CN108762270A - The two-way rapidly-exploring random tree modified two-step method planning algorithm of changeable probability - Google Patents
The two-way rapidly-exploring random tree modified two-step method planning algorithm of changeable probability Download PDFInfo
- Publication number
- CN108762270A CN108762270A CN201810561112.2A CN201810561112A CN108762270A CN 108762270 A CN108762270 A CN 108762270A CN 201810561112 A CN201810561112 A CN 201810561112A CN 108762270 A CN108762270 A CN 108762270A
- Authority
- CN
- China
- Prior art keywords
- node
- path
- probability
- temp
- way
- 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 20
- 230000004888 barrier function Effects 0.000 claims abstract description 18
- 230000008569 process Effects 0.000 claims abstract description 5
- 238000005259 measurement Methods 0.000 claims description 4
- 230000000903 blocking effect Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 abstract description 4
- 238000005457 optimization Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 7
- 238000005070 sampling Methods 0.000 description 6
- 230000033001 locomotion Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012805 post-processing Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000015654 memory Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0217—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with energy consumption, time reduction or distance reduction criteria
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The present invention relates to a kind of two-way rapidly-exploring random tree modified two-step method planning algorithms of changeable probability; first; when importing state space graph; it needs to be set for state space pretreatment according to vehicle volume; state space edge is extended protection; it prevents node from getting too close to state space edge, causes to collide.Secondly, use a kind of changeable probability Object selection strategy quickening convergence rate based on node environment, finally, curved cut-off is carried out to the path after generation, whether there is barrier judgment between starting point and the line of subsequent node using first node, extra node is deleted, path is optimized, reduces turn number and total path length in trolley driving process.Changeable probability optimization algorithm is realized on original two-way RRT algorithms, is improved search speed in the way of target direction, is reduced calculation amount；Path length and node number are reduced simultaneously, and ensures trafficability.
Description
Technical field
The present invention relates to a kind of intelligent vehicle Path Planning Technique, more particularly to a kind of two-way rapidly-exploring random tree of changeable probability
Modified two-step method planning algorithm.
Background technology
Intelligent vehicle path planning refers to that intelligent vehicle finds an initial pose point to object pose point in configuration space
Continuous collisionless path, while this paths will also meet environmental constraints and intelligent vehicle itself movement characteristic.
For such case, there has been proposed RRT (rapidly-exploring random tree) algorithms, which is random search side
Formula, since it uses the planning mode of stochastical sampling, can need not be pre-processed in the non-convex space realizing route search of higher-dimension,
And search speed is fast, is especially apparent in higher dimensional space speed advantage, has been obtained extensively in robot motion planning field in recent years
General application and research.But itself there is also some defects：(1) it is sampled as stochastical sampling, a large amount of invalid samplings cause to calculate
Method convergence rate is slow；(2) metric function (nearest neighbor algorithm) may be difficult to obtain effectively there are Complex Constraints
Solution；(3) randomness of algorithm can cause the path generated unsmooth, will appear when directly using path a large amount of turnovers with it is invalid
Curved path.For the above-mentioned deficiency of basic RRT algorithms, domestic and foreign scholars also continuously improve the algorithm, with suitable
Answer different application environments.Kuffner and LaValle proposes Bi-RRT (two-way RRT), from original state and dbjective state
Two trees of parallel generation, can fast implement convergence；Then they have also been proposed RRT-connect algorithms, and the algorithm is in node
It is expanded using directive property when extension, the probability that directive property is expanded is also required to according to circumstances choose in practical applications.For RRT
The unsmooth problem in path caused by the randomness of algorithm, Fraichard and Scheuer are proposed to be made smoothly of clothoid
Processing, but clothoid solution calculation amount is very big；Lau et al. uses 5 Beziers, but does not account for path song
The continuity of rate and the own characteristic of robot, calculation amount are also larger.
Invention content
The present invention be directed to Rapid-Exploring Random Tree Algorithms to solve the problems, such as that robot motion planning exists, it is proposed that a kind of
The two-way rapidly-exploring random tree modified two-step method planning algorithm of changeable probability ensures to ensure road ability under search speed.
