CN113985873A - Planning method for shovel points of autonomous digging operation of loader - Google Patents
Planning method for shovel points of autonomous digging operation of loader Download PDFInfo
- Publication number
- CN113985873A CN113985873A CN202111248688.1A CN202111248688A CN113985873A CN 113985873 A CN113985873 A CN 113985873A CN 202111248688 A CN202111248688 A CN 202111248688A CN 113985873 A CN113985873 A CN 113985873A
- Authority
- CN
- China
- Prior art keywords
- point
- digging
- point cloud
- loader
- planning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000009412 basement excavation Methods 0.000 claims abstract description 80
- 239000000463 material Substances 0.000 claims abstract description 53
- 238000005520 cutting process Methods 0.000 claims description 21
- 238000011068 loading method Methods 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 16
- 238000011158 quantitative evaluation Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 4
- 230000005484 gravity Effects 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 230000001131 transforming effect Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000011156 evaluation Methods 0.000 description 13
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 238000011160 research Methods 0.000 description 4
- 125000004122 cyclic group Chemical group 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005265 energy consumption Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 230000032683 aging Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000004630 mental health Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0238—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors
- G05D1/024—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors in combination with a laser
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
- G05D1/0251—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means extracting 3D information from a plurality of images taken from different locations, e.g. stereo vision
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Electromagnetism (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Optics & Photonics (AREA)
- Multimedia (AREA)
- Operation Control Of Excavators (AREA)
Abstract
The invention is suitable for the field of unmanned engineering machinery, and provides a planning method for an excavation point of autonomous excavation operation of a loader, which comprises the following steps: s1, firstly, establishing a global map; s2, segmenting the material pile serving as the autonomous excavation operation working object of the loader in the global map by using a clustering algorithm; s3, planning a digging point according to the material pile point cloud data; s4, the control system controls the loader to carry out one-time autonomous excavation operation at the planned excavation point to obtain an updated material pile point cloud and complete a working cycle; and S5, planning a next digging point according to the updated material pile point cloud, and performing next working cycle. The invention fills the industry blank of the planning method of the independent digging operation digging point of the domestic loader, and solves the problems in the background technology that: the excavator task planning method is not suitable for the problem of autonomous excavation task planning of a loader.
Description
Technical Field
The invention belongs to the field of unmanned engineering machinery, and particularly relates to a planning method for an excavation point of autonomous excavation operation of a loader.
Background
The loader is an engineering machine widely applied to various engineering constructions, generally performs 'shovel-loading-transporting-unloading' cyclic operation, and the problems of influence on physical and mental health of a driver, harm to life safety of the driver, serious aging of the driver and the like existing in the traditional loader can be effectively solved by developing the unmanned technology research of the loader. In loader unmanned technology, the purpose of the cutting point planning is to arrange the coordinates and direction of the cutting point appropriately for a given work object. The planning of the shovel points of the automatic shovel operation of the loader must meet the basic conditions of shoveling, and the selection of a proper shovel position on the material pile is the premise of smoothly carrying out the shovel operation. After meeting the shoveling requirement, the shovel is easy to shovel, and reasonable shovel point planning is the basis for obtaining good shoveling effects such as high full bucket, low energy consumption and the like.
At present, the research on the autonomous operation of the loader at home and abroad is still in a laboratory stage, and any autonomous operation loader product is not seen at home and abroad. The research on the planning of the shovel points of the autonomous digging operation of the loader in China is still blank. However, the operation mode of the loader is greatly different from that of the excavator, the excavator can carry out excavation operation for many times when moving once, and the loader has stronger mobility compared with the excavator; since the excavator performs the excavation operation from top to bottom and the loader performs the cutting operation from bottom to top, the excavator task planning method is not suitable for the autonomous cutting task planning of the loader.
Disclosure of Invention
The embodiment of the invention aims to provide a method for planning an excavation point of an autonomous excavation operation of a loader, and aims to solve the problem that the conventional excavator task planning method is not suitable for planning an autonomous excavation task of the loader.
