CN117387633A - Path planning method for unmanned excavator, electronic equipment and medium - Google Patents
Path planning method for unmanned excavator, electronic equipment and medium Download PDFInfo
- Publication number
- CN117387633A CN117387633A CN202311705307.7A CN202311705307A CN117387633A CN 117387633 A CN117387633 A CN 117387633A CN 202311705307 A CN202311705307 A CN 202311705307A CN 117387633 A CN117387633 A CN 117387633A
- Authority
- CN
- China
- Prior art keywords
- node
- expansion
- random
- nodes
- path
- 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 44
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 60
- 238000001514 detection method Methods 0.000 claims abstract description 53
- 230000033001 locomotion Effects 0.000 claims abstract description 26
- 238000005457 optimization Methods 0.000 claims abstract description 7
- 238000005070 sampling Methods 0.000 claims description 58
- 230000002457 bidirectional effect Effects 0.000 claims description 21
- 238000013138 pruning Methods 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 15
- 230000004888 barrier function Effects 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 7
- 238000009499 grossing Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 230000007704 transition Effects 0.000 abstract description 5
- 238000001914 filtration Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000002146 bilateral effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Operation Control Of Excavators (AREA)
Abstract
The application relates to the technical field of path planning, in particular to a path planning method, electronic equipment and medium of an unmanned excavator, which comprise the following steps: acquiring information of a starting point, a target point and an obstacle of the unmanned excavator and a local environment image; and then based on a preset dynamic step strategy, a preset target deviation strategy and a preset unmanned excavator motion collision detection strategy, expanding the two random tree nodes to obtain expansion nodes corresponding to the two random trees, then based on a preset unmanned excavator motion constraint strategy and a minimum path cost strategy, reselecting father nodes and rewiring the expansion nodes corresponding to the two random trees, and finally obtaining a first moving path and performing path optimization when a random tree algorithm meets a termination condition to obtain a final moving path of the unmanned excavator. Therefore, the number of the finally generated path nodes is small, the convergence efficiency of the algorithm is greatly improved, the rationality of the path is ensured, and the transition is smoother.
Description
Technical Field
The present invention relates to the field of path planning technologies, and in particular, to a path planning method, an electronic device, and a medium for an unmanned excavator.
Background
The navigation system of the unmanned excavator is a foundation for supporting the unmanned excavator to efficiently complete various tasks, and the key technology of the navigation system is path planning. In a complex space, the unmanned excavator detects the surrounding environment by utilizing a sensor of the unmanned excavator, and environment map information is constructed. The path planning of the unmanned excavator is a key link in the field of unmanned excavators, and the final purpose is to find an unobstructed path from a starting point to a target point, and on the basis, the time spent is as little as possible, and the path traversed is as short as possible.
The Bi-RRT algorithm is an algorithm that is improved on the basis of the RRT algorithm. The algorithm generates two trees at the starting point and the ending point simultaneously, and utilizes the information of the two trees to improve the quality of the path. When the two trees meet at a node, the algorithm will return a path that connects the start and end points. The Bi-RRT algorithm can find a feasible path faster than the RRT algorithm, which has a faster search speed because it starts searching from both the start point and the target point, avoiding searching a large number of useless areas. However, the Bi-RRT algorithm lacks guidance of environmental information, and has the problems of more generated nodes, more tortuous paths and overlarge steering angles, so that the path planning quality is low, and rapid convergence cannot be realized.
Disclosure of Invention
In view of the above problems, the present application provides a path planning method, an electronic device and a medium for an unmanned excavator, and in order to improve the planning efficiency of an algorithm and the quality of a generated path, an improved RRT algorithm is provided based on a Bi-RRT algorithm, and the algorithm introduces a dynamic step size, a bidirectional target bias, a maximum corner limit and path track optimization, so as to ensure the probability completeness of random sampling and have a certain target directionality. When expanding to the target point, the method can escape from the trap area by utilizing a dynamic step bidirectional deflection expanding mode, and can pass through an outlet and a narrow channel more smoothly, so that the convergence efficiency of an algorithm is improved, the maximum corner limit is added to ensure the rationality of a steering angle, the path is more reasonable, the quality of the path is further improved after the path track is optimized, the number of the finally generated path nodes is less, and the transition is smoother.
In a first aspect, an embodiment of the present application provides a path planning method for an unmanned excavator, including:
acquiring a starting point, a target point, barrier information and a local environment image of the unmanned excavator;
Based on a preset dynamic step strategy, a preset target deflection strategy and a preset unmanned excavator motion collision detection strategy, adopting a bidirectional rapid expansion random tree algorithm to alternately expand two random tree nodes to obtain expansion nodes corresponding to the two random trees;
based on a preset unmanned excavator motion constraint strategy and a minimum path cost strategy, a father node is reselected for expansion nodes corresponding to the two random trees, and the two updated random trees are obtained through rerouting;
responding to the fact that the distance between corresponding expansion nodes obtained by the two random trees is smaller than a set value, and communicating the two random trees to obtain a first moving path of the unmanned excavator;
pruning optimization processing is carried out on the first moving path based on a preset path pruning algorithm to obtain a second moving path of the unmanned excavator;
and performing smoothing treatment on the second moving path to obtain a final moving path of the unmanned excavator.