The technical scheme is that：A kind of two-way rapidly-exploring random tree modified two-step method planning algorithm of changeable probability, specifically
Include the following steps：
1) state space pretreatment is set for according to operation vehicle volume：Expand barrier region, reserves peace
Full distance；
2) RRT algorithms two-way to changeable probability carry out coordinates measurement：Two-way RRT algorithms generate path L, in iteration growth crack
In generating process, changeable probability algorithm is added, increases the constraints of surrounding enviroment, after often generating a node, using function
Detect (q) is detected using this node as driving vehicle center, and with the presence or absence of blocking in area circle needed for driving vehicle, i.e., area is justified
Whether with barrier region there is intersection, if any intersection, is distributed by non-uniform probability according to intersection and obtains a probability value P at random, generally
Rate value P and the target of setting are biased to probability value Pset and are compared, and Pset is less than 10%, P and is more than Pset, then abandons this node,
Use random function to generate node again；When P is less than Pset, then approves this node, be put into corresponding set；
3) path optimizing：
3.1) it initializes：Path L node path will have been generated and assigned Q, Q=(q0, q1, q2…qn), and by q0It assigns
qtemp, i=1；
3.2) q is judged by checkPath () function successivelytempWith its subsequent node qiBetween ∈ Q connecting line segments whether
There are barrier, i < n judge execution 3.3)；As i >=n, into 3.4)；
3.3) checkPath if () return value is 1, i.e. qtempWith its subsequent node qiClear between ∈ Q, then i=i
It+1 and returns and 3.2 continues to judge；If checkPath () return value is 0, i.e. qtempWith its subsequent node qiThere is obstacle between ∈ Q
Object, then by qtempWith qi-1Between knot removal, and by qi-1Assign qtempAnd it returns to 3.2 and continues to judge；
3.4) node is not deleted by link () functional link residue, generates path optimizing.
The beneficial effects of the present invention are：The two-way rapidly-exploring random tree modified two-step method planning algorithm of changeable probability of the present invention,
Vehicle is avoided to collide on path first with state space pretreatment；Then it realizes and becomes on original two-way RRT algorithms
Probability optimization algorithm improves search speed in the way of target direction, reduces calculation amount；Finally by post-processing realizing route
The reduction of length and node number.Emulation experiment shows that the algorithm can promote search speed, while reducing path length and section
Point number, and ensure trafficability.
Description of the drawings
Fig. 1 is reset condition space diagram of the present invention；
Fig. 2 is state space graph after state space edge treated of the present invention；
Fig. 3 is the two-way algorithm simulating results of original RRT such as figure below figure；
Fig. 4 is the route programming result that changeable probability algorithm improvement is added analogous diagram on Matlab of the invention；
Fig. 5 is the method for the present invention treated route result figure.
Specific implementation mode
In actual use, due to the volume of vehicle itself, (X, the Y) reality at state space edge and vehicle center
It needs to keep at a distance on border, therefore when importing state space graph, needs to be set for state sky according to vehicle volume
Between pre-process, state space edge is extended protection, prevents node from getting too close to state space edge, causes to collide.
A kind of changeable probability Object selection strategy based on node environment is used, i.e., after generating a node, using letter
Number detect (q) is detected with the presence or absence of (point for being not included in available mode space) is blocked in the single distance interval in periphery, such as
It is that target point carries out one extension there is no terminal is then chosen, obtains a tree node；Otherwise the target using a setting is inclined
To probability value Pset (general setting be less than 10%), when this random generating probability P is more than Pset, then random function is used to give birth to
At when less than Pset, also using terminal for target point.
Randomness is sampled in view of RRT algorithms, the Selection Strategy that target is directed toward despite the use of, but the path generated is usual
All it is unnatural, tortuous.In actual use, break can bring intelligent vehicle repetitive operation to turn to, and travel unnecessary road
Diameter, and can accelerating vehicle abrasion.Therefore, the path based on shortest path is proposed based on practical application and post-processes flow, it is right
Path after generation carries out curved cut-off, deletes unnecessary node, shorten path length, i.e., firstly the need of importing before
The path node obtained in coordinates measurement, then using first node as starting point, check with the connecting line of subsequent node whether with
Space with obstacle forms intersection, this node is deleted if not, otherwise continues checking for subsequent node connection by starting point of new node
Situation.
