CN115142513A - Control method and device for excavator, processor and storage medium - Google Patents
Control method and device for excavator, processor and storage medium Download PDFInfo
- Publication number
- CN115142513A CN115142513A CN202210573667.5A CN202210573667A CN115142513A CN 115142513 A CN115142513 A CN 115142513A CN 202210573667 A CN202210573667 A CN 202210573667A CN 115142513 A CN115142513 A CN 115142513A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- point
- target
- dimensional
- map
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 239000000463 material Substances 0.000 claims abstract description 73
- 238000012545 processing Methods 0.000 claims abstract description 46
- 238000009412 basement excavation Methods 0.000 claims abstract description 39
- 230000011218 segmentation Effects 0.000 claims description 37
- 239000006185 dispersion Substances 0.000 claims description 27
- 230000001788 irregular Effects 0.000 claims description 8
- 238000013135 deep learning Methods 0.000 claims description 6
- 238000000638 solvent extraction Methods 0.000 claims 2
- 238000013480 data collection Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 239000002689 soil Substances 0.000 description 6
- 230000009471 action Effects 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000007599 discharging Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 238000005065 mining Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
Classifications
-
- E—FIXED CONSTRUCTIONS
- E02—HYDRAULIC ENGINEERING; FOUNDATIONS; SOIL SHIFTING
- E02F—DREDGING; SOIL-SHIFTING
- E02F9/00—Component parts of dredgers or soil-shifting machines, not restricted to one of the kinds covered by groups E02F3/00 - E02F7/00
- E02F9/20—Drives; Control devices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Mining & Mineral Resources (AREA)
- Civil Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Structural Engineering (AREA)
- Operation Control Of Excavators (AREA)
Abstract
The embodiment of the invention provides a control method and device for an excavator, a processor and a storage medium, and belongs to the field of engineering machinery. The control method for the excavator comprises the following steps: acquiring point cloud data of a target area; processing the point cloud data to identify an object to be identified in a target area, wherein the object to be identified comprises a stockpile and a mine card; determining a target excavation point of a material pile and a target loading point of an ore card; excavating the material pile according to the target excavation point; and unloading the excavated materials to the mine card according to the target loading point. The invention can improve the automation degree of the excavator operation.
Description
Technical Field
The invention relates to the field of engineering machinery, in particular to a control method and device for an excavator, a processor and a storage medium.
Background
With the development of unmanned technology, industrial automatic driving is also concerned. The excavator is one of the most main models in the field of engineering machinery, can meet various working conditions and complete various construction requirements, and has higher requirements on automatic driving technical operation. Most of the conventional excavators still need field personnel to supervise and control the excavator to carry out digging and discharging actions, so that the problem of low operation automation degree exists.
Disclosure of Invention
An embodiment of the present invention provides a control method and apparatus for an excavator, a processor, and a storage medium, so as to solve the problem in the prior art that the degree of automation of an excavator operation is low.
In order to achieve the above object, a first aspect of embodiments of the present invention provides a control method for an excavator, including:
acquiring point cloud data of a target area;
processing the point cloud data to identify an object to be identified in a target area, wherein the object to be identified comprises a stockpile and a mine card;
determining a target excavation point of a material pile and a target loading point of an ore card;
excavating the material pile according to the target excavation point;
and unloading the excavated materials to the mine card according to the target loading point.
In the embodiment of the present invention, processing point cloud data to identify an object to be identified in a target area includes: establishing a three-dimensional point cloud map according to the point cloud data; performing clustering segmentation processing on the three-dimensional point cloud map to obtain a processed three-dimensional point cloud map, wherein the processed three-dimensional point cloud map comprises a target point cloud set of a corresponding category of an object to be identified; converting the processed three-dimensional point cloud map into a two-dimensional grid map; and identifying the grid where the target point cloud set is located in the two-dimensional grid map based on a preset identification strategy so as to identify the object to be identified.
In the embodiment of the present invention, performing clustering segmentation processing on a three-dimensional point cloud map to obtain a processed three-dimensional point cloud map includes: performing ground segmentation processing on the three-dimensional point cloud map to obtain a first point cloud map, wherein the first point cloud map does not include the ground; clustering the first point cloud map to obtain a second point cloud map, wherein the second point cloud map comprises a plurality of categories of point cloud sets; and carrying out segmentation processing on the second point cloud map to obtain a processed three-dimensional point cloud map.
In the embodiment of the present invention, the segmenting the second point cloud map to obtain the processed three-dimensional point cloud map includes: determining the number of point clouds in each point cloud set in the second point cloud map; and removing the point cloud sets with the point cloud number less than the preset number threshold value to obtain the processed three-dimensional point cloud map.
In the embodiment of the present invention, based on a preset identification policy, identifying a grid in which a target point cloud set is located in a two-dimensional grid map to identify an object to be identified includes: determining a grid height value corresponding to each grid in the two-dimensional grid map, wherein the grid height value is the maximum height value in the point cloud data in the grids; determining related information of grid height values of grids where target point cloud sets are located in a two-dimensional grid map, wherein the related information comprises a dispersion degree parameter and a mean value; under the condition that the dispersion degree parameter is smaller than a preset dispersion degree threshold value and the mean value is larger than a preset mean value, identifying a mine card corresponding to a grid where the target point cloud set is located; and under the condition that the dispersion degree parameter is greater than or equal to a preset dispersion degree threshold value and/or the mean value is less than or equal to a preset mean value, identifying the material pile corresponding to the grid where the target point cloud set is located.
