CN104765371A - Route planning method based on rolling window deep searching and fuzzy control fusion - Google Patents
Route planning method based on rolling window deep searching and fuzzy control fusion Download PDFInfo
- Publication number
- CN104765371A CN104765371A CN201510193519.0A CN201510193519A CN104765371A CN 104765371 A CN104765371 A CN 104765371A CN 201510193519 A CN201510193519 A CN 201510193519A CN 104765371 A CN104765371 A CN 104765371A
- Authority
- CN
- China
- Prior art keywords
- point
- path
- fuzzy control
- detect
- scrolling windows
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Feedback Control In General (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention relates to a route planning method based on rolling window deep searching and fuzzy control fusion. The route planning method is characterized by comprising the following steps that (S01) environment modeling is carried out, wherein a polar coordinate mode is adopted; (S02) rolling optimization and deep searching are carried out to search for route key points, wherein a circular rolling window is made with the current position of a robot as the circle center and the distance of sensors of the robot as the radius, the optimal sub targets of a next step are calculated according to the position of a target point and a specific optimizing strategy, and thus the route key points are obtained; (S03) whether the route key points are valid or not is detected, and fuzzy control is applied between every two adjacent route key points to search for a route and arrive at the target point. The route planning method is based on rolling window deep searching and is simple, the searching range is limited more ingeniously, and efficiency is improved; the deep searching and the fuzzy control are fused, and the real-time obstacle avoidance function is achieved while the global route planning is carried out.
Description
Technical field
The present invention relates to robotics, particularly the paths planning method that merges of a kind of deep search based on scrolling windows and fuzzy control.
Background technology
Robot is the installations automatically performing work.It both can accept mankind commander, can run again the program of layout in advance, also can according to the principle guiding principle action of formulating with artificial intelligence technology.The development of current robot grows up all over the world just with surprising rapidity.In the research of mobile robot's correlation technique, airmanship is its core, and path planning receives increasing concern as one of core content in navigation, existing lot of research.
At present, the method commonly used has Visual Graph method, heuristic graph searching method, Artificial Potential Field Method, A* algorithm etc.These algorithms have respective relative merits, as Artificial Potential Field has good real-time, but there is trap area, and A* algorithm is more suitable for solving single-object problem.In recent years, progress was constantly determined in the research along with intelligent algorithm, and many intelligent algorithms are also used in the path planning of mobile robot, comprise fuzzy logic, neural network, genetic algorithm, ant group algorithm and particle cluster algorithm etc.These algorithms have respective advantage, but also there is many problems, as excessive in algorithm complexity, local optimum, search volume etc.These algorithms require high to hardware condition, and can not meet the requirement of real-time of robot.
Summary of the invention
The object of the invention is the paths planning method proposing to merge based on deep search and the fuzzy control of scrolling windows, be intended to propose a kind of paths planning method, the method utilizes Rolling Planning, controlling depth hunting zone, global path key point can be found fast, reduce planning time; And between the key point of path, use fuzzy control, instruct local paths planning, there is Real Time Obstacle Avoiding function.
The present invention adopts following scheme to realize: the paths planning method that a kind of deep search based on scrolling windows and fuzzy control are merged, and it is characterized in that comprising the following steps:
Step S01: environmental modeling, adopts polar coordinate mode;
Step S02: rolling optimization deep search finds path key point, with robot current location for the center of circle, with robot sensor distance for radius, do circular scrolling window, next step optimum sub-goal is calculated, i.e. way to acquire key point according to aiming spot and specific optimisation strategy;
Step S03: whether effectively detect path key point, use fuzzy control between path key point adjacent between two, find path, arrive impact point.
In an embodiment of the present invention, the specific implementation of described step S01:
Step S011: set the current location of robot as S
i, the distance of reaction of robot sensor is R, S
iand the distance of G is D between impact point; With S
ifor scrolling windows C is in the center of circle
iif, R≤D, then scrolling windows C
iradius is R, if R>D, then and scrolling windows C
iradius is D; With S
ifor ray starting point, do the ray being parallel to x-axis, using this ray as polar axis shaft;
Step S012: the barrier in space represents with footpath, pole and polar angle;
Step S013: by scrolling windows C
i, be divided into n sector region { d
1, d
2..., d
n, each fan-shaped angle is 360/n degree.
In an embodiment of the present invention, the specific implementation of described step S02:
Step S021: initialization m local is explored a little;
Connect robot current location S
iwith impact point G, line and scrolling windows C
iintersect at P
ipoint;
At S
ip
ion line segment, m sensing point { q is evenly set
1, q