CN110497403A - A kind of manipulator motion planning method improving two-way RRT algorithm - Google Patents

A kind of manipulator motion planning method improving two-way RRT algorithm Download PDF

Info

Publication number
CN110497403A
CN110497403A CN201910715625.9A CN201910715625A CN110497403A CN 110497403 A CN110497403 A CN 110497403A CN 201910715625 A CN201910715625 A CN 201910715625A CN 110497403 A CN110497403 A CN 110497403A
Authority
CN
China
Prior art keywords
new
node
path
tree
mechanical arm
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201910715625.9A
Other languages
Chinese (zh)
Inventor
陈灵
尧多显
杨傲雷
徐昱琳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
University of Shanghai for Science and Technology
Original Assignee
University of Shanghai for Science and Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by University of Shanghai for Science and Technology filed Critical University of Shanghai for Science and Technology
Priority to CN201910715625.9A priority Critical patent/CN110497403A/en
Publication of CN110497403A publication Critical patent/CN110497403A/en
Pending legal-status Critical Current

Links

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B25HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25JMANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00Programme-controlled manipulators
    • B25J9/16Programme controls
    • B25J9/1656Programme controls characterised by programming, planning systems for manipulators
    • B25J9/1664Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning

Landscapes

  • Engineering & Computer Science (AREA)
  • Robotics (AREA)
  • Mechanical Engineering (AREA)
  • Feedback Control In General (AREA)

Abstract

The invention discloses a kind of manipulator motion planning methods for improving two-way RRT algorithm, the two-way RRT algorithm of this method fusion tradition, introduce the searching mode of optimal father node and the connection type of more new node, greatly reduce the distance of robotic arm path planning, it is ensured that the search speed of two-way RRT algorithm and cook up preferably path;The target position of given mechanical arm simultaneously obtains obstacle information in environment, one collisionless path is gone out using improved two-way RRT algorithmic rule, mechanical arm moves to target position according to the path of planning, to complete mechanical arm based on the motion planning for improving two-way RRT algorithm.The present invention uses improved two-way RRT algorithm, can greatly reduce the path cost of planning, the path of an optimization is cooked up for mechanical arm, it is optimal for solving the problems, such as motion path not.This method is applicable not only to the motion planning research of mechanical arm under higher dimensional space, and can be applied to mobile robot field, has broad application prospects.