In the embodiment of the present invention, processing point cloud data to identify an object to be identified in a target area includes: establishing a three-dimensional point cloud map according to the point cloud data; and segmenting the three-dimensional point cloud map based on a deep learning point cloud segmentation algorithm to identify the object to be identified.
In the embodiment of the invention, the determining of the target excavation point of the material pile and the target loading point of the mine card comprises the following steps: establishing a stock pile three-dimensional geometric model corresponding to the stock pile according to the point cloud data corresponding to the stock pile; establishing a three-dimensional geometric model of the ore cards corresponding to the material pile according to the point cloud data corresponding to the ore cards; respectively carrying out gridding processing on the three-dimensional geometric model of the material pile and the three-dimensional geometric model of the ore card to obtain a plurality of first regular geometric bodies corresponding to the three-dimensional geometric model of the material pile and a plurality of second regular geometric bodies corresponding to the three-dimensional geometric model of the ore card; determining the central point of the first regular geometric body as a target digging point of the stockpile; and determining a target loading point of the mine card according to the central point of the second regular geometric body.
In the embodiment of the present invention, determining the target loading point of the mine card according to the central point of the second regular geometric body includes: determining a loading area of the mine card; and determining the central point of the second irregular geometric body corresponding to the loading area as a target loading point of the mine card.
In the embodiment of the present invention, the control method further includes: and determining the central point with the highest height in the central points of the first regular geometric bodies as the initial target digging point of the stock pile.
In the embodiment of the present invention, the control method further includes: the distances among the center points of a plurality of second irregular geometric bodies corresponding to the loading areas and determining the farthest central point of the excavator as an initial target loading point of the mine truck.
In the embodiment of the invention, the excavation of the stockpile according to the target excavation point comprises the following steps: excavating the material pile according to a target excavation point based on a preset excavation strategy; unloading the excavated material onto the mine card according to a target loading point, comprising: and unloading the excavated material onto the mine card according to the target loading point based on a preset unloading strategy.
In the embodiment of the present invention, acquiring point cloud data of a target area includes: the method comprises the steps of obtaining point cloud data of a target area through at least one of a laser radar, a global navigation satellite system and an information network system.
A second aspect of embodiments of the present invention provides a processor configured to execute the control method for an excavator according to the above.
A third aspect of an embodiment of the present invention provides a control device for an excavator, including: the point cloud data acquisition equipment is used for acquiring point cloud data of a target area; and a processor according to the above.
In an embodiment of the invention, the point cloud data acquisition device comprises at least one of: laser radar, global navigation satellite systems, and information network systems.
A fourth aspect of the embodiments of the present invention provides an excavator, including: the control device for the excavator is described above.
A fifth aspect of embodiments of the present invention provides a machine-readable storage medium having stored thereon instructions, which, when executed by a processor, cause the processor to execute a control method for an excavator according to the above.
According to the control method for the excavator, the point cloud data of the target area are obtained and processed to identify the object to be identified in the target area, so that the target excavation point of the material pile and the target loading point of the mine card are determined, the material pile is excavated according to the target excavation point and the excavated material is unloaded onto the mine card according to the target loading point. According to the method, field personnel do not need to supervise and control the excavator to carry out material digging and unloading actions, the point cloud data of the target area are obtained to identify the object to be identified in the target area, so that the positions of the material pile and the mine card are accurately determined, automatic path planning and automatic operation planning can be realized, the target digging point of the material pile and the target loading point of the mine card are determined, the accurate positioning of the digging working position and the unloading working position of the excavator can be realized, the working efficiency of the excavator can be improved by carrying out operation according to the target digging point and the target loading point, the automation degree of excavator operation is improved, the working effectiveness of the excavator is guaranteed, and the production efficiency is further improved.
Additional features and advantages of embodiments of the present invention will be described in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the embodiments of the invention and not to limit the embodiments of the invention. In the drawings:
FIG. 1 schematically illustrates a flow diagram of a control method for an excavator in an embodiment of the invention;
FIG. 2 is a flow chart schematically illustrating the processing steps of point cloud data in one embodiment of the invention;
FIG. 3 schematically illustrates a communication diagram of an excavator in an embodiment of the invention;
fig. 4 schematically shows a flowchart of a step of identifying an object to be identified in an embodiment of the present invention.
Detailed Description
The following detailed description of embodiments of the invention refers to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating embodiments of the invention, are given by way of illustration and explanation only, not limitation.
Fig. 1 schematically shows a flowchart of a control method for an excavator in an embodiment of the present invention. As shown in fig. 1, in an embodiment of the present invention, a control method for an excavator is provided, which is described by taking the method as an example of being applied to a processor, and the method may include the following steps:
step S102, point cloud data of a target area is obtained.
It is understood that the target area is a working area of the excavator.
Specifically, the processor may obtain point cloud data of a target area of the excavator, where the specific obtaining manner of the point cloud data may be laser measurement, laser measurement equipment such as a laser radar, or photogrammetry equipment such as a camera scanner, or Global Navigation Satellite System (GNSS), etc.
And step S104, processing the point cloud data to identify an object to be identified in the target area, wherein the object to be identified comprises a stockpile and a mine card.
It can be understood that the object to be identified is an object to be identified in the target area, including a stockpile and a mine card.
Specifically, the processor may process the point cloud data, for example, the point cloud data may be identified by an identification algorithm or a model, so as to determine that the object to be identified is a stockpile or a mine card.
Fig. 2 schematically shows a flow chart of the point cloud data processing steps in an embodiment of the present invention, in an embodiment, processing the point cloud data to identify an object to be identified in a target area includes the following steps S202 to S208:
step S202, a three-dimensional point cloud map is established according to the point cloud data.