The embodiment of the invention is realized in such a way that a method for planning the excavation points of the autonomous excavation operation of a loader comprises the following steps:
s1, opening a loader to a designated working area, and firstly establishing a global map, wherein the method for establishing the global map comprises the steps that an unmanned aerial vehicle carries a remote sensing device, a handheld remote sensing device or a vehicle-mounted remote sensing device, and the remote sensing device comprises a laser radar, a structured light camera, a flight time ranging camera and a stereo camera;
s2, segmenting the material pile serving as the autonomous excavation operation working object of the loader in the global map by using a clustering algorithm to obtain three-dimensional point cloud data of the material pile; the source of the three-dimensional point cloud data is an image collected by a laser radar or a depth camera;
s3, planning a digging point according to the material pile point cloud data, and sending the planned coordinates and direction of the digging point to a control system by a digging point planning module;
s4, the control system controls the loader to carry out primary autonomous excavation operation at the planned excavation point, remote sensing equipment is installed on the loader and environmental changes are scanned in real time, registration and splicing are carried out on the new stock pile point cloud and the raw stock pile point cloud after primary excavation operation is finished, the updated stock pile point cloud is obtained, and a working cycle is finished;
and S5, planning a next digging point according to the updated material pile point cloud, and performing next working cycle.
According to a further technical scheme, according to the step S3, the processing steps of the three-dimensional point cloud data are as follows:
step1, a digging point planning module takes stockpile point cloud data as input, firstly carries out down-sampling processing on the point cloud data, reduces the amount of the point cloud data and improves the subsequent processing speed;
step2, carrying out statistical filtering on the point cloud, and eliminating outliers;
step3, performing stockpile curved surface reconstruction based on the processed point cloud to obtain the surface shape of the stockpile;
step4, searching an optimal digging point based on the processed point cloud data and the reconstructed curved surface; firstly, the position and the direction of a digging point are assumed on the bottom contour line of the material pile, and then the quantitative evaluation of the digging point is carried out, wherein the quantitative indexes comprise the unbalance degree, the convexity and the full bucket rate.
According to the further technical scheme, according to the step3, the curved surface reconstruction method comprises algorithms such as triangulation and Crimen interpolation.
According to the further technical scheme, according to the step4, the unbalance loading degree refers to the degree of deviation of the gravity center of the material in the bucket from the center of the bucket.
According to a further aspect, according to step4, the convexity refers to the degree of concavity and convexity of the pile profile with respect to the main cutting edge of the bucket.
According to the step4, the full bucket rate refers to the ratio of the volume of materials shoveled into the bucket to the rated volume of the bucket.
According to the further technical scheme, according to the step4, the offset degree and convexity evaluation method comprises the following steps:
step1, after a shoveling point capable of shoveling is supposed, extracting point cloud of a shoveling local neighborhood;
step2, transforming the extracted point cloud of the excavation local neighborhood into a coordinate system which takes an excavation point as an original point, takes the excavation point direction as the positive direction of the y axis and takes the vertical direction as the positive direction of the z axis;
step3, shoveling and digging a local neighborhood point cloud curved surface for fitting;
step4, when the point cloud is fitted into a plane, representing the slope of the plane relative to the xz plane as an offset degree; when the point cloud is fitted into a quadric surface, representing x item coefficient of the quadric surface as unbalance loading degree, and representing x2The term coefficients are characterized as convexity.
According to the further technical scheme, according to the step4, the full bucket rate evaluation method is to plan the excavation trajectory after assuming an excavation point capable of excavating.
The embodiment of the invention provides a method for planning a shovel point for autonomous shoveling operation of a loader, and 1, the method for planning the shovel point for autonomous shoveling operation of the loader provided by the invention provides a scheme for the method for planning the shovel point, and a key ring is connected for realizing unmanned operation of the loader. 2. The method for planning the excavation points can enable the loader to automatically identify the material pile during operation, guide the loader to identify a working object and operate on the continuously planned excavation points until a task is finished. 3. The planning method for the excavation points, provided by the invention, takes the unbalance loading degree of the bucket into consideration, can ensure that the load borne by the bucket is uniform, and can protect the structural safety of the loader. 4. The method for planning the digging points considers the concave-convex degree of the surface shape of the material pile, finds the digging points with smaller friction force on the bucket during digging, and reduces the energy consumption of the loader. 5. The bucket full-fill rate is one of the main parameters for determining the performance and the productivity of earth moving machines such as a loader, and the full-fill rate of each digging point is predicted when the digging point is planned, so that the working efficiency is ensured. 6. The process of searching the optimal digging point in the digging point planning is a cyclic processing process which consumes the most processor resources, and downsampling and filtering operation is carried out on point clouds before the process is carried out, so that the processing speed of the system is guaranteed.
