Mining point recommendation method and device for high platform truck loading, electronic equipment and storage medium

Abstract

The invention provides a mining point recommendation method and device for high platform loading, electronic equipment and a storage medium, and the method comprises the steps: obtaining a plurality of point cloud data of a to-be-mined region, and determining a target elevation map of the to-be-mined region based on the plurality of point cloud data; gradient information of each target grid area is calculated, and the position of a target high platform in the to-be-mined area is determined based on the gradient information of each target grid area and a target height threshold value; and based on the material pile volume information on the target high platform position and the limiting information of the excavator, determining a target recommended excavation point meeting the bucket full load of the excavator in the target high platform position. Therefore, only the point cloud data is obtained, the elevation information of the to-be-excavated area is determined, then the material pile volume information of the to-be-excavated material pile is obtained through analysis, and the target recommended excavation point capable of guaranteeing full load of the excavator bucket is determined according to the material pile volume information. In this way, the full-fill rate of the excavator is increased; and the system processing complexity can be reduced, and the working stability of the excavator is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of excavators, in particular to a high platform loading excavating point recommendation method and device, electronic equipment and a storage medium. BACKGROUND

[0002] In the process of excavator excavating operation, in order to ensure the health condition of the operator of the excavator, the current general remote control technology is adopted, the operator does not enter the excavating site, but remotely controls the operation of the excavator, which can be based on the image collected from the excavating site, and then the position of the material pile is determined according to the image, and then the excavator is controlled to excavate at the appropriate excavating point. However, since the obtained is a two-dimensional image, the volume characteristics and other information of the material pile cannot be completely understood, and the problem of low excavating control accuracy still exists.

[0003] In the related art, in order to solve the above problem, a multi-sensor fusion control scheme can be adopted, and the information of the material pile to be excavated is obtained in all directions through the data collected by multiple sensors to excavate, which can effectively solve the problem that the material pile information cannot be accurately obtained in the two-dimensional image. However, since the multi-source sensor calibration is complex, error accumulation problems will occur after long-term operation, and the accuracy will continue to decrease as the operation time increases, which seriously affects the stability of the excavating operation. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a high platform loading excavating point recommendation method and device, electronic equipment and a storage medium, which can obtain only point cloud data, determine the elevation information of the excavating area, and then analyze the material pile volume information of the material pile to be excavated, and determine the target recommended excavating point that can ensure the full load of the excavator bucket. In this way, not only the dependence of the traditional image scheme on the material type is avoided, but also the material pile depth and volume distribution can be accurately identified, and the full bucket rate of the excavator is improved. The system processing complexity is also reduced, and the stability of the excavator operation is improved.

[0005] In a first aspect, an excavating point recommendation method for high platform loading is provided, which comprises: obtaining a plurality of point cloud data of a to-be-excavated area, and determining a target elevation map of the to-be-excavated area based on the plurality of point cloud data; the target elevation map comprises a plurality of target grid areas and corresponding elevation information of each target grid area; calculating gradient information of each target grid area, and determining a target high platform position in the to-be-excavated area based on the gradient information of each target grid area and a target height threshold value; wherein the target height threshold value is a threshold value that dynamically changes with the height of the target high platform in the excavating process; Based on the stockpile volume information at the target high platform position and the limit information of the excavator, a target recommended digging point in the target high platform position that satisfies full loading of the bucket of the excavator is determined.

[0006] In a second aspect, the embodiments of the present application further provide a high platform loading digging point recommendation device, which comprises: A target elevation map determination module is configured to acquire a plurality of point cloud data of a to-be-excavated area, and determine a target elevation map of the to-be-excavated area based on the plurality of point cloud data; the target elevation map comprises a plurality of target grid areas and corresponding elevation information of each target grid area; A target high platform position determination module is configured to calculate gradient information of each target grid area, and determine a target high platform position in the to-be-excavated area based on the gradient information of each target grid area and a target height threshold value; the target height threshold value is a threshold value that dynamically changes with the height of the target high platform in the excavation process; A target recommended digging point determination module is configured to determine a target recommended digging point in the target high platform position that satisfies full loading of the bucket of the excavator based on the stockpile volume information at the target high platform position and the limit information of the excavator.

[0007] In a third aspect, the embodiments of the present application further provide an electronic device, which comprises a processor, a storage medium and a bus, the storage medium stores machine readable instructions executable by the processor, when the electronic device is running, the processor and the storage medium communicate through the bus, and the processor executes the machine readable instructions to perform the high platform loading digging point recommendation method of the first aspect.

[0008] In a fourth aspect, the embodiments of the present application further provide a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to perform the high platform loading digging point recommendation method of the first aspect.

[0009] The high platform loading recommendation method, device, electronic equipment and storage medium provided by the embodiment of the application, obtain a plurality of point cloud data of a to-be-excavated area, and determine a target elevation map of the to-be-excavated area based on the plurality of point cloud data; the target elevation map comprises a plurality of target grid areas and elevation information corresponding to each target grid area; gradient information of each target grid area is calculated, and a target high platform position in the to-be-excavated area is determined based on the gradient information of each target grid area and a target height threshold value; the target height threshold value is a threshold value that dynamically changes with the height change of the target high platform in the excavation process; based on the volume information of the material pile at the target high platform position and the limiting information of the excavator, a target recommended excavation point in the target high platform position that satisfies full loading of the bucket of the excavator is determined. In this way, by only obtaining point cloud data, the elevation information of the to-be-excavated area is determined, and then the volume information of the to-be-excavated material pile is analyzed to determine the target recommended excavation point that can ensure full loading of the bucket of the excavator. In this way, not only the dependence of the traditional image scheme on the material type is avoided, but also the depth and volume distribution of the material pile can be accurately identified, and the full bucket rate of the excavator is improved; the system processing complexity is also reduced, and the stability of the excavator operation is improved.

[0010] In order to make the above objectives, characteristics and advantages of the present application more apparent, clear and easy to understand, the following will describe the preferred embodiments in detail, and the accompanying drawings will be described as follows. BRIEF DESCRIPTION OF DRAWINGS

[0011] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0012] Figure 1 A flowchart of a high platform loading recommendation method provided by the embodiment of the present application; Figure 2 A high platform operation schematic diagram provided by the embodiment of the present application; Figure 3 A visual target elevation map schematic diagram provided by the embodiment of the present application; Figure 4 A visual target high platform position schematic diagram provided by the embodiment of the present application; Figure 5 A state diagram of the excavator when the zero position is provided by the embodiment of the present application; Figure 6 A target recommended excavation point position schematic diagram provided by the embodiment of the present application; Figure 7A structure schematic diagram of a high platform loading excavating point recommendation device provided by an embodiment of the present application; Figure 8 A structure schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0013] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application and are not all the embodiments of the present application. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, every other embodiment obtained by a person skilled in the art without creative work belongs to the scope of protection of the present application.

[0014] Firstly, the technical background of the present application is introduced: In traditional excavator operation, especially in loading and unloading tasks, the operator must perform high-intensity repetitive operations in the cab for a long time. The construction site environment is harsh, often accompanied by dust, noise, vibration and other adverse factors, which has a serious impact on the health of the operator. In addition, since the loading operation needs to accurately control the relative position between the excavator and the truck, the operator must maintain high concentration, and any carelessness may cause collision accidents and safety hazards.

[0015] In recent years, the introduction of remote control technology provides a new solution to improve the operating environment. The existing remote control system usually adopts the form of a simulated cab, which transmits real-time video and feedback through operating levers, enabling the operator to control the excavator in a comfortable environment away from the construction site. Although this method improves the working conditions and improves safety, for loading and unloading tasks that require high repetitive operations, the operator still needs to continuously perform complex manual control, and the requirement for operating skills is still high.