Specifically, after obtaining the point cloud data of the target area, the processor may establish a corresponding three-dimensional point cloud map according to the point cloud data, for example, the three-dimensional point cloud map may be established through a map construction algorithm (e.g., a laser SLAM algorithm). In one embodiment, the processor may fuse laser radar data, global navigation satellite System data, or Information Network System (INS) via a synchronous positioning and mapping algorithm to build a three-dimensional point cloud map (i.e., a three-dimensional environment map).
And S204, performing clustering segmentation processing on the three-dimensional point cloud map to obtain a processed three-dimensional point cloud map, wherein the processed three-dimensional point cloud map comprises a target point cloud set of a corresponding category of the object to be identified.
It is understood that the cluster segmentation process may include two processing manners, i.e., a cluster processing manner and a segmentation processing manner, the sequence is not limited, and understandably, the cluster processing manner is used for classification, specifically, a label may be set for classification, and the segmentation processing manner is a removal processing manner, which is used for removing or segmenting the unnecessary data. The processed three-dimensional point cloud map, that is, the three-dimensional point cloud map after the clustering segmentation processing, includes a target point cloud set of corresponding categories of objects to be identified (including stockpiles and mine cards), that is, the target point cloud set is a set including point cloud data of corresponding categories of objects to be identified, and the target point cloud set includes, for example, a set of point cloud data corresponding to stockpiles and a set of point cloud data corresponding to mine cards.
Specifically, the processor may perform clustering segmentation processing on the three-dimensional point cloud map to obtain a processed three-dimensional point cloud map including a target point cloud set of a category corresponding to an object to be identified (including a stockpile and a mine card), and may specifically perform clustering segmentation processing through a clustering algorithm and/or a segmentation algorithm, which is not described herein again.
And step S206, converting the processed three-dimensional point cloud map into a two-dimensional grid map.
Specifically, the processor may perform two-dimensional projection and rasterization on the three-dimensional point cloud map, so as to obtain a two-dimensional grid map, and understandably, the two-dimensional grid map also includes a target point cloud set of a category corresponding to the object to be identified.
And S208, identifying the grid where the target point cloud set is located in the two-dimensional grid map based on a preset identification strategy so as to identify the object to be identified.
It is understood that the identification policy is a preset identification method for identifying objects to be identified, including stockpiles and mine cards.
Specifically, the processor may identify a grid where a target point cloud set in the two-dimensional grid map is located based on a preset identification strategy, so as to identify whether the object to be identified is a stockpile or a mine card. Further, the preset identification strategy can identify whether the category corresponding to the target point cloud set is a stockpile or a mine card according to the related information (for example, the gravity center position) of the two-dimensional grid map.
Step S104 is followed by step S106 of determining a target excavation point of the stockpile and a target loading point of the mine card.
It will be understood that the target excavation point is the location at which the excavator excavates the stockpile. The target loading point is the position where the excavator loads the material on the mine card after the excavating action.
Specifically, the processor may determine the target excavation point of the stockpile and the target loading point of the mine card, respectively, based on a preset target excavation point determination algorithm and a target loading point determination algorithm.
And step S108, excavating the stockpile according to the target excavating point.
Specifically, the processor may control the working device of the excavator to excavate the target excavation point of the material pile after determining the target excavation point.
And step S110, unloading the excavated materials to the mine card according to the target loading point.
Specifically, the processor, after determining the target loading point, may control a work implement of the excavator to unload excavated material onto the mine card based on the target loading point.
According to the control method for the excavator, the point cloud data of the target area is obtained and processed to identify the object to be identified in the target area, so that the target excavation point of the material pile and the target loading point of the ore card are determined, the material pile is excavated according to the target excavation point and the excavated material is unloaded onto the ore card according to the target loading point. According to the method, the excavator does not need to be supervised and controlled by field personnel to carry out material digging and discharging actions, the identification of the object to be identified in the target area is realized by acquiring the point cloud data of the target area, so that the positions of the material pile and the mine card are accurately determined, automatic path planning and automatic operation planning can be realized, the accurate positioning of the digging working position and the unloading working position of the excavator can be realized by determining the target digging point of the material pile and the target loading point of the mine card, the working efficiency of the excavator can be improved by carrying out operation according to the target digging point and the target loading point, the automation degree of the excavator operation is improved, the working effectiveness of the excavator is ensured, and the production efficiency is further improved.
In one embodiment, performing a cluster segmentation process on the three-dimensional point cloud map to obtain a processed three-dimensional point cloud map includes: performing ground segmentation processing on the three-dimensional point cloud map to obtain a first point cloud map, wherein the first point cloud map does not comprise the ground; clustering the first point cloud map to obtain a second point cloud map, wherein the second point cloud map comprises a plurality of categories of point cloud sets; and carrying out segmentation processing on the second point cloud map to obtain a processed three-dimensional point cloud map.
It is to be understood that the ground segmentation process is used to segment ground point cloud data in a three-dimensional point cloud map, the first point cloud map being a three-dimensional point cloud map that does not include ground point cloud data.
Specifically, the processor may perform ground segmentation on the three-dimensional point cloud map to remove the ground, so as to obtain a first point cloud map that does not include the ground, and further perform clustering on the first point cloud map to obtain a second point cloud map that includes multiple categories of point cloud sets, where each category of point cloud set may have a tag, for example, the second point cloud map may include point cloud sets of multiple categories of tags such as stockpiles, mine cards, trees, and sundries, so as to perform segmentation on the second point cloud map to remove point cloud sets that are not to-be-identified objects (including stockpiles and mine cards), so as to obtain a processed three-dimensional point cloud map, and the processed three-dimensional point cloud map includes a target point cloud set of a category corresponding to the to-be-identified object.