The two-way rapidly-exploring random tree modified two-step method planning algorithm of changeable probability of the present invention, is as follows：
The first step：Test platform is Intel i5,3.2GHz processors and 12GB memories, setting experiment scene state space
Size is 500 × 500, vehicle width 10, length 16, and beginning and end is set as [1,1] and [499,499], barrier
Region is black, as shown in Figure 1.State space pretreatment is set for according to vehicle volume first, by state space edge
Being extended protection, i.e. the right and left and headstock tailstock distance of vehicle center point (x, y) apart from vehicle is respectively x '=5, y '=
8, respectively to reserve safe distance 1 in processing, i.e. vehicle center point (x, y) at least will be x '=6 from obstacle distance, y '=7,
It prevents node from getting too close to state space edge, causes to collide.So the length and width of barrier are respectively increased by 1 by me in emulation, stay
Go out safe distance, as shown in Figure 2.If spacing is smaller between barrier, it cannot be guaranteed that vehicle can pass through after extension, then it is assumed that herein
It can not pass through.(notices that barrier is expanded in Fig. 3, expand part and do not showed with black, but can see route spacing
There is a distance from barrier.)
Second step：RRT algorithms two-way to changeable probability emulate on Matlab, and basic thought is：With starting point qinit
With target point qgoalFor the initial point of two search trees T1 and T2, search tree is built respectively, first by qinitIt is put into set E1(E1
It is to search for the q successfully generated every timenewSet), by qgoalIt is put into set E2(E2It is to search for the q ' successfully generated every timenew's
Set), it is extended, is searched for for the first time, q with wherein one tree T1init=qnea, with qnearFor starting point, using step-length ε as distance,
In a manner of stochastical sampling a state node q is constructed at accessible placerand, such as qnearWith this state node qrandBetween line
There is no barrier, then by this state node qrandAssign qnew1, qnew1It is put into E1, find the first leaf node q on T1new1, this
Shi Jihe E1In have qinitAnd qnew12 points；Then it carries out searching for for second, qnew1=qnear, with qnearFor starting point, it is with step-length ε
Distance constructs a state node q again in a manner of stochastical sampling at accessible placerand, such as qnearWith this state node
qrandThere is no barrier between line, then by this state node qrandAssign qnew2, qnew2It is put into E1, find the second leaf on T1
Child node qnew2；It is sequentially generated each node on T1.Same method is with qgoalEach node on T2 is generated for initial point.
Search for E1And E2In whether have identical point, i.e. qnewi=q 'newj, or in E1And E2In be respectively present a point qnewiWith
q’newj, this distance between two points be less than or equal to step-length ε, then by the two point set qnewiAnd q 'newjFor q1endAnd q2end.If meeting item
Part, it is believed that search is completed.When a search is completed, respectively in E1And E2In with q1endAnd q2endQ is traced back to for starting pointinitAnd qgoal,
In E1In obtain a paths l1, in E2In obtain a paths l2, finally l1 is connected to obtain one with all nodes in l2
The final path L of item, this generates Path Method for two-way RRT algorithms.
In order to ensure path road ability, changeable probability algorithm is added and increases periphery in iteration growth crack generating process
The constraints of environment after often generating a node, uses function detect (q) detections using this node as driving vehicle center,
With the presence or absence of blocking in area circle needed for driving vehicle, i.e., whether area circle with barrier region has intersection, if any using one
The target of setting is biased to probability value Pset (general setting is less than 10%) and the distribution of this non-uniform probability generates random number P and carries out
Compare, generates random number P more than Pset when this non-uniform probability is distributed, then abandon this node, use random function to generate again
Node then approves this node, is put into corresponding set when P is less than Pset.Exist in area circle needed for driving vehicle and blocks, root
According to the position distribution blocked and size cases are blocked, random number P can be automatically generated by non-uniform probability distribution, and target deviation refers to
In stochastical sampling point qrandThe super q of Shi JinlianggoalThat direction takes a little, rather than grows cotyledon node towards other direction, thus more
Fast generation path, just sets when carrying out generation path.
The results are shown in Figure 3 for the original two-way algorithm simulatings of RRT.The route programming result that changeable probability algorithm improvement is added exists
It is emulated on Matlab as shown in Figure 4.