In one possible implementation manner, based on a preset dynamic step strategy, a preset target deviation strategy and a preset unmanned excavator motion collision detection strategy, two random tree nodes are alternately expanded by adopting a bidirectional rapid expansion random tree algorithm to obtain expansion nodes corresponding to two random trees, and the method comprises the following steps:
Respectively taking the starting point position and the target point position as root nodes of two random trees, and respectively carrying out node expansion from the root nodes of the two random trees by utilizing random sampling to obtain random sampling points corresponding to the two random trees;
acquiring two nearest nodes on the two random trees, which are corresponding to the two random sampling points, and alternately generating corresponding expansion nodes of the two random trees based on a preset dynamic step strategy, a preset target deviation strategy and a preset unmanned excavator motion collision detection strategy, wherein for any random tree, the method comprises the following steps:
s1: according to the direction from the nearest node to the random sampling point to the corresponding random sampling point on any random tree, a first expansion node is obtained, wherein the calculation formula of the first expansion node is as follows:wherein (1)>For any expansion node corresponding to the random tree, < ->Random sampling points corresponding to any random tree, < ->For one node closest to the corresponding random sampling point on any random tree, +.>For Euclidean distance between random sampling point and nearest node of corresponding random sampling point, +.>To expand the step length;
opposite nodeAnd->Performing collision detection, and if no collision exists between the first expansion node and the obstacle, adding the first expansion node into a corresponding random tree; if collision exists with the obstacle, adjusting the expansion step length and the target deflection to obtain a second expansion node, wherein the calculation formula of the second expansion node is as follows :Wherein (1)>For any expansion node corresponding to the random tree, < ->Random sampling points corresponding to any random tree, < ->For one node closest to the corresponding random sampling point on any random tree, +.>For any target point corresponding to the random tree, < ->For Euclidean distance between random sampling point and nearest node of corresponding random sampling point, +.>For the Euclidean distance between the target point and the nearest node to the corresponding random sampling point, +.>Nearest node to the corresponding random sampling point +.>To random sampling point->Step length of direction expansion, step length of direction expansion>Nearest node to the corresponding random sampling point +.>To the target point->The expansion step length of the direction,；
s2: opposite nodeAnd->Performing collision detection, and if no collision exists between the second expansion node and the obstacle, adding the second expansion node into a corresponding random tree; if collision with obstacle exists, the expansion step length is +.>And->Performing exchange adjustment to obtain a third expansion node, wherein the calculation formula of the third expansion node is as follows:
s3: opposite nodeAnd->Performing collision detection, and if no collision exists between the third expansion node and the obstacle, adding the third expansion node into a corresponding random tree; if collision exists with the obstacle, returning to an empty expansion node of the corresponding random tree.
In one possible implementation of the present invention,the calculation formula of (2) is as follows>Wherein (1)>Is the density index of the obstacle->Wherein->And->Respectively representing the number of barrier pixel points and the total number of pixel points in the binary image obtained by binarizing the acquired local environment image, wherein the gray value of the barrier pixel points is 255,/and/respectively representing the number of barrier pixel points and the total number of pixel points in the binary image obtained by binarizing the acquired local environment image>Indicates the number of collisions with obstacles in collision detection, +.>Representing the total number of collision detections, +.>Is constant. In one possible implementation, the preset unmanned excavator motion collision detection strategy includes:
judging whether an obstacle exists between two nodes or not by judging whether the connection line between the two nodes is intersected with the obstacle or not, and determining that the obstacle exists between the two nodes if the connection line between the two nodes is intersected with the obstacle.
In one possible implementation manner, based on a preset unmanned excavator motion constraint strategy and a minimum path cost strategy, reselecting a parent node from expansion nodes corresponding to two random trees to obtain two updated random trees, including:
acquiring any random tree with expansion nodes as the center and radius as the centerThe parent node set to be selected in the range of (1), wherein the parent node set to be selected does not contain expansion nodes;
Traversing all the father nodes to be selected in the father node set to find the father node which is the father node to be selected and simultaneously meets the requirement that the steering angle formed by the father node to be selected, the father node to be selected and the expansion node is smaller than the maximum steering angle of the unmanned excavator, the connection line between the father node to be selected and the expansion node has no collision with the obstacle, and the father node to be selected with the minimum path cost from the starting point of the unmanned excavator to the expansion node through the father node to be selected is taken as the father node of the expansion node, and if the father node is not found, taking one node which is closest to the corresponding random sampling point on any random tree as the father node of the expansion node;
and adding the path between the father node of the expansion node and the expansion node into the corresponding random tree to update the corresponding random tree.
In one possible implementation, the step of rewiring includes:
acquiring any random tree with expansion nodes as the center and radius as the centerThe set of child nodes to be selected in the range of (a), wherein the set of child nodes to be selected does not contain a parent node of the expansion node;
traversing all the child nodes to be selected in the child node set to find the child node to be selected, which simultaneously satisfies that the steering angle formed by the father node of the expansion node, the expansion node and the child node to be selected is smaller than the maximum steering angle of the unmanned excavator, the connection line between the child node to be selected and the expansion node has no collision with the obstacle, and the path cost from the starting point of the unmanned excavator to the child node to be selected is minimum, and the child node to be selected is used as the child node of the expansion node;
And adding the child nodes of the expansion node, paths among the child nodes of the expansion node and the child nodes of the expansion node into the corresponding random tree to update the corresponding random tree.
In one possible implementation, the path cost is calculated by the formula:
wherein,representing the Euclidean distance between two adjacent connection nodes, Q representing the total number of connections between two adjacent nodes on the path, +.>Index indicating the distance between the path and the obstacle, < >>，/>Represents the distance between the path and the obstacle, < >>Indicating the number of steering of the unmanned excavator on the route, +.>、/>、/>A constant greater than 0.
In one possible implementation, smoothing the second travel path with a cubic B-spline curve results in a final travel path for the unmanned excavator.
In a second aspect, embodiments of the present application provide an electronic device, including a memory and a processor, where the memory stores executable code, and the processor executes the executable code to implement embodiments as possible in the first aspect.
In a third aspect, embodiments of the present application provide a computer-readable storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform the embodiments as possible in the first aspect.
The beneficial effects of this application lie in: the improved RRT algorithm is provided on the basis of Bi-RRT algorithm, the algorithm introduces a dynamic step strategy, a bidirectional target deflection strategy, a maximum rotation angle limiting strategy and a path track optimizing strategy, the expansion step is dynamically adjusted by taking the density and the complexity of the obstacle into consideration through collecting local environment images, meanwhile, the expansion step is dynamically adjusted and the bidirectional target deflection is introduced when a bidirectional rapid expansion random tree algorithm is adopted for expanding nodes, the trap area can be escaped by utilizing the expansion mode of the two dynamic step and the bidirectional deflection when the target point is expanded, the exit and the narrow channel can be more smoothly passed, the convergence efficiency of the algorithm is improved, the rationality of the steering angle is ensured by adding the maximum rotation angle limiting strategy, the path is more reasonable, the quality of the path is further improved after the path track is optimized, the number of finally generated path nodes is less, and the transition is smoother.