In the embodiment of the invention, the ground is removed by ground segmentation, then clustering is carried out to realize the classification of point cloud data except the ground, then segmentation is carried out, a point cloud data set comprising a stockpile and a mine card can be obtained, and the identification efficiency and accuracy of the object to be identified can be improved.
Further, in an embodiment, performing ground segmentation on the three-dimensional point cloud map to obtain the first point cloud map may include obtaining a height value of the point cloud, and removing the point cloud data with the height value smaller than a preset threshold, that is, removing the ground point cloud data, thereby implementing the ground segmentation. By comparing the high-degree values, ground segmentation processing can be rapidly achieved, and recognition efficiency is improved.
In one embodiment, the segmentation processing is performed on the second point cloud map to obtain a processed three-dimensional point cloud map, and the segmentation processing comprises the following steps: determining the number of point clouds in each point cloud set in the second point cloud map; and removing the point cloud sets with the point cloud number less than the preset number threshold value to obtain the processed three-dimensional point cloud map.
It can be understood that the preset number threshold is a reference threshold of the number of point clouds in a preset point cloud set, and only the point cloud set reaching the preset number threshold corresponds to a stockpile or a mine card.
It can be understood that the processor may determine the number of point clouds in each point cloud set in the second point cloud map, compare the number of point clouds with a preset number threshold, and remove point cloud sets whose number of point clouds is less than the preset number threshold, thereby obtaining a three-dimensional point cloud map including a target point cloud set of a category corresponding to an object to be identified.
In the embodiment of the invention, the point cloud set of the objects which are not to be identified can be removed by comparing the number of the point clouds, the identification efficiency of the objects to be identified is improved, and the identification time is shortened.
In one embodiment, based on a preset identification strategy, identifying a grid in which a target point cloud set is located in a two-dimensional grid map to identify an object to be identified includes: determining a grid height value corresponding to each grid in the two-dimensional grid map, wherein the grid height value is the maximum height value in the point cloud data in the grids; determining related information of the grid height value of a grid where each target point cloud set is located in the two-dimensional grid map, wherein the related information comprises a dispersion degree parameter and a mean value; under the condition that the dispersion degree parameter is smaller than a preset dispersion degree threshold value and the mean value is larger than a preset mean value, identifying a mine card corresponding to a grid where the target point cloud set is located; and under the condition that the dispersion degree parameter is greater than or equal to a preset dispersion degree threshold value and/or the mean value is less than or equal to a preset mean value, identifying the stockpile corresponding to the grid where the target point cloud set is located.
It is to be understood that the information related to the grid height values may include a degree of dispersion parameter and a mean value, wherein the degree of dispersion parameter is information of the degree of dispersion characterizing the grid height values of a plurality of grids, and a specific degree of dispersion parameter may include, but is not limited to, variance or standard deviation, etc. The preset discrete degree threshold is a preset discrete degree parameter threshold. The preset average value is a preset average value threshold value representing grid height values of a plurality of grids.
Specifically, the processor may determine a maximum height value of point cloud data in each grid in the two-dimensional grid map, determine the maximum height value as a grid height value corresponding to the grid, determine relevant information (including a dispersion degree parameter and a mean value) of the grid height values of the grids covered by each target point cloud set, further compare the dispersion degree parameter with a preset dispersion degree threshold value, and compare the mean value with a preset mean value, if the dispersion degree parameter is smaller than the preset dispersion degree threshold value and the mean value is greater than the preset mean value, the processor identifies that the grid where the target point cloud set is located corresponds to a mine card, otherwise, the processor identifies that the grid where the target point cloud set is located is a stockpile.
In the embodiment of the invention, the grid height value of each grid in the two-dimensional grid map is determined, the dispersion degree parameter and the mean value of the grid height value of the grid where the target point cloud set is located are compared, and the dispersion degree parameter and the mean value are respectively compared with the preset dispersion degree threshold value and the preset mean value, so that whether the target point cloud set corresponds to a mine card or a stockpile is judged, the identification accuracy of the object to be identified can be improved, the identification rate is accelerated, and the identification efficiency is improved.
In one embodiment, processing point cloud data to identify an object to be identified in a target area includes: establishing a three-dimensional point cloud map according to the point cloud data; and segmenting the three-dimensional point cloud map based on a deep learning point cloud segmentation algorithm to identify the object to be identified.
Specifically, after the processor obtains the point cloud data of the target area, a corresponding three-dimensional point cloud map can be established according to the point cloud data, and the three-dimensional point cloud map can be segmented through a deep learning point cloud segmentation algorithm, for example, the deep learning point cloud segmentation algorithm can be PointNet, voxelNet and the like, the deep learning point cloud segmentation algorithm can directly segment the stockpile and the mine card from the three-dimensional point cloud map, the identification precision of the object to be identified is improved, the error rate of segmentation of the three-dimensional point cloud map is greatly reduced, the object to be identified can be more accurately segmented from the three-dimensional point cloud map, and the purpose of accurately identifying the stockpile and the mine card is achieved. Further, the specific process of establishing the three-dimensional point cloud map according to the point cloud data is as described in the above embodiments, and is not described herein again.
