the unloading area, determine the optimal excavation point and the optimal unloading point, including: Based on the excavation sub-area, determine the optimal excavation point; Based on the unloading area, determine multiple unloading points; Obtain the stockpile volumes of multiple unloading points based on the multiple unloading points; Based on the stockpile volumes of multiple unloading points and the stockpile volume threshold of the unloading point, obtain multiple unloading points that meet the volume threshold; Based on the multiple unloading points that meet the volume threshold, use the subjective weighting method and the objective weighting method to obtain the optimal unloading position; Based on the optimal unloading position and the optimal excavation point, use the Hybrd A* path planning algorithm combined with the simulated annealing algorithm to obtain the unloading path, and obtain the optimal unloading point based on the unloading path and the optimal unloading position.

5. The method for cleaning the cabin of an unmanned loader according to claim 4, wherein Preprocessing the point cloud map inside the cabin to obtain the preprocessed point cloud map inside the cabin, including: For the point cloud map inside the cabin, sequentially filter out the ground point cloud based on conditional filtering, remove the noise point cloud based on statistical filtering, and perform downsampling based on voxel filtering to obtain the preprocessed point cloud map inside the cabin.

6. The method for the cleaning operation of an unmanned loader according to claim 5, wherein, Based on the preprocessed point cloud map of the cabin interior, the excavation area is obtained by applying the Alpha Shapes algorithm and the connected component clustering algorithm, including: Based on the preprocessed point cloud map of the cabin interior, the Alpha Shapes algorithm is used for boundary extraction to obtain the inner and outer boundary contours of the point cloud inside the cabin; Based on the inner and outer boundary contours of the point cloud inside the cabin, the connected component clustering algorithm is used to distinguish the boundaries between the cabin and the stockpile, obtaining the cabin boundary and the stockpile boundary; Based on the cabin boundary and the stockpile boundary, the outer quadrilateral cabin boundary and the inner quadrilateral stockpile boundary are obtained; Based on the outer quadrilateral cabin boundary and the inner quadrilateral stockpile boundary, the excavation area is obtained.

7. The method for cleaning the cabin of an unmanned loader according to claim 6, wherein Based on the preprocessed point cloud map of the cabin interior, the Alpha Shapes algorithm is used for boundary extraction to obtain the inner and outer boundary contours of the point cloud inside the cabin, including: After projecting the preprocessed point cloud map of the cabin interior onto the xy plane for dimensionality reduction, n points in the point cloud can form n·(n - 1) / 2 line segments; The Alpha Shapes algorithm is used to obtain the boundary lines among the n·(n - 1) / 2 line segments, obtaining the inner and outer boundary contours of the point cloud inside the cabin.

8. The method for cleaning the cabin of an unmanned loader according to claim 7, wherein, Based on the inner and outer boundary contours of the point cloud inside the cabin, the connected component clustering algorithm is used to distinguish the boundaries between the cabin and the stockpile, obtaining the cabin boundary and the stockpile boundary, including: Perform two-dimensional rasterization on the inner and outer boundary contours of the point cloud inside the cabin, traverse all point clouds in sequence, and place the point clouds into the corresponding grids; Count the number of point clouds in each grid, binarize the number of point clouds in the grid, and mark the grids with the number of point clouds greater than the threshold as visited; Mark the visited and adjacent grids with the same group number, and group the point clouds contained in the grids with the same number into a point cloud cluster; Sort the point cloud clusters according to the number of point clouds to obtain the cabin boundary and the stockpile boundary.

9. The method for cleaning the cabin of an unmanned loader according to claim 8, wherein, Based on the cabin boundary and the stockpile boundary, the outer quadrilateral cabin boundary and the inner quadrilateral stockpile boundary are obtained, including: Based on the cabin boundary, traverse all the points on it and find the maximum and minimum points to determine the outer quadrilateral cabin boundary; Based on the stockpile boundary, use the adaptive boundary fitting algorithm to obtain the inner quadrilateral stockpile boundary.

10. An operation device for the cabin cleaning of an unmanned loader, characterized in that, Including: A processing module for obtaining the point cloud map of the cabin interior and preprocessing the point cloud map of the cabin interior to obtain the preprocessed point cloud map of the cabin interior; A calculation module for obtaining the excavation area based on the preprocessed point cloud map of the cabin interior by applying the Alpha Shapes algorithm and the connected component clustering algorithm; An execution module for dividing based on the excavation area to obtain multiple excavation sub-areas, and executing the cabin cleaning operation strategy based on the multiple excavation sub-areas until the excavation tasks of all areas are completed.

Images