[0016] Therefore, it is of great practical significance to integrate an automatic loading function in the remote control system. By using intelligent algorithms to calculate the excavating point and the unloading point in real time and optimizing the recommendation strategy in combination with the characteristics of high platform operation, the operator's work burden can be significantly reduced, the operation accuracy and efficiency can be improved, and safety accidents caused by human operation errors can be reduced.

[0017] The existing automatic loading technology mainly includes two schemes of image-based and multi-sensor fusion-based, but both have obvious defects. The image-based scheme only relies on 2D visual information, although it can identify the surface features of the material, it lacks depth perception, resulting in a generally low full-bucket rate, and is easily affected by light, dust and other environments, with a high misidentification rate. At the same time, this scheme needs to train a special model for different materials, which has high implementation cost and poor generalization ability. The multi-sensor fusion-based scheme improves the environmental perception ability through the combination of laser radar, vision and inertial measurement unit (IMU) and other devices, but due to the complexity of multi-source sensor calibration, error accumulation problem occurs after long-term operation, typical positioning deviation can reach 0.5 m, and the accuracy continues to decline as the operation time increases, which seriously affects the stability of operation.

[0018] Based on this, the embodiment of the present application provides a high platform loading excavation point recommendation method to improve the full-bucket rate of the excavator and the stability of the excavator operation.

[0019] Please refer to Figure 1 , Figure 1 The flowchart of the high platform loading excavation point recommendation method provided by the embodiment of the present application is shown in Figure 1 The high platform loading excavation point recommendation method provided by the embodiment of the present application includes: S101, acquiring a plurality of point cloud data of a to-be-excavated area, and determining a target elevation map of the to-be-excavated area based on the plurality of point cloud data; the target elevation map includes a plurality of target grid areas and elevation information corresponding to each target grid area.

[0020] S102, calculating gradient information of each target grid area, and determining a target high platform position in the to-be-excavated area based on the gradient information of each target grid area and a target height threshold value; wherein the target height threshold value is a threshold value that dynamically changes with the height of the target high platform in the excavation process.

[0021] S103, determining a target recommended excavation point in the target high platform position that satisfies full loading of the bucket of the excavator based on the volume information of the material pile on the target high platform position and the limit information of the excavator.

[0022] The high platform loading excavation point recommendation method provided by the embodiment of the present application acquires only point cloud data, determines the elevation information of the to-be-excavated area, and then analyzes the volume information of the to-be-excavated material pile to determine the target recommended excavation point that can ensure full loading of the bucket of the excavator. In this way, not only the dependence of the traditional image scheme on the type of material is avoided, but also the depth and volume distribution of the material pile can be accurately identified, the full-bucket rate of the excavator is improved, the system processing complexity is reduced, and the stability of the excavator operation is improved.

[0023] The steps of the embodiments of the present application are described below. S101, a plurality of point cloud data of a to-be-excavated area is acquired, and a target elevation map of the to-be-excavated area is determined based on the plurality of point cloud data; the target elevation map includes a plurality of target grid areas and elevation information corresponding to each target grid area.

[0024] In the embodiments of the present application, the excavation operation in the high platform environment is targeted. In this operation mode, the excavator is located above the high platform, and the high platform is piled up by the to-be-excavated material pile. The excavation work of the material pile on the slope of the high platform is performed.

[0025] For example, please refer to Figure 2 , Figure 2 The high platform operation schematic diagram provided by the embodiments of the present application is shown in Figure 2 , the excavator is placed on the high platform, and the excavation work is performed on the material pile on the slope of the high platform.

[0026] In an optional implementation, in order to ensure the health of the operator of the excavator, the remote control technology is generally used at present. The operator does not enter the excavation site, but controls the operation of the excavator remotely. In related technologies, the position of the material pile can be determined according to the collected image of the excavation site, and then the excavator is controlled to excavate at the appropriate excavation point. However, since the two-dimensional image is obtained, the volume characteristics and other information of the material pile cannot be completely understood, and the problem of low excavation control accuracy still exists. Further, in order to solve the above problem, a multi-sensor fusion control scheme can be used. The information of the to-be-excavated material pile is obtained by full-range acquisition of the data collected by multiple sensors, which can effectively solve the problem that the material pile information cannot be accurately obtained in the two-dimensional image. However, since the multi-source sensor calibration is complex, error accumulation problems will occur after long-term operation, and the accuracy will continue to decrease as the operation time increases, which seriously affects the stability of the excavation operation.

[0027] Therefore, the present application provides a high platform loading excavation point recommendation method. The point cloud data is obtained by a single sensor, and then the volume information of the to-be-excavated material pile is obtained by analysis. This method not only avoids the dependence of the traditional image scheme on the material type, but also accurately identifies the depth and volume distribution of the material pile, thereby improving the full bucket rate of the excavator. Compared with the multi-sensor fusion scheme, the present application uses a single dominant sensor architecture, which greatly reduces the system complexity and exhibits excellent robustness and operation stability.

[0028] In an optional embodiment, a plurality of point cloud data of the to-be-excavated area can be acquired by the laser radar sensor, and then a target elevation map of the to-be-excavated area is determined according to the acquired plurality of point cloud data, and then subsequent processing of the to-be-excavated material pile is completed according to the acquired target elevation map.

[0029] In an optional embodiment, the acquired point cloud data is data in the laser coordinate system, and in order to ensure consistency of subsequent data processing, the point cloud data needs to be converted to the excavator coordinate system after coordinate system conversion, and then a plurality of grid data is discretized for processing to obtain the target elevation map.

[0030] Specifically, the step of "determining a target elevation map of the to-be-excavated area based on the plurality of point cloud data" comprises: a1: performing coordinate system conversion on the plurality of point cloud data to obtain three-dimensional coordinates of a plurality of observation data points in the excavator coordinate system.

[0031] a2: discretizing a plurality of observation data points to a plurality of grid regions based on a preset grid resolution; wherein each grid region contains at least one observation data point.

[0032] a3: filtering out abnormal observation data points from the plurality of observation data points to obtain a plurality of target data points.

[0033] a4: for each target data point, calculating a height error value of the grid region in which the target data point is located; wherein the height error value is determined based on the difference between the measured height value of the target data point and the estimated height value stored in the map.

[0034] a5: determining a grid height offset value based on the average value of the plurality of height error values.

[0035] a6: offsetting the plurality of grid regions by the grid height offset value to obtain the target elevation map of the to-be-excavated area.

[0036] In the embodiments of the present application, the conversion of point cloud data from the laser coordinate system to the excavator coordinate system can be based on the mapping relationship between the laser coordinate system and the excavator coordinate system, and the coordinate data of each point cloud data is converted according to the mapping relationship one by one to obtain the three-dimensional coordinates of a plurality of observation data points in the excavator coordinate system.

[0037] Further, after obtaining a plurality of observation points in the excavator coordinate system, the plurality of observation data points need to be discretized into different grid regions in order to subsequently process the grid regions to obtain the target elevation map.

[0038] Here, the three-dimensional coordinates of the plurality of observation data points need to be discretized into a 2.5D grid region, specifically, the three-dimensional coordinates of the plurality of observation data points can be discretized into a 2.5D grid region by a vertical projection method.

[0039] wherein refers to a geometric method of projecting the plurality of observation data points along the vertical direction to a plane, and the three-dimensional coordinates of the plurality of observation data points are discretized into a 2.5D grid region by the vertical projection method.

[0040] In an optional implementation, when the plurality of observation data is discretized into a plurality of grid regions, the discretization can be performed according to a preset grid resolution.

[0041] For example, if the three-dimensional coordinates of the observation data point P are p(x, y, z), the grid index corresponding to the observation data point P is P'(i, j) = (⌊x / r⌋, ⌊y / r⌋), where r is a preset grid resolution.

[0042] Here, the grid resolution can be set according to the area of the current region to be excavated and the data processing accuracy requirement, and the grid resolution corresponding to different areas of the region to be excavated and the data processing accuracy requirement is different, which is not limited here.