Drawings
FIG. 1 is a schematic view of an autonomous excavation work cycle of a loader according to an embodiment of the present invention;
FIG. 2 is a flowchart of a method for planning digging points according to an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating the evaluation of the degree of deviation from the ground engaging point and the degree of convexity in the embodiment of the present invention;
fig. 4 is a schematic diagram illustrating prediction of the digging point full-fighting rate in the embodiment of the present invention.
In the drawings: 1 pile profile, 2 digging trajectory.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Specific implementations of the present invention are described in detail below with reference to specific embodiments.
As shown in fig. 1 and 2, a method for planning a cutting point of an autonomous cutting operation of a loader according to an embodiment of the present invention includes the following steps:
s1, opening a loader to a designated working area, and firstly establishing a global map, wherein the method for establishing the global map comprises the steps that an unmanned aerial vehicle carries a remote sensing device, a handheld remote sensing device or a vehicle-mounted remote sensing device, and the remote sensing device comprises a laser radar, a structured light camera, a flight time ranging camera and a stereo camera;
s2, segmenting the material pile serving as the autonomous excavation operation working object of the loader in the global map by using a clustering algorithm to obtain three-dimensional point cloud data of the material pile; the source of the three-dimensional point cloud data is an image collected by a laser radar or a depth camera;
s3, planning a digging point according to the material pile point cloud data, and sending the planned coordinates and direction of the digging point to a control system by a digging point planning module;
s4, the control system controls the loader to carry out primary autonomous excavation operation at the planned excavation point, remote sensing equipment is installed on the loader and environmental changes are scanned in real time, registration and splicing are carried out on the new stock pile point cloud and the raw stock pile point cloud after primary excavation operation is finished, the updated stock pile point cloud is obtained, and a working cycle is finished;
and S5, planning a next digging point according to the updated material pile point cloud, and performing next working cycle.
As shown in fig. 1, 2 and 3, as a preferred embodiment of the present invention, according to S3, the processing steps of the three-dimensional point cloud data are as follows:
step1, a digging point planning module takes stockpile point cloud data as input, firstly carries out down-sampling processing on the point cloud data, reduces the amount of the point cloud data and improves the subsequent processing speed;
step2, carrying out statistical filtering on the point cloud, and eliminating outliers;
step3, performing stockpile curved surface reconstruction based on the processed point cloud to obtain the surface shape of the stockpile;
step4, searching an optimal digging point based on the processed point cloud data and the reconstructed curved surface; firstly, the position and the direction of a digging point are assumed on the bottom contour line of the material pile, and then the quantitative evaluation of the digging point is carried out, wherein the quantitative indexes comprise the unbalance degree, the convexity and the full bucket rate.
As shown in fig. 1 and 2, as a preferred embodiment of the present invention, according to step3, the surface reconstruction method includes triangulation, kriging interpolation, and other algorithms.
As shown in fig. 1 and 2, as a preferred embodiment of the present invention, the degree of unbalance loading refers to a load in which the center of gravity of the material in the bucket is shifted from the center of the bucket according to step4.
As shown in fig. 1 and 2, as a preferred embodiment of the present invention, according to step4, the convexity refers to the degree of concavity and convexity of the pile profile with respect to the bucket cutting edge.
As shown in fig. 1 and 2, as a preferred embodiment of the present invention, according to step4, the full-fill rate refers to a ratio of a volume of material scooped by the bucket to a rated volume of the bucket.
As shown in fig. 1, 2 and 3, as a preferred embodiment of the present invention, according to step4, the offset and convexity estimation method is as follows:
step1, after a shoveling point capable of shoveling is supposed, extracting point cloud of a shoveling local neighborhood;
step2, transforming the extracted point cloud of the excavation local neighborhood into a coordinate system which takes an excavation point as an original point, takes the excavation point direction as the positive direction of the y axis and takes the vertical direction as the positive direction of the z axis;
step3, shoveling and digging a local neighborhood point cloud curved surface for fitting;
step4, when the point cloud is fitted into a plane, representing the slope of the plane relative to the xz plane as an offset degree; when the point cloud is fitted into a quadric surface, representing x item coefficient of the quadric surface as unbalance loading degree, and representing x2The term coefficients are characterized as convexity.
As shown in fig. 1, 2 and 4, as a preferred embodiment of the present invention, according to step4, the full-skip rate estimation method is to predict the full-skip rate according to two information, namely, the pile profile and the digging trajectory after assuming a shovelable digging point.