Description

A kind of manipulator motion planning method improving two-way RRT algorithm
Technical field
The present invention relates to manipulator motion planning field more particularly to a kind of manipulator motions for improving two-way RRT algorithm Planing method.
Background technique
Robot motion planning is the basic problem of robot research field, i.e., in given initial position and target position Between find the path for meeting constraint condition for robot.The robot motion planning method of early stage directly makees robot Treat for particle, and mechanical arm be it is irregular, can not be therefore most of for moving directly as particle in state space The motion planning method of robot can not be directly extended to mechanical arm.
The avoidance object of planning of mechanical arm is to cook up the optimal path of a meet demand, for this problem, has been mentioned Artificial Potential Field Method, A* search method, genetic algorithm, C space law, ant group algorithm etc. are gone out, but these algorithms all have limitation.People The problem of work potential field method is can not to avoid local minimum problem, and A* algorithm is theoretically time optimal, but the disadvantage is that it Space increase be it is exponential other, ant group algorithm is substantially parallel algorithm, it problem space multiple spot start simultaneously at into The multi-thread independent solution search of row, but the algorithm search time is longer, easily falls into stagnation problem.
Based on the path planning algorithm of Quick Extended random tree (RRT/rapidly exploring random tree), By carrying out collision detection to the sampled point in state space, the modeling to space is avoided, mechanical arm can be efficiently solved Motion planning problem under higher dimensional space and Complex Constraints.
Traditional two-way RRT algorithm grows two Quick Extended random trees simultaneously from initial position and target position to search for State space, generating a paths enables the effective avoiding obstacles of mechanical arm, is efficient rule in a kind of higher dimensional space The method of drawing.But traditional two-way RRT algorithm lays particular emphasis on convergent rapidity, the path of planning be not it is optimal, do not account for The cost cost of planning path length, searching route strategy are all based on the search of stochastical sampling, exist much to white space Futile searches, waste search time.
Summary of the invention
In view of the deficiencies of the prior art, the present invention proposes a kind of manipulator motion planning sides for improving two-way RRT algorithm Method.This method uses improved two-way RRT algorithm, can greatly reduce the path cost of planning, cooks up one for mechanical arm The path of item optimization, it is optimal for solving the problems, such as motion path not.
In order to achieve the above objectives, the present invention adopts the following technical scheme:
A kind of manipulator motion planning method improving two-way RRT algorithm, specifically includes the following steps:
Step 1: given mechanical arm target position obtains the inverse solution of target position by the method for inverse kinematics;
Step 2: the size of all barriers, location information in environment are obtained;
Step 3: the two-way RRT algorithm of fusion tradition introduces the connection of the selection mode and more new node of optimal father node Mode improves two-way RRT algorithm, and the path planning of mechanical arm is then carried out using improved two-way RRT algorithm, generates one Collisionless path from initial position to target position;
Step 4: mechanical arm is moved according to the path planned, then judges whether mechanical arm reaches target position, The stop motion if reaching, otherwise mechanical arm continues movement until reaching target position.
Compared with prior art, the beneficial effect comprise that
The present invention improves the mode of father node selection on the basis of traditional two-way RRT algorithm, using cost function come The node for choosing minimum cost in expanding node field is father node;Meanwhile each iteration all can more new node connection type, To guaranteeing lower computation complexity, the path of an optimization can be rapidly cooked up for mechanical arm, then mechanical arm according to The path planned is moved, and it is optimal for solving the problems, such as motion path not.
Detailed description of the invention
Fig. 1 is the flow chart for improving two-way RRT algorithm and being used for manipulator motion planning method.
Fig. 2 is the point spread figure improved in two-way RRT algorithm.
Fig. 3 is the selection mode figure for improving optimal father node in two-way RRT algorithm.
Fig. 4 is the connection type figure for improving more new node in two-way RRT algorithm.
Fig. 5 is sixdegree-of-freedom simulation illustraton of model.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing, to the present invention into Row is further described.It should be appreciated that specific implementation example described herein is not used to limit only to explain the present invention The fixed present invention.
As shown in Figure 1, a kind of manipulator motion planning method for improving two-way RRT algorithm, the workflow of this method are retouched It states are as follows: the emulation platform of sixdegree-of-freedom simulation is built first with open source robot operating system ROS;The mesh of given mechanical arm Cursor position obtains the inverse solution of target position by the method for mechanical arm inverse kinematics;Obtain size, the position letter of all barriers Breath;Improved two-way RRT algorithm is used to cook up a collisionless path for mechanical arm;Mechanical arm according to planning path into Row movement, until reaching target position.Specifically includes the following steps:
Step 1: given mechanical arm target position obtains the inverse solution of target position by the method for inverse kinematics;Specifically such as Under: sixdegree-of-freedom simulation model is put up, as shown in figure 5, given target position, solution finds out its target position by inverting Each joint angle judges that inverse solution whether there is, and if it exists, be set as dbjective state xgoal;If it does not exist, target point is reset It sets, until finding out reachable dbjective state.
Step 2: the size of all barriers, location information in environment are obtained;It is specific as follows: all barriers in detection environment Hinder object, obtain the size of all barriers, location information in environment, provides collision letter to generate collisionless path in step 3 Breath.
Step 3: the two-way RRT algorithm of fusion tradition introduces the connection of the selection mode and more new node of optimal father node Mode improves two-way RRT algorithm, and the path planning of mechanical arm is then carried out using improved two-way RRT algorithm, generates one Collisionless path from initial position to target position;
Improved two-way RRT algorithm extension principle is as shown in Figure 2, Figure 3 and Figure 4: respectively from initial position and target position Set two path tree T of buildingaAnd Tb, two-way RRT algorithm obtains sampled point x in state space stochastical samplingrand, then in TaOn look for To distance xrandNearest node xnearest, from xnearestTo xrandSide extend up a certain distance and obtain new node xnew, with xnewCentered on point, r is radius, choose xnewNeighbouring neighbor node region, found in neighbor node region root node from Line cost function cost (xnew) the minimum and line not node x with barrier collisionnearAs xnewFather node obtains new branch (xnear, xnew), it is added on tree;The connection type of more new node, to obtain optimal path;With xnewAs path tree TbExpand The direction of exhibition, path tree TbTowards xnewDirection continue to extend branch, until new node and xnewIt is overlapped or falls into barrier Space;If the T after the above iterationaWith TbIt does not connect, then next iteration is from TbStart to repeat above-mentioned expansion process;So hand over For iteration until TaWith TbConnect and find a path from initial position to target position;Specific step is as follows:
(1) to random tree TaIt is extended, random tree TaBy initial position xinitAs starting point, i.e. tree TaRoot node, By xgoalAs target point, and by xinitIt as the father node of this extension, extends, utilizes since the father node currently defined Stochastical sampling function randomly chooses a sampled point x in free spacerand;Stochastical sampling mode is as follows: each in random tree Growth course in, come the direction of growth of decision tree be target point or random point according to random chance;It is set in sampling function Determine parameter Prob, obtain one 0 to 1.0 random value p every time, when 0 < p < Prob, random tree is grown towards target point; As Prob < p < 1, random tree is grown towards a random direction.
(2) distance x is found in current random treerandNearest node xnearest, in xrandAnd xnearestLine on look for One point xnew, i.e., newborn node, xnew=xnearest+Δd*|xrand-xnearest|, wherein xnearestFor distance x in random treerand Nearest node, Δ d are customized step-length.
(3) to xnewCollision detection is done, if do not collided, with xnewFor the center of circle, r is radius, according to node formula Near (V, xnew)={ x ∈ V:| | xnew-x||≤γ((logn)/n)1/d, choose xnewNeighbouring neighbor node region, i.e., xnearSet Xnear(all nodes in border circular areas on tree), wherein d is Spatial Dimension, and γ is the constant of selection, V be with The set of machine tree node, x are certain nodes in region of search, and n is current iteration number.
(4) as shown in figure 3, selecting the mode of optimal father node (to xnewFind optimal father node): by xnearestIt fixes tentatively and is xmin, then from root node to xminAnd xminTo xnewPath distance fix tentatively for minimal path spend cmin, then loop through xnewNeighbor node set XnearInterior all nodes, from new node xnewTo set XnearInterior child node xnearGenerate respective road Diameter σ, if cost (xnear)+cost (σ) < cminThat is root node is to xnearPath spend with newly connect path cost the sum of Less than cminIf xnearAnd xnewLine collision detection it is qualified, then by the xnearAs the smallest xmin, minimal path, which is spent, is then Root node is to the xnearWith the xnearTo xnewSummation, finally by the xnearWith xnewIt connects, is added on random tree.
(5) as shown in figure 4, the connection type of more new node, to obtain optimal path;Loop through neighbor node set XnearIn other remaining xnear, judge a certain xnearTo xnewPath spend plus root node to xnewPath spend whether Less than the xnearTo the path distance of root node, i.e. cost (xnew)+cost (σ) < cost (xnear) whether true, if so, that Collision detection is carried out to its σ and defines the x if not detecting barriernearIt fixes tentatively as father node, then rejects all Other all x being connected with the father nodenearWith remaining xnearEdge, that is, E ← E { xparent, xnear, E, which is represented, to be constituted Side set, and by new node xnewWith father node xnearSide be re-added to tree in i.e. E ← E ∪ { xnew, xnear}。
(6) random tree TaTrial and TbConnection, algorithm terminates if connection;Otherwise to random tree TbIt is extended, random tree TbThe mode of extension is slightly different, and has extended the new node x of one treenewAfterwards, it is set using this new target point as second The direction of extension;Random tree TbBy xgoalAs starting point (root node), with xnewAs random tree TbThe direction of extension, i.e. handle xnewAs the sampled point of present tree, it can persistently extend new branch in such a way that step (2) is identical in (5), until new section Point and xnewIt is overlapped or falls into Obstacles.
(7) if after extending above TaWith TbDo not connect, then it is next from random tree TbStart iteration, repeats step (1) new branch is extended to (6) and attempt to connect with another path tree;Such alternating iteration is until TaWith TbIt connects and finds one Item is from xinitTo xgoalPath P ATH (Ta, Tb)。
Step 4: mechanical arm is moved according to the path planned, then judges whether mechanical arm reaches target position, The stop motion if reaching, otherwise mechanical arm continues movement until reaching target position.Specifically: by step 3 by changing Into the path that goes out of two-way RRT algorithmic rule be sent to mechanical arm, then mechanical arm is moved according to received path, mechanical Arm during the motion can Real-time Feedback current location information judge whether mechanical arm reaches target position, if do not reach mesh Cursor position mechanical arm will continue to move, until reaching target position.
The two-way RRT algorithm of the method for the present invention fusion tradition, introduces the searching mode and more new node of optimal father node Connection type, improve two-way RRT algorithm, grow two Quick Extended random trees simultaneously from initial position and target position and come A collisionless path is finally planned in search condition space.Path generation can be found for new node by finding optimal father node mode The smaller father node of valence, the connection type of each iteration all more new nodes is by the reconnect mode between node come more new root section Point arrives the path cost of the node, by improving two-way RRT algorithm, can reduce the path cost of planning, greatly for machinery Arm cooks up the path of an optimization.

Claims (5)

1. a kind of manipulator motion planning method for improving two-way RRT algorithm, which is characterized in that specifically includes the following steps:
Step 1: given mechanical arm target position obtains the inverse solution of target position by the method for inverse kinematics;
Step 2: the size of all barriers, location information in environment are obtained;
Step 3: the two-way RRT algorithm of fusion tradition introduces the selection mode of optimal father node and the connection side of more new node Formula improves two-way RRT algorithm, and the path planning of mechanical arm is then carried out using improved two-way RRT algorithm, generate one from Collisionless path of the initial position to target position;
Step 4: mechanical arm is moved according to the path planned, then judges whether mechanical arm reaches target position, if arriving Up to then stop motion, otherwise mechanical arm continues movement until reaching target position.
2. the manipulator motion planning method according to claim 1 for improving two-way RRT algorithm, which is characterized in that described Step 1 is specific as follows: putting up sixdegree-of-freedom simulation model, gives target position, find out its target position by solution of inverting Each joint angle, judge that inverse solution whether there is, and if it exists, be set as dbjective state xgoal;If it does not exist, target point is reset Position, until finding out reachable dbjective state.
3. the manipulator motion planning method according to claim 1 for improving two-way RRT algorithm, which is characterized in that described Step 2 is specific as follows: all barriers in detection environment obtain the size of all barriers, location information in environment, for step Collisionless path is generated in rapid three, and collision information is provided.
4. the manipulator motion planning method according to claim 1 for improving two-way RRT algorithm, which is characterized in that described Step 3, improved two-way RRT algorithm extension principle are as follows: constructing two path trees from initial position and target position respectively TaAnd Tb, two-way RRT algorithm obtains sampled point x in state space stochastical samplingrand, then in TaOn find distance xrandNearest section Point xnearest, from xnearestTo xrandSide extend up a certain distance and obtain new node xnew, with xnewCentered on point, r is half Diameter chooses xnewThe offline cost function cost of root node is found in neighbouring neighbor node region in neighbor node region (xnew) the minimum and line not node x with barrier collisionnearAs xnewFather node, obtain new branch (xnear, xnew), add It is added on tree;The connection type of more new node, to obtain optimal path;With xnewAs path tree TbThe direction of extension, path Set TbTowards xnewDirection continue to extend branch in a similar way, until new node and xnewIt is overlapped or falls into barrier sky Between;If the T after the above iterationaWith TbIt does not connect, then next iteration is from TbStart to repeat above-mentioned expansion process;So alternately Iteration is until TaWith TbConnect and find a path from initial position to target position;Specific step is as follows:
(1) to random tree TaIt is extended, random tree TaBy initial position xinitAs starting point, i.e. tree TaRoot node, will xgoalAs target point, and by xinitAs this extension father node, extended since the father node currently defined, using with Machine sampling function randomly chooses a sampled point x in free spacerand;Stochastical sampling mode is as follows: each in random tree It come the direction of growth of decision tree is target point or random point according to random chance in growth course;
(2) distance x is found in current random treerandNearest node xnearest, in xrandAnd xnearestLine on look for a bit xnew, i.e., newborn node, xnew=xnearest+Δd*|xrand-xnearest|, wherein xnearestFor distance x in random treerandRecently Node, Δ d are customized step-length;
(3) to xnewCollision detection is done, if do not collided, with xnewFor the center of circle, r is radius, according to node formula Near (V, xnew)={ x ∈ V:| | xnew-x||≤γ((logn)/n)1/d, choose xnewNeighbouring neighbor node region, i.e. xnearSet Xnear, all nodes that border circular areas is interior to be set, wherein d is Spatial Dimension, and γ is the constant of selection, and V is random tree node Set, x is certain node in region of search, and n is current iteration number;
(4) mode for selecting optimal father node, i.e., to xnewFind optimal father node: by xnearestIt fixes tentatively as xmin, then from root section Point arrives xminAnd xminTo xnewPath distance fix tentatively for minimal path spend cmin, then loop through xnewNeighbor node collection Close XnearInterior all nodes, from new node xnewTo set XnearInterior child node xnearRespective path σ is generated, if cost (xnear)+cost (σ) < cminThat is root node is to xnearPath spend and the sum of spend with the path that newly connect less than cminIf xnearAnd xnewLine collision detection it is qualified, then by the xnearAs the smallest xmin, minimal path cost be then root node to this xnearWith the xnearTo xnewSummation, finally by the xnearWith xnewIt connects, is added on random tree;
(5) connection type of more new node, to obtain optimal path;Loop through neighbor node set XnearIn it is remaining its He is xnear, judge a certain xnearTo xnewPath spend plus root node to xnewPath spend whether be less than the xnearTo root The path distance of node, i.e. cost (xnew)+cost (σ) < cost (xnear) whether true, if so, so its σ is touched Detection is hit, if not detecting barrier, defines the xnearIt fixes tentatively as father node, then rejects and all be connected with the father node Other all xnearWith remaining xnearEdge, that is, E ← E { xparent, xnear, E represents the set on constituted side, and will New node xnewWith father node xnearSide be re-added to tree in i.e. E ← E ∪ { xnew, xnear};
(6) random tree TaTrial and TbConnection, algorithm terminates if connection;Otherwise to random tree TbIt is extended, random tree TbExpand The mode of exhibition is slightly different, and has extended the new node x of one treenewAfterwards, it is extended using this new target point as second tree Direction;Random tree TbBy xgoalAs starting point (root node), with xnewAs random tree TbThe direction of extension, i.e., xnewMake For the sampled point of present tree, it can persistently extend new branch in such a way that step (2) is identical in (5), until new node with xnewIt is overlapped or falls into Obstacles;
(7) if after extending above TaWith TbDo not connect, then it is next from random tree TbStart iteration, repeats step (1) and arrive (6) it extends new branch and attempts to connect with another path tree;Such alternating iteration is until TaWith TbConnect and find one from xinitTo xgoalPath P ATH (Ta, Tb)。
5. the manipulator motion planning method according to claim 1 for improving two-way RRT algorithm, which is characterized in that described Step 4 specifically: mechanical arm will be sent to by the path that improved two-way RRT algorithmic rule goes out in step 3, then mechanical arm Moved according to received path, mechanical arm during the motion can Real-time Feedback current location information to judge mechanical arm be No arrival target position, if not reaching target position mechanical arm will continue to move, until reaching target position.
CN201910715625.9A 2019-08-05 2019-08-05 A kind of manipulator motion planning method improving two-way RRT algorithm Pending CN110497403A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910715625.9A CN110497403A (en) 2019-08-05 2019-08-05 A kind of manipulator motion planning method improving two-way RRT algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910715625.9A CN110497403A (en) 2019-08-05 2019-08-05 A kind of manipulator motion planning method improving two-way RRT algorithm

Publications (1)

Publication Number Publication Date
CN110497403A true CN110497403A (en) 2019-11-26

Family

ID=68587719

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910715625.9A Pending CN110497403A (en) 2019-08-05 2019-08-05 A kind of manipulator motion planning method improving two-way RRT algorithm

Country Status (1)

Country Link
CN (1) CN110497403A (en)

Cited By (44)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110919661A (en) * 2019-12-26 2020-03-27 中国科学院沈阳自动化研究所 Motion planning method for mechanical arm in glove box closed space
CN111251306A (en) * 2020-03-18 2020-06-09 广东省智能机器人研究院 Mechanical arm path planning method with chassis error
CN111531550A (en) * 2020-07-09 2020-08-14 浙江大华技术股份有限公司 Motion planning method and device, storage medium and electronic device
CN111650941A (en) * 2020-06-10 2020-09-11 湖南爱米家智能科技有限公司 Medical mobile robot path planning method, device, medium and equipment based on RRT-Connect improvement
CN111678523A (en) * 2020-06-30 2020-09-18 中南大学 Rapid BI _ RRT obstacle avoidance trajectory planning method based on STAR algorithm optimization
CN111761582A (en) * 2020-07-08 2020-10-13 浙江大学 Mobile mechanical arm obstacle avoidance planning method based on random sampling
CN112223291A (en) * 2020-10-21 2021-01-15 哈工大机器人(合肥)国际创新研究院 Mechanical arm obstacle avoidance method and device based on three-dimensional task space constraint
CN112338916A (en) * 2020-10-29 2021-02-09 深圳市大象机器人科技有限公司 Mechanical arm obstacle avoidance path planning method and system based on fast expansion random tree
CN112393739A (en) * 2020-10-29 2021-02-23 国网安徽省电力有限公司检修分公司 Improved rapid search random tree path planning method in large-area environment
CN112549016A (en) * 2020-10-21 2021-03-26 西安工程大学 Mechanical arm motion planning method
CN112677153A (en) * 2020-12-16 2021-04-20 东北林业大学 Improved RRT algorithm and industrial robot path obstacle avoidance planning method
CN112833904A (en) * 2021-01-05 2021-05-25 北京航空航天大学 Unmanned vehicle dynamic path planning method based on free space and fast search random tree algorithm
CN112947489A (en) * 2021-04-08 2021-06-11 华东理工大学 Method and device for planning collision-free path of welding robot in complex environment
CN112987799A (en) * 2021-04-16 2021-06-18 电子科技大学 Unmanned aerial vehicle path planning method based on improved RRT algorithm
CN113031004A (en) * 2021-03-05 2021-06-25 西北工业大学 Unmanned ship water surface target detection and path planning method based on three-dimensional laser radar
CN113084811A (en) * 2021-04-12 2021-07-09 贵州大学 Mechanical arm path planning method
CN113103236A (en) * 2021-04-22 2021-07-13 山东大学 Rapid and gradual optimal mechanical arm obstacle avoidance path planning method
CN113119115A (en) * 2021-03-22 2021-07-16 深圳市优必选科技股份有限公司 Mechanical arm motion planning method and device, readable storage medium and mechanical arm
CN113172631A (en) * 2021-05-11 2021-07-27 西南交通大学 Mechanical arm autonomous obstacle avoidance method based on improved RRT algorithm
CN113276109A (en) * 2021-04-21 2021-08-20 国网上海市电力公司 RRT algorithm-based double-mechanical-arm decoupling motion planning method and system
CN113282077A (en) * 2021-04-08 2021-08-20 浙江工业大学 Concentric tube robot motion planning method based on normal distribution RRT and Jacobian matrix
CN113296496A (en) * 2021-04-05 2021-08-24 青岛科技大学 Multi-sampling-point-based gravitational adaptive step size bidirectional RRT path planning method
CN113319013A (en) * 2021-07-08 2021-08-31 陕西科技大学 Apple intelligent sorting method based on machine vision
CN113324558A (en) * 2021-05-17 2021-08-31 亿嘉和科技股份有限公司 Grid map traversal algorithm based on RRT
CN113359748A (en) * 2021-06-22 2021-09-07 浙江科技学院 Improved Multi-RRT path planning method based on fusion prediction and AGV trolley
CN113448336A (en) * 2021-08-30 2021-09-28 天津施格机器人科技有限公司 3D obstacle avoidance path planning method
CN113485356A (en) * 2021-07-27 2021-10-08 西北工业大学 Robot rapid movement planning method
CN113515127A (en) * 2021-07-23 2021-10-19 华北电力大学(保定) Mobile robot path planning method and system
CN113723750A (en) * 2021-07-20 2021-11-30 中国科学技术大学先进技术研究院 Method and system for constructing robot humanoid operation action knowledge base
CN113885509A (en) * 2021-10-21 2022-01-04 广东电网有限责任公司广州供电局 Emergency power supply vehicle path planning method, device, equipment and storage medium
CN114115271A (en) * 2021-11-25 2022-03-01 江苏科技大学 Robot path planning method and system for improving RRT
CN114177008A (en) * 2022-01-12 2022-03-15 上海大学 Upper limb rehabilitation robot control method and system based on variable virtual clamp
CN114310904A (en) * 2022-01-19 2022-04-12 中南大学 Novel bidirectional RRT method suitable for mechanical arm joint space path planning
CN114593743A (en) * 2022-03-02 2022-06-07 杭州华鲲云起信息技术有限公司 Path planning method and device based on improved bidirectional RRT algorithm
CN114700937A (en) * 2022-01-13 2022-07-05 深圳市越疆科技有限公司 Mechanical arm, movement path planning method thereof, control system, medium and robot
CN115091460A (en) * 2022-07-13 2022-09-23 江苏科技大学 Intelligent steel grabbing machine mechanical arm path planning method and system
CN115167388A (en) * 2022-06-07 2022-10-11 哈尔滨理工大学 RRT multi-robot formation path planning algorithm based on target guidance
CN115870990A (en) * 2023-01-03 2023-03-31 西南交通大学 Obstacle avoidance path planning method for mechanical arm
CN115950439A (en) * 2023-03-15 2023-04-11 季华实验室 Bidirectional RRT path planning method, device, electronic equipment and storage medium
CN115946108A (en) * 2022-10-09 2023-04-11 中国人民解放军海军工程大学 Mechanical arm dynamic obstacle avoidance path planning method
CN115958590A (en) * 2021-12-24 2023-04-14 合肥哈工图南智控机器人有限公司 RRT-based mechanical arm deep frame obstacle avoidance motion planning method and device
CN116652952A (en) * 2023-06-09 2023-08-29 清华大学 Operation method and system for limited environment flexible cable by using double mechanical arms
CN116652972A (en) * 2023-07-31 2023-08-29 成都飞机工业(集团)有限责任公司 Series robot tail end track planning method based on bidirectional greedy search algorithm
CN117124335A (en) * 2023-10-25 2023-11-28 山东工商学院 Improved RRT path planning method based on path marking backtracking strategy

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120165982A1 (en) * 2010-12-27 2012-06-28 Samsung Electronics Co., Ltd. Apparatus for planning path of robot and method thereof
CN106737671A (en) * 2016-12-21 2017-05-31 西安科技大学 The bilayer personification motion planning method of seven degrees of freedom copy man mechanical arm
CN106843211A (en) * 2017-02-07 2017-06-13 东华大学 A kind of method for planning path for mobile robot based on improved adaptive GA-IAGA
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

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120165982A1 (en) * 2010-12-27 2012-06-28 Samsung Electronics Co., Ltd. Apparatus for planning path of robot and method thereof
CN106737671A (en) * 2016-12-21 2017-05-31 西安科技大学 The bilayer personification motion planning method of seven degrees of freedom copy man mechanical arm
CN106843211A (en) * 2017-02-07 2017-06-13 东华大学 A kind of method for planning path for mobile robot based on improved adaptive GA-IAGA
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

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
李赟程: "基于ROS平台下高维构形空间中机械臂的运动规划研究", 《中国硕士学位论文全文数据库-信息科技辑》 *

Cited By (66)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110919661A (en) * 2019-12-26 2020-03-27 中国科学院沈阳自动化研究所 Motion planning method for mechanical arm in glove box closed space
CN111251306A (en) * 2020-03-18 2020-06-09 广东省智能机器人研究院 Mechanical arm path planning method with chassis error
CN111650941A (en) * 2020-06-10 2020-09-11 湖南爱米家智能科技有限公司 Medical mobile robot path planning method, device, medium and equipment based on RRT-Connect improvement
CN111678523A (en) * 2020-06-30 2020-09-18 中南大学 Rapid BI _ RRT obstacle avoidance trajectory planning method based on STAR algorithm optimization
CN111761582A (en) * 2020-07-08 2020-10-13 浙江大学 Mobile mechanical arm obstacle avoidance planning method based on random sampling
CN111761582B (en) * 2020-07-08 2021-05-18 浙江大学 Mobile mechanical arm obstacle avoidance planning method based on random sampling
CN111531550A (en) * 2020-07-09 2020-08-14 浙江大华技术股份有限公司 Motion planning method and device, storage medium and electronic device
CN112223291A (en) * 2020-10-21 2021-01-15 哈工大机器人(合肥)国际创新研究院 Mechanical arm obstacle avoidance method and device based on three-dimensional task space constraint
CN112549016A (en) * 2020-10-21 2021-03-26 西安工程大学 Mechanical arm motion planning method
CN112223291B (en) * 2020-10-21 2022-02-11 哈工大机器人(合肥)国际创新研究院 Mechanical arm obstacle avoidance method and device based on three-dimensional task space constraint
CN112338916A (en) * 2020-10-29 2021-02-09 深圳市大象机器人科技有限公司 Mechanical arm obstacle avoidance path planning method and system based on fast expansion random tree
CN112393739A (en) * 2020-10-29 2021-02-23 国网安徽省电力有限公司检修分公司 Improved rapid search random tree path planning method in large-area environment
CN112338916B (en) * 2020-10-29 2024-07-23 深圳市大象机器人科技有限公司 Mechanical arm obstacle avoidance path planning method and system based on rapid expansion random tree
CN112677153A (en) * 2020-12-16 2021-04-20 东北林业大学 Improved RRT algorithm and industrial robot path obstacle avoidance planning method
CN112677153B (en) * 2020-12-16 2022-09-06 东北林业大学 Improved RRT algorithm and industrial robot path obstacle avoidance planning method
CN112833904B (en) * 2021-01-05 2024-06-04 北京航空航天大学 Unmanned vehicle dynamic path planning method based on free space and rapid random tree searching algorithm
CN112833904A (en) * 2021-01-05 2021-05-25 北京航空航天大学 Unmanned vehicle dynamic path planning method based on free space and fast search random tree algorithm
CN113031004B (en) * 2021-03-05 2024-04-16 西北工业大学 Unmanned ship water surface target detection and path planning method based on three-dimensional laser radar
CN113031004A (en) * 2021-03-05 2021-06-25 西北工业大学 Unmanned ship water surface target detection and path planning method based on three-dimensional laser radar
WO2022198993A1 (en) * 2021-03-22 2022-09-29 深圳市优必选科技股份有限公司 Method and apparatus for manipulator motion planning, readable storage medium, and manipulator
CN113119115A (en) * 2021-03-22 2021-07-16 深圳市优必选科技股份有限公司 Mechanical arm motion planning method and device, readable storage medium and mechanical arm
CN113296496A (en) * 2021-04-05 2021-08-24 青岛科技大学 Multi-sampling-point-based gravitational adaptive step size bidirectional RRT path planning method
CN113282077B (en) * 2021-04-08 2022-06-17 浙江工业大学 Concentric tube robot motion planning method based on normal distribution and Jacobian matrix
CN112947489A (en) * 2021-04-08 2021-06-11 华东理工大学 Method and device for planning collision-free path of welding robot in complex environment
CN112947489B (en) * 2021-04-08 2022-11-22 华东理工大学 Method and device for planning collision-free path of welding robot in complex environment
CN113282077A (en) * 2021-04-08 2021-08-20 浙江工业大学 Concentric tube robot motion planning method based on normal distribution RRT and Jacobian matrix
CN113084811B (en) * 2021-04-12 2022-12-13 贵州大学 Mechanical arm path planning method
CN113084811A (en) * 2021-04-12 2021-07-09 贵州大学 Mechanical arm path planning method
CN112987799A (en) * 2021-04-16 2021-06-18 电子科技大学 Unmanned aerial vehicle path planning method based on improved RRT algorithm
CN112987799B (en) * 2021-04-16 2022-04-05 电子科技大学 Unmanned aerial vehicle path planning method based on improved RRT algorithm
CN113276109A (en) * 2021-04-21 2021-08-20 国网上海市电力公司 RRT algorithm-based double-mechanical-arm decoupling motion planning method and system
CN113276109B (en) * 2021-04-21 2024-04-26 国网上海市电力公司 Dual-mechanical-arm decoupling motion planning method and system based on RRT algorithm
CN113103236A (en) * 2021-04-22 2021-07-13 山东大学 Rapid and gradual optimal mechanical arm obstacle avoidance path planning method
CN113172631A (en) * 2021-05-11 2021-07-27 西南交通大学 Mechanical arm autonomous obstacle avoidance method based on improved RRT algorithm
CN113324558A (en) * 2021-05-17 2021-08-31 亿嘉和科技股份有限公司 Grid map traversal algorithm based on RRT
CN113359748A (en) * 2021-06-22 2021-09-07 浙江科技学院 Improved Multi-RRT path planning method based on fusion prediction and AGV trolley
CN113359748B (en) * 2021-06-22 2022-05-10 杭州奇派自动化设备有限公司 Improved Multi-RRT path planning method based on fusion prediction and AGV trolley
CN113319013A (en) * 2021-07-08 2021-08-31 陕西科技大学 Apple intelligent sorting method based on machine vision
CN113723750A (en) * 2021-07-20 2021-11-30 中国科学技术大学先进技术研究院 Method and system for constructing robot humanoid operation action knowledge base
CN113515127B (en) * 2021-07-23 2022-09-13 华北电力大学(保定) Mobile robot path planning method and system
CN113515127A (en) * 2021-07-23 2021-10-19 华北电力大学(保定) Mobile robot path planning method and system
CN113485356A (en) * 2021-07-27 2021-10-08 西北工业大学 Robot rapid movement planning method
CN113485356B (en) * 2021-07-27 2022-06-21 西北工业大学 Robot rapid movement planning method
CN113448336A (en) * 2021-08-30 2021-09-28 天津施格机器人科技有限公司 3D obstacle avoidance path planning method
CN113885509A (en) * 2021-10-21 2022-01-04 广东电网有限责任公司广州供电局 Emergency power supply vehicle path planning method, device, equipment and storage medium
CN113885509B (en) * 2021-10-21 2024-02-06 广东电网有限责任公司广州供电局 Emergency power supply vehicle path planning method, device, equipment and storage medium
CN114115271A (en) * 2021-11-25 2022-03-01 江苏科技大学 Robot path planning method and system for improving RRT
CN114115271B (en) * 2021-11-25 2024-04-26 江苏科技大学 Robot path planning method and system for improving RRT
CN115958590A (en) * 2021-12-24 2023-04-14 合肥哈工图南智控机器人有限公司 RRT-based mechanical arm deep frame obstacle avoidance motion planning method and device
CN114177008A (en) * 2022-01-12 2022-03-15 上海大学 Upper limb rehabilitation robot control method and system based on variable virtual clamp
CN114700937B (en) * 2022-01-13 2024-02-13 深圳市越疆科技有限公司 Mechanical arm, motion path planning method thereof, control system, medium and robot
CN114700937A (en) * 2022-01-13 2022-07-05 深圳市越疆科技有限公司 Mechanical arm, movement path planning method thereof, control system, medium and robot
CN114310904B (en) * 2022-01-19 2024-07-02 中南大学 Novel bidirectional RRT method suitable for space path planning of mechanical arm joint
CN114310904A (en) * 2022-01-19 2022-04-12 中南大学 Novel bidirectional RRT method suitable for mechanical arm joint space path planning
CN114593743A (en) * 2022-03-02 2022-06-07 杭州华鲲云起信息技术有限公司 Path planning method and device based on improved bidirectional RRT algorithm
CN115167388A (en) * 2022-06-07 2022-10-11 哈尔滨理工大学 RRT multi-robot formation path planning algorithm based on target guidance
CN115091460A (en) * 2022-07-13 2022-09-23 江苏科技大学 Intelligent steel grabbing machine mechanical arm path planning method and system
CN115946108A (en) * 2022-10-09 2023-04-11 中国人民解放军海军工程大学 Mechanical arm dynamic obstacle avoidance path planning method
CN115870990A (en) * 2023-01-03 2023-03-31 西南交通大学 Obstacle avoidance path planning method for mechanical arm
CN115950439B (en) * 2023-03-15 2023-06-02 季华实验室 Bidirectional RRT path planning method and device, electronic equipment and storage medium
CN115950439A (en) * 2023-03-15 2023-04-11 季华实验室 Bidirectional RRT path planning method, device, electronic equipment and storage medium
CN116652952A (en) * 2023-06-09 2023-08-29 清华大学 Operation method and system for limited environment flexible cable by using double mechanical arms
CN116652972A (en) * 2023-07-31 2023-08-29 成都飞机工业(集团)有限责任公司 Series robot tail end track planning method based on bidirectional greedy search algorithm
CN116652972B (en) * 2023-07-31 2023-11-10 成都飞机工业(集团)有限责任公司 Series robot tail end track planning method based on bidirectional greedy search algorithm
CN117124335B (en) * 2023-10-25 2024-01-05 山东工商学院 Improved RRT path planning method based on path marking backtracking strategy
CN117124335A (en) * 2023-10-25 2023-11-28 山东工商学院 Improved RRT path planning method based on path marking backtracking strategy

Similar Documents

Publication Publication Date Title
CN110497403A (en) A kind of manipulator motion planning method improving two-way RRT algorithm
CN106444755B (en) Mobile robot path planning method based on improved genetic algorithm
CN108444489A (en) A kind of paths planning method improving RRT algorithms
CN106695802A (en) Improved RRT&lt;*&gt; obstacle avoidance motion planning method based on multi-degree-of-freedom mechanical arm
US9411335B2 (en) Method and apparatus to plan motion path of robot
US20220063099A1 (en) Framework of robotic online motion planning
CN106041931A (en) Collaborative collision-preventing path optimization method for multiple AGV robots in multi-barrier space
CN112809665B (en) Mechanical arm motion planning method based on improved RRT algorithm
CN110919661A (en) Motion planning method for mechanical arm in glove box closed space
CN112428274B (en) Space motion planning method of multi-degree-of-freedom robot
CN110275528B (en) Improved path optimization method for RRT algorithm
CN108413963A (en) Bar-type machine people&#39;s paths planning method based on self study ant group algorithm
CN115723129B (en) Continuous operation motion planning method for mechanical arm
Klanke et al. Dynamic path planning for a 7-DOF robot arm
Zghair et al. Intelligent Hybrid Path Planning Algorithms for Autonomous Mobile Robots.
Ren et al. Rearrangement-based manipulation via kinodynamic planning and dynamic planning horizons
Xu et al. Efficient object manipulation to an arbitrary goal pose: Learning-based anytime prioritized planning
CN115097814A (en) Mobile robot path planning method, system and application based on improved PSO algorithm
Naik et al. Pre-grasp approaching on mobile robots: a pre-active layered approach
BAYGIN et al. PSO based path planning approach for multi service robots in dynamic environments
Tang et al. Coordinated motion planning of dual-arm space robot with deep reinforcement learning
Soofiyani et al. A straight moving path planner for mobile robots in static environments using cellular automata
CN113146637B (en) Robot Cartesian space motion planning method
Wang et al. Research on multi-robots self-organizing cooperative pursuit algorithm based on Voronoi graph
Bhadoria et al. Optimized angular a star algorithm for global path search based on neighbor node evaluation

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20191126

RJ01 Rejection of invention patent application after publication