In one embodiment, determining a target excavation point for a stockpile and a target loading point for a mine card comprises: establishing a stockpile three-dimensional geometric model corresponding to the stockpile according to the point cloud data corresponding to the stockpile; establishing a three-dimensional geometric model of the ore cards corresponding to the material pile according to the point cloud data corresponding to the ore cards; respectively carrying out gridding processing on the three-dimensional geometric model of the material pile and the three-dimensional geometric model of the ore card to obtain a plurality of first regular geometric bodies corresponding to the three-dimensional geometric model of the material pile and a plurality of second regular geometric bodies corresponding to the three-dimensional geometric model of the ore card; determining the central point of the first regular geometric body as a target digging point of the material pile; and determining a target loading point of the mine card according to the central point of the second regular geometric body.
It is understood that the three-dimensional geometric model of the material pile is a circumscribed regular geometric body, such as a cube, including the point cloud set where the material pile is located, and the three-dimensional geometric model of the mine card is a circumscribed regular geometric body, such as a cube, including the point cloud set corresponding to the mine card.
Specifically, the processor may establish a three-dimensional geometric model of the material pile corresponding to the material pile according to the point cloud data corresponding to the material pile, establish a three-dimensional geometric model of the ore card corresponding to the material pile according to the point cloud data corresponding to the ore card, perform meshing processing on the three-dimensional geometric model of the material pile and the three-dimensional geometric model of the ore card respectively, divide the three-dimensional geometric model of the material pile and the three-dimensional geometric model of the ore card into a plurality of first regular geometric bodies and a plurality of second regular geometric bodies respectively, determine a center point coordinate of the first regular geometric body and a center point coordinate of the second regular geometric body, determine the center point coordinate of the first regular geometric body as a target excavation point of the material pile, and determine a target loading point of the ore card according to the center point coordinate of the second regular geometric body.
In one embodiment, determining the target loading point of the mine card from the center point of the second regular geometry comprises: determining a loading area of the mine card; and determining the central point of the second irregular geometric body corresponding to the loading area as a target loading point of the mine card.
It will be appreciated that the loading area of the mine card is the area of the mine card used to load material dug by the excavator.
Specifically, the processor may determine a loading area of the mine card, and the specific method for determining the loading area may determine a second regular geometric body, as the loading area, where the height value is above a preset height threshold and the second regular geometric body does not include the point cloud data or includes the point cloud data in an amount smaller than a smaller threshold, and determine a central point of the second regular geometric body corresponding to the loading area as a target loading point of the mine card.
In one embodiment, the control method for an excavator further includes: and determining the central point with the highest height in the central points of the first regular geometric bodies as an initial target digging point of the stockpile.
It can be understood that the central point with the maximum height among the central points of the plurality of first regular geometric bodies is determined and is used as the initial target digging point of the material pile, so that the excavator starts to dig from the position where the material pile is highest, regular material digging can be realized, and the digging effect of the excavator is improved.
In one embodiment, the control method for an excavator further includes: and determining the central point which is farthest away from the excavator in the central points of the plurality of second irregular geometric bodies corresponding to the loading area as an initial target loading point of the mine card.
It can be understood that the initial target loading point is the position where loading of materials starts first, the central point which is farthest away from the excavator in the central points of the plurality of second irregular geometric bodies corresponding to the loading area is determined and is used as the initial target loading point of the mine truck, and the materials are unloaded from the position which is farthest away from the excavator in the loading area, so that unloading is performed regularly, and the working efficiency of the excavator is improved.
In other embodiments, the processor may also determine a central point of the second irregular geometric bodies corresponding to the loading area, which has the highest value and is located at the leftmost position or the rightmost position, as the initial target loading point of the mine card.
In one embodiment, digging the stockpile according to the target digging point comprises: and excavating the stockpile according to the target excavation point based on a preset excavation strategy.
It can be understood that the preset excavation strategy is a preset strategy for excavating the material pile by the excavator, for example, excavating from left to right and/or from top to bottom according to the position of the target excavation point, and the like.
Specifically, the processor may excavate the stockpile from left to right and from top to bottom in order of the position of the target excavation point based on a preset excavation strategy (e.g., from left to right and from top to bottom).
In the embodiment of the invention, the excavator can work more efficiently by setting the corresponding excavation strategy, and the efficiency of excavation operation is further improved.
In one embodiment, unloading excavated material onto a mine card according to a target loading point includes: and unloading the excavated materials to the mine card according to the target loading point based on a preset unloading strategy.
It can be understood that the preset unloading strategy is a preset strategy for unloading the material pile by the excavator, for example, unloading is performed from left to right and/or from top to bottom according to the position of the target loading point, and the like.
Specifically, the processor may unload the material in a left-to-right and top-to-bottom order of the location of the target loading point based on a preset unloading strategy (e.g., left-to-right and top-to-bottom).
In the embodiment of the invention, the excavator can work more efficiently by setting the corresponding unloading strategy, and the efficiency of the excavating operation is further improved.
In one embodiment, acquiring point cloud data of a target area includes: the method comprises the steps of obtaining point cloud data of a target area through at least one of a laser radar, a global navigation satellite system and an information network system.
The point cloud data of the target area obtained by any one or combination of multiple modes of the laser radar, the global navigation satellite system and the information network system can be obtained by the processor, the positioning data obtained by the global navigation satellite system and/or the information network system can be used for increasing the precision and positioning functions, and when the point cloud data of the target area is obtained by combination of multiple modes, the point cloud data obtained by multiple modes can be fused by an algorithm so as to accurately position the excavating working position and the unloading working position of the excavator, so that the image building efficiency is improved, and the working effectiveness of the excavator is ensured.