Third walks：The path node obtained in coordinates measurement before is imported, then with starting point qinitFor starting point, according to
Secondary and follow-up first node, second node, Section 3 point line, obtain line segment L01、L02、L03, and check L01、L02、L03Whether with barrier
Space is hindered to form intersection, such as L03There are intersection, L01、L02There is no intersection, then delete first node, retains second node；Again with Section 2
Point is starting point, is sequentially connected each node after second node, obtains line segment L23、L24、L25、L26, check L23、L24、L25、L26It is
It is no to form intersection, such as L with space with obstacle26There are intersection, L23、L24、L25There is no intersection, then delete this 3rd, 4 node, retains the 5th
Node, and so on, generate path optimizing.It is as follows：
3.1 initialization：Path node path will have been generated and assigned Q (q0, q1, q2…qn), and assign q0 to qtemp, i=
1；
3.2 judge q successively by checkPath () functiontempWith its subsequent node qiWhether deposited between ∈ Q connecting line segments
In barrier, i < n judge execution 3.3；As i >=n, into 3.4.
If 3.3 checkPath () return values are 1, i.e. qtempWith its subsequent node qiClear between ∈ Q, then i=i+
It 1 and returns and 3.2 continues to judge；If checkPath () return value is 0, i.e. qtempWith its subsequent node qiThere is obstacle between ∈ Q
Object, then by qtempWith qi-1Between knot removal, and by qi-1Assign qtempAnd it returns to 3.2 and continues to judge.
3.4 are not deleted node by link () functional link residue, generate path optimizing.
Treated, and route result is illustrated in fig. 5 shown below, and dotted line is the search result under changeable probability algorithm, and solid line is post-processing
Under path.
Claims (1)
1. a kind of two-way rapidly-exploring random tree modified two-step method planning algorithm of changeable probability, which is characterized in that specifically include following step
Suddenly：
1) state space pretreatment is set for according to operation vehicle volume：Expand barrier region, reserve safety away from
From；
2) RRT algorithms two-way to changeable probability carry out coordinates measurement：Two-way RRT algorithms generate path L, are generated in iteration growth crack
In the process, changeable probability algorithm is added, increases the constraints of surrounding enviroment, after often generating a node, using function
Detect (q) is detected using this node as driving vehicle center, and with the presence or absence of blocking in area circle needed for driving vehicle, i.e., area is justified
Whether with barrier region there is intersection, if any intersection, is distributed by non-uniform probability according to intersection and obtains a probability value P at random, generally
Rate value P and the target of setting are biased to probability value Pset and are compared, and Pset is less than 10%, P and is more than Pset, then abandons this node,
Use random function to generate node again；When P is less than Pset, then approves this node, be put into corresponding set；
3) path optimizing：
3.1) it initializes：Path L node path will have been generated and assigned Q, Q=(q0, q1, q2...qn), and by q0Assign qtemp, i
=1；
3.2) q is judged by checkPath () function successivelytempWith its subsequent node qiWith the presence or absence of barrier between ∈ Q connecting line segments
Object, i < n is hindered to judge execution 3.3)；As i >=n, into 3.4)；
3.3) checkPath if () return value is 1, i.e. qtempWith its subsequent node qiClear between ∈ Q, then i=i+1 is simultaneously
3.2 are returned to continue to judge；If checkPath () return value is 0, i.e. qtempWith its subsequent node qiThere is barrier between ∈ Q, then
By qtempWith qi-1Between knot removal, and by qi-1Assign qtempAnd it returns to 3.2 and continues to judge；
3.4) node is not deleted by link () functional link residue, generates path optimizing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810561112.2A CN108762270B (en) | 2018-06-01 | 2018-06-01 | Improved path planning algorithm for variable probability bidirectional fast search random tree |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810561112.2A CN108762270B (en) | 2018-06-01 | 2018-06-01 | Improved path planning algorithm for variable probability bidirectional fast search random tree |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108762270A true CN108762270A (en) | 2018-11-06 |