Drawings
Fig. 1 is a step flowchart of a path planning method of an unmanned excavator provided in an embodiment of the present application;
FIG. 2 is a schematic view of a random tree node expansion provided in an embodiment of the present application;
FIG. 3 is a schematic diagram of a reselection parent node provided by an embodiment of the present application;
FIG. 4 is a schematic diagram of rewiring provided by an embodiment of the present application;
fig. 5a is a schematic diagram of a path before pruning according to an embodiment of the present application;
fig. 5b is a schematic diagram of a path after pruning the path according to the embodiment of the present application;
fig. 6 is a schematic diagram comparing effects before and after pruning of a path according to an embodiment of the present application;
fig. 7a is a schematic diagram of a path generated by the Bi-RRT algorithm provided in an embodiment of the present application;
fig. 7b is a schematic diagram of a path generated by the modified RRT algorithm provided in an embodiment of the present application;
fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application;
fig. 9 is a block diagram of a computer-readable storage medium according to an embodiment of the present application.
Detailed Description
So that the manner in which the above recited objects, features and advantages of the present application can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to the appended drawings and detailed description, which follow. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application are within the scope of the protection of the present application.
The terminology used in the description section of the present application is for the purpose of describing particular embodiments of the present application only and is not intended to be limiting of the present application. It should be noted that references to "one" or "a plurality" in this application are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be interpreted as "one or more" unless the context clearly indicates otherwise.
Embodiments of the present application are described below with reference to the accompanying drawings. As one of ordinary skill in the art can appreciate, with the development of technology and the appearance of new scenes, the technical solutions provided in the embodiments of the present application are applicable to similar technical problems.
Referring to fig. 1, an embodiment of the application discloses a path planning method for an unmanned excavator, including:
s11, acquiring a starting point, a target point, barrier information and a local environment image of the unmanned excavator;
s12, based on a preset dynamic step strategy, a preset target deviation strategy and a preset unmanned excavator motion collision detection strategy, two random tree nodes are alternately expanded by adopting a bidirectional rapid expansion random tree algorithm to obtain expansion nodes corresponding to the two random trees;
S13, based on a preset unmanned excavator motion constraint strategy and a minimum path cost strategy, reselecting father nodes from expansion nodes corresponding to the two random trees and rewiring to obtain updated two random trees;
s14, responding to the fact that the distance between corresponding expansion nodes obtained by the two random trees is smaller than a set value, and connecting the two random trees to obtain a first moving path of the unmanned excavator;
s15, pruning optimization processing is carried out on the first moving path based on a preset path pruning algorithm to obtain a second moving path of the unmanned excavator;
s16, performing smoothing processing on the second moving path to obtain a final moving path of the unmanned excavator.
It should be noted that, first, the starting point, the target point, the obstacle information and the local environment image of the unmanned excavator are acquired, wherein the local environment image of the unmanned excavator is acquired by the image acquisition device. For example, the image capturing apparatus described above may capture a local environment in which the unmanned excavator travels using a 360 degree industrial camera or the like carried forward on the unmanned excavator, and the image capturing apparatus is not particularly limited herein. After obtaining a local environment image, firstly denoising the acquired image by using filtering treatment to remove most of noise in the image, wherein the filtering treatment algorithm adopts a linear filtering algorithm or a nonlinear filtering algorithm, and the linear filtering algorithm adopts a Gaussian filtering algorithm, a block filtering algorithm or an average filtering algorithm; the nonlinear filtering algorithm adopts median filtering or bilateral filtering, is not particularly limited herein, and is preferably Gaussian filtering in the application; and after the filtering process is completed, performing binarization process to obtain a binary image of the local environment image, wherein the pixel points of the barrier region are 255, and the pixel points of the other regions are 0.
In the steps of the embodiment, firstly, the starting point, the target point and the obstacle information of the unmanned excavator and the local environment image are acquired; and then, based on a preset dynamic step strategy, a preset target deviation strategy and a preset unmanned excavator motion collision detection strategy, adopting a bidirectional rapid expansion random tree algorithm to alternately expand two random tree nodes to obtain expansion nodes corresponding to the two random trees, then, based on a preset unmanned excavator motion constraint strategy and a minimum path cost strategy, reselecting father nodes from the expansion nodes corresponding to the two random trees and rewiring to obtain two updated random trees, and finally, obtaining a first moving path when the random tree algorithm meets a termination condition and carrying out path optimization to obtain a final moving path of the unmanned excavator. According to the embodiment of the application, a dynamic step strategy, a bidirectional target deflection strategy, a maximum rotation angle limiting strategy and a path track optimizing strategy are introduced, the expansion step is dynamically adjusted by taking the density and the complexity of the obstacle into consideration through collecting local environment images, meanwhile, the expansion step is dynamically adjusted and the bidirectional target deflection is introduced when a bidirectional rapid expansion random tree algorithm is adopted to expand nodes, so that when the target points are expanded, a trap area can be escaped by using two dynamic step sizes and a bidirectional deflection expansion mode, an exit and a narrow channel can be more smoothly passed, the convergence efficiency of the algorithm is improved, the reasonability of a steering angle is guaranteed by adding the maximum rotation angle limiting strategy, the path is more reasonable, the quality of the path is further improved after the path track is optimized, the number of finally generated path nodes is less, and the transition is smoother.
In an optional embodiment of the present application, based on a preset dynamic step strategy, a preset target deviation strategy and a preset unmanned excavator motion collision detection strategy, two random tree nodes are alternately expanded by adopting a bidirectional rapid expansion random tree algorithm to obtain expansion nodes corresponding to two random trees, including:
respectively taking the starting point position and the target point position as root nodes of two random trees, and respectively carrying out node expansion from the root nodes of the two random trees by utilizing random sampling to obtain random sampling points corresponding to the two random trees;
acquiring two nearest nodes on the two random trees, which are corresponding to the two random sampling points, and alternately generating corresponding expansion nodes of the two random trees based on a preset dynamic step strategy, a preset target deviation strategy and a preset unmanned excavator motion collision detection strategy, wherein for any random tree, the method comprises the following steps:
s1: according to the direction from the nearest node to the random sampling point to the corresponding random sampling point on any random tree, a first expansion node is obtained, wherein the calculation formula of the first expansion node is as follows:wherein (1)>For any expansion node corresponding to the random tree, < - >Random sampling points corresponding to any random tree, < ->For one node closest to the corresponding random sampling point on any random tree, +.>For Euclidean distance between random sampling point and nearest node of corresponding random sampling point, +.>To expand the step length;
opposite nodeAnd->Performing collision detection, and if no collision exists between the first expansion node and the obstacle, adding the first expansion node into a corresponding random tree; if collision exists with the obstacle, adjusting the expansion step length and the target deflection to obtain a second expansion node, wherein the calculation formula of the second expansion node is: -a> Wherein (1)>For any expansion node corresponding to the random tree, < ->Is any one of followingRandom sampling points corresponding to machine tree, +.>For one node closest to the corresponding random sampling point on any random tree, +.>For any target point corresponding to the random tree, < ->For Euclidean distance between random sampling point and nearest node of corresponding random sampling point, +.>For the euclidean distance between the target point and the one nearest to the corresponding random sampling point,nearest node to the corresponding random sampling point +.>To random sampling point->Step length of direction expansion, step length of direction expansion>Nearest node to the corresponding random sampling point +. >To the target point->Step length of direction expansion, step length of direction expansion>；
S2: opposite nodeAnd->Performing collision detection, and if no collision exists between the second expansion node and the obstacle, adding the second expansion node into a corresponding random tree; if collision with obstacle exists, the expansion step length is +.>And->Performing exchange adjustment to obtain a third expansion node, wherein the calculation formula of the third expansion node is as follows:
s3: opposite nodeAnd->Performing collision detection, and if no collision exists between the third expansion node and the obstacle, adding the third expansion node into a corresponding random tree; if collision exists with the obstacle, returning to an empty expansion node of the corresponding random tree.
Specifically, referring to fig. 2, the embodiment of the present application uses a random treeDescription of generating expansion node for example, first initialize the random tree +.>And is +.>Begin to expand (in the random tree +.>When expanding of (a), the starting point is replaced by. By random meansSampling function Sample () obtains random sampling point +.>By the nearest node function->Obtaining a random tree->Upper distance random sampling point->Nearest node->. Next, generation of a new node is started. Different from Bi-RRT, the improved RRT algorithm adopts a dynamic step length and target deflection method to carry out new node (expansion node)/(expansion node) >The process is as follows:
1) According toTo->According to formula (1-1) to generate a new node +.>Wherein->To expand the step length.
（1-1）
Opposite nodePerforming collision detection, and returning +.>The method comprises the steps of carrying out a first treatment on the surface of the If the collision detection is not satisfied, let->To random sampling point->The step size of the direction is +.>，/>To the target point->The step size of the direction is +.>Wherein->Obtaining a new node ++according to formula (1-2)>
（1-2）
2) New node to be generatedAnd node->Performing collision detection, and returning to the new node if the collision detection is successful. If the collision detection fails, exchanging the two bias expansion step sizes, and generating a new node +_according to the formula (1-3)>。
（1-3）
3) New node to be generatedAnd->Performing collision detection, and returning +.>If failure indicates difficulty in target bias, return a null +.>. The new node is obtained->After that, judge->Whether it is empty or not, if not, re-selecting +.>Is rerouted to the parent node of (a); if->If the tree is empty, the random tree is alternately continued to be +.>Expanding, and continuing to perform the new node according to the generated new random sampling points>And generating. In an alternative embodiment of the present application, the step size is extended +.>The calculation formula of (2) is as follows:
Wherein,is the density index of the obstacle->Wherein->And->Respectively representing the number of barrier pixel points and the total number of pixel points in the binary image obtained by binarizing the acquired local environment image, wherein the gray value of the barrier pixel points is 255,/and/respectively representing the number of barrier pixel points and the total number of pixel points in the binary image obtained by binarizing the acquired local environment image>Indicates the number of collisions with obstacles in collision detection, +.>Representing the total number of collision detections, +.>For a constant, 2-5 are used in the embodiment of the application.
The density index and collision probability of the obstacle are obtained through processing by obtaining the local environment image, the local obstacle complexity of the driving path of the unmanned excavator is represented, real-time dynamic adjustment of the expansion step length on the driving path is carried out according to the local obstacle complexity obtained by the local environment image photographed in real time, the generation quality of the path and the convergence efficiency of an algorithm are improved, and the expansion step length is obtainedIs known from the calculation formula of->The larger the local obstacle complexity, the larger the expansion step size +.>Smaller (less)>The larger the local obstacle complexity is, the greater the +.>The smaller the expansion step size +.>The smaller.
In an alternative embodiment of the present application, a preset unmanned excavator motion collision detection strategy includes: judging whether an obstacle exists between two nodes or not by judging whether the connection line between the two nodes is intersected with the obstacle or not, and determining that the obstacle exists between the two nodes if the connection line between the two nodes is intersected with the obstacle.
It should be noted that, the shape of the obstacle may be a circle or a rectangle, when the collision detection is determined, in the process of expanding the random tree, the edge connected by the two nodes cannot intersect with any edge of the circular obstacle or the rectangular obstacle, if the determination result is that the intersection indicates that the two nodes cannot pass the collision detection, that is, the obstacle exists between the two nodes; the fact that the judgment result is that the two nodes are disjoint means that the two nodes can pass collision detection, namely no obstacle exists between the two nodes.
In an optional embodiment of the present application, based on a preset unmanned excavator motion constraint policy and a minimum path cost policy, reselecting a parent node from expansion nodes corresponding to two random trees to obtain two updated random trees, including:
acquiring any random tree with expansion nodes as the center and radius as the centerThe parent node set to be selected in the range of (1), wherein the parent node set to be selected does not contain expansion nodes;
traversing all the father nodes to be selected in the father node set to find the father node which is the father node to be selected and simultaneously meets the requirement that the steering angle formed by the father node to be selected, the father node to be selected and the expansion node is smaller than the maximum steering angle of the unmanned excavator, the connection line between the father node to be selected and the expansion node has no collision with the obstacle, and the father node to be selected with the minimum path cost from the starting point of the unmanned excavator to the expansion node through the father node to be selected is taken as the father node of the expansion node, and if the father node is not found, taking one node which is closest to the corresponding random sampling point on any random tree as the father node of the expansion node;
And adding the path between the father node of the expansion node and the expansion node into the corresponding random tree to update the corresponding random tree.