In a specific embodiment, a control method for an excavator is provided, which includes the following specific steps:
(1) A laser radar is deployed in the upper front of the excavator, a GNSS (Global Navigation Satellite System) and/or an INS (Information Network System) is deployed at the tail, and a vehicle-mounted computer is deployed in the cab, and can be used as a hardware condition for realizing work area positioning of the excavator, which is specifically shown in fig. 3.
(2) The method comprises the following steps that the excavator fuses GNSS/INS data through laser SLAM to establish a three-dimensional point cloud map (namely a three-dimensional environment map), and a point cloud data processing algorithm is adopted in the three-dimensional point cloud map to identify a working object mine card and a soil pile, and specifically comprises the following steps:
(1) collecting front point cloud data;
(2) establishing a three-dimensional point cloud map according to the point cloud data;
(3) removing the ground (namely, dividing the ground), then clustering, dividing the classes with less point cloud number to obtain point cloud sets of two classes of stockpiles and mine cards, and converting the three-dimensional point cloud map into a two-dimensional grid map;
(4) and identifying the two objects and marking the positions in the map by means of a classification strategy.
Specifically, as shown in fig. 4, the specific steps of identifying the object to be identified may be: converting the three-dimensional point cloud map into a two-dimensional grid map, taking the maximum point cloud height value in each grid as a height value corresponding to the grid, calculating the variance and the mean value of the grid height values of the grids corresponding to each cluster (namely, each category of point cloud set), and identifying the cluster as a mine card if the mean value of the height values is greater than a height threshold value and the variance of the height values is less than a variance threshold value, otherwise, identifying the cluster as a soil heap (namely a stock heap).
(3) And establishing a three-dimensional geometric model of the object to be recognized after the object to be recognized is recognized, and gridding the three-dimensional geometric model, and extracting a target excavation point and a target loading point from the three-dimensional geometric model.
Specifically, the extraction step for the target mining point may be as follows: firstly, fitting three-dimensional point cloud information of a soil heap environment by using a three-dimensional reconstruction method according to soil heap point cloud data acquired by a laser radar; then, a segmentation algorithm is used for segmenting a soil heap point cloud part from the three-dimensional point cloud, and a three-dimensional geometric model (for example, the shape of the three-dimensional geometric model is a cube) is established; finally, gridding a plurality of small cubes on a three-dimensional geometric model of the soil pile, recording coordinates of the center points of the small cubes in real time, and outputting the center coordinates of the cubes with the highest height as an initial excavation target point; and then, the mining target points are sequentially ranked from left to right and from top to bottom to serve as the subsequent mining target points.
The extraction procedure for the target loading point may be as follows: firstly, after collecting point cloud data of a mine truck by using a laser radar, fitting three-dimensional point cloud information of a mine truck body by using a three-dimensional reconstruction method; then, a point cloud part of the mine card is separated by utilizing a segmentation algorithm, and a three-dimensional geometric model (for example, the shape of the model is a cube) is established; finally, capturing point clouds in the loading area on a three-dimensional geometric model of the mine card, grid-connecting a plurality of small cubes, recording the coordinates of the center points of the small cubes in real time, and outputting the center coordinates of the cube with the highest height and the leftmost side as an initial loading target point; then, the loading points are sequentially ordered from left to right and from top to bottom to serve as the subsequent loading target points.
In the embodiment of the invention, the environmental perception around the excavator is carried out by carrying the laser radar and/or the global navigation satellite system and/or the information network system on the excavator, wherein the data of the point cloud collected by the radar can be used for environment mapping and work object identification, the data of the global navigation satellite system and/or the information network system can be used for increasing the precision and positioning functions, the accurate positioning of the work position and the unloading work position of the excavator can be realized by processing the fusion data through an algorithm, the mapping efficiency is improved, and the working effectiveness of the excavator is ensured; the grid of the sensed map and the work object can support the realization of automatic path planning and automatic operation planning.
An embodiment of the present invention provides a processor configured to execute the control method for an excavator according to the above embodiments.
An embodiment of the present invention provides a control device for an excavator, including: the point cloud data acquisition equipment is used for acquiring point cloud data of a target area; and a processor configured to: acquiring point cloud data of a target area; processing the point cloud data to identify an object to be identified in a target area, wherein the object to be identified comprises a stockpile and a mine card; determining a target excavation point of the material pile and a target loading point of the mine card; excavating the material pile according to the target excavation point; and unloading the excavated materials to the mine card according to the target loading point.
According to the technical scheme, the point cloud data of the target area are obtained through the point cloud data acquisition equipment, the point cloud data are processed by the processor to identify the object to be identified in the target area, so that the target excavation point of the material pile and the target loading point of the ore card are determined, the material pile is excavated according to the target excavation point, and the excavated material is unloaded onto the ore card according to the target loading point. According to the method, the excavator does not need to be supervised and controlled by field personnel to carry out material digging and discharging actions, the identification of the object to be identified in the target area is realized by acquiring the point cloud data of the target area, so that the positions of the material pile and the mine card are accurately determined, automatic path planning and automatic operation planning can be realized, the accurate positioning of the digging working position and the unloading working position of the excavator can be realized by determining the target digging point of the material pile and the target loading point of the mine card, the working efficiency of the excavator can be improved by carrying out operation according to the target digging point and the target loading point, the automation degree of the excavator operation is improved, the working effectiveness of the excavator is ensured, and the production efficiency is further improved.
In one embodiment, the point cloud data acquisition device comprises at least one of: laser radar, global navigation satellite systems, and information network systems.
An embodiment of the present invention provides an excavator, including: the control device for an excavator according to the above embodiments.