In an embodiment of the present invention, fig. 1 is a schematic view of a working cycle of an autonomous excavation operation of a loader. The planning of the digging point is an important link of the autonomous digging operation of the loader, and is not an isolated part, and the completion of the planning of the digging point needs to depend on other links in the working cycle of the autonomous digging operation. The working cycle of the autonomous excavation operation of the loader is described as follows: 1. after a loader working area is appointed, firstly, establishing a global map, wherein the global map is an important basis for the work of path planning and the like of a loader and a dump truck, the establishing method of the global map comprises the step that an unmanned aerial vehicle carries remote sensing equipment, handheld remote sensing equipment or vehicle-mounted remote sensing equipment, and the remote sensing equipment comprises a laser radar, a structured light camera, a flight time ranging camera, a stereo camera and the like. 2. And next, segmenting the material pile which is the autonomous excavation operation working object of the loader in the global map by using algorithms such as clustering and the like to obtain three-dimensional point cloud data of the material pile. The source of the three-dimensional point cloud data can be a laser radar, and can also be obtained by performing three-dimensional reconstruction according to an image collected by a depth camera. 3. And then planning the digging point according to the material pile point cloud data, and sending the planned coordinates and direction of the digging point to a control system by a digging point planning module. 4. Next, the system controls the loader to perform an autonomous digging operation at the planned digging point. The loader is provided with a remote sensing device for scanning environmental changes in real time, and the shape of the stockpile is inevitably changed after one spading operation is completed, so that the latest stock pile point cloud data is acquired after one spading operation is completed, the remote sensing device arranged on the loader cannot scan the full appearance of the stockpile in the operation process, but can scan the range of the change of the surface shape of the stockpile, and therefore, the new stock pile point cloud and the stock pile point cloud are required to be registered and spliced to obtain the updated stock pile point cloud, and a working cycle is completed. 5. And then planning a next digging point according to the updated material pile point cloud, and carrying out the next working cycle.
Fig. 2 is a flowchart of a planning method for a digging point of autonomous digging operation of a loader, and the specific flow is described as follows: the digging point planning module takes the material pile point cloud data as input, firstly carries out down-sampling processing on the point cloud data, reduces the amount of the point cloud data and improves the subsequent processing speed. Secondly, statistical filtering is carried out on the point cloud, and outliers are removed. And then, carrying out stock pile curved surface reconstruction based on the processed point cloud to obtain the surface shape of the stock pile. One of the purposes of performing the curved surface reconstruction is to obtain the profile of the bottom of the material pile, the assumption of the digging point in the subsequent process is performed along the profile of the material pile, the profile of the material pile is used as one of the constraints of the assumptions of the digging point, and the direction of the assumed digging point is constrained to point to the material pile, so that the digging point can be dug, and the spatial scattered data needs to be subjected to gridding processing to obtain the profile of the bottom of the material pile, and then interpolation is performed on the basis. The curved surface reconstruction method comprises algorithms such as triangulation and kriging interpolation, and fig. 4(a) is a schematic diagram of curved surface reconstruction by using the triangulation method. The second purpose of the surface reconstruction is to perform the following full bucket rate prediction, and the specific method will be described later; the third purpose is to monitor the work site by remote control center personnel, so that the management personnel can observe the work progress and the site situation in real time. Thus, the point cloud data is preprocessed.
And then searching an optimal excavation point based on the processed point cloud data and the reconstructed curved surface. Firstly, the position and the direction of a digging point are assumed on the bottom contour line of the material pile, and then the quantitative evaluation of the digging point is carried out, wherein the quantitative indexes comprise the unbalance degree, the convexity and the full bucket rate.
The degree of unbalance loading refers to the degree that the gravity center of materials in the bucket deviates from the center of the bucket, and the inclination of the digging direction causes uneven load on the bucket and damages the structure of the loader; the convexity refers to the concave-convex degree of the material pile profile relative to the main cutting edge of the bucket, and the excessive depression of the material relative to the bucket increases the friction force of the bucket and influences the full bucket rate. The full-fill rate refers to the ratio of the volume of materials shoveled by the bucket to the rated volume of the bucket, the full-fill rate of the bucket is one of main parameters for determining the performance and the productivity of earth moving machines such as an excavator, a scraper and a loader, and the offset degree and the convexity degree influence the full-fill rate finally obtained by shoveling operation. These three indexes are indexes that the driver does not ignore in operating the loader for the shoveling work.
The detailed procedure for the skewness and convexity estimation is described as follows: after a spading point is supposed to be good, extracting the point cloud of a spading local neighborhood, wherein the spading local neighborhood refers to an operation material pile local area when spading operation is carried out on the supposed spading point, and the area can be defined as a point cloud contained in a rectangular frame which has the same width as a bucket or slightly wider than the bucket, is slightly deeper than a deepest point of a spading planning and has a height slightly higher than a highest point of a spading track. And then converting the extracted point clouds of the shoveling local neighborhood into a coordinate system which takes the shoveling points as the original points, takes the direction of the shoveling points as the positive direction of the y axis, and vertically upwards as the positive direction of the z axis. The next step is the shoveling local neighborhood point cloud curved surface fitting, the curved surface fitting is not for visualization, but estimation of unbalance loading degree and convexity is carried out according to parameters of a fitting curved surface, all curved surfaces capable of quantifying the unbalance loading degree and the convexity can be used for the step, for example, when the point cloud is fitted into a cylindrical surface, the unbalance loading degree can be represented by the position of an axis relative to a y axis, the convex and concave surfaces of the curved surface can enable the axis to be positioned at different sides of the material pile, and the radius of the cylindrical surface can be used for representing the convexity or concavity; when the point cloud is fitted into a conical surface, the characterization method of the unbalance loading degree and the convexity is similar to that of a cylindrical surface; when the point cloud is fitted into a plane, the offset degree can be represented by the slope of the plane relative to the xz plane; when the point cloud is fitted into a quadric surface, the offset degree can be represented by x-item coefficients of the quadric surface, and the convexity can be represented by x 2-item coefficients.
The fill-out rate evaluation method is described in detail as follows: the method for realizing autonomous excavation in the existing research results mainly comprises the steps that a plurality of excavation tracks are stored in a control system of a loader, a driver inputs information such as types of materials before each operation, the loader selects a corresponding working mode according to the information to carry out autonomous excavation, and under the condition, an excavation track module can directly call the planned excavation track; for another situation, when the loader adopts an autonomous excavation method with non-excavation trajectory control, such as admittance control or a loader autonomous loading dynamic control method based on a segmented loading method, the statistical value of the excavation trajectory is taken as the output of the step, because the same excavation strategy does not have too great a difference between different excavation trajectories of the same material pile and does not have too great an influence on the prediction of the full-bucket rate of the next step. After the digging track is obtained, the full-fill rate prediction can be performed according to two pieces of information, namely, the material pile profile 1 is taken as one surface, the digging track 2 is multiplied by the bucket width to be taken as the other surface, grids with uniform sizes are divided on the two surfaces obtained through interpolation, the area of each square grid is multiplied by the distance between corresponding squares on the two surfaces, and the grids are added to directly calculate the volume of the material, as shown in an example in fig. 4 (b).
After the evaluation parameters of the three indexes of the unbalance loading degree, the convexity and the full bucket rate are obtained, the three parameters can be integrated to carry out quantitative evaluation on the excavation point, and proper weights are set for the three indexes to obtain the excavation point evaluation value. Comparing the evaluation value of the current excavation point with the evaluation values of other excavation points, and preferably selecting the current excavation point until the selection is finished, wherein the excavation point decision module outputs the coordinate and the direction of the optimal excavation point.
It is conceivable that the index for performing the excavation point evaluation is expandable, and other indexes besides the degree of unbalance loading, the convexity, and the full bucket rate may be added to the excavation point evaluation index according to specific requirements, for example, the loader form path length caused by the planned excavation point, and the distance between the excavation points of two adjacent excavations.
As described above, the idea of finding the optimal cutting point in the dashed box in fig. 2 is: under the condition of ensuring spayable, coordinates and directions of different spaying points are assumed, and quantitative evaluation of the assumed spaying points is carried out. One implementation method is as follows: assuming discrete spading point coordinates and directions, namely assuming a spading point coordinate every a plurality of meters, assuming a spading direction every a plurality of angles for each spading point coordinate, and selecting an optimal spading point from the spading direction coordinates; the other implementation method is that the excavation point is optimized by using optimization algorithms such as genetic algorithm, particle swarm algorithm or simulated degradation algorithm, the coordinate and the direction of the excavation point are optimization variables, excavation can be regarded as constraint, and the minimum evaluation value of the excavation point is regarded as an optimization target.