[0043] In an optional implementation, each grid region contains at least one observation data point, and the horizontal and vertical coordinates of the grid index corresponding to the observation points in the same grid region are consistent, and the height coordinates are different.

[0044] Further, for the plurality of observation points contained in each grid region, there can be abnormal points that affect subsequent calculations, therefore, in order to ensure the accuracy of subsequent calculations, it is necessary to filter out abnormal observation data points from the plurality of observation data points, and then obtain a plurality of target data points.

[0045] In an optional implementation, the abnormal observation points can be filtered by a Kalman filter update method, the update step of the Kalman filter is a process of optimizing system state estimation by combining a predicted state and an actual observation value, the reliability of prediction and observation is calculated according to the Kalman gain, and then the state update is completed by correcting the predicted value with the residual error, the update step is essentially a joint probability maximization of two Gaussian distributions (prediction and observation), and the optimal fusion is realized by linear minimum variance estimation. This process needs to meet the linear Gaussian system condition to ensure that the posterior probability remains Gaussian distribution.

[0046] Specifically, based on the sensor noise model, the grid height estimation height value and the variance of the grid region are dynamically updated, wherein the variance is initially set to a large value, and the grid height estimation height value and the variance of the grid region are dynamically updated by the following formula: ; Wherein h is the grid height estimation height value; is the variance; is the noise variance value that increases with the square of the distance; P Z is the Z-axis coordinate value of the observation data point P.

[0047] ; Wherein, is the variance; is the noise variance value that increases with the square of the distance.

[0048] In an optional implementation, observation data points that significantly deviate from the current estimate can be excluded by Mahalanobis distance test, and to prevent geometric distortion caused by subsequent averaging processing, the highest observation data point can also be retained for vertical edges such as walls when excluding abnormal observation data points.

[0049] Further, for the target data points of the excluded abnormal observation data points, the height drift in the height error compensation process can be compensated according to the real-time measurement of the sensor, for each target data point, the height error value of the grid region where the target data point is located is calculated, based on the average value of the determined multiple height error values, the grid height offset value is determined; after the multiple grid regions are offset by the grid height offset value, the map is aligned with the current latest observation data points, and the target elevation map of the to-be-excavated region is obtained.

[0050] In an optional implementation, for each target data point, the difference between the measured height value of the target data point and the estimated height stored in the map can be used to determine, specifically, the height error value of the target data point can be determined by the following formula: ; Wherein εi is the height error value of the grid region where the target data point is located; Z measured is the measured height value of the target data point measured by the sensor; h map is the estimated height value stored in the map.

[0051] In an optional embodiment, in order to reduce calculation errors when determining the average value of the plurality of height error values, the height error values of target data points on a region with higher passability (low slope, low roughness) in the region to be excavated can be selected for calculation. By calculating the average value of the height error values of the above-mentioned target data points, noise introduced by steep slopes or obstacles can be avoided, and the accuracy of subsequent calculations can be improved.

[0052] Specifically, the grid height offset value can be determined by the following formula: ; wherein, Δh is the grid height offset value; n is the number of target data points; εi is the height error value of the grid region where the target data point is located.

[0053] In an optional embodiment, after the target elevation map is determined, the elevation information of the target elevation map is used to represent the elevation information of the region to be excavated. In order to ensure the editability of subsequent processing, the elevation information of the obtained target elevation map is converted into a gridmap format that can be recognized by a robot operating system (ros) and is published for visualization, so as to facilitate subsequent determination of accurate excavation points based on the obtained target elevation map.

[0054] For example, please refer to Figure 3 , Figure 3 The visual target elevation map provided by the embodiments of the present application is shown in Figure 3 , which includes a plurality of target grid regions.

[0055] Further, the target elevation map includes a plurality of target grid regions and corresponding elevation information of each target grid region. The gradient information of each target grid region can be calculated based on the corresponding elevation information of each target grid region, and the target highland position in the region to be excavated can be determined.

[0056] S102, calculate the gradient information of each target grid region, and determine the target highland position in the region to be excavated based on the gradient information of each target grid region and a target height threshold value, wherein the target height threshold value is a threshold value that dynamically changes with the height of the target highland in the excavation process.

[0057] In an optional embodiment, the gradient information of each target grid region can be calculated according to the neighborhood elevation difference.

[0058] Specifically, the step of "calculating the gradient information of each target grid region" includes: b1: for each target grid region, based on the position coordinates of each target data point in the target grid region and the grid spacing information, determine the target partial derivative of the target grid region.

[0059] b2: for each target grid region, the gradient information of the target grid region is calculated based on the target partial derivative of the target grid region.

[0060] In an optional embodiment, for each target grid region, the partial derivative of the grid can be calculated according to the first-order difference method, specifically, the position coordinates (i, j) of the target data point in the target grid region and the target partial derivatives of x and y thereof can be calculated by the following formula:

[0061] wherein, is the partial derivative of the target data point in x; is the partial derivative of the target data point in y; Δx and Δy are the grid spacing information.

[0062] Further, after the target partial derivative of the target grid is determined, the gradient information of the target grid region can be determined according to the inverse trigonometric function.

[0063] Specifically, the gradient information of the target grid region can be determined by the following formula: wherein, S is the gradient information of the target grid region; is the partial derivative of the target data point in x; is the partial derivative of the target data point in y.

[0064] Further, after the gradient information of each target grid region is calculated, the target height threshold corresponding to the current is determined according to the gradient information represented by the gradient information of each target grid region, and then the target highland position in the to-be-excavated region is determined according to the gradient information of each target grid and the target height threshold.

[0065] Specifically, the step of "determining the target highland position in the to-be-excavated region based on the gradient information of each target grid region and the target height threshold" comprises: c1: determining at least one position grid region whose gradient information is higher than the target height threshold based on the gradient information of each target grid region.

[0066] c2: determining the position of the at least one position grid region as the target highland position.

[0067] In an optional embodiment, as the excavator operation continues to recommend, the height of the highland in the to-be-excavated region will gradually decrease, therefore, in order to ensure the accuracy of the analysis of the highland position, it is necessary to dynamically adjust the target height threshold in real time according to the gradient information of each target grid region. ​

[0068] Specifically, based on the gradient information of each target grid, a height value range where the gradient information is relatively concentrated (a larger number of grid areas fall within this height value range) can be determined, and the target platform position can be determined based on the determined target height threshold.

[0069] In an optional embodiment, the specific scheme for determining the target platform position is: comparing the gradient information of each target grid area with the target height threshold, and then determining at least one position grid area whose gradient information is higher than the target height threshold, and determining the position corresponding to the at least one position grid area as the target platform position.

[0070] For example, there are currently target grid area 1, target grid area 2, target grid area 3 and target grid area 4. The gradient information of target grid area 1 is 10m, the gradient information of target grid area 2 is 3m, the gradient information of target grid area 3 is 7m, and the gradient information of target grid area 4 is 4m. At this time, the determined target height threshold is 5.5m, then the target grid areas above this target height threshold are target grid area 1 and target grid area 4. At this time, the locations of target grid area 1 and target grid area 4 are determined as the target platform locations.

[0071] In an optional implementation, after the target platform position is determined, the target platform position may be visually marked to prompt the operator of the specific position of the current target platform position.

[0072] For example, see Figure 4 , Figure 4 This is a schematic diagram of the visualization of the target platform position provided in the embodiment of the present application, such as Figure 4 As shown in FIG, area 410 is the target high platform position in the area to be excavated.

[0073] Furthermore, after determining the target platform position, the target recommended excavation point at the target platform position that satisfies the excavator bucket full load can be determined based on the volume information of the material pile on the target platform and the excavation limit information, and then excavation is carried out at the target recommended excavation point to complete the excavation operation while ensuring the full bucket rate of the excavator.

[0074] S103 : Determine a target recommended excavation point at the target platform position that satisfies a full bucket load of the excavator based on the material pile volume information at the target platform position and the excavator's position limit information.

[0075] In an optional embodiment, the recommended target excavation points are upper and lower edge positions on the target platform position, which are a pair of excavation points.

[0076] Specifically, the step of "determining a target recommended digging point in the target plateau position that satisfies full loading of the bucket of the excavator based on the stockpile volume information in the target plateau position and the position limit information of the excavator" comprises: d1: fitting the height information of the plateau points contained in the target plateau position to determine the upper boundary and the lower boundary of the target plateau position, and determining the stockpile volume information of each stockpile contained in the target plateau position based on the upper boundary and the lower boundary.

[0077] d2: determining at least one target stockpile position that satisfies full loading of the bucket of the excavator based on the stockpile volume information of each stockpile.

[0078] d3: determining a candidate recommended digging point closest to the position of the excavator in the at least one target stockpile position.

[0079] d4: determining the large arm pose and the small arm pose corresponding to the candidate recommended digging point based on the candidate recommended digging point, the large arm coordinate system and the small arm coordinate system of the excavator pre-constructed.

[0080] d5: if the large arm pose and the small arm pose corresponding to the candidate recommended digging point both satisfy the preset excavator position limit parameters, determining the candidate recommended digging point as the target recommended digging point.

[0081] In an optional embodiment, after determining the target plateau position, the height information of the plateau points in the target plateau position needs to be fitted to determine the upper boundary and the lower boundary of the target plateau position, and then the stockpile volume information is determined according to the plurality of boundary points contained in the upper boundary and the lower boundary.

[0082] Here, the height information of all plateau points in the target plateau position can be fitted.

[0083] Specifically, the step of "determining the stockpile volume information of each stockpile contained in the target plateau position based on the upper boundary and the lower boundary" comprises: e1: determining a plurality of upper boundary points contained in the upper boundary and a plurality of lower boundary points contained in the lower boundary.

[0084] e2: determining a plurality of pairs of boundary points corresponding to the plurality of upper boundary points and the plurality of lower boundary points.

[0085] e3: for each pair of boundary points, a preset number of interpolations are performed on the pair of boundary points, and integrations are performed on the plurality of interpolated points to obtain the stockpile volume information between the pair of boundary points.

[0086] In the embodiments of the present application, in order to ensure the accuracy of subsequent calculation, the upper edge boundary needs to be adjusted after being fitted, so as to make the obtained upper and lower edge boundary points correspond to each other and pass through the origin of the coordinate system of the excavator.

[0087] Further, after determining the plurality of upper and lower edge boundary points, a plurality of pairs of boundary points are correspondingly determined. For each pair of boundary points, a preset number of interpolations are performed on the pair of boundary points, and integrations are performed on the plurality of interpolated points after interpolation to obtain the volume information of the stockpile between the pair of boundary points.

[0088] For example, 100 points can be interpolated for each pair of boundary points, and integrations are performed on the 100 interpolated points to obtain the volume information of the stockpile.

[0089] Further, in order to ensure the excavating efficiency of the excavator, it is necessary to ensure that the bucket is fully loaded each time the excavator excavates. Therefore, after determining the volume information of the plurality of stockpiles, the target stockpile position that can be excavated is determined according to the relationship between the volume information of the stockpile and the volume of the bucket.

[0090] Specifically, the step of "determining at least one target stockpile position that satisfies the full loading of the bucket of the excavator based on the volume information of each stockpile" comprises: f1: detecting whether the volume of each stockpile is greater than the volume of the bucket of the excavator based on the volume information of each stockpile.

[0091] f2: determining the stockpile whose volume is greater than the volume of the bucket of the excavator as the target stockpile position.

[0092] In an optional embodiment, for the volume information of each determined stockpile, it is detected whether the volume of the stockpile is greater than the volume of the bucket of the excavator. If the volume of the stockpile is greater than the volume of the bucket of the excavator, it is considered that the full loading of the bucket can be ensured during this time of excavation, and the stockpile can be determined as the target stockpile position, so that the full loading of the bucket of the excavator can be ensured during excavation.

[0093] In another optional embodiment, if there is no stockpile whose volume is greater than the volume of the bucket of the excavator, prompt information needs to be generated to prompt the operator to arrange the stockpile or move the position of the excavator, and continue the excavating operation under the condition of ensuring the full loading of the bucket.

[0094] Specifically, the excavating point recommendation method further comprises: g1: generating adjustment prompt information if the target highland position does not contain the target stockpile position that satisfies the full loading of the bucket of the excavator.

[0095] In an optional embodiment, if the target high position does not contain a target pile position that satisfies the full load of the bucket of the excavator, it is represented that there is no excavating point that fully meets the excavation, and an adjustment prompt information needs to be generated to prompt the operator to arrange the piles or move the position of the excavator to complete the excavation to ensure the full bucket rate of the excavator and improve the excavation efficiency of the excavator.

[0096] In an optional embodiment, the adjustment prompt information can be a text prompt information, which can be exemplarily "current full bucket excavation position does not exist, please adjust"; or can be a prompt to the operator through a prompt light; or can be a prompt to the operator through a prompt player on the operating system.

[0097] Further, after the target pile position is determined, a point in the target pile position that is far from the position of the excavator can be determined as a candidate recommended excavating point, and in order to ensure the accuracy and reachability of the operation of the excavator, the candidate recommended excavating point, the excavator boom coordinate system and the excavator arm coordinate system that are determined in advance are used to determine the boom pose and the arm pose corresponding to the candidate recommended excavating point, and if the boom pose and the arm pose corresponding to the candidate recommended excavating point both satisfy the preset excavator limiting parameters, the candidate recommended excavating point is determined as the target recommended excavating point.

[0098] Specifically, the step of "determining the boom pose and the arm pose corresponding to the candidate recommended excavating point based on the candidate recommended excavating point, the excavator boom coordinate system and the excavator arm coordinate system that are determined in advance" includes: h1: obtaining the excavator boom coordinate system and the excavator arm coordinate system that are determined in advance.

[0099] h2: judging whether the candidate recommended excavating point, the origin of the excavator boom coordinate system and the origin of the excavator arm coordinate system satisfy a triangular set relationship under the excavator boom coordinate system or the excavator arm coordinate system.

[0100] h3: if the candidate recommended excavating point, the origin of the excavator boom coordinate system and the origin of the excavator arm coordinate system satisfy the triangular set relationship, determining the boom pose and the arm pose corresponding to the candidate recommended excavating point according to the triangular set relationship.

[0101] In an optional embodiment, referring to Figure 5 , Figure 5 The zero position state diagram of the excavator provided by the embodiments of the present application is as follows: Figure 5As shown in the figure, where arm_link is the coordinate system of the small arm, book_link is the coordinate system of the large arm, the angle between the z-axis of the large arm coordinate system and the vertical direction is 1 radian, which is the zero position of the large arm, and the angle between the z-axis of the small arm and the large arm is 1.5 radians, which is the zero position of the small arm.

[0102] Further, assuming that the origin of the small arm coordinate system is O1, the coordinates in the arm_base_link coordinate system are (x1, y1, z1), the origin of the large arm coordinate system is O2, the coordinates in the arm_base_link coordinate system are (x2, y2, z2), and P is the candidate recommended digging point closest to the position of the excavator in the target material pile position, the coordinates in the arm_base_link coordinate system are (x, y, z). If the three points P, O1, and O2 can form a triangle, that is, the sum of two sides is greater than the third side, the sum of two sides is less than the third side, and the size of the arm is determined after the calculation of the three triangular sets, it is judged that it is within the limit, then the candidate recommended digging point P is the point that the motion control module can plan to the point when controlling the excavator to work.

[0103] In another optional embodiment, if the large arm pose and / or the small arm pose does not satisfy the preset excavator limit parameter, the candidate digging point needs to be found again, and then the target digging point satisfying the limit parameter is determined according to the candidate digging point.

[0104] Specifically, the digging point recommendation method further comprises: i1: If the large arm pose and / or the small arm pose does not satisfy the preset excavator limit parameter, determine the updated recommended digging point closest to the position of the excavator in the other material pile position where the bucket of the excavator is full, until the large arm pose and the small arm pose corresponding to the new updated recommended digging point both satisfy the preset excavator limit parameter, and determine the updated recommended digging point as the target recommended digging point.

[0105] In the embodiments of the present application, if it is determined that the large arm pose and / or the small arm pose does not satisfy the preset excavator limit parameter, the updated recommended digging point closest to the position of the excavator in the other material pile position is determined again, the excavator limit parameter is determined again, until the large arm pose and the small arm pose corresponding to the new updated recommended digging point both satisfy the preset excavator limit parameter, and the updated recommended digging point is determined as the target recommended digging point.

[0106] Further, after the target recommended digging point is determined, the specific position of the target recommended digging point can be visually displayed, so that the operator determines the specific position of the digging point of the current digging operation, and then controls the excavator to work.

[0107] For example, see Figure 6 , Figure 6 This is a schematic diagram of the target recommended excavation point location provided in the embodiment of the present application, such as Figure 6 As shown, excavation point 610 and excavation point 620 are recommended upper and lower boundary points of excavation, and the operator can control the excavator to excavate at the location of the current excavation point.

[0108] The excavation point recommendation method for high-platform loading provided in an embodiment of the present application obtains multiple point cloud data of an area to be excavated and, based on the multiple point cloud data, determines a target elevation map of the area to be excavated. The target elevation map includes multiple target grid areas and elevation information corresponding to each target grid area. The method calculates gradient information for each target grid area and determines the location of a target high platform in the area to be excavated based on the gradient information and a target height threshold. The target height threshold dynamically changes as the height of the target high platform changes during excavation. Based on the volume information of the material pile at the target high platform location and the excavator's position limits, the method determines a target recommended excavation point at the target high platform location that satisfies a full bucket load for the excavator. Thus, by only obtaining point cloud data to determine the elevation information of the area to be excavated, the volume information of the material pile to be excavated is analyzed and determined. Based on the material pile volume information, the method determines a target recommended excavation point that ensures a full bucket load for the excavator. This method not only avoids the reliance of traditional image-based methods on material type, but also accurately identifies the depth and volume distribution of the material pile, improving the excavator's bucket fill rate. It also reduces system processing complexity and enhances excavator operation stability.

[0109] Based on the same inventive concept, an embodiment of the present application also provides an excavation point recommendation device for high-platform loading corresponding to the excavation point recommendation method for high-platform loading. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the above-mentioned excavation point recommendation method for high-platform loading in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0110] See also Figure 7 , Figure 7 This is a schematic diagram of the structure of a high-platform loading excavation point recommendation device provided in an embodiment of the present application. Figure 7 As shown in , the excavation point recommendation device 700 includes: The target elevation map determining module 710 is configured to obtain a plurality of point cloud data of the area to be excavated and determine a target elevation map of the area to be excavated based on the plurality of point cloud data; the target elevation map includes a plurality of target grid areas and elevation information corresponding to each target grid area; The target highland position determination module 720 is configured to calculate gradient information of each target grid region, and determine a target highland position in the region to be excavated based on the gradient information of each target grid region and a target height threshold. The target height threshold is a threshold that dynamically changes with the height of the target highland during the excavation process. The target recommended excavation point determination module 730 is configured to determine a target recommended excavation point in the target highland position that satisfies full loading of the bucket of the excavator based on the stockpile volume information on the target highland position and the limit information of the excavator.

[0111] In an optional implementation, when the target recommended excavation point determination module 730 is configured to determine a target recommended excavation point in the target highland position that satisfies full loading of the bucket of the excavator based on the stockpile volume information on the target highland position and the limit information of the excavator, the target recommended excavation point determination module 730 is configured to: fit the height information of the highland points contained in the target highland position to determine an upper boundary and a lower boundary of the target highland position, and determine the stockpile volume information of each stockpile contained in the target highland position based on the upper boundary and the lower boundary; determine at least one target stockpile position that satisfies full loading of the bucket of the excavator based on the stockpile volume information of each stockpile; determine a candidate recommended excavation point closest to the position of the excavator in the at least one target stockpile position; determine a large-arm pose and a small-arm pose corresponding to the candidate recommended excavation point based on the candidate recommended excavation point, a large-arm coordinate system and a small-arm coordinate system of the excavator that are constructed in advance; if the large-arm pose and the small-arm pose corresponding to the candidate recommended excavation point both satisfy preset limit parameters of the excavator, the candidate recommended excavation point is determined as the target recommended excavation point.

[0112] In an optional implementation, when the target recommended excavation point determination module 730 is configured to determine the stockpile volume information of each stockpile contained in the target highland position based on the upper boundary and the lower boundary, the target recommended excavation point determination module 730 is configured to: determine a plurality of upper boundary points contained in the upper boundary and a plurality of lower boundary points contained in the lower boundary; determine a plurality of corresponding boundary point pairs based on the plurality of upper boundary points and the plurality of lower boundary points; for each boundary point pair, perform a preset number of interpolations on the boundary point pair, and perform integration on a plurality of interpolated points to obtain stockpile volume information between the boundary point pair.

[0113] In an alternative embodiment, the target recommended digging point determination module 730 is configured to: detect, based on the stockpile volume information of each stockpile, whether the stockpile volume of the stockpile is greater than the volume of the bucket of the excavator; determine, as the target stockpile position, the stockpile whose stockpile volume is greater than the volume of the bucket of the excavator.

[0114] In an alternative embodiment, the target recommended digging point determination module 730 is configured to, based on the candidate recommended digging point, the excavator boom coordinate system and the excavator arm coordinate system constructed in advance, determine the boom pose and the arm pose corresponding to the candidate recommended digging point, the target recommended digging point determination module 730 is configured to: obtain the excavator boom coordinate system and the excavator arm coordinate system constructed in advance; determine, in the excavator boom coordinate system or the excavator arm coordinate system, whether the candidate recommended digging point, the origin of the excavator boom coordinate system and the origin of the excavator arm coordinate system satisfy a triangular set relationship; if the candidate recommended digging point, the origin of the excavator boom coordinate system and the origin of the excavator arm coordinate system satisfy the triangular set relationship, determine the boom pose and the arm pose corresponding to the candidate recommended digging point according to the triangular set relationship.

[0115] In an alternative embodiment, the digging point recommendation device 700 further comprises a recommended digging point updating module (not shown in the figure), and the recommended digging point updating module is configured to: if the boom pose and / or the arm pose do not satisfy the preset excavator limiting parameter, determine an updated recommended digging point closest to the position of the excavator among other stockpile positions where the bucket of the excavator is full, until the boom pose and the arm pose corresponding to the new updated recommended digging point both satisfy the preset excavator limiting parameter, and determine the updated recommended digging point as the target recommended digging point.

[0116] In an alternative embodiment, the target high platform position determination module 720 is configured to, based on the gradient information of each target grid area and a target height threshold, determine the target high platform position in the to-be-excavated area, the target high platform position determination module 720 is configured to: based on the gradient information of each target grid area, determine at least one position grid area whose gradient information is higher than the target height threshold; The location of the at least one location grid area is determined as the target platform location.

[0117] In an optional embodiment, when the target platform position determination module 720 is used to calculate the gradient information of each target grid area, the target platform position determination module 720 is used to: For each target grid area, based on the position coordinates of each target data point in the target grid area and the grid spacing information, determine the target partial derivative of the target grid area; For each target grid area, the gradient information of the target grid area is obtained based on the target partial derivative of the target grid area.

[0118] In an optional embodiment, when the target elevation map determining module 710 is used to determine the target elevation map of the to-be-excavated area based on the plurality of point cloud data, the target elevation map determining module 710 is used to: Performing coordinate system conversion on the plurality of point cloud data to obtain three-dimensional coordinates of a plurality of observation data points in an excavator coordinate system; Discretize multiple observation data points into multiple grid areas based on a preset grid resolution; each grid area contains at least one observation data point; Filtering out abnormal observation data points from the plurality of observation data points to obtain a plurality of target data points; For each target data point, calculating a height error value for the grid area where the target data point is located; wherein the height error value is determined based on the difference between the measured height value of the target data point and the estimated height value stored in the map; Determining a grid height offset value based on an average of the determined plurality of height error values; After the plurality of grid areas are offset by the grid height offset value, a target elevation map of the area to be excavated is obtained.

[0119] In an optional embodiment, the mining point recommendation device 700 further includes a prompt information generation module (not shown in the figure), and the prompt information generation module is used to: If the target platform position does not include a target material pile position that satisfies a full load of the bucket of the excavator, an adjustment prompt message is generated.

[0120] The high platform loading device provided by the embodiment of the present application obtains a plurality of point cloud data of a to-be-excavated area, and determines a target elevation map of the to-be-excavated area based on the plurality of point cloud data; the target elevation map comprises a plurality of target grid areas and elevation information corresponding to each target grid area; gradient information of each target grid area is calculated, and a target high platform position in the to-be-excavated area is determined based on the gradient information of each target grid area and a target height threshold value; the target height threshold value is a threshold value that dynamically changes with the height change of the target high platform in the excavation process; a target recommended excavation point in the target high platform position that satisfies full loading of a bucket of the excavator is determined based on volume information of a material pile on the target high platform position and limiting information of the excavator. In this way, by only obtaining point cloud data, the elevation information of the to-be-excavated area is determined, and then the volume information of the to-be-excavated material pile is analyzed and obtained, and the target recommended excavation point that can ensure full loading of the bucket of the excavator is determined according to the volume information of the material pile. In this way, not only the dependence of the traditional image scheme on the material type is avoided, but also the depth and volume distribution of the material pile can be accurately identified, and the full bucket rate of the excavator is improved; the system processing complexity is also reduced, and the stability of the operation of the excavator is improved.

[0121] Please refer to Figure 8 , Figure 8 A structural schematic diagram of an electronic device provided by an embodiment of the present application is shown in FIG. 8. Figure 8 As shown in FIG. 8, the electronic device 800 comprises a processor 810, a memory 820 and a bus 830.

[0122] The memory 820 stores machine-readable instructions executable by the processor 810, and when the electronic device 800 is running, the processor 810 communicates with the memory 820 through the bus 830, so that the processor 810 executes the following instructions when running: obtain a plurality of point cloud data of a to-be-excavated area, and determine a target elevation map of the to-be-excavated area based on the plurality of point cloud data; the target elevation map comprises a plurality of target grid areas and elevation information corresponding to each target grid area; calculate gradient information of each target grid area, and determine a target high platform position in the to-be-excavated area based on the gradient information of each target grid area and a target height threshold value; the target height threshold value is a threshold value that dynamically changes with the height change of the target high platform in the excavation process; determine a target recommended excavation point in the target high platform position that satisfies full loading of a bucket of the excavator based on volume information of a material pile on the target high platform position and limiting information of the excavator.

[0123] In an optional implementation, the instructions executed by the processor 810 include that, based on the stockpile volume information at the target plateau position and the position limit information of the excavator, determining a target recommended digging point in the target plateau position that satisfies full loading of the bucket of the excavator, includes: fitting the plateau point height information contained in the target plateau position, determining an upper boundary and a lower boundary of the target plateau position, and determining the stockpile volume information of each stockpile contained in the target plateau position based on the upper boundary and the lower boundary; based on the stockpile volume information of each stockpile, determining at least one target stockpile position that satisfies full loading of the bucket of the excavator; determining a candidate recommended digging point in the at least one target stockpile position closest to the position of the excavator; based on the candidate recommended digging point, a pre-constructed excavator boom coordinate system and an excavator arm coordinate system, determining a boom pose and an arm pose corresponding to the candidate recommended digging point; if the boom pose and the arm pose corresponding to the candidate recommended digging point both satisfy the preset excavator position limit parameters, the candidate recommended digging point is determined as the target recommended digging point.

[0124] In an optional implementation, the instructions executed by the processor 810 include that, based on the upper boundary and the lower boundary, determining the stockpile volume information of each stockpile contained in the target plateau position, includes: determining a plurality of upper boundary points contained in the upper boundary and a plurality of lower boundary points contained in the lower boundary; based on the plurality of upper boundary points and the plurality of lower boundary points, determining a plurality of corresponding boundary point pairs; for each boundary point pair, performing a preset number of interpolations on the boundary point pair, and integrating the plurality of interpolated points to obtain the stockpile volume information between the boundary point pair.

[0125] In an optional implementation, the instructions executed by the processor 810 include that, based on the stockpile volume information of each stockpile, determining at least one target stockpile position that satisfies full loading of the bucket of the excavator, includes: based on the stockpile volume information of each stockpile, detecting whether the stockpile volume of the stockpile is greater than the volume of the bucket of the excavator; determining the stockpile with a stockpile volume greater than the volume of the bucket of the excavator as the target stockpile position.

[0126] In an optional embodiment, the instructions executed by the processor 810, wherein determining the boom posture and the arm posture corresponding to the candidate recommended excavation point based on the candidate recommended excavation point and the pre-built excavator boom coordinate system and the excavator arm coordinate system, includes: Obtain the pre-built excavator boom coordinate system and excavator arm coordinate system; In the excavator boom coordinate system or the excavator arm coordinate system, determining whether a triangular set relationship is satisfied among the candidate recommended excavation point, the origin of the excavator boom coordinate system, and the origin of the excavator arm coordinate system; If a triangle set relationship is satisfied between the candidate recommended excavation point, the origin of the excavator boom coordinate system, and the origin of the excavator arm coordinate system, the boom posture and the arm posture corresponding to the candidate recommended excavation point are determined according to the triangle set relationship.

[0127] In an optional implementation, the instructions executed by the processor 810 further include: If the boom posture and / or the arm posture do not meet the preset excavator limit parameters, an updated recommended excavation point closest to the excavator position is determined among other material pile positions with a fully loaded bucket of the excavator, until the boom posture and the arm posture corresponding to the new updated recommended excavation point both meet the preset excavator limit parameters, and the updated recommended excavation point is determined as the target recommended excavation point.

[0128] In an optional embodiment, in the instructions executed by the processor 810, determining the target platform position in the to-be-excavated area based on the gradient information of each target grid area and the target height threshold includes: Based on the gradient information of each target grid area, determining at least one location grid area having gradient information higher than the target height threshold; The location of the at least one location grid area is determined as the target platform location.

[0129] In an optional implementation, in the instructions executed by the processor 810, the step of calculating the gradient information of each target grid area includes: For each target grid area, based on the position coordinates of each target data point in the target grid area and the grid spacing information, determine the target partial derivative of the target grid area; For each target grid area, the gradient information of the target grid area is obtained based on the target partial derivative of the target grid area.

[0130] In an optional embodiment, in the instructions executed by the processor 810, determining the target elevation map of the area to be excavated based on the plurality of point cloud data includes: The plurality of point cloud data is converted in coordinate system to obtain three-dimensional coordinates of the plurality of observation data points in the coordinate system of the excavator; The plurality of observation data points are discretized into a plurality of grid regions based on a preset grid resolution, wherein each grid region contains at least one observation data point; Abnormal observation data points are filtered out from the plurality of observation data points to obtain a plurality of target data points; For each target data point, a height error value of the grid region where the target data point is located is calculated, wherein the height error value is determined based on the difference between the measured height value of the target data point and the estimated height value stored in the map; A grid height offset value is determined based on the average of the plurality of height error values; After the plurality of grid regions are offset by the grid height offset value, a target elevation map of the area to be excavated is obtained.

[0131] In an optional implementation, the instructions executed by the processor 810 further include: If the target high position does not contain a target pile position that satisfies the full load of the bucket of the excavator, an adjustment prompt information is generated.

[0132] In the above manner, by only obtaining point cloud data, the elevation information of the area to be excavated is determined, and then the pile volume information of the pile to be excavated is analyzed to determine the target recommended excavation point that can ensure the full load of the bucket of the excavator. In this way, not only the dependence on the material type in the traditional image scheme is avoided, but also the depth and volume distribution of the pile can be accurately identified, and the full bucket rate of the excavator is improved. The system processing complexity is also reduced, and the stability of the excavator operation is improved. Meanwhile, for the plurality of observation points contained in each grid region, there may be abnormal points that affect subsequent calculations. In order to ensure the accuracy of subsequent calculations, abnormal observation data points need to be filtered out from the plurality of observation data points to obtain a plurality of target data points. When determining the average of the plurality of height error values, in order to reduce calculation errors, the height error values of the target data points on the area to be excavated with high passability (low slope and low roughness) can be selected for calculation. By calculating the average of the height error values of the above target data points, noise introduced by steep slopes or obstacles can be avoided, and the accuracy of subsequent calculations is improved. Meanwhile, in order to ensure the accuracy of the analysis of high position, the target height threshold needs to be dynamically adjusted in real time according to the gradient information of each target grid region.

[0133] The embodiment of the application further provides a computer readable storage medium, and the computer readable storage medium stores a computer program, so that when the computer program is run by a processor, the following instructions are executed: Obtaining a plurality of point cloud data of a to-be-excavated region, and determining a target elevation map of the to-be-excavated region based on the plurality of point cloud data; the target elevation map comprises a plurality of target grid regions and corresponding elevation information of each target grid region; Calculating gradient information of each target grid region, and determining a target highland position in the to-be-excavated region based on the gradient information of each target grid region and a target height threshold; the target height threshold is a threshold that dynamically changes with the height of the target highland in the excavation process; Based on the stockpile volume information at the target highland position and the limit information of the excavator, a target recommended excavation point in the target highland position that satisfies full loading of the bucket of the excavator is determined.

[0134] In an optional implementation, the instructions executed by the computer-readable storage medium, the instructions for determining a target recommended excavation point in the target highland position that satisfies full loading of the bucket of the excavator based on the stockpile volume information at the target highland position and the limit information of the excavator, comprise: Fitting the highland point height information contained in the target highland position to determine an upper boundary and a lower boundary of the target highland position, and determining the stockpile volume information of each stockpile contained in the target highland position based on the upper boundary and the lower boundary; Based on the stockpile volume information of each stockpile, at least one target stockpile position that satisfies full loading of the bucket of the excavator is determined; A candidate recommended excavation point closest to the position of the excavator is determined in the at least one target stockpile position; Based on the candidate recommended excavation point, a pre-constructed excavator boom coordinate system and an excavator arm coordinate system, a boom pose and an arm pose corresponding to the candidate recommended excavation point are determined; If the boom pose and the arm pose corresponding to the candidate recommended excavation point both satisfy the preset excavator limit parameters, the candidate recommended excavation point is determined as the target recommended excavation point.

[0135] In an optional implementation, the instructions executed by the computer-readable storage medium, the instructions for determining the stockpile volume information of each stockpile contained in the target highland position based on the upper boundary and the lower boundary, comprise: Determining a plurality of upper boundary points contained in the upper boundary and a plurality of lower boundary points contained in the lower boundary; Based on the plurality of upper boundary points and the plurality of lower boundary points, a plurality of corresponding pairs of boundary points are determined; For each boundary point pair, a preset number of interpolations are performed on the boundary point pair, and integrations are performed on the plurality of interpolated interpolation points to obtain the stockpile volume information between the boundary point pair.

[0136] In an alternative embodiment, the instructions executed by the computer-readable storage medium, wherein the determining at least one target stockpile position satisfying the full load of the bucket of the excavator based on the stockpile volume information of each stockpile, comprises: detecting whether the stockpile volume of each stockpile is greater than the volume of the bucket of the excavator based on the stockpile volume information of each stockpile; determining the stockpile whose stockpile volume is greater than the volume of the bucket of the excavator as the target stockpile position.

[0137] In an alternative embodiment, the instructions executed by the computer-readable storage medium, wherein the determining the large arm pose and the small arm pose corresponding to the candidate recommended digging point based on the candidate recommended digging point, the pre-constructed large arm coordinate system of the excavator and the small arm coordinate system of the excavator, comprises: obtaining the pre-constructed large arm coordinate system of the excavator and the small arm coordinate system of the excavator; judging whether the candidate recommended digging point, the origin of the large arm coordinate system of the excavator and the origin of the small arm coordinate system of the excavator satisfy a triangular set relationship under the large arm coordinate system of the excavator or the small arm coordinate system of the excavator; if the candidate recommended digging point, the origin of the large arm coordinate system of the excavator and the origin of the small arm coordinate system of the excavator satisfy the triangular set relationship, determining the large arm pose and the small arm pose corresponding to the candidate recommended digging point according to the triangular set relationship.

[0138] In an alternative embodiment, the instructions executed by the computer-readable storage medium further comprise: if the large arm pose and / or the small arm pose do not satisfy the preset excavator limiting parameter, determining an updated recommended digging point closest to the position of the excavator among other stockpile positions satisfying the full load of the bucket of the excavator, until the large arm pose and the small arm pose corresponding to the new updated recommended digging point both satisfy the preset excavator limiting parameter, and determining the updated recommended digging point as the target recommended digging point.

[0139] In an alternative embodiment, the instructions executed by the computer-readable storage medium, wherein the determining the target high platform position in the to-be-dug region based on the gradient information of each target grid region and the target height threshold, comprises: determining at least one position grid region whose gradient information is higher than the target height threshold based on the gradient information of each target grid region; determine a position where the at least one position grid area is located as the target highland position.

[0140] In an alternative implementation, the instructions executed by the computer-readable storage medium, the computing the gradient information of each target grid area comprises: For each target grid area, based on the position coordinates of each target data point in the target grid area and the grid spacing information, determine the target partial derivative of the target grid area; For each target grid area, based on the target partial derivative of the target grid area, calculate the gradient information of the target grid area.

[0141] In an alternative implementation, the instructions executed by the computer-readable storage medium, the determining the target elevation map of the area to be excavated based on the plurality of point cloud data comprises: Perform coordinate system conversion on the plurality of point cloud data to obtain three-dimensional coordinates of a plurality of observation data points in the excavator coordinate system; Disperse the plurality of observation data points to a plurality of grid areas based on a preset grid resolution; wherein each grid area contains at least one observation data point; Filter out abnormal observation data points from the plurality of observation data points to obtain a plurality of target data points; For each target data point, calculate the height error value of the grid area where the target data point is located; wherein the height error value is determined based on the difference between the measured height value of the target data point and the estimated height value stored in the map; Based on the average value of the plurality of height error values determined, determine the grid height offset value; After offsetting the plurality of grid areas by the grid height offset value, obtain the target elevation map of the area to be excavated.

[0142] In an alternative implementation, the instructions executed by the computer-readable storage medium further comprise: If the target highland position does not contain a target stockpile position that satisfies the full load of the excavator's bucket, generate an adjustment prompt information.

[0143] By the above manner, by only acquiring the point cloud data, the elevation information of the to-be-excavated region is determined, and then the stockpile volume information of the to-be-excavated stockpile is analyzed and obtained, and the target recommended excavation point that can guarantee the full load of the excavator bucket is determined according to the stockpile volume information. In this way, not only the dependence of the traditional image scheme on the material type is avoided, but also the stockpile depth and volume distribution can be accurately identified, and the full bucket rate of the excavator is improved; the system processing complexity is also reduced, and the stability of the excavator operation is improved; meanwhile, for the abnormal points that may exist in the multiple observation points in each grid region and affect the subsequent calculation, in order to ensure the accuracy of the subsequent calculation, the abnormal observation data points need to be filtered out from the multiple observation data points, and then the multiple target data points are obtained; when the average value of the multiple height error values is determined, in order to reduce the calculation error, the height error values of the target data points on the region with higher passability (low slope and low roughness) in the to-be-excavated region can be selected for calculation, and by calculating the average value of the height error values of the above target data points, the noise introduced by the steep slope or obstacle can be avoided, and the accuracy of the subsequent calculation is improved; meanwhile, in order to ensure the accuracy of the analysis of the high platform position, the target height threshold needs to be dynamically adjusted in real time according to the gradient information of each target grid region.

[0144] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0145] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some communication interfaces, and can be electrical, mechanical or other forms.

[0146] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e. they can be located in one place, or distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0147] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit.

[0148] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a nonvolatile computer readable storage medium executable by a processor. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a magnetic disk or an optical disk, and various program code storage media.

[0149] Finally, it should be noted that: the above-described embodiments are merely specific embodiments of the present application, used to illustrate the technical solutions of the present application, and not to limit them. The protection scope of the present application is not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can make modifications or easily think of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed by the present application, or make equivalent replacements to some of the technical features. The modifications, changes or replacements do not cause the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for recommending excavation points for high-platform loading, characterized in that: The mining point recommendation method includes: Acquire multiple point cloud data of the area to be excavated, and determine a target elevation map of the area to be excavated based on the multiple point cloud data; the target elevation map includes multiple target grid areas and elevation information corresponding to each target grid area; Calculating the gradient information of each target grid area, and determining the position of the target platform in the area to be excavated based on the gradient information of each target grid area and a target height threshold; wherein the target height threshold is a threshold that changes dynamically as the height of the target platform changes during the excavation process; Based on the material pile volume information at the target platform position and the excavator's limit information, a target recommended excavation point at the target platform position that satisfies a full bucket load of the excavator is determined.

2. The mining point recommendation method according to claim 1, characterized in that: The step of determining a target recommended excavation point at the target platform position that satisfies a full bucket load of the excavator based on the volume information of the material pile at the target platform position and the limit information of the excavator includes: Fitting the height information of the high platform point included in the target high platform position to determine the upper boundary and the lower boundary of the target high platform position, and determining the volume information of each material pile included in the target high platform position based on the upper boundary and the lower boundary; Determining at least one target material pile position that satisfies a full load of the excavator bucket based on the material pile volume information of each material pile; determining a candidate recommended excavation point closest to the position of the excavator in the at least one target stockpile position; Determine the boom posture and arm posture corresponding to the candidate recommended excavation point based on the candidate recommended excavation point and a pre-constructed excavator boom coordinate system and excavator arm coordinate system; If the arm posture and the arm posture corresponding to the candidate recommended excavation point both meet preset excavator limit parameters, the candidate recommended excavation point is determined as the target recommended excavation point.

3. The mining point recommendation method according to claim 2, characterized in that: The determining of the volume information of each material pile contained in the target platform position based on the upper boundary and the lower boundary includes: Determine a plurality of upper boundary points included in the upper boundary and a plurality of lower boundary points included in the lower boundary; Determining corresponding pairs of boundary points based on the plurality of upper boundary points and the plurality of lower boundary points; For each boundary point pair, a preset number of interpolations are performed on the boundary point pair, and integration is performed on the multiple interpolation points after the interpolation to obtain the volume information of the stockpile between the boundary point pairs.

4. The mining point recommendation method according to claim 2, characterized in that: The determining, based on the material pile volume information of each material pile, at least one target material pile position that satisfies a full load of the excavator bucket includes: Based on the material pile volume information of each material pile, detecting whether the material pile volume of the material pile is greater than the volume of the bucket of the excavator; A material pile having a volume greater than the volume of the bucket of the excavator is determined as the target material pile position.

5. The mining point recommendation method according to claim 2, characterized in that: The determining of the boom posture and the arm posture corresponding to the candidate recommended excavation point based on the candidate recommended excavation point and the pre-constructed excavator boom coordinate system and the excavator arm coordinate system includes: Obtain the pre-built excavator boom coordinate system and excavator arm coordinate system; In the excavator boom coordinate system or the excavator arm coordinate system, determining whether a triangular set relationship is satisfied among the candidate recommended excavation point, the origin of the excavator boom coordinate system, and the origin of the excavator arm coordinate system; If a triangle set relationship is satisfied between the candidate recommended excavation point, the origin of the excavator boom coordinate system, and the origin of the excavator arm coordinate system, the boom posture and the arm posture corresponding to the candidate recommended excavation point are determined according to the triangle set relationship.

6. The mining point recommendation method according to claim 2, characterized in that: The mining point recommendation method further includes: If the boom posture and / or the arm posture do not meet the preset excavator limit parameters, an updated recommended excavation point closest to the excavator position is determined among other material pile positions with a fully loaded bucket of the excavator, until the boom posture and the arm posture corresponding to the new updated recommended excavation point both meet the preset excavator limit parameters, and the updated recommended excavation point is determined as the target recommended excavation point.

7. The mining point recommendation method according to claim 1, characterized in that: The step of determining the target platform position in the area to be excavated based on the gradient information of each target grid area and the target height threshold comprises: Based on the gradient information of each target grid area, determining at least one location grid area having gradient information higher than the target height threshold; The location of the at least one location grid area is determined as the target platform location.

8. The mining point recommendation method according to claim 1, characterized in that: Calculating the gradient information of each target grid area includes: For each target grid area, based on the position coordinates of each target data point in the target grid area and the grid spacing information, determine the target partial derivative of the target grid area; For each target grid area, the gradient information of the target grid area is obtained based on the target partial derivative of the target grid area.

9. The mining point recommendation method according to claim 1, characterized in that: Determining a target elevation map of the area to be excavated based on the plurality of point cloud data includes: Performing coordinate system conversion on the plurality of point cloud data to obtain three-dimensional coordinates of a plurality of observation data points in an excavator coordinate system; Discretize multiple observation data points into multiple grid areas based on a preset grid resolution; each grid area contains at least one observation data point; Filtering out abnormal observation data points from the plurality of observation data points to obtain a plurality of target data points; For each target data point, calculating a height error value for the grid area where the target data point is located; wherein the height error value is determined based on the difference between the measured height value of the target data point and the estimated height value stored in the map; Determining a grid height offset value based on an average of the determined plurality of height error values; After the plurality of grid areas are offset by the grid height offset value, a target elevation map of the area to be excavated is obtained.

10. The mining point recommendation method according to claim 2, characterized in that: The mining point recommendation method further includes: If the target platform position does not include a target material pile position that satisfies a full load of the excavator bucket, an adjustment prompt message is generated.

11. A device for recommending excavation points for high-platform loading, characterized in that: The excavation point recommendation device includes: a target elevation map determination module, configured to obtain a plurality of point cloud data of the area to be excavated and determine a target elevation map of the area to be excavated based on the plurality of point cloud data; the target elevation map includes a plurality of target grid areas and elevation information corresponding to each target grid area; a target platform position determination module, configured to calculate the gradient information of each target grid area and determine the position of the target platform in the area to be excavated based on the gradient information of each target grid area and a target height threshold; wherein the target height threshold is a threshold that changes dynamically as the height of the target platform changes during the excavation process; The target recommended excavation point determination module is used to determine a target recommended excavation point at the target platform position that satisfies a full bucket load of the excavator based on the material pile volume information at the target platform position and the excavator's limit information.

12. An electronic device, characterized in that: include: A processor, a memory, and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the memory communicate via the bus, and the processor executes the machine-readable instructions to perform the steps of the method for recommending an excavation point for high-platform loading according to any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the method for recommending excavation points for high-platform loading according to any one of claims 1 to 10.

Images