An embodiment of the present invention provides a machine-readable storage medium having instructions stored thereon, which, when executed by a processor, cause the processor to execute the control method for an excavator according to the above-described embodiment.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising one of 8230; \8230;" 8230; "does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (17)
1. A control method for an excavator, comprising:
acquiring point cloud data of a target area;
processing the point cloud data to identify an object to be identified in the target area, wherein the object to be identified comprises a stockpile and a mine card;
determining a target excavation point of the material pile and a target loading point of the mine card;
excavating the material pile according to the target excavation point;
and unloading the excavated materials to the mine card according to the target loading point.
2. The control method according to claim 1, wherein the processing the point cloud data to identify an object to be identified of the target area comprises:
establishing a three-dimensional point cloud map according to the point cloud data;
performing clustering segmentation processing on the three-dimensional point cloud map to obtain a processed three-dimensional point cloud map, wherein the processed three-dimensional point cloud map comprises a target point cloud set of a corresponding category of the object to be identified;
converting the processed three-dimensional point cloud map into a two-dimensional grid map;
and identifying the grid where the target point cloud set is located in the two-dimensional grid map based on a preset identification strategy so as to identify the object to be identified.
3. The control method according to claim 2, wherein the performing cluster segmentation processing on the three-dimensional point cloud map to obtain a processed three-dimensional point cloud map comprises:
performing ground segmentation processing on the three-dimensional point cloud map to obtain a first point cloud map, wherein the first point cloud map does not include the ground;
clustering the first point cloud map to obtain a second point cloud map, wherein the second point cloud map comprises a plurality of categories of point cloud sets;
and carrying out segmentation processing on the second point cloud map to obtain the processed three-dimensional point cloud map.
4. The control method according to claim 3, wherein the segmenting the second point cloud map to obtain the processed three-dimensional point cloud map comprises:
determining the number of point clouds in each point cloud set in the second point cloud map;
and removing the point cloud sets of which the point cloud number is less than a preset number threshold value to obtain the processed three-dimensional point cloud map.
5. The control method according to claim 2, wherein the identifying a grid in the two-dimensional grid map, where the target point cloud is located, based on a preset identification strategy to identify the object to be identified comprises:
determining a grid height value corresponding to each grid in the two-dimensional grid map, wherein the grid height value is the maximum height value in the point cloud data in the grid;
determining related information of the grid height value of the grid where each target point cloud set is located in the two-dimensional grid map, wherein the related information comprises a dispersion degree parameter and a mean value;
under the condition that the dispersion degree parameter is smaller than a preset dispersion degree threshold value and the mean value is larger than a preset mean value, identifying that the grid where the target point cloud set is located corresponds to the mine card;
and under the condition that the dispersion degree parameter is greater than or equal to the preset dispersion degree threshold value and/or the mean value is less than or equal to the preset mean value, identifying that the grid where the target point cloud set is located corresponds to the stockpile.
6. The control method according to claim 1, wherein the processing the point cloud data to identify an object to be identified of the target area comprises:
establishing a three-dimensional point cloud map according to the point cloud data;
and partitioning the three-dimensional point cloud map based on a deep learning point cloud partitioning algorithm so as to identify the object to be identified.
7. The control method of claim 1, wherein the determining a target excavation point of the stockpile and a target loading point of the mine card comprises:
establishing a stockpile three-dimensional geometric model corresponding to the stockpile according to the point cloud data corresponding to the stockpile;
establishing a three-dimensional geometric model of the ore cards corresponding to the material pile according to the point cloud data corresponding to the ore cards;
respectively carrying out gridding processing on the three-dimensional geometric model of the material pile and the three-dimensional geometric model of the ore card to obtain a plurality of first regular geometric bodies corresponding to the three-dimensional geometric model of the material pile and a plurality of second regular geometric bodies corresponding to the three-dimensional geometric model of the ore card;
determining a central point of the first regular geometric body as a target digging point of the material pile;
and determining a target loading point of the mine card according to the central point of the second regular geometric body.
8. The control method of claim 7, wherein said determining a target loading point of the mine card from the center point of the second regular geometry comprises:
determining a loading area of the mine card;
and determining the central point of the second irregular geometric body corresponding to the loading area as a target loading point of the mine card.
9. The control method according to claim 7, characterized by further comprising:
and determining the central point with the maximum height in the central points of the first regular geometric bodies as an initial target digging point of the stockpile.
10. The control method according to claim 8, characterized by further comprising:
and determining a central point which is farthest from an excavator in central points of a plurality of second irregular geometric bodies corresponding to the loading area as an initial target loading point of the mine card.
11. The control method according to claim 1, wherein the excavating the stockpile according to the target excavation point includes:
digging the material pile according to the target digging point based on a preset digging strategy;
the unloading of excavated material onto the mine card according to the target loading point comprises:
and unloading the excavated material onto the mine card according to the target loading point based on a preset unloading strategy.
12. The control method according to claim 1, wherein the acquiring point cloud data of the target area comprises:
and acquiring point cloud data of the target area by at least one of a laser radar, a global navigation satellite system and an information network system.
13. A processor characterized by being configured to execute the control method for an excavator according to any one of claims 1 to 12.
14. A control apparatus for an excavator, comprising:
the point cloud data acquisition equipment is used for acquiring point cloud data of a target area; and
the processor of claim 13.
15. The control apparatus of claim 14, wherein the point cloud data collection device comprises at least one of:
lidar, global navigation satellite systems, and information network systems.
16. An excavator, comprising:
the control device for an excavator according to claim 14.