As another option, the planning of a certain excavation point can be realized without depending on a global map, but the quantitative evaluation of the excavation point evaluation index can be directly carried out by using certain frame data acquired by vehicle-mounted remote sensing equipment. The cutting point planning procedure of this method is the same as the method described above, and fig. 3 and 4 show an embodiment of the cutting point evaluation of this method, in this case defining the cutting point as the middle position of the main cutting edge of the bucket, as described below:
fig. 3 is an example of estimating the unbalance loading degree and the convexity of a certain assumed excavation point, fig. 3(a) is a processed stock pile point cloud, the point cloud in the rectangular frame in fig. 3(b) is the excavation local neighborhood of the assumed excavation point, fig. 3(c) is the point cloud which has been extracted and subjected to coordinate transformation, the origin of coordinates is the position of a mark in the figure, fig. 3(d) is a surface fitting effect graph, in this example, the point cloud is subjected to quadratic surface fitting, and a quadratic surface equation is as follows:
Z＝c1X2+c2Y2+c3XY+c4X+c5Y+c6
XYZ in the formula are point cloud XYZ coordinates respectively,
X＝[x1 x2 x3 x4 … xn]T
Y＝[y1 y2 y3 y4 … yn]T
Z＝[z1 z2 z3 z4 … zn]T
for the above quadratic surface equation, in | c4I denotes the degree of unbalance loading, in c1Horizontal convexity is characterized.
Fig. 4 is a schematic diagram of the prediction of the full fill rate, fig. 4(a) is an effect diagram of curved surface reconstruction of the material pile by a greedy triangulation method, and fig. 4(b) is a side view of the digging operation, wherein a solid line 1 is a profile of the material pile, and a dashed line 2 is a digging trajectory, and then the full fill rate can be predicted as the area of a closed graph where a section line is located in the middle multiplied by the bucket width.
The embodiment of the invention provides a method for planning a shovel point for automatic shovel operation of a loader, and 1, the method for planning the shovel point for automatic shovel operation of the loader provided by the invention provides a scheme for the method for planning the shovel point, and a key ring is connected for realizing unmanned operation of the loader. 2. The method for planning the excavation points can enable the loader to automatically identify the material pile during operation, guide the loader to identify a working object and operate on the continuously planned excavation points until a task is finished. 3. The planning method for the excavation points, provided by the invention, takes the unbalance loading degree of the bucket into consideration, can ensure that the load borne by the bucket is uniform, and can protect the structural safety of the loader. 4. The method for planning the digging points considers the concave-convex degree of the surface shape of the material pile, finds the digging points with smaller friction force on the bucket during digging, and reduces the energy consumption of the loader. 5. The bucket full-fill rate is one of the main parameters for determining the performance and the productivity of earth moving machines such as a loader, and the full-fill rate of each digging point is predicted when the digging point is planned, so that the working efficiency is ensured. 6. The process of searching the optimal digging point in the digging point planning is a cyclic processing process which consumes the most processor resources, and downsampling and filtering operation is carried out on point clouds before the process is carried out, so that the processing speed of the system is guaranteed.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (8)
1. A method for planning a digging point of autonomous digging operation of a loader is characterized by comprising the following steps:
s1, opening a loader to a designated working area, and firstly establishing a global map, wherein the method for establishing the global map comprises the steps that an unmanned aerial vehicle carries a remote sensing device, a handheld remote sensing device or a vehicle-mounted remote sensing device, and the remote sensing device comprises a laser radar, a structured light camera, a flight time ranging camera and a stereo camera;
s2, segmenting the material pile serving as the autonomous excavation operation working object of the loader in the global map by using a clustering algorithm to obtain three-dimensional point cloud data of the material pile; the source of the three-dimensional point cloud data is an image collected by a laser radar or a depth camera;
s3, planning a digging point according to the material pile point cloud data, and sending the planned coordinates and direction of the digging point to a control system by a digging point planning module;
s4, the control system controls the loader to carry out primary autonomous excavation operation at the planned excavation point, remote sensing equipment is installed on the loader and environmental changes are scanned in real time, registration and splicing are carried out on the new stock pile point cloud and the raw stock pile point cloud after primary excavation operation is finished, the updated stock pile point cloud is obtained, and a working cycle is finished;
and S5, planning a next digging point according to the updated material pile point cloud, and performing next working cycle.
2. The method for planning a cutting point for autonomous cutting work of a loader according to claim 1, wherein the processing steps of the three-dimensional point cloud data according to S3 are as follows:
step1, a digging point planning module takes stockpile point cloud data as input, firstly carries out down-sampling processing on the point cloud data, reduces the amount of the point cloud data and improves the subsequent processing speed;
step2, carrying out statistical filtering on the point cloud, and eliminating outliers;
step3, performing stockpile curved surface reconstruction based on the processed point cloud to obtain the surface shape of the stockpile;
step4, searching an optimal digging point based on the processed point cloud data and the reconstructed curved surface; firstly, the position and the direction of a digging point are assumed on the bottom contour line of the material pile, and then quantitative evaluation of the digging point is carried out, wherein the quantitative indexes comprise the unbalance degree, the convexity and the full bucket rate.
3. The method for planning a digging point for autonomous digging operation of a loader according to claim 2, wherein according to step3, the curved surface reconstruction method comprises triangulation, kriging interpolation and other algorithms.
4. The method of claim 2, wherein the degree of unbalance loading is the degree to which the center of gravity of the material in the bucket is shifted from the center of the bucket according to step4.
5. The method of claim 2, wherein the convexity refers to the degree of concavity and convexity of the heap profile with respect to the main cutting edge of the bucket, according to step4.
6. The method for planning a cutting point for autonomous cutting operation of a loader according to claim 2, wherein the full-bucket rate refers to a ratio of a volume of material scooped by the bucket to a rated volume of the bucket according to step4.
7. The method for planning a cutting point for autonomous cutting operation of a loader according to claim 2, wherein according to step4, the method for estimating the degree of unbalance loading and the degree of convexity is as follows:
step1, after a shoveling point capable of shoveling is supposed, extracting point cloud of a shoveling local neighborhood;
step2, transforming the extracted point cloud of the excavation local neighborhood into a coordinate system which takes an excavation point as an original point, takes the excavation point direction as the positive direction of the y axis and takes the vertical direction as the positive direction of the z axis;
step3, shoveling and digging a local neighborhood point cloud curved surface for fitting;
step4, when the point cloud is fitted into a plane, representing the slope of the plane relative to the xz plane as an offset degree; when the point cloud is fitted into a quadric surface, representing x item coefficient of the quadric surface as unbalance loading degree, and representing x2The term coefficients are characterized as convexity.
8. The method for planning a digging point for autonomous digging operation of a loader according to claim 2, wherein according to step4, the method for estimating the full-fill rate is to predict the full-fill rate according to two information of a pile profile and a digging track after assuming a shovelable digging point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111248688.1A CN113985873A (en) | 2021-10-26 | 2021-10-26 | Planning method for shovel points of autonomous digging operation of loader |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111248688.1A CN113985873A (en) | 2021-10-26 | 2021-10-26 | Planning method for shovel points of autonomous digging operation of loader |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113985873A true CN113985873A (en) | 2022-01-28 |
Family
ID=79741684
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111248688.1A Pending CN113985873A (en) | 2021-10-26 | 2021-10-26 | Planning method for shovel points of autonomous digging operation of loader |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113985873A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114648161A (en) * | 2022-03-14 | 2022-06-21 | 河南理工大学 | Self-adaptive intelligent loading system of large-tonnage loader |
| CN115030250A (en) * | 2022-06-14 | 2022-09-09 | 厦门大学 | Resistance prediction method and device for shovel loading operation of loader |
| CN116242363A (en) * | 2023-03-06 | 2023-06-09 | 燕山大学 | Unmanned aerial vehicle guided excavator autonomous operation method and system thereof |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104090279A (en) * | 2014-07-11 | 2014-10-08 | 四川省绵阳西南自动化研究所 | Excavation working face detection device based on laser radar |
| US20150046044A1 (en) * | 2011-09-23 | 2015-02-12 | Volvo Construction Equipment Ab | Method for selecting an attack pose for a working machine having a bucket |
| RU2560013C1 (en) * | 2014-06-24 | 2015-08-20 | Федеральное государственное бюджетное образовательное учреждение высшего профессионального образования "Национальный минерально-сырьевой университет "Горный" | Loading machine |
| CN111368664A (en) * | 2020-02-25 | 2020-07-03 | 吉林大学 | Loader full-fill rate identification method based on machine vision and bucket position information fusion |
| CN111954739A (en) * | 2018-04-27 | 2020-11-17 | 株式会社小松制作所 | Control device for loading machine and control method for loading machine |
| CN113309169A (en) * | 2021-07-01 | 2021-08-27 | 吉林大学 | Autonomous unloading system and method in unmanned loader chamber |
-
2021
- 2021-10-26 CN CN202111248688.1A patent/CN113985873A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150046044A1 (en) * | 2011-09-23 | 2015-02-12 | Volvo Construction Equipment Ab | Method for selecting an attack pose for a working machine having a bucket |
| RU2560013C1 (en) * | 2014-06-24 | 2015-08-20 | Федеральное государственное бюджетное образовательное учреждение высшего профессионального образования "Национальный минерально-сырьевой университет "Горный" | Loading machine |
| CN104090279A (en) * | 2014-07-11 | 2014-10-08 | 四川省绵阳西南自动化研究所 | Excavation working face detection device based on laser radar |
| CN111954739A (en) * | 2018-04-27 | 2020-11-17 | 株式会社小松制作所 | Control device for loading machine and control method for loading machine |
| CN111368664A (en) * | 2020-02-25 | 2020-07-03 | 吉林大学 | Loader full-fill rate identification method based on machine vision and bucket position information fusion |
| CN113309169A (en) * | 2021-07-01 | 2021-08-27 | 吉林大学 | Autonomous unloading system and method in unmanned loader chamber |
Non-Patent Citations (6)
| Title |
|---|
| MARTIN MAGNUSSON: "Consistent Pile-Shape Quantification for Autonomous Wheel Loaders", 《2011 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS》 * |
| NORIHO KOYACHI: "Unmanned Loading Operation By Autonomous Wheel Loader", 《ICROS-SICE INTERNATIONAL JOINT CONFERENCE 2009》, pages 2 - 5 * |
| 宋子岭: "《移动机器人及室内环境三维模型重建技术》", 徐州中国矿业大学出版社, pages: 130 - 132 * |
| 李学飞: "A neural network–based approach for fill factor estimation and bucket detection on construction vehicles", 《INDUSTRIAL APPLICATION》 * |
| 李学飞: "基于克里金和粒子群算法的 装载机铲掘轨迹规划", 《吉林大学学报》 * |
| 洪钱港: "装载机自动铲装实验研究", 《煤矿机械》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114648161A (en) * | 2022-03-14 | 2022-06-21 | 河南理工大学 | Self-adaptive intelligent loading system of large-tonnage loader |
| CN115030250A (en) * | 2022-06-14 | 2022-09-09 | 厦门大学 | Resistance prediction method and device for shovel loading operation of loader |
| CN116242363A (en) * | 2023-03-06 | 2023-06-09 | 燕山大学 | Unmanned aerial vehicle guided excavator autonomous operation method and system thereof |
| CN116242363B (en) * | 2023-03-06 | 2024-07-26 | 燕山大学 | Unmanned aerial vehicle guided excavator autonomous operation method and system thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113985873A (en) | Planning method for shovel points of autonomous digging operation of loader | |
| US10914049B1 (en) | Excavating earth from a dig site using an excavation vehicle | |
| CN109902857B (en) | Automatic planning method and system for loading point of transport vehicle | |
| US8903689B2 (en) | Autonomous loading | |
| EP2758605B1 (en) | Method for selecting an attack pose for a working machine having a bucket | |
| KR101546708B1 (en) | System and method for computing the excavcated soil volume using 3d scanner | |
| CN114722586B (en) | Optimal automatic excavating operation method of intelligent electric shovel based on stacking surface prediction model | |
| CN113256588B (en) | Real-time updating method for refuse dump and refuse discharge edge line in unmanned strip mine | |
| CN117910285B (en) | Creation method, device, equipment and storage medium of library basin design curved surface model | |
| CN115142513A (en) | Control method and device for excavator, processor and storage medium | |
| Finkbeiner et al. | Shape recognition of material heaps in outdoor environments and optimal excavation planning | |
| Alhasan et al. | Earthwork haul-truck cycle-time monitoring: a case study. | |
| Otsuki et al. | Research on standardization of construction site time-series change information as learning data for automatic generation of work plan of construction machinery in earthworks | |
| CN118706105A (en) | Engineering machinery control method based on real-time map, electronic equipment and storage medium | |
| KR20230166481A (en) | Construction machinary and operation method of the same | |
| CN115202360A (en) | Automatic control method, equipment and medium for streaming machine | |
| CN117419704A (en) | Map area updating method and system for surface mine loading area | |
| CN116319887A (en) | Material pile shoveling method and device, electronic equipment and medium | |
| CN118429544A (en) | Loading operation method and system of unmanned loading equipment, storage medium and engineering machinery |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220128 |
|
| RJ01 | Rejection of invention patent application after publication |