Specifically, the embodiment of the application uses a random treeFor purposes of illustration of reselection of a parent node, the improved RRT algorithm of the present application introduces a maximum rotation angle limit to improve reselection of a parent node, as follows:
1) Acquisition nodeSet of parent nodes to be selected within the range of radius r as circle center +.>(do not include->). 2) From the collection->Select->Is->And calculate +.>Is the parent of (a)Node,/->And->The steering angle formed determines whether it is smaller than the maximum steering angle +.>. If not less than->The parent node to be selected is discarded +.>And continue from the collection->Selecting a father node; if less than->Continuing to judge the parent node to be selected +.>And->Whether or not collision detection is enabled. If collision detection is enabled, calculating +.from the origin->Warp->To->And updating the minimum path cost while retaining +.>A new parent node. If collision detection is not passed, continue from the collection +.>A parent node is selected. 3) Repeating step 2) until the set +. >Is traversed, and finally a father node which meets the maximum rotation angle limit and the collision detection condition and has the minimum path cost is found. If not found, will ∈>Set to->Is a parent node of (c).
In an alternative embodiment of the present application, the step of rewiring includes:
acquiring any random tree with expansion nodes as the center and radius as the centerThe set of child nodes to be selected in the range of (a), wherein the set of child nodes to be selected does not contain a parent node of the expansion node;
traversing all the child nodes to be selected in the child node set to find the child node to be selected, which simultaneously satisfies that the steering angle formed by the father node of the expansion node, the expansion node and the child node to be selected is smaller than the maximum steering angle of the unmanned excavator, the connection line between the child node to be selected and the expansion node has no collision with the obstacle, and the path cost from the starting point of the unmanned excavator to the child node to be selected is minimum, and the child node to be selected is used as the child node of the expansion node;
and adding the child nodes of the expansion node, paths among the child nodes of the expansion node and the child nodes of the expansion node into the corresponding random tree to update the corresponding random tree.
The embodiment of the application uses a random treeFor purposes of example and re-routing, the present application improves The RRT algorithm introduces maximum corner limits to improve rerouting, which is done as follows:
1) Acquisition nodeSet of parent nodes to be selected within the range of radius r as circle center +.>(do not include->Parent node +.>). 2) From the collection->Select->Is->And calculate +.>Parent node of +.>And->Whether the steering angle formed is smaller than the maximum steering angle +.>. If not less than->Then from the collection->Selecting new sub-nodes to be selected again; if less than->Judging the sub node to be selected +.>And->Whether or not collision detection is enabled. If collision detection is enabled, calculating +.from the origin->To->And updates the minimum path cost and +.>A new child node; if collision detection is not passed, continue from the collection +.>Selecting new child node to be selected +.>. 3) Repeating the step 2) until the parent node set to be selected is +.>And (5) traversing all the parent nodes to be selected, completing calculation, and updating the random tree.
Referring to FIG. 4, a process of re-routing is illustratively shown in the followingAnd r is the radius of the circle. />Four selectable child nodes are respectively +.>、/>、/>And->Wherein->、/>Is rejected because it does not meet the maximum rotation angle limit, < > >And->Meets the maximum rotation angle limit and will +>After setting as parent node, the path cost is smaller, so will +.>Andset to->Is a child node of (a). The path cost is calculated by the sum of Euclidean distances between two adjacent nodes in the path.
It should be further noted that after expanding the node, reselecting the parent node, and rewiring, a new node is obtainedJudging->And random tree->Whether the shortest distance of the upper node is smaller than the set value, if so, the upper node is +>And->Connecting and returning two random trees; otherwise, alternate pair random tree->Repeating the steps until the two random trees are successfully connected or the upper limit of the iteration times is reached.
In an alternative embodiment of the present application, the calculation formula of the path cost is:
wherein (1)>Representing the Euclidean distance between two adjacent connection nodes, Q representing the total number of connections between two adjacent nodes on the path, +.>Index indicating the distance between the path and the obstacle, < >>，/>Represents the distance between the path and the obstacle, < >>Indicating the number of steering of the unmanned excavator on the route, +.>、/>、/>A constant greater than 0. It should be noted that, in the foregoing embodiment, the straight line distance (euclidean distance) between two nodes may be used as the path cost between two nodes, and in one embodiment of the present application, the path cost may be calculated by comprehensively considering the euclidean distance of the path, the distance between the obstacle and the path, the steering frequency, and the like, so as to ensure the safety and the efficient running of the unmanned excavator running path, and as the above formula indicates, the longer the total euclidean distance of the path, the greater the cost; the larger the distance between the path and the obstacle is, the smaller the cost is; the more times the unmanned excavator turns on the path, the greater the cost.
In an optional embodiment of the present application, pruning optimization is performed on the first moving path based on a preset path pruning algorithm to obtain a second moving path of the unmanned excavator, where the preset path pruning algorithm specifically includes the following steps:
from the start point, collision detection and maximum rotation angle detection are performed to detect whether an obstacle exists between the start point and the third node (counted from the start point), and whether the steering angle after connection is smaller than. If the collision detection and maximum rotation angle limitation conditions are simultaneously met, deleting a second node from the path, and repeating the operation; if the collision detection or maximum rotation angle limitation condition is not satisfied, starting from the second node, the node and the third node (counted from the node) are repeated until the connection to the target point is made, thereby completing the path pruning.
In particular, referring to fig. 5a, a specific operation of the path pruning algorithm is described. From the starting pointInitially, an attempt is made to connect the third node +.>And performing collision detection and maximum rotation angle detection. Due to->And->There is an obstacle in between and the connection fails. Then, use node ++>As starting point, try to connect +. >And the same detection is performed. />And->Can pass collision detection, and->、/>And (3) withThe steering angle is smaller than->Both conditions are satisfied at the same time, thus the node +.>Delete and attempt to connect to the next node. Similarly, the connection is also detected, deleting the node +.>. Finally try to connect node->Although the connection passes the collision detectionMeasure, but->、/>And->The steering angle is greater than->Therefore reserve node +.>. The result after pruning the path is shown in fig. 5 b.
It should be further noted that the path pruning algorithm can effectively reduce the number of redundant nodes, shorten the path length, and improve the path quality. Referring to fig. 6, a comparison of path quality before and after path pruning is shown. The solid line represents the path without pruning, and the broken line represents the path after pruning. It is obvious that the path pruning can significantly reduce the number of nodes and path cost, and improve the quality of the path.
In an alternative embodiment of the present application, the third-order B-spline curve is used to smooth the second movement path to obtain the final movement path of the unmanned excavator.
Specifically, when the nodes in the random tree are directly connected by line segments, the path generated by the algorithm may have a problem of being not smooth enough, and particularly under the condition that the environment map is complex, the finally generated path may be tortuous, which is not beneficial to driving control. Therefore, the generated path is smoothed by using a cubic B-spline curve, so as to obtain a smoother path, wherein the cubic B-spline curve belongs to a known technology, and detailed description thereof is omitted herein.
In the application, the effectiveness of the improved RRT algorithm is verified in an environment map through simulation experiments. The performance of the algorithm is measured by planning the duration, expanding the node number and the path cost. Experiments were performed under the Windows 10 operating system using MATLAB 2018. The host was equipped with an Intel (R) Core (TM) i5-9300H processor with a main frequency of 2.40 GHz and a memory size of 16 GB. An obstacle environment is set for testing. In a map of size 500 m ×500 m, the paths of the unmanned excavator generated by the Bi-RRT algorithm and the modified RRT algorithm of the present application are shown in fig. 7a and 7b, respectively.
It can be derived from the graph that the improved RRT algorithm in the embodiment of the present application introduces a dynamic step strategy, a bidirectional target bias strategy, a maximum rotation angle limiting strategy and a path track optimizing strategy, dynamically adjusts the expansion step by taking the density and complexity of the obstacle into consideration by collecting the local environment image, and dynamically adjusts the expansion step and introduces the bidirectional target bias when expanding the nodes by adopting the bidirectional fast expansion random tree algorithm, thereby ensuring that when expanding the target points, the trap area can be escaped by using the expansion mode of two dynamic step and bidirectional bias, and the exit and the narrow channel can be more smoothly passed, thereby improving the convergence efficiency of the algorithm, while the addition of the maximum rotation angle limiting strategy ensures the rationality of the steering angle, so that the path is more reasonable, the quality of the path is further improved after the path track is optimized, the number of the finally generated path nodes is less, and the transition is smoother.
Referring to fig. 8, an embodiment of the present application discloses an electronic device 20 comprising a processor 21 and a memory 22; wherein the memory 22 is used for storing a computer program; the processor 21 is configured to implement the path planning method of the unmanned excavator provided by the foregoing method embodiment by executing a computer program.
For the specific process of the path planning method of the unmanned excavator, reference may be made to the corresponding content disclosed in the foregoing embodiment, and no further description is given here.
The memory 22 may be a carrier for storing resources, such as a read-only memory, a random access memory, a magnetic disk, or an optical disk, and the storage may be a temporary storage or a permanent storage.
In addition, the electronic device 20 further includes a power supply 23, a communication interface 24, an input-output interface 25, and a communication bus 26; wherein the power supply 23 is used for providing working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and an external device, and the communication protocol to be followed is any communication protocol applicable to the technical solution of the present application, which is not specifically limited herein; the input/output interface 25 is used for acquiring external input data or outputting external output data, and the specific interface type thereof may be selected according to the specific application requirement, which is not limited herein.
Further, the embodiment of the application also discloses a computer readable storage medium, as shown in fig. 9, for storing a computer program 31, where the computer program, when executed by a processor, implements the path planning method of the unmanned excavator provided in the foregoing method embodiment.
For the specific process of the path planning method of the unmanned excavator, reference may be made to the corresponding content disclosed in the foregoing embodiment, and no further description is given here.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, so that the same or similar parts between the embodiments are referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The foregoing has described in detail the method, apparatus and storage medium for path planning for an unmanned excavator provided by the present application, and specific examples have been applied herein to illustrate the principles and embodiments of the present application, and the description of the foregoing examples is only for aiding in understanding the method and core idea of the present application; meanwhile, as those skilled in the art will vary in the specific embodiments and application scope according to the ideas of the present application, the contents of the present specification should not be construed as limiting the present application in summary.
Claims (10)
1. A path planning method for an unmanned excavator, comprising:
acquiring a starting point, a target point, barrier information and a local environment image of the unmanned excavator;
based on a preset dynamic step strategy, a preset target deflection strategy and a preset unmanned excavator motion collision detection strategy, adopting a bidirectional rapid expansion random tree algorithm to alternately expand two random tree nodes to obtain expansion nodes corresponding to the two random trees;
based on a preset unmanned excavator motion constraint strategy and a minimum path cost strategy, reselecting father nodes from the expansion nodes corresponding to the two random trees and rewiring to obtain updated two random trees;
Responding to the fact that the distance between corresponding expansion nodes obtained by the two random trees is smaller than a set value, and communicating the two random trees to obtain a first moving path of the unmanned excavator;
pruning optimization processing is carried out on the first moving path based on a preset path pruning algorithm to obtain a second moving path of the unmanned excavator;
and carrying out smoothing treatment on the second moving path to obtain a final moving path of the unmanned excavator.
2. The path planning method of an unmanned excavator according to claim 1, wherein the two random tree node expansion is alternately performed by using a bidirectional rapid expansion random tree algorithm to obtain two random tree corresponding expansion nodes based on a preset dynamic step strategy, a preset target deviation strategy and a preset unmanned excavator motion collision detection strategy, and the method comprises the following steps:
respectively taking the starting point position and the target point position as root nodes of two random trees, and respectively expanding nodes from the root nodes of the two random trees by utilizing random sampling to obtain random sampling points corresponding to the two random trees;
acquiring two nearest nodes on the two random trees, which are corresponding to the two random sampling points, and alternately generating corresponding expansion nodes of the two random trees based on a preset dynamic step strategy, a preset target deviation strategy and a preset unmanned excavator motion collision detection strategy, wherein for any random tree, the method comprises the following steps:
S1: according to the direction from the nearest node to the random sampling point to the corresponding random sampling point on any random tree, a first expansion node is obtained, wherein the calculation formula of the first expansion node is as follows:
wherein,for any expansion node corresponding to the random tree, < ->Random sampling points corresponding to any random tree, < ->For one node closest to the corresponding random sampling point on any random tree, +.>For Euclidean distance between random sampling point and nearest node of corresponding random sampling point, +.>To expand the step length;
opposite nodeAnd->Performing collision detection, and if no collision exists between the first expansion node and the obstacle, adding the first expansion node into a corresponding random tree; if collision exists with the obstacle, adjusting the expansion step length and the target deflection to obtain a second expansion node, wherein the calculation formula of the second expansion node is as follows:
wherein,for any expansion node corresponding to the random tree, < ->Is a random sampling point corresponding to any random tree,for one node closest to the corresponding random sampling point on any random tree, +.>For any target point corresponding to the random tree, < ->For Euclidean distance between random sampling point and nearest node of corresponding random sampling point, +. >For the Euclidean distance between the target point and the nearest node to the corresponding random sampling point, +.>Nearest node to the corresponding random sampling point +.>To random sampling point->Step length of direction expansion, step length of direction expansion>Nearest node to the corresponding random sampling point +.>To the target point->Step length of direction expansion, step length of direction expansion>；
S2: opposite nodeAnd->Performing collision detection, and if no collision exists between the second expansion node and the obstacle, adding the second expansion node into a corresponding random tree; if collision with obstacle exists, the expansion step length is +.>And->Performing exchange adjustment to obtain a third expansion node, wherein the calculation formula of the third expansion node is as follows:
s3: opposite nodeAnd->Performing collision detection, and if no collision exists between the third expansion node and the obstacle, adding the third expansion node into a corresponding random tree; if collision exists with the obstacle, returning to an empty expansion node of the corresponding random tree.
3. The method for path planning for an unmanned excavator according to claim 2, wherein the expanding step lengthThe calculation formula of (2) is as follows:
wherein,is the density index of the obstacle->Wherein->And->Respectively representing the number of barrier pixel points and the total number of pixel points in the binary image obtained by binarizing the acquired local environment image, wherein the gray value of the barrier pixel points is 255,/and/respectively representing the number of barrier pixel points and the total number of pixel points in the binary image obtained by binarizing the acquired local environment image >Indicates the number of collisions with obstacles in collision detection, +.>Representing the total number of collision detections, +.>Is constant.
4. The path planning method of an unmanned excavator according to claim 2, wherein the preset unmanned excavator movement collision detection strategy comprises:
judging whether an obstacle exists between two nodes or not by judging whether the connection line between the two nodes is intersected with the obstacle or not, and determining that the obstacle exists between the two nodes if the connection line between the two nodes is intersected with the obstacle.
5. The path planning method of an unmanned excavator according to claim 1, wherein the re-selecting the parent node for the expansion node corresponding to the two random trees to obtain the updated two random trees based on a preset unmanned excavator motion constraint strategy and a minimum path cost strategy comprises:
acquiring any random tree with expansion nodes as the center and radius as the centerThe parent node set to be selected does not contain the expansion node;
traversing all the father nodes to be selected in the father node set to find out the father node which simultaneously satisfies the father nodes to be selected, the father node to be selected and the expansion node, wherein the steering angle formed by the father node to be selected and the expansion node is smaller than the maximum steering angle of the unmanned excavator, the connection line between the father node to be selected and the expansion node does not collide with an obstacle, and the father node to be selected with the minimum path cost from the starting point of the unmanned excavator to the expansion node through the father node to be selected is used as the father node of the expansion node;
And adding paths between the father node of the expansion node and the expansion node into the corresponding random tree to update the corresponding random tree.
6. The method of path planning for an unmanned excavator of claim 5 wherein the step of rewiring comprises:
acquiring any random tree with expansion nodes as the center and radius as the centerA set of child nodes to be selected within a range of (a), wherein the set of child nodes to be selected does not include a parent node of the expansion node;
traversing all the child nodes to be selected in the child node set to find a child node to be selected, which simultaneously satisfies that the steering angle formed by the father node, the expansion node and the child node to be selected of the expansion node is smaller than the maximum steering angle of the unmanned excavator, the connection line between the child node to be selected and the expansion node does not collide with an obstacle, and the path cost from the starting point of the unmanned excavator to the child node to be selected is minimum, as the child node of the expansion node;
and adding the child nodes of the expansion node, the paths among the child nodes of the expansion node and the child nodes of the expansion node into the corresponding random tree to update the corresponding random tree.
7. The path planning method of an unmanned excavator of claim 6 wherein the path cost is calculated by the formula:
wherein,representing the Euclidean distance between two adjacent wiring nodes, Q-tableShowing the total number of links between two adjacent nodes on the path,/->Index indicating the distance between the path and the obstacle, < >>，/>Represents the distance between the path and the obstacle, < >>Indicating the number of steering of the unmanned excavator on the route, +.>、/>、/>A constant greater than 0.
8. The path planning method of the unmanned excavator according to claim 1, wherein smoothing the second movement path by using a cubic B-spline curve results in a final movement path of the unmanned excavator.
9. An electronic device, comprising: a processor, a memory and a computer program stored on the memory and capable of running on the processor, which when executed by the processor, performs the steps of the path planning method of the unmanned excavator of any one of claims 1 to 8.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the path planning method of the unmanned excavator according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311705307.7A CN117387633B (en) | 2023-12-13 | 2023-12-13 | Path planning method for unmanned excavator, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311705307.7A CN117387633B (en) | 2023-12-13 | 2023-12-13 | Path planning method for unmanned excavator, electronic equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117387633A true CN117387633A (en) | 2024-01-12 |
| CN117387633B CN117387633B (en) | 2024-05-14 |
Family
ID=89435974
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311705307.7A Active CN117387633B (en) | 2023-12-13 | 2023-12-13 | Path planning method for unmanned excavator, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117387633B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100223008A1 (en) * | 2007-03-21 | 2010-09-02 | Matthew Dunbabin | Method for planning and executing obstacle-free paths for rotating excavation machinery |
| CN108981704A (en) * | 2018-07-13 | 2018-12-11 | 昆明理工大学 | A kind of two-way RRT paths planning method of target gravitation based on dynamic step length |
| CN110083165A (en) * | 2019-05-21 | 2019-08-02 | 大连大学 | A kind of robot paths planning method under complicated narrow environment |
| CN112902971A (en) * | 2021-03-22 | 2021-06-04 | 中国长江三峡集团有限公司 | Fast extended random tree algorithm based on Gaussian sampling and target deviation guidance, electronic equipment and storage medium |
| CN113467476A (en) * | 2021-08-02 | 2021-10-01 | 福州大学 | Non-collision detection rapid stochastic tree global path planning method considering corner constraint |
| CN113485367A (en) * | 2021-08-06 | 2021-10-08 | 浙江工业大学 | Path planning method of multifunctional stage mobile robot |
| US20210365036A1 (en) * | 2020-05-22 | 2021-11-25 | Cnh Industrial America Llc | Localized obstacle avoidance for optimal v2v path planning |
| CN114161416A (en) * | 2021-12-06 | 2022-03-11 | 贵州大学 | Robot path planning method based on potential function |
| CN114689070A (en) * | 2022-03-08 | 2022-07-01 | 三一重机有限公司 | Path planning method and device |
| CN114764249A (en) * | 2022-04-27 | 2022-07-19 | 西安建筑科技大学 | Real-time obstacle avoidance path planning method, system, device and medium |
| CN116300932A (en) * | 2023-03-17 | 2023-06-23 | 杭州柳叶刀机器人有限公司 | Robot motion path planning method and system based on improved RRT-Connect algorithm |
-
2023
- 2023-12-13 CN CN202311705307.7A patent/CN117387633B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100223008A1 (en) * | 2007-03-21 | 2010-09-02 | Matthew Dunbabin | Method for planning and executing obstacle-free paths for rotating excavation machinery |
| CN108981704A (en) * | 2018-07-13 | 2018-12-11 | 昆明理工大学 | A kind of two-way RRT paths planning method of target gravitation based on dynamic step length |
| CN110083165A (en) * | 2019-05-21 | 2019-08-02 | 大连大学 | A kind of robot paths planning method under complicated narrow environment |
| US20210365036A1 (en) * | 2020-05-22 | 2021-11-25 | Cnh Industrial America Llc | Localized obstacle avoidance for optimal v2v path planning |
| CN112902971A (en) * | 2021-03-22 | 2021-06-04 | 中国长江三峡集团有限公司 | Fast extended random tree algorithm based on Gaussian sampling and target deviation guidance, electronic equipment and storage medium |
| CN113467476A (en) * | 2021-08-02 | 2021-10-01 | 福州大学 | Non-collision detection rapid stochastic tree global path planning method considering corner constraint |
| CN113485367A (en) * | 2021-08-06 | 2021-10-08 | 浙江工业大学 | Path planning method of multifunctional stage mobile robot |
| CN114161416A (en) * | 2021-12-06 | 2022-03-11 | 贵州大学 | Robot path planning method based on potential function |
| CN114689070A (en) * | 2022-03-08 | 2022-07-01 | 三一重机有限公司 | Path planning method and device |
| CN114764249A (en) * | 2022-04-27 | 2022-07-19 | 西安建筑科技大学 | Real-time obstacle avoidance path planning method, system, device and medium |
| CN116300932A (en) * | 2023-03-17 | 2023-06-23 | 杭州柳叶刀机器人有限公司 | Robot motion path planning method and system based on improved RRT-Connect algorithm |
Non-Patent Citations (3)
| Title |
|---|
| YUBIAO LEI; YAFEI WANG; SHAOTENG WU;等: "A Fuzzy Logic-Based Adaptive Dynamic Window Approach for Path Planning of Automated Driving Mining Truck", 2021 IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS (ICM), 30 March 2021 (2021-03-30) * |
| 张云峰;马振书;孙华刚;陆继山;: "基于改进快速扩展随机树的机械臂路径规划", 火力与指挥控制, vol. 41, no. 05, 31 May 2016 (2016-05-31) * |
| 谢中东: "挖掘机自主挖掘轨迹规划方法研究", 南方农机, no. 20, 31 October 2021 (2021-10-31) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117387633B (en) | 2024-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11086016B2 (en) | Method and apparatus for tracking obstacle | |
| Li et al. | Multivehicle cooperative local mapping: A methodology based on occupancy grid map merging | |
| CN109579854B (en) | Unmanned vehicle obstacle avoidance method based on fast expansion random tree | |
| CN108444490B (en) | Robot path planning method based on depth fusion of visible view and A-x algorithm | |
| CN114111825B (en) | Path planning method, path planning device, electronic equipment, engineering machinery and storage medium | |
| CN110515094B (en) | Robot point cloud map path planning method and system based on improved RRT | |
| CN111121812B (en) | Path optimization method, electronic device and storage medium | |
| CN114705196B (en) | Self-adaptive heuristic global path planning method and system for robot | |
| CN115782867B (en) | Track collision risk assessment method, device, electronic equipment and storage medium | |
| CN108592912A (en) | A kind of autonomous heuristic approach of indoor mobile robot based on laser radar | |
| KR101037379B1 (en) | The moving robot exploration system founded the distance information of a surrounding circumstance required from distance sensor and the exploration method using the moving robot exploration system | |
| CN113467476B (en) | Collision-free detection rapid random tree global path planning method considering corner constraint | |
| CN112987749A (en) | Hybrid path planning method for intelligent mowing robot | |
| Fan et al. | Solving find path problem in mapped environments using modified A* algorithm | |
| CN115981311A (en) | Path planning method and system for complex pipeline maintenance robot | |
| CN117387633B (en) | Path planning method for unmanned excavator, electronic equipment and medium | |
| Song et al. | G2P-SLAM: Generalized RGB-D SLAM framework for mobile robots in low-dynamic environments | |
| CN114379569A (en) | Method and device for generating driving reference line | |
| CN110084825A (en) | A kind of method and system based on image edge information navigation | |
| CN116399364B (en) | Vehicle driving road network generation method, device, chip, terminal, equipment and medium | |
| CN117824652A (en) | Robot path planning method based on safety artificial potential field and RRT | |
| CN116764225B (en) | Efficient path-finding processing method, device, equipment and medium | |
| Ramasubramanian et al. | On the enhancement of firefighting robots using path-planning algorithms | |
| CN116255985A (en) | Search and rescue ROV path planning system and method for three-dimensional environment | |
| CN109855622A (en) | Method for searching path and equipment for mobile robot |
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 |