17. A machine-readable storage medium having instructions stored thereon, which when executed by a processor causes the processor to perform the control method for an excavator according to any one of claims 1 to 12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210573667.5A CN115142513B (en) | 2022-05-25 | 2022-05-25 | Control method and device for excavator, processor and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210573667.5A CN115142513B (en) | 2022-05-25 | 2022-05-25 | Control method and device for excavator, processor and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115142513A true CN115142513A (en) | 2022-10-04 |
| CN115142513B CN115142513B (en) | 2024-05-07 |
Family
ID=83406240
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210573667.5A Active CN115142513B (en) | 2022-05-25 | 2022-05-25 | Control method and device for excavator, processor and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115142513B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115328171A (en) * | 2022-10-11 | 2022-11-11 | 青岛慧拓智能机器有限公司 | Method, device, chip, terminal, equipment and medium for generating position of loading point |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE19730233A1 (en) * | 1997-07-15 | 1999-01-21 | M S C Mes Sensor Und Computert | Automated excavator control for producing flat surfaces by removing excavated material |
| CN103362172A (en) * | 2012-03-29 | 2013-10-23 | 哈尼施费格尔技术公司 | Collision detection and mitigation systems and methods for excavator |
| CN109034201A (en) * | 2018-06-26 | 2018-12-18 | 阿里巴巴集团控股有限公司 | Model training and rule digging method and system |
| US10329740B2 (en) * | 2017-01-18 | 2019-06-25 | Novatron Oy | Earth moving machine, range finder arrangement and method for 3D scanning |
| CN114164877A (en) * | 2021-11-09 | 2022-03-11 | 中联重科土方机械有限公司 | Method for loading material, controller and excavating equipment |
| CN114186008A (en) * | 2021-12-09 | 2022-03-15 | 广西柳工机械股份有限公司 | Unmanned-operation material pile digging method, device, equipment and storage medium |
-
2022
- 2022-05-25 CN CN202210573667.5A patent/CN115142513B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE19730233A1 (en) * | 1997-07-15 | 1999-01-21 | M S C Mes Sensor Und Computert | Automated excavator control for producing flat surfaces by removing excavated material |
| CN103362172A (en) * | 2012-03-29 | 2013-10-23 | 哈尼施费格尔技术公司 | Collision detection and mitigation systems and methods for excavator |
| CN104302848A (en) * | 2012-03-29 | 2015-01-21 | 哈尼施费格尔技术公司 | Overhead view system for shovel |
| US10329740B2 (en) * | 2017-01-18 | 2019-06-25 | Novatron Oy | Earth moving machine, range finder arrangement and method for 3D scanning |
| CN109034201A (en) * | 2018-06-26 | 2018-12-18 | 阿里巴巴集团控股有限公司 | Model training and rule digging method and system |
| CN114164877A (en) * | 2021-11-09 | 2022-03-11 | 中联重科土方机械有限公司 | Method for loading material, controller and excavating equipment |
| CN114186008A (en) * | 2021-12-09 | 2022-03-15 | 广西柳工机械股份有限公司 | Unmanned-operation material pile digging method, device, equipment and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115328171A (en) * | 2022-10-11 | 2022-11-11 | 青岛慧拓智能机器有限公司 | Method, device, chip, terminal, equipment and medium for generating position of loading point |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115142513B (en) | 2024-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11494930B2 (en) | Techniques for volumetric estimation | |
| CN112526993B (en) | Grid map updating method, device, robot and storage medium | |
| CN109902857B (en) | Automatic planning method and system for loading point of transport vehicle | |
| US10198632B2 (en) | Survey data processing device, survey data processing method, and survey data processing program | |
| CN114359494A (en) | Mining area three-dimensional map collecting and updating method and system | |
| CN115375866B (en) | Method, device, equipment and medium for updating three-dimensional geological model of mining area | |
| McKinnon et al. | Automatic identification of large fragments in a pile of broken rock using a time-of-flight camera | |
| CN115142513B (en) | Control method and device for excavator, processor and storage medium | |
| Badenko et al. | Algorithms of laser scanner data processing for ground surface reconstruction | |
| CN115164868A (en) | Robot positioning method, device, robot and storage medium | |
| CN113985873A (en) | Planning method for shovel points of autonomous digging operation of loader | |
| US20230182743A1 (en) | Method and system for extracting road data and method and system for controlling self-driving car | |
| CN114022760B (en) | Railway tunnel barrier monitoring and early warning method, system, equipment and storage medium | |
| CN116012613B (en) | Method and system for measuring and calculating earthwork variation of strip mine based on laser point cloud | |
| CN116340307B (en) | Ramp layer generation method and device, high-precision map and electronic equipment | |
| CN117292081A (en) | Storage yard volume calculation method based on three-dimensional reconstruction and terminal equipment | |
| CN114445590A (en) | Method and device for engineering equipment, processor and engineering equipment | |
| Bliznyuk et al. | Living Earth—A Methodology for Modeling the Environment of Construction Sites Via Digital Twins | |
| CN116679315A (en) | Method and device for detecting operation terrain and engineering equipment for detecting operation terrain | |
| Finkbeiner et al. | Shape recognition of material heaps in outdoor environments and optimal excavation planning | |
| Balamurali et al. | Better Predict the Dynamic of Geometry of In-Pit Stockpiles Using Geospatial Data and Polygon Models | |
| CN117197398B (en) | Statistical method, device, equipment and storage medium of mine resource model | |
| CN117636287B (en) | Method for collecting and processing high-precision map of open-air mining area based on crowdsourcing | |
| CN117419704A (en) | Map area updating method and system for surface mine loading area | |
| US20240218635A1 (en) | Method for determining location and orientation of earthworks machine in worksite |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |