Shovel control method and device of loading machine, loading machine, medium and product

Abstract

The invention relates to a spading control method and device of a loading machine, the loading machine, a medium and a product, and relates to the technical field of control. The spading control method comprises the following steps: acquiring point cloud data of a material pile in an operation area of the loader; rasterizing the point cloud data based on a grid resolution to obtain a grid map, the grid resolution being set based on a first distance between the current position of the loader and the material pile; based on a second distance between the current position of the loader and at least one grid on the edge of the grid map, determining an initial spading position of the loader in the operation area; and controlling the loading machine to shovel the material pile based on the initial shoveling position.

Description

Technical Field

[0001] The present disclosure relates to the field of control technology, and in particular to a loader excavation control method, device, loader, medium and product. Background Art

[0002] A loader is a type of construction machinery that uses a bucket to scoop up, transport, and unload materials to a designated location. Its operations span a wide range of complex environments, including construction sites, mines, and ports. During construction, the accuracy of a loader's shoveling and digging operations has a crucial impact on the overall quality of the project. Summary of the Invention

[0003] According to some embodiments of the present disclosure, a loader excavation control method is provided, comprising: acquiring point cloud data of a material pile within a working area of ​​the loader; rasterizing the point cloud data based on a grid resolution to obtain a grid map, wherein the grid resolution is set based on a first distance between a current position of the loader and the material pile; determining an initial excavation position of the loader within the working area based on a second distance between the current position of the loader and at least one grid on an edge of the grid map; and controlling the loader to excavate the material pile based on the initial excavation position.

[0004] According to other embodiments of the present disclosure, a shoveling control device for a loader is provided, comprising: an acquisition module configured to acquire point cloud data of a material pile within a working area of ​​the loader; a processing module configured to rasterize the point cloud data based on a grid resolution to obtain a grid map, wherein the grid resolution is set based on a first distance between a current position of the loader and the material pile; a determination module configured to determine an initial shoveling position of the loader within the working area based on a second distance between the current position of the loader and at least one grid on an edge of the grid map; and a control module configured to control the loader to shovel the material pile based on the initial shoveling position.

[0005] According to some further embodiments of the present disclosure, a loader digging control device is provided, comprising: a memory; and a processor coupled to the memory, the processor being configured to execute the loader digging control method of any one of the above embodiments based on instructions stored in the memory device.

[0006] According to still further embodiments of the present disclosure, a loader is provided, comprising the digging control device for the loader according to any one of the above embodiments.

[0007] According to some further embodiments of the present disclosure, a computer-readable storage medium is provided, on which computer instructions are stored. When the instructions are executed by a processor, the loader excavation control method in any of the above embodiments is implemented.

[0008] According to some further embodiments of the present disclosure, a computer program product is provided, comprising instructions, which, when executed by a processor, enable the processor to execute the digging control method for a loader according to any one of the above embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0010] The present disclosure can be more clearly understood from the following detailed description with reference to the accompanying drawings, in which:

[0011] Figure 1 A flow chart showing a digging control method of a loader according to some embodiments of the present disclosure;

[0012] Figure 2 A schematic diagram illustrating a grid map according to some embodiments of the present disclosure;

[0013] Figure 3 A structural schematic diagram showing a partial structure of a loader according to some embodiments of the present disclosure;

[0014] Figure 4 A flowchart showing a digging control method of a loader according to other embodiments of the present disclosure;

[0015] Figure 5 A block diagram showing a digging control device of a loader according to some embodiments of the present disclosure;

[0016] Figure 6 A block diagram showing a digging control device of a loader according to other embodiments of the present disclosure;

[0017] Figure 7 A block diagram illustrating a digging control device of a loader according to further embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0018] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that unless otherwise specifically stated, the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure.

[0019] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0020] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.

[0021] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0022] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0023] It should be noted that like reference numerals and letters refer to like items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0024] In the prior art, loaders typically rely on manual experience to operate and dig materials. This approach, on the one hand, results in long operating times that can easily fatigue operators and lead to operational errors. On the other hand, varying skill levels among operators make it difficult to accurately dig materials, often resulting in over- or under-digging. Consequently, digging control accuracy is often low.

[0025] In view of this, it is urgent to design an accurate excavation control method to improve the accuracy of the loader's excavation operation.

[0026] The present disclosure proposes a shoveling control method for a loader, which can obtain point cloud data of a material pile within the working area of ​​the loader, and set the grid resolution for rasterizing the point cloud data according to the distance between the loader and the material pile. Since the raster resolution is set according to the distance between the loader and the material pile. When the distance between the loader and the material pile changes, the raster resolution will also change dynamically. Compared with the raster map generation method using a fixed raster resolution, the raster map generated by the method according to the embodiment of the present disclosure is more flexible, and can provide different resolution accuracies according to the different distances between the loader and the material pile, adapt to the scene requirements, and balance the relationship between the map data storage volume, the calculation amount and the map accuracy.

[0027] Figure 1 A flow chart illustrating a digging control method of a loader according to some embodiments of the present disclosure is shown.

[0028] like Figure 1 As shown, in step 110 , point cloud data of the material pile within the working area of ​​the loader is obtained.

[0029] In some embodiments, the loader may be equipped with a sensor (eg, a laser radar, a monocular vision camera, etc.) for acquiring point cloud data of the pile.

[0030] In some embodiments, the point cloud data of the pile within the loader's operating area may include the entire point cloud data of the pile. For example, before performing a shoveling operation, the loader may be driven around the pile so that the sensors installed on the loader can scan the pile in all directions, thereby acquiring complete point cloud data of the pile.

[0031] In other embodiments, the point cloud data of the pile within the loader's operating area may include only a portion of the pile's point cloud data. For example, if the loader is equipped with a laser radar, only the portion of the point cloud data within the laser radar's sensing range may be acquired when the loader is stationary.

[0032] Here, on the one hand, if a full-scale scan of the material pile is required before each excavation operation, a certain amount of excavation operation time will be wasted, resulting in low excavation efficiency; on the other hand, in some operation scenarios (such as the scene where the material pile is located in a narrow and long passage), it is not possible to meet the condition that the loader drives around the material pile for a full-scale scan to obtain all the point cloud data of the material pile. In this scenario, if the excavation control must rely on all the point cloud data of the material pile to be realized, the excavation control will have poor adaptability to the working environment, which may have an adverse effect on the accuracy of the excavation control.

[0033] Therefore, to effectively improve the loader's excavation accuracy even when the loader does not perform a full scan of the pile, but only acquires point cloud data for a portion of the pile, this application proposes a method for setting the grid resolution based on the distance between the loader and the pile. This allows the loader to flexibly adjust the grid resolution used to rasterize the pile's point cloud data based on the distance between the loader and the pile, thereby improving the adaptability of excavation control to the operating environment and enhancing excavation accuracy. Furthermore, this reduces the time required to acquire point cloud data, effectively increasing excavation efficiency.

[0034] In step 120 , the point cloud data is rasterized based on the grid resolution to obtain a grid map.

[0035] Here, the grid resolution is set based on a first distance between the current position of the loader and the stockpile.

[0036] In some embodiments, the current position of the loader can be determined based on a global positioning system (GPS). For example, the current position of the loader can be represented by position coordinates obtained based on real-time kinematic (RTK) technology.

[0037] In some embodiments, the first distance may be the distance between the current position of the loader and the center of mass of the pile.

[0038] In some embodiments, the position coordinates of the center of mass of the pile may be determined based on the position coordinates of the point cloud points in the point cloud data, and then the first distance may be determined based on the position coordinates of the center of mass of the pile and the position coordinates of the current position of the loader.

[0039] For example, the average value of the position coordinates of all the point cloud points in the point cloud data can be determined as the position coordinates of the center of mass of the pile. The first distance is determined based on the Euclidean distance between the position coordinates of the center of mass of the pile and the position coordinates of the current position of the loader.

[0040] For example, the point cloud data includes the position coordinates of three point cloud points, namely (x1, y1, z1), (x2, y2, z2), and (x3, y3, z3). The position coordinates of the center of mass of the pile are (x4, y4, z4), where x4 = (x1+x2+x3) / 3, y4 = (y1+y2+y3) / 3, and z4 = (z1+z2+z3) / 3. Assume that the position coordinates of the loader are (x5, y5, z5), the first distance

[0041] It should be noted that rasterization is the process of projecting 3D point cloud data onto a 2D plane and discretizing it into regular grid cells (also called "grid cells," hereinafter referred to as "grids"). A raster map is composed of multiple grid cells.

[0042] Each grid cell can store the height values ​​(i.e., the z-coordinates) of the point cloud points within the area corresponding to that grid cell. The grid resolution determines the size of each grid cell and can be expressed in units of length (e.g., meters). For example, in a two-dimensional grid map, each grid cell is a square with a side length equal to the grid resolution.

[0043] Figure 2 A schematic diagram illustrating a grid map according to some embodiments of the present disclosure.

[0044] like Figure 2 As shown in FIG, as an example, after scanning a pile of materials, point cloud data of the pile of materials is obtained. Assuming that the grid resolution is 0.2 meters, the point cloud data of the pile of materials is rasterized based on this grid resolution to obtain an n×n two-dimensional grid map ( Figure 2 A 4×4 grid map is schematically shown), where the size of each grid is 0.2 m×0.2 m.

[0045] It should be noted that a grid map can be used to describe the shape and location of a stockpile. For example, the coordinates of each point cloud point in the grid map can reflect the physical location of the stockpile. The edges of the grid map can reflect the physical boundaries of the stockpile. The height values ​​of the point cloud points stored in the grid map (i.e., the z-coordinates of the point cloud points) can also reflect the physical height of the stockpile.

[0046] For example, the height of the pile corresponding to each grid can be determined based on the height values ​​of each point cloud point stored in each grid. For example, the height of the pile corresponding to each grid can be determined based on the average of the height values ​​of each point cloud point stored in each grid. For example, if the height values ​​of three point cloud points stored in a grid are z1', z2', and z3', respectively, then the height of the pile corresponding to this grid is z4' = (z1' + z2' + z3') / 3.

[0047] It should be understood that the edge of the grid map is the boundary of the rectangular area formed by the minimum and maximum x-coordinates and the minimum and maximum y-coordinates of the point cloud points in the grid map.

[0048] In step 130 , an initial digging position of the loader within the work area is determined based on a second distance between the current position of the loader and at least one grid on the edge of the grid map.

[0049] In some embodiments, at least one grid on the edge of the grid map includes multiple grids, and a second distance between the loader and each of the multiple grids can be determined, and the position corresponding to the grid with the smallest second distance is determined as the initial digging position.

[0050] In some embodiments, the position coordinates of each grid are determined based on the position coordinates of the point cloud points in each grid. Then, a second distance between the loader and each grid is determined based on the position coordinates of the loader and the position coordinates of each grid.

[0051] For example, if a grid contains only one point cloud point, the two-dimensional position coordinates of the point cloud point in the grid map can be determined as the position coordinates of the grid.

[0052] For example, a grid may contain multiple point cloud points. In this case, the position coordinates of the grid can be determined based on the average value of the position coordinates of each point cloud point in the grid map. For example, a grid includes three point cloud points, and the position coordinates of these three point cloud points in the grid map are (x1', y1'), (x2', y2'), and (x3', y3'), respectively. Then the position coordinates of the grid are (x4', y4'), where x4' = (x1'+x2'+x3') / 3 and y4' = (y1'+y2'+y3') / 3. Assuming that the position coordinates of the current position of the loader are (x5, y5), the second distance between the loader and the grid is

[0053] In this way, the position coordinates of the grid are determined by using the position coordinates of the point cloud points contained in each grid. Compared with the method of directly using the position coordinates of the center of the grid as the position coordinates of the grid, the position coordinates of the grid can more accurately reflect the distribution of the point cloud points in the area, thereby improving the accuracy of the grid map's description of the material pile, thereby improving the accuracy of the determined initial excavation position, and helping to improve the excavation accuracy.

[0054] In some embodiments, a second distance between the loader and each grid is determined based on a Euclidean distance between the position coordinates of the loader and the position coordinates of each grid.

[0055] For example, reference Figure 2 The grid map has 12 grids at its edges (e.g., the top, bottom, left, and right boundaries). The Euclidean distance between the position coordinates of each grid in the 12 grids and the position coordinates of the loader is determined as the distance between each grid and the loader. The position corresponding to the grid with the smallest distance from the loader among the 12 grids is determined as the initial digging position. For example, the position coordinates of the grid with the second smallest distance from the loader can be determined as the position coordinates of the initial digging position.

[0056] In step 140 , the loader is controlled to dig the pile based on the initial digging position.

[0057] In some embodiments, the bucket of the loader is controlled to dig the pile of materials from an initial digging position.

[0058] In some embodiments, the initial digging position can be the same as or different from the current position of the loader. For example, if the initial digging position is different from the current position of the loader, the loader can be controlled to move from the current position to the initial digging position, and then dig the pile from the initial digging position.

[0059] In the above embodiment, the grid resolution used to rasterize the point cloud data of the stockpile is adjusted based on the first distance between the loader and the stockpile. This allows the resulting grid map to accurately provide relevant information about the stockpile (e.g., its shape and location) for the loader's excavation control. The second distance between the loader and a grid cell on the edge of the grid map accurately reflects the distance between the loader and the physical boundary of the stockpile, making the initial excavation position determined based on this second distance more accurate. In this way, the loader can accurately excavate material based on this initial excavation position, improving the accuracy of the loader's excavation operation.

[0060] The following first describes the grid resolution setting method of the present disclosure in conjunction with some embodiments.

[0061] In some embodiments, the grid resolution is positively correlated with the first distance. The greater the first distance, the greater the grid resolution. In other words, the farther the loader is from the pile, the coarser the grid divisions become. The smaller the first distance, the smaller the grid resolution. In other words, the closer the loader is to the pile, the finer the grid divisions become.

[0062] Since the grid resolution can be adjusted according to the distance between the loader and the pile, the grid map obtained after rasterization processing can accurately provide information about the pile when the loader is in any position, making the initial excavation position determined based on the grid map more accurate, so that the loader can accurately excavate materials based on the initial excavation position, thereby improving the accuracy of the loader's excavation operation.

[0063] In some further embodiments, in response to the first distance being less than a specified distance, the grid resolution is set to a fixed value; and in response to the first distance being greater than or equal to the specified distance, the grid resolution is set based on the first distance, wherein the grid resolution is positively correlated with the first distance and is greater than or equal to the fixed value. Herein, the specified distance is also referred to as the first specified distance.

[0064] For example, if the distance is d1 (expressed in length units, such as meters), the grid resolution It can be set according to the following formula:

[0065]

[0066] Wherein, d2 is a fixed value (expressed in length units, such as meters), P L Indicates the current position of the loader, P C represents the position of the center of mass of the pile, ||P L -P C || represents the first distance between the current position of the loader and the pile, r(||P L -PC ||) represents the distance based on the first distance ||P L -P C || The grid resolution is determined in a positive correlation and satisfies r(||P L -P C ||)≥d2.

[0067] As a non-limiting example, d1 is 3 meters and d2 is 0.1 meters. The above formula indicates that when the first distance between the current position of the loader and the pile is less than 3 meters, the grid resolution will be set to a fixed value of 0.1 meters; when the first distance between the current position of the loader and the pile is greater than or equal to 3 meters, the grid resolution will be based on the first distance || P L -P C || positive correlation is determined. r(||P L -P C ||) is greater than or equal to 0.1 meters.

[0068] It should be understood that a larger grid resolution results in a larger grid cell size in the resulting grid map, resulting in fewer grid cells and, consequently, less data to process. However, this also means that each grid cell covers a larger physical area of ​​the stockpile, resulting in a coarser description of the stockpile (i.e., a lower grid map accuracy).

[0069] Conversely, the smaller the grid resolution, the smaller the size of each grid in the resulting grid map, the more grids there are in the grid map, and the larger the amount of data required for subsequent processing. However, this also means that the physical range of the stockpile covered by each grid is smaller, and the description of the stockpile is more detailed (i.e., the grid map has higher accuracy).

[0070] Based on this, in some of the above embodiments, on the one hand, considering that when the first distance between the loader's current position and the material pile is small (i.e., close-range operation), the detailed information of the material pile (such as the irregular shape of the edge of the material pile, etc.) has a greater impact on the loader's excavation control accuracy. If a larger grid resolution is used, the grid map's representation of the material pile will be less accurate, and the detailed information of the material pile will not be accurately provided. This will affect the loader's judgment of relevant information such as the material pile's boundaries and height, and will be detrimental to the accurate determination of the initial excavation position. Therefore, in this case, a smaller grid resolution is selected to obtain the grid map, so that the grid map can accurately provide detailed information about the material pile, thereby improving the accuracy of the loader's excavation operation.

[0071] On the other hand, considering that the first distance between the loader's current position and the pile is relatively large (i.e., operating at a long distance), the detailed information of the pile has less impact on the loader's excavation control accuracy. For example, in a large material yard, the loader can perform excavation operations based on the approximate orientation of the pile. In this case, if a smaller grid resolution is still used, the grid map data volume will be too large, which will in turn lead to a large amount of calculation required to determine the initial excavation position, increasing the computational burden and hindering the rapid determination of the initial excavation position. Therefore, in this case, choosing a larger grid resolution to obtain the grid map effectively reduces the amount of calculation required to determine the initial excavation position and improves the efficiency of the excavation operation.

[0072] Furthermore, when operating from a distance, the grid resolution varies in direct correlation with the first distance between the loader's current position and the stockpile. Specifically, when the loader is close to the stockpile, a smaller grid resolution is used to refine the digging action; when the loader is further away, a larger grid resolution is used to reduce computational complexity. This allows the grid resolution to be flexibly adjusted based on the distance between the loader and the stockpile, effectively balancing the accuracy and efficiency of the digging operation, thereby significantly improving both the accuracy and efficiency of the loader's digging.

[0073] In some embodiments, in response to the first distance being greater than or equal to a specified distance, a grid resolution may be set based on the first distance and the volume of the stockpile, wherein the grid resolution is positively correlated with both the first distance and the volume of the stockpile. The specified distance is also referred to herein as a second specified distance.

[0074] In the case of long-distance operation, if the volume of the material pile is large, it means that the shape and position of the material pile are easier to identify. In this case, a larger grid resolution can be used to make the physical range covered by each grid larger to reduce the amount of calculation and improve the efficiency of the excavation operation. If the volume of the material pile is small, it means that the shape and position of the material pile are difficult to identify. In this case, a smaller grid resolution is used so that the grid map can accurately provide detailed information about the material pile to improve the accuracy of the excavation operation.

[0075] That is, in remote operation, the grid resolution can be adjusted in a positive correlation with the first distance between the loader's current position and the pile, as well as the pile's volume. This further considers the pile's volume when setting the grid resolution used for rasterization, improving the adaptability of excavation control to piles of varying sizes, thereby further effectively improving the loader's excavation accuracy and efficiency.

[0076] In some embodiments, in response to the first distance being greater than or equal to a specified distance, a grid resolution may be set based on the first distance, the volume of the pile, and the turning radius of the loader, wherein the grid resolution is positively correlated with the first distance, the volume of the pile, and the turning radius of the loader. The specified distance is also referred to herein as a third specified distance.

[0077] In the case of long-distance operation, if the loader's turning radius is large, it means that the loader's excavation action requires a larger spatial range to be implemented. In this case, a larger grid resolution can be used to make the physical range covered by each grid larger to provide more macro-environmental information, while reducing the amount of calculation and improving the efficiency of the excavation operation; if the loader's turning radius is small, it means that the loader can perform fine excavation actions in a smaller spatial range. In this case, a smaller grid resolution can be used so that the grid map can accurately provide detailed information of the material pile to improve the accuracy of the excavation operation.

[0078] In other words, when operating remotely, the grid resolution can be adjusted in a positive correlation with the distance between the loader's current position and the pile, the pile's volume, and the loader's turning radius. By factoring the loader's turning radius into the grid resolution used for rasterization, the adaptability of excavation control to the loader's specific conditions can be improved, further effectively enhancing the accuracy and efficiency of the loader's excavation operations.

[0079] In some embodiments, in response to the first distance being greater than or equal to a specified distance, a first parameter may be determined based on the first distance and the turning radius of the loader, and a second parameter may be determined based on the volume of the pile. A grid resolution is determined based on the sum of the first and second parameters. The second parameter is non-zero. For example, the second parameter is a non-zero constant.

[0080] In this way, the invalid situation of grid resolution being 0 can be avoided, and the reliability of grid resolution setting can be improved.

[0081] In some embodiments, the first parameter can be determined based on the product of the first distance and the loader's turning radius. For example, the first distance can be normalized using the sensing distance of a sensor installed on the loader, which is used to acquire point cloud data of the pile. An activation function can then be used to determine the first parameter based on the product of the normalized first distance and the loader's turning radius. This allows for smoother adjustment of the grid resolution.

[0082] For example, the first parameter can be in, is the activation function, k represents the turning radius of the loader, (||P L -P C||) represents the first distance, d max Indicates the maximum perception distance (e.g., 20 meters) of the loader's sensor (e.g., LiDAR).

[0083] In some embodiments, a corresponding weight coefficient can be set for the activation function, and the first parameter can be determined based on the product of the weight coefficient and the activation function. The weight coefficient is set based on the positive correlation of the first distance. For example, the first parameter can be Where m1 is the weight coefficient corresponding to the activation function. In this way, the grid resolution can be adjusted more accurately.

[0084] In some embodiments, the grid resolution is determined based on a preset base resolution and the sum of the first parameter and the second parameter.

[0085] In some embodiments, the base resolution is greater than a fixed value of the grid resolution set when the first distance is less than a specified distance. For example, the grid resolution can be determined based on the product of the base resolution and the sum of the first parameter and the second parameter. In this way, it can be ensured that the grid resolution set when the first distance is greater than or equal to the specified distance is greater than or equal to the fixed value of the grid resolution set when the first distance is less than the specified distance.

[0086] For example, in the case of long-distance operation, the grid resolution can be determined according to the following formula:

[0087]

[0088] Among them, P L Indicates the current position of the loader, P C represents the position of the center of mass of the pile, ||P L -P C || represents the first distance, is the first parameter, m2 is the second parameter, r base It is a preset basic resolution (for example, 0.2 meters).

[0089] In the above embodiments, the "first specified distance", "second specified distance" and "third specified distance" may be the same or different. For example, the second specified distance and the third specified distance may be greater than or equal to the first specified distance.

[0090] Next, the implementation of the loader digging a pile of materials based on an initial digging position will be further described in conjunction with some embodiments.

[0091] During the excavation process, a multi-objective optimization algorithm can be used to determine the target excavation path. This target excavation path includes the loader's initial excavation position and the target stopping position for each excavation. The starting position of the loader's first excavation is the initial excavation position, and the stopping position of the loader's previous excavation is the starting position for the next excavation. Determination of the initial excavation position has been discussed previously, so the multi-objective optimization algorithm here focuses on determining the target stopping position for each excavation.

[0092] It should be understood that "dynamic adjustment of grid resolution" in this application refers to the ability of the grid resolution to dynamically change with the distance between the loader and the stockpile. In this application, before executing excavation control, the grid resolution is first determined based on the distance between the loader's current position and the stockpile to generate a grid map. Subsequent calculations for determining the initial excavation position and the target stop position for each excavation are based on this determined grid map.

[0093] In some embodiments, an objective function is constructed with the goals of minimizing the resistance experienced by the loader's bucket during each digging process, minimizing the path length between the starting and stopping positions of each digging operation, and maximizing the loader's digging efficiency. The objective function is solved to determine the target stopping position for each digging operation, and the loader is controlled to dig the pile based on the initial digging position and the target stopping position for each digging operation.

[0094] Here, the digging efficiency is determined based on the loader's digging time and the volume of the pile dug each time. For example, the digging efficiency can be determined based on the loader's mechanical efficiency coefficient, the loader's digging time and the volume of the pile dug each time. For example, the loader's digging efficiency for the kth (k ≥ 1) digging time is E k =η·V k / t k , where η represents the mechanical efficiency coefficient (e.g. 0.8-0.9), V k represents the volume of the pile excavated for the kth time, t k Indicates the k-th excavation operation time.

[0095] After determining the target stop position of each shoveling by the loader by solving the objective function, the loader bucket can be controlled to move along the target shoveling path formed by the initial shoveling position and the target stop position of each shoveling to shovel the material pile.

[0096] For example, during a loader excavation operation, the loader is controlled to use the initial excavation position as the starting position for the first excavation, perform the first excavation, and stop at the target stop position for the first excavation. Subsequently, the loader is controlled to use the target stop position for the first excavation as the starting position for the second excavation, perform the second excavation, and stop at the target stop position for the second excavation. Thereafter, the loader is controlled to use the target stop position for the second excavation as the starting position for the third excavation, perform the third excavation, and stop at the target stop position for the third excavation. This process continues in this manner until the loader completes excavation of the pile.

[0097] Therefore, based on accurately determining the initial excavation position by dynamically setting the grid resolution, the present application can further accurately determine the stopping position of each excavation by constructing an objective function, thereby planning the optimal path for each excavation, so that the loader can complete the excavation operation efficiently and accurately according to the planned target excavation path.

[0098] In some embodiments, the constructed objective function may be expressed as min(Σ(digging resistance)+Σ(path length)−(digging efficiency)).

[0099] As an example, the objective function can be constructed as follows:

[0100]

[0101] Among them, F k is the resistance (N) experienced by the loader bucket during the kth digging process, L k,k+1 is the path length (m) between the starting position of the kth shovel and the starting position of the k+1th shovel (i.e., the stopping position of the kth shovel), E k is the kth excavation efficiency (m 3 / s), ω1, ω2, ω3 are F k 、L k,k+1 and E k The weight coefficient is ω1+ω2+ω3=1. For example, ω1, ω2, and ω3 can be fixed constants.

[0102] In some embodiments, a sensor (e.g., a pin sensor) can be installed at the connection between the loader's boom and bucket to measure the strain at the connection, thereby calculating the resistance applied to the bucket based on the strain. Those skilled in the art will appreciate that the resistance applied to the bucket can be calculated using stress calculation methods relevant to the art. This description will not be elaborated upon here.

[0103] In some embodiments, the constructed objective function can be solved based on an improved non-dominated sorting genetic algorithm (NSGA-II). Those skilled in the art will appreciate that the improved non-dominated sorting genetic algorithm (NSGA-II) is a commonly used algorithm in the art for solving objective functions for multi-objective optimization. Those skilled in the art can use this algorithm to solve the objective function constructed in this application to obtain the target stopping position for each excavation.

[0104] In this way, on the one hand, considering that the excavation efficiency reflects the speed of the loader's excavation operation, maximizing the excavation efficiency can maximize the construction progress.

[0105] On the other hand, considering that digging resistance and the path length between the start and stop positions of each digging operation affect the loader's fuel consumption and mechanical wear, for example, the greater the digging resistance and the longer the path length between the start and stop positions of each digging operation, the greater the loader's fuel consumption and mechanical wear. Conversely, the smaller the digging resistance and the shorter the path length between the start and stop positions of each digging operation, the lower the loader's fuel consumption and mechanical wear. Therefore, minimizing the digging resistance and the path length between the start and stop positions of each digging operation can effectively reduce the cost of digging operations.

[0106] Therefore, the objective function constructed in the above manner can effectively balance the cost and excavation efficiency of the loader performing the excavation operation, thereby controlling the loader to perform the excavation operation based on the solution of the objective function, enabling the loader to perform the excavation operation at a lower cost and more efficiently.

[0107] In some embodiments, the objective function may be solved based on pre-set constraints to determine the target stopping position of the loader for each digging operation.

[0108] Here, the pre-set constraints include at least one of a first constraint related to the cutting angle of the loader's bucket during each digging, a second constraint related to the digging depth of the loader during each digging, a third constraint related to the volume of the pile of materials dug by the loader during each digging, and a fourth constraint related to the digging direction of the starting position of the loader during each digging relative to the stopping position of each digging.

[0109] In some embodiments, the first constraint condition includes that the cutting angle of each digging is less than or equal to a first threshold.

[0110] It should be understood that the bucket's engagement angle refers to the angle formed between the loader's bucket and the loader's boom during the excavation operation.

[0111] Figure 3A structural schematic diagram showing a partial structure of a loader according to some embodiments of the present disclosure.

[0112] like Figure 3 As shown, during the excavation operation, the angle formed between the bucket 1 and the arm 2 of the loader is the bucket's cutting angle 3.

[0113] In this way, considering that an excessively large cutting-in angle may cause excessive stress concentration on the leading edge of the bucket of the loader during the excavation process, causing damage to the structure of the bucket, therefore, by introducing a first constraint condition related to the cutting-in angle of the loader's bucket, the possibility of structural damage to the bucket of the loader during the excavation operation based on the solution of the objective function can be reduced, thereby enabling the loader to perform excavation operations reliably.

[0114] In some embodiments, the first threshold may be a fixed value.

[0115] In some embodiments, the first threshold may be dynamically determined based on a historical standard deviation of the cut-in angles.

[0116] For example, the first constraint can be expressed as:

[0117] θ k =arctan(Δz k / Δs k )≤n1-f1std(θ)

[0118] Among them, θ k represents the cutting angle of the loader bucket during the kth digging, Δz k represents the digging depth of the kth digging (m), Δs k represents the horizontal displacement of the bucket during the k-th digging (m), n1 is the first threshold, std(θ) represents the historical standard deviation of the cutting angle, and f1 is the preset adjustment coefficient of the historical standard deviation.

[0119] Here, the historical standard deviation of the engagement angle reflects its historical fluctuations. A larger historical standard deviation indicates more dramatic historical variations in the engagement angle; a smaller historical standard deviation indicates more stable historical variations. Introducing the historical standard deviation of the engagement angle dynamically adjusts the constraints on the engagement angle, reducing abnormal fluctuations and improving the reliability of the objective function solution, thereby enabling the loader to perform excavation operations more reliably.

[0120] In some embodiments, the second constraint condition includes that the digging depth of each digging is less than or equal to a second threshold, wherein the second threshold is determined based on the material of the material in the pile.

[0121] It should be understood that the digging depth refers to the maximum distance that the front edge of the bucket (such as the tooth tip of the bucket) of the loader bucket cuts into the pile during the digging operation.

[0122] Continue to refer Figure 3 ,like Figure 3 As shown, the digging depth D is the maximum distance reached by the bucket front 4 (e.g., the tooth tip of the bucket) after cutting into the pile 5 from the digging point.

[0123] In this way, on the one hand, considering that a larger digging depth can make the loader dig more fully each time, it helps to improve the digging efficiency; on the other hand, considering that the digging depth is positively correlated with the resistance encountered by the bucket when inserted into the pile, if the digging depth is too large, the resistance encountered by the bucket when inserted into the pile will be greater, and the loader will need to apply greater force to the bucket to overcome the resistance from the pile, which will cause the relevant components of the loader (such as the cylinder, oil pump and other components in the hydraulic system used to drive the bucket movement) to be subjected to greater pressure, which may easily cause mechanical wear and even structural damage of the loader.

[0124] Therefore, by introducing a second constraint condition related to the loader's digging depth, the loader's digging depth during each digging operation can be kept within a reasonable range, reducing the occurrence of problems such as structural damage caused by excessive digging depth or insufficient digging due to insufficient digging depth, thereby enabling the loader to reliably perform digging operations while improving digging efficiency.

[0125] In some embodiments, the second threshold value may be determined inversely according to the hardness of the material in the stockpile. For example, if the material in the stockpile is harder, such as stone, the corresponding second threshold value may be smaller; conversely, if the material in the stockpile is softer, such as sand, the corresponding second threshold value may be larger.

[0126] In some embodiments, the second threshold may be a fixed value.

[0127] In some embodiments, the second threshold may be dynamically determined based on a historical standard deviation of the digging depths.

[0128] For example, the second constraint can be expressed as:

[0129] 0≤Δz k ≤n2·(1-f2·std(z))

[0130] Where Δz k represents the digging depth of the kth digging (m), n2 is the second threshold, std(z) represents the historical standard deviation of the digging depth, and f2 is the preset adjustment coefficient of the historical standard deviation.

[0131] Here, the historical standard deviation of the digging depth reflects the degree of fluctuation in digging depth over the course of historical operations. A larger historical standard deviation indicates more dramatic historical variations in digging depth; a smaller historical standard deviation indicates more stable historical variations. Introducing the historical standard deviation of the digging depth dynamically adjusts the digging depth constraint range, reducing abnormal fluctuations and improving the reliability of the objective function solution, thereby enabling the loader to perform digging operations more reliably.

[0132] In some embodiments, the third constraint condition includes that the volume of the pile excavated each time by the loader is greater than or equal to a third threshold, wherein the volume of the pile excavated each time by the loader is determined based on the grid map, the grid resolution, and the width of the loader bucket.

[0133] In some embodiments, the volume of the pile of materials excavated each time by the loader is determined as follows: based on the grid resolution and the width of the loader's bucket, the area of ​​the pile of materials covered by the loader's bucket each time is determined in the partial grid corresponding to the grid map; based on the position coordinates of the point cloud points in the partial grid, the volume of the pile of materials excavated each time by the loader is determined.

[0134] In some embodiments, the bucket's travel distance (also known as the movement step length) for each digging operation is set based on the grid resolution. The area formed by this travel distance and the bucket's width represents the area of ​​the pile covered by the bucket during each digging operation. The grid cell corresponding to this area is determined from the grid map, and the volume of the pile dug by the loader during each digging operation is calculated based on the position coordinates of the point cloud points in this grid cell.

[0135] For example, the volume of the pile of materials in the area (i.e., the volume of the excavated pile) can be determined by performing an integral calculation based on the position coordinates of the point cloud points in a part of the grid. For example, the volume of the pile of materials excavated by the loader bucket for the kth time can be Wherein, Sk represents the area of ​​the pile covered by the bucket of the shovel loader for the kth time, and z(x, y) represents the height value corresponding to the position coordinates of the point cloud point in the part of the grid corresponding to Sk.

[0136] In some embodiments, the distance the bucket moves each time it digs is an integer multiple of the grid resolution. This makes it easier to calculate the volume of the pile dug by the loader each time and reduces calculation errors.

[0137] In some embodiments, the third threshold may be a fixed value.

[0138] In some embodiments, the third threshold may be dynamically determined based on a historical standard deviation of the volume of the pile dug each time by the loader.

[0139] For example, the third constraint can be expressed as:

[0140]

[0141] Among them, V k represents the volume of the pile dug by the bucket of the loader for the kth time, n3 is the third threshold, std(V) represents the historical standard deviation of the volume of the pile dug by the loader each time, and f3 is the preset adjustment coefficient of the historical standard deviation.

[0142] Here, the historical standard deviation of the volume of the pile excavated by the loader reflects the degree of fluctuation in the volume of the pile excavated by the loader during its historical operations. A larger historical standard deviation indicates a more dramatic historical variation in the volume of the pile excavated by the loader; a smaller historical standard deviation indicates a more stable historical variation in the volume of the pile excavated by the loader. Introducing the historical standard deviation of the volume of the pile excavated by the loader can dynamically adjust the constraint range of the volume of the pile excavated by the loader, reduce abnormal fluctuations, and improve the reliability of the solution to the objective function, thereby enabling the loader to perform excavation operations more reliably.

[0143] It should be noted here that the volume of the pile excavated by the loader each time is positively correlated with the full bucket rate of the loader each time.

[0144] The full bucket rate of a loader refers to the ratio between the volume of the pile loaded by the loader bucket in one excavation operation and the rated capacity of the bucket.

[0145] For example, the bucket fill rate of a loader can be expressed as a percentage. If the rated capacity of the bucket is 3 cubic meters, and the bucket loads a pile volume of 2.7 cubic meters in one excavation operation, the bucket fill rate is 90%.

[0146] In some embodiments, the third threshold value can be set based on the full bucket rate requirement in the engineering application. For example, the third threshold value can be determined in a positive correlation with the full bucket rate. For example, if the full bucket rate required in an urban road construction application is lower than that required in a mining application, then the third threshold value set in the urban road construction application can be lower than the third threshold value set in the mining application.

[0147] In the above embodiments, the full bucket rate of each loader shovel has a significant impact on both the loader's shovel efficiency and shovel cost. For example, a high full bucket rate means the loader can load more material per shovel, reducing the number of round trips and transports, saving fuel consumption, thereby improving shovel efficiency and reducing shovel costs. In contrast, a low full bucket rate means the loader can load less material per shovel, requiring the loader to frequently travel back and forth between the material pile and the transport vehicle, increasing fuel consumption, and resulting in low shovel efficiency and higher shovel costs.

[0148] Therefore, by introducing a third constraint condition related to the volume of the pile of materials excavated by the loader each time, the full bucket rate of the loader each time can be flexibly met the requirements of engineering applications, thereby effectively improving the loader's excavation efficiency and reducing excavation costs.

[0149] In some embodiments, the fourth constraint condition includes the angle between the digging direction of the loader's starting position for each digging operation relative to the stopping position for each digging operation and the direction of the loader's current position relative to the center of mass of the pile being less than or equal to a fourth threshold. It should be understood that the digging direction of the loader's digging operation is the direction in which the loader's bucket moves from the starting position to the stopping position for each digging operation.

[0150] In some embodiments, the fourth threshold is a fixed value.

[0151] In some embodiments, the angle between the digging direction of each digging by the loader and the direction of the loader's current position relative to the center of mass of the pile of materials can be calculated by using the dot product of the direction vector of the digging direction of each digging and the direction vector of the loader's current position relative to the center of mass of the pile of materials.

[0152] For example, the angle δ between the digging direction of each digging by the loader and the direction of the current position of the loader relative to the position of the center of mass of the pile is k =arccos(d k ·u c ), where d k =p k+1 -p k / ||p k+1 -p k ||, d k represents the starting position p of the kth excavation k Relative to the starting position p of the k+1th shovel k+1 (i.e., the stopping position of the k-th shoveling) direction vector (i.e., the shoveling direction of the k-th shoveling), u c =p c -p k / ||p c -p k || represents the current position p of the loader during the kth digging operation k Position p relative to the center of mass of the pile c The direction vector, d k ·u c is the dot product of two direction vectors.

[0153] For example, the fourth constraint can be expressed as δ k =arccos(d k ·u c )≤n4, that is, dk ·u c ≤cos(n4). n4 is the fourth threshold.

[0154] In the above embodiment, considering that the loader's digging direction affects the path length of each digging stroke, a fourth constraint condition related to the digging direction of each digging stroke is introduced. This optimizes the digging direction to find the shortest path for each digging stroke, improving the reliability of the target stopping position obtained for each digging stroke. Furthermore, a reasonable digging direction can also reduce the resistance encountered by the bucket when entering the pile, reducing mechanical wear on the loader and thus lowering the cost of the loader's digging operations.

[0155] Furthermore, by constraining the digging direction by making the angle between the digging direction of each digging operation and the direction of the loader's current position relative to the center of mass of the pile smaller, compared to simply constraining the digging direction of each digging operation (e.g., fixing the digging direction within a certain range), the loader's digging direction can be made as close to the center of mass of the pile as possible. This, on the one hand, allows the bucket to dig toward the center of the pile during each digging operation, helping to shorten the path length of each digging operation. On the other hand, the density of material near the center of mass of the pile is generally higher. By making the digging direction closer to the center of mass of the pile, the bucket can load more material during a single digging operation, helping to increase the loader's bucket fill rate. This effectively improves the efficiency of the loader's digging operation.

[0156] In some embodiments, solving the objective function can also determine a target digging direction for each digging start position relative to each digging stop position. This allows the loader's bucket to be controlled to move in accordance with the target digging direction along a target digging path defined by the initial digging position and the target digging stop position for each digging step, thereby digging the pile.

[0157] In this way, by solving the objective function, the optimal digging direction and digging path for the loader to perform digging operations can be obtained, and the loader can perform low-cost, efficient and reliable digging operations based on the optimal digging direction and digging path.

[0158] Figure 4 A flow chart showing a method for controlling the shoveling of a loader according to other embodiments of the present disclosure is shown. For example, Figure 4 The excavation control method shown can be used as Figure 1 The excavation control method shown is executed by a specific implementation.

[0159] like Figure 4 As shown, in step 410 , point cloud data of a pile of materials within the working area of ​​the loader is acquired.

[0160] In some embodiments, a sensor on the loader (e.g., a laser radar or a monocular camera) scans the loader's operating area to obtain point cloud data of the operating area. The point cloud data of the operating area is filtered and segmented to obtain point cloud data of the stockpile.

[0161] In step 420 , a grid resolution is set according to a first distance between the current position of the loader and the stockpile, and the point cloud data of the stockpile is rasterized based on the grid resolution to obtain a grid map.

[0162] Here, the setting method of the grid resolution can be implemented similarly to the method in the previous related embodiments. For specific instructions, please refer to the description in the previous related embodiments, and no further details will be given here.

[0163] In step 430 , a second distance between the current position of the loader and each of the plurality of grids on the edge of the grid map is calculated.

[0164] In some embodiments, point cloud processing software can be used to extract the spatial coordinates (i.e., x, y, and z coordinates) of each point cloud point from the point cloud data of the stockpile and store them in x_coords, y_coords, and z_coords, respectively. After rasterizing the point cloud data to obtain a grid map, the minimum and maximum x coordinates and the minimum and maximum y coordinates can be determined from x_coords and y_coords to determine the edges of the grid map.

[0165] In some embodiments, the number of columns and rows of the grid may be calculated and the index of each grid may be determined.

[0166] It should be understood that the index of the grid is used to uniquely identify and locate each grid. For example, in a two-dimensional grid map, the index of the grid (i, j) represents the grid in the i-th row and the j-th column.

[0167] In some embodiments, the position coordinates of each point cloud point in each grid on the edge of the grid map can be obtained from x_coords and y_coords based on the index of the grid. The average position coordinates of the point cloud points in the grid are used as the position coordinates of the grid. Based on the position coordinates of the loader and the position coordinates of the grid, a second distance between the loader and the grid is calculated.

[0168] In step 440 , the position corresponding to the grid with the smallest second distance is determined as the initial digging position of the loader in the working area.

[0169] In some embodiments, the initial digging position may be recorded by recording the index of the grid having the second smallest distance from the loader.

[0170] In step 450 , an objective function is constructed. Here, the objective function is constructed with the goals of minimizing the resistance experienced by the loader bucket during each digging process, minimizing the path length between the starting position and the stopping position of each digging process, and maximizing the digging efficiency of the loader.

[0171] In step 460 , the objective function is solved based on preset constraints to determine the target stopping position of each digging operation of the loader and the target digging direction of the starting position of each digging operation relative to the stopping position of each digging operation.

[0172] Here, the pre-set constraints include at least one of a first constraint related to the cutting angle of the bucket of the loader each time it digs, a second constraint related to the digging depth of the loader each time it digs, a third constraint related to the volume of the pile of materials dug each time the loader digs, and a fourth constraint related to the digging direction of the loader each time it digs.

[0173] In some embodiments, the objective function may be solved based on an improved non-dominated sorting genetic algorithm (NSGA-II) to find an optimal solution that satisfies the constraints through multiple generations of evolution, and output a target stopping position for each excavation.

[0174] In step 470 , the bucket of the loader is controlled to move in a target digging direction along a target digging path formed by the initial digging position and the target stop position to dig the pile.

[0175] In some embodiments, the volume of the pile of materials excavated each time may be calculated and accumulated until the total volume of the pile of materials excavated reaches a set value, and then the excavation of the pile of materials is completed.

[0176] Steps 430 to 470 can refer to the above Figure 1 The implementation of the relevant steps in the excavation control method shown is implemented similarly. For specific instructions, please refer to the description in the relevant embodiments above, which will not be repeated here.

[0177] It should be understood that the above Figures 1 to 3 The description of the related embodiments in the illustrated embodiment also applies to Figure 4 The excavation control method shown in the figure can be found in the previous text. Figures 1 to 3 The embodiments shown will not be described in detail here.

[0178] Figure 5 A block diagram illustrating a digging control device of a loader according to some embodiments of the present disclosure is shown.

[0179] like Figure 5As shown, the excavation control device 500 includes an acquisition module 501 , a processing module 502 , a determination module 503 and a control module 504 .

[0180] The acquisition module 501 is configured to acquire point cloud data of a material pile within the working area of ​​the loader.

[0181] The processing module 502 is configured to perform rasterization processing on the point cloud data based on a grid resolution to obtain a grid map, where the grid resolution is set based on a first distance between the current position of the loader and the pile of materials.

[0182] The determination module 503 is configured to determine an initial digging position of the loader in the work area based on a second distance between the current position of the loader and at least one grid on the edge of the grid map.

[0183] The control module 504 is configured to control the loader to dig the pile based on the initial digging position.

[0184] In some embodiments, the grid resolution is positively correlated with the first distance.

[0185] In some embodiments, the excavation control device 500 may further include a setting module, which is configured to set the grid resolution as follows: in response to the first distance being less than a specified distance, the grid resolution is set to a fixed value; in response to the first distance being greater than or equal to the specified distance, the grid resolution is set based on the first distance, and the grid resolution is positively correlated with the first distance and is greater than or equal to the fixed value.

[0186] In some embodiments, the setting module is configured to set a grid resolution based on the first distance and a volume of the stockpile in response to the first distance being greater than or equal to a specified distance, wherein the grid resolution is positively correlated with the volume of the stockpile.

[0187] In some embodiments, the setting module is configured to set a grid resolution based on the first distance, a volume of the pile, and a turning radius of the loader in response to the first distance being greater than or equal to a specified distance, wherein the grid resolution is positively correlated with the turning radius.

[0188] In some embodiments, the setting module is configured to determine a first parameter based on the first distance and the turning radius, and determine a second parameter based on the volume of the pile in response to the first distance being greater than or equal to the specified distance, wherein the second parameter is not zero; and determine the grid resolution based on the sum of the first parameter and the second parameter.

[0189] In some embodiments, the control module 504 is configured to construct an objective function with the goals of minimizing the resistance encountered by the loader's bucket during each digging process, minimizing the path length between the starting position and the stopping position of each digging of the loader, and maximizing the digging efficiency of the loader, wherein the digging efficiency is determined based on the operating time of each digging of the loader and the volume of the pile of materials dug by the loader each time; solving the objective function to determine the target stopping position of each digging of the loader; and controlling the loader to dig the pile of materials based on the initial digging position and the target stopping position.

[0190] In some embodiments, the control module 504 is configured to solve the objective function based on pre-set constraints to determine the target stopping position, wherein the constraints include at least one of a first constraint related to the cutting angle of the bucket of the loader during each digging, a second constraint related to the digging depth of the loader during each digging, a third constraint related to the volume of the pile of material dug by the loader during each digging, and a fourth constraint related to the digging direction of the starting position of each digging of the loader relative to the stopping position of each digging.

[0191] In some embodiments, the first constraint condition includes that the cutting angle of each digging is less than or equal to a first threshold.

[0192] In some embodiments, the second constraint condition includes that the digging depth of each digging is less than or equal to a second threshold, and the second threshold is determined based on the material of the material in the pile.

[0193] In some embodiments, the third constraint condition includes that the volume of the pile excavated each time by the loader is greater than or equal to a third threshold, wherein the volume of the pile excavated each time by the loader is determined based on the grid map, the grid resolution, and the width of the loader bucket.

[0194] In some embodiments, the determination module 503 is configured to determine the volume of the pile of materials excavated each time by the loader in the following manner: based on the grid resolution and the width of the loader's bucket, determine the partial grid in the grid map corresponding to the area of ​​the pile of materials covered by the loader's bucket each time; based on the position coordinates of the point cloud points in the partial grid, determine the volume of the pile of materials excavated each time by the loader.

[0195] In some embodiments, the fourth constraint includes an angle between the digging direction and the direction of the loader's current position relative to the position of the center of mass of the pile being less than or equal to a fourth threshold.

[0196] In some embodiments, the solution also obtains the target digging direction of the starting position of each digging of the loader relative to the stopping position of each digging, and the control module is configured to control the bucket of the loader to move along the target digging path formed by the initial digging position and the target stop position according to the target digging direction to dig the pile of materials.

[0197] In some embodiments, at least one grid on the edge of the grid map includes multiple grids, and the determination module 503 is configured to determine a second distance between the loader and each of the multiple grids; and determine the position corresponding to the grid with the smallest second distance as the initial digging position.

[0198] In some embodiments, the determination module 503 is configured to determine the position coordinates of each grid based on the position coordinates of the point cloud points in each grid; and determine the second distance between the loader and each grid based on the position coordinates of the loader and the position coordinates of each grid.

[0199] In some embodiments, the first distance is determined based on position coordinates of the current position of the loader and position coordinates of a center of mass of the pile, where the position coordinates of the center of mass of the pile are determined based on position coordinates of point cloud points in the point cloud data.

[0200] Figure 6 A block diagram illustrating a digging control device of a loader according to other embodiments of the present disclosure is shown.

[0201] like Figure 6 As shown, the excavation control device 600 includes: a memory 601 and a processor 602 coupled to the memory 601 , and the processor 602 is configured to execute the excavation control method in any one embodiment of the present disclosure based on instructions stored in the memory 601 .

[0202] The memory 601 may include, for example, a system memory, a fixed non-volatile storage medium, etc. The system memory may store, for example, an operating system, an application program, a boot loader, a database, and other programs.

[0203] Figure 7 A block diagram illustrating a digging control device of a loader according to further embodiments of the present disclosure is shown.

[0204] like Figure 7 As shown, the excavation control device 700 includes: a memory 701 and a processor 702 coupled to the memory 701 , and the processor 702 is configured to execute the method in any one of the aforementioned embodiments based on instructions stored in the memory 701 .

[0205] The memory 701 may include, for example, a system memory, a fixed non-volatile storage medium, etc. The system memory may store, for example, an operating system, application programs, a boot loader, and other programs.

[0206] The excavation control device 700 may also include an input / output interface 703, a network interface 704, a storage interface 705, and the like. These interfaces 703, 704, and 705, as well as the memory 701 and the processor 702, may be connected, for example, via a bus 706. The input / output interface 703 provides a connection interface for input / output devices such as a display, mouse, keyboard, touch screen, microphone, and speakers. The network interface 704 provides a connection interface for various networked devices. The storage interface 705 provides a connection interface for external storage devices such as SD cards and USB flash drives.

[0207] The embodiments of the present disclosure also provide a loader, comprising the digging control device of any one of the above embodiments (eg, digging control device 500\600\700).

[0208] An embodiment of the present disclosure further provides a computer-readable storage medium, comprising computer program instructions, which implement the method of any one of the above embodiments when executed by a processor.

[0209] The embodiments of the present disclosure further provide a computer program product, including a computer program, which implements the method of any one of the above embodiments when executed by a processor.

[0210] Those skilled in the art will appreciate that embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable non-transient storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0211] Thus far, the loader excavation control scheme according to the present disclosure has been described in detail. To avoid obscuring the concept of the present disclosure, some details known in the art have not been described. Based on the above description, those skilled in the art can fully understand how to implement the technical scheme disclosed herein.

[0212] The methods and systems of the present disclosure may be implemented in many ways. For example, the methods and systems of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless otherwise specified. In addition, in some embodiments, the present disclosure may also be implemented as programs recorded in a recording medium, which include machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers recording media that store programs for executing the methods according to the present disclosure.

[0213] Although some specific embodiments of the present disclosure have been described in detail by way of examples, those skilled in the art will appreciate that the above examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Those skilled in the art will appreciate that modifications may be made to the above embodiments without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A loader excavation control method, comprising: Acquire point cloud data of the material pile within the loader's operating area; rasterizing the point cloud data based on a grid resolution to obtain a grid map, wherein the grid resolution is set based on a first distance between a current position of the loader and the stockpile; determining an initial digging position of the loader within the work area based on a second distance between a current position of the loader and at least one grid cell on an edge of the grid map; The loader is controlled to dig the pile of materials based on the initial digging position.

2. The excavation control method according to claim 1, wherein: The grid resolution is positively correlated with the first distance.

3. The excavation control method according to claim 1, wherein: The grid resolution is set as follows: In response to the first distance being less than a specified distance, setting the grid resolution to a fixed value; In response to the first distance being greater than or equal to the designated distance, the grid resolution is set based on the first distance, the grid resolution being positively correlated with the first distance and greater than or equal to the fixed value.

4. The excavation control method according to claim 3, wherein: The setting the grid resolution based on the first distance includes: The grid resolution is set based on the first distance and the volume of the stockpile, and the grid resolution is positively correlated with the volume of the stockpile.

5. The excavation control method according to claim 4, wherein: The setting of the grid resolution based on the first distance and the volume of the stockpile includes: The grid resolution is set based on the first distance, the volume of the pile, and a turning radius of the loader, and the grid resolution is positively correlated with the turning radius.

6. The excavation control method according to claim 5, wherein: The step of setting the grid resolution based on the first distance, the volume of the pile, and the turning radius of the loader includes: determining a first parameter based on the first distance and the turning radius, and determining a second parameter based on the volume of the stockpile, wherein the second parameter is not zero; The grid resolution is determined based on the sum of the first parameter and the second parameter.

7. The excavation control method according to any one of claims 1 to 6, wherein: The controlling the loader to dig the pile based on the initial digging position includes: An objective function is constructed with the goals of minimizing the resistance experienced by the bucket of the loader during each digging process, minimizing the path length between the starting position and the stopping position of each digging process of the loader, and maximizing the digging efficiency of the loader, wherein the digging efficiency is determined based on the operating time of each digging process of the loader and the volume of the pile of material dug by the loader each time; Solving the objective function to determine a target stopping position of the loader for each shoveling operation; The loader is controlled to dig the pile based on the initial digging position and the target stop position.

8. The excavation control method according to claim 7, wherein: Solving the objective function to determine the target stopping position of the loader for each shoveling operation includes: Solve the objective function based on pre-set constraints to determine the target stopping position, The constraints include at least one of a first constraint related to the cutting angle of the bucket of the loader during each digging, a second constraint related to the digging depth of the loader during each digging, a third constraint related to the volume of the pile of materials dug by the loader during each digging, and a fourth constraint related to the digging direction of the starting position of the loader during each digging relative to the stopping position of each digging.

9. The excavation control method according to claim 8, wherein: The first constraint condition includes that the cutting angle of each digging is less than or equal to a first threshold.

10. The excavation control method according to claim 8, wherein: The second constraint condition includes that the digging depth of each digging is less than or equal to a second threshold, and the second threshold is determined based on the material of the material in the pile.

11. The excavation control method according to claim 8, wherein: The third constraint condition includes that the volume of the pile of materials excavated each time by the loader is greater than or equal to a third threshold, wherein the volume of the pile of materials excavated each time by the loader is determined based on the grid map, the grid resolution, and the width of the bucket of the loader.

12. The excavation control method according to claim 11, wherein: The volume of the pile excavated by the loader each time is determined as follows: Determining, based on the grid resolution and the width of the loader bucket, a portion of the grid in the grid map corresponding to an area of ​​the stockpile covered by the loader bucket during each shoveling operation; The volume of the pile excavated by the loader each time is determined based on the position coordinates of the point cloud points in the partial grid.

13. The excavation control method according to claim 8, wherein: The fourth constraint condition includes that an angle between the digging direction and a direction of the current position of the loader relative to a position of a center of mass of the pile is less than or equal to a fourth threshold.

14. The excavation control method according to any one of claims 1 to 6, wherein: The at least one grid on the edge of the grid map comprises a plurality of grids, Determining an initial digging position of the loader based on a second distance between the loader and at least one grid on an edge of the grid map includes: determining the second distance between the loader and each of the plurality of grids; The position corresponding to the grid with the smallest second distance is determined as the initial digging position.

15. The excavation control method according to claim 14, wherein: Determining the second distance between the loader and each of the plurality of grids includes: Determining the position coordinates of each grid according to the position coordinates of the point cloud points in each grid; The second distance between the loader and each of the grids is determined based on the position coordinates of the loader and the position coordinates of each of the grids.

16. The excavation control method according to any one of claims 1 to 6, wherein: The first distance is determined based on the position coordinates of the current position of the loader and the position coordinates of the center of mass of the pile, and the position coordinates of the center of mass of the pile are determined based on the position coordinates of the point cloud points in the point cloud data.

17. A loader excavation control device, comprising: an acquisition module configured to acquire point cloud data of a material pile within an operating area of ​​the loader; a processing module configured to perform rasterization processing on the point cloud data based on a grid resolution to obtain a grid map, wherein the grid resolution is set based on a first distance between a current position of the loader and the stockpile; a determination module configured to determine an initial digging position of the loader in the work area based on a second distance between a current position of the loader and at least one grid on an edge of the grid map; The control module is configured to control the loader to dig the pile based on the initial digging position.

18. A shoveling control device for a loader, comprising: Memory; and A processor coupled to the memory, wherein the processor is configured to execute the digging control method for a loader according to any one of claims 1 to 16 based on instructions stored in the memory.

19. A loader comprising: The excavation control device according to claim 17 or 18.

20. A computer-readable storage medium having computer instructions stored thereon, wherein when the instructions are executed by a processor, the loader excavation control method according to any one of claims 1 to 16 is implemented.

21. A computer program product comprising instructions, which, when executed by a processor, cause the processor to execute the digging control method for a loader according to any one of claims 1 to 16.

Images