| CN108762270B CN108762270B (en) | 2021-04-27 |
Family
ID=64002223
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810561112.2A Expired - Fee Related CN108762270B (en) | 2018-06-01 | 2018-06-01 | Improved path planning algorithm for variable probability bidirectional fast search random tree |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108762270B (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109116858A (en) * | 2018-11-07 | 2019-01-01 | 上海木木聚枞机器人科技有限公司 | It is a kind of on specified path around barrier paths planning method and system |
| CN109798909A (en) * | 2019-02-01 | 2019-05-24 | 安徽达特智能科技有限公司 | A kind of method of global path planning |
| CN110118559A (en) * | 2019-04-30 | 2019-08-13 | 厦门大学 | A kind of guide to visitors robot dynamic obstacle avoidance method and apparatus based on changeable probability strategy |
| CN110275528A (en) * | 2019-06-04 | 2019-09-24 | 合肥工业大学 | For the method for optimizing route of RRT algorithm improvement |
| CN110986953A (en) * | 2019-12-13 | 2020-04-10 | 深圳前海达闼云端智能科技有限公司 | Path planning method, robot and computer readable storage medium |
| 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 |
| CN112344938A (en) * | 2020-10-31 | 2021-02-09 | 哈尔滨工程大学 | Space environment path generation and planning method based on pointing and potential field parameters |
| 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 |
| CN113064426A (en) * | 2021-03-17 | 2021-07-02 | 安徽工程大学 | Intelligent vehicle path planning method for improving bidirectional fast search random tree algorithm |
| 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 |
| CN113419542A (en) * | 2021-07-16 | 2021-09-21 | 浙江大华技术股份有限公司 | Path planning method, device 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 |
| CN114161416A (en) * | 2021-12-06 | 2022-03-11 | 贵州大学 | Robot path planning method based on potential function |
| WO2023016101A1 (en) * | 2021-08-13 | 2023-02-16 | 苏州大学 | Heuristic bias sampling-based indoor environment robot exploration method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110035087A1 (en) * | 2009-08-10 | 2011-02-10 | Samsung Electronics Co., Ltd. | Method and apparatus to plan motion path of robot |
| CN103777629A (en) * | 2013-09-05 | 2014-05-07 | 武汉汉迪机器人科技有限公司 | Self-guide carrying platform and navigation control method for carrying platform |
| CN104155974A (en) * | 2013-07-29 | 2014-11-19 | 深圳信息职业技术学院 | Path planning method and apparatus for robot fast collision avoidance |
| CN107943053A (en) * | 2017-12-15 | 2018-04-20 | 陕西理工大学 | A kind of paths planning method of mobile robot |
| CN108088447A (en) * | 2017-12-15 | 2018-05-29 | 陕西理工大学 | A kind of path post-processing approach of mobile robot |
-
2018
- 2018-06-01 CN CN201810561112.2A patent/CN108762270B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110035087A1 (en) * | 2009-08-10 | 2011-02-10 | Samsung Electronics Co., Ltd. | Method and apparatus to plan motion path of robot |
| CN104155974A (en) * | 2013-07-29 | 2014-11-19 | 深圳信息职业技术学院 | Path planning method and apparatus for robot fast collision avoidance |
| CN103777629A (en) * | 2013-09-05 | 2014-05-07 | 武汉汉迪机器人科技有限公司 | Self-guide carrying platform and navigation control method for carrying platform |
| CN107943053A (en) * | 2017-12-15 | 2018-04-20 | 陕西理工大学 | A kind of paths planning method of mobile robot |
| CN108088447A (en) * | 2017-12-15 | 2018-05-29 | 陕西理工大学 | A kind of path post-processing approach of mobile robot |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109116858A (en) * | 2018-11-07 | 2019-01-01 | 上海木木聚枞机器人科技有限公司 | It is a kind of on specified path around barrier paths planning method and system |
| CN109116858B (en) * | 2018-11-07 | 2021-09-07 | 诺亚机器人科技(上海)有限公司 | Obstacle-detouring path planning method and system on designated path |
| CN109798909A (en) * | 2019-02-01 | 2019-05-24 | 安徽达特智能科技有限公司 | A kind of method of global path planning |
| CN110118559A (en) * | 2019-04-30 | 2019-08-13 | 厦门大学 | A kind of guide to visitors robot dynamic obstacle avoidance method and apparatus based on changeable probability strategy |
| CN110118559B (en) * | 2019-04-30 | 2021-05-25 | 厦门大学 | Navigation robot dynamic obstacle avoidance method and device based on variable probability strategy |
| CN110275528A (en) * | 2019-06-04 | 2019-09-24 | 合肥工业大学 | For the method for optimizing route of RRT algorithm improvement |
| CN110275528B (en) * | 2019-06-04 | 2022-08-16 | 合肥工业大学 | Improved path optimization method for RRT algorithm |
| CN110986953A (en) * | 2019-12-13 | 2020-04-10 | 深圳前海达闼云端智能科技有限公司 | Path planning method, robot and computer readable storage medium |
| CN110986953B (en) * | 2019-12-13 | 2022-12-06 | 达闼机器人股份有限公司 | Path planning method, robot and computer readable storage medium |
| 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 |
| CN112344938A (en) * | 2020-10-31 | 2021-02-09 | 哈尔滨工程大学 | Space environment path generation and planning method based on pointing and potential field parameters |
| CN112344938B (en) * | 2020-10-31 | 2022-07-19 | 安徽中科源起科技有限公司 | Space environment path generation and planning method based on pointing and potential field parameters |
| CN113064426A (en) * | 2021-03-17 | 2021-07-02 | 安徽工程大学 | Intelligent vehicle path planning method for improving bidirectional fast search random tree algorithm |
| 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 |
| 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 |
| 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 |
| CN113419542A (en) * | 2021-07-16 | 2021-09-21 | 浙江大华技术股份有限公司 | Path planning method, device 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 |
| WO2023016101A1 (en) * | 2021-08-13 | 2023-02-16 | 苏州大学 | Heuristic bias sampling-based indoor environment robot exploration method |
| CN114161416A (en) * | 2021-12-06 | 2022-03-11 | 贵州大学 | Robot path planning method based on potential function |
| CN114161416B (en) * | 2021-12-06 | 2023-04-28 | 贵州大学 | Robot path planning method based on potential function |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108762270B (en) | 2021-04-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108762270A (en) | The two-way rapidly-exploring random tree modified two-step method planning algorithm of changeable probability | |
| CN109976148A (en) | Robot motion's paths planning method, device, storage medium and terminal device | |
| CN108896052A (en) | A kind of mobile robot smooth paths planing method under the environment based on DYNAMIC COMPLEX | |
| Xue et al. | Path planning of mobile robot based on improved ant colony algorithm for logistics | |
| CN102799179B (en) | Mobile robot path planning algorithm based on single-chain sequential backtracking Q-learning | |
| CN111752306B (en) | Unmanned aerial vehicle route planning method based on fast-expanding random tree | |
| CN108253984A (en) | A kind of method for planning path for mobile robot based on improvement A star algorithms | |
| CN107943053A (en) | A kind of paths planning method of mobile robot | |
| CN105527964A (en) | Robot path planning method | |
| CN109459031A (en) | A kind of unmanned plane RRT method for optimizing route based on greedy algorithm | |
| Pan et al. | Research for path planning based on improved astart algorithm | |
| Meng et al. | UAV path re-planning based on improved bidirectional RRT algorithm in dynamic environment | |
| CN113359746A (en) | Path planning method and device based on improved bidirectional RRT and Dijkstra fusion algorithm | |
| CN113189988B (en) | Autonomous path planning method based on Harris algorithm and RRT algorithm composition | |
| CN110275528A (en) | For the method for optimizing route of RRT algorithm improvement | |
| CN111251306A (en) | Mechanical arm path planning method with chassis error | |
| CN108088447A (en) | A kind of path post-processing approach of mobile robot | |
| CN115129064A (en) | Path planning method based on fusion of improved firefly algorithm and dynamic window method | |
| Zhang et al. | Mobile robot path planning base on the hybrid genetic algorithm in unknown environment | |
| Li et al. | SP-NN: A novel neural network approach for path planning | |
| CN109977455B (en) | Ant colony optimization path construction method suitable for three-dimensional space with terrain obstacles | |
| Ma et al. | Robot path planning using fusion algorithm of ant colony optimization and genetic algorithm | |
| Li et al. | Neural-fuzzy control of truck backer-upper system using a clustering method | |
| CN111582556B (en) | Intelligent parcel sorting system path planning method based on RRT algorithm | |
| CN114310904A (en) | Novel bidirectional RRT method suitable for mechanical arm joint space path planning |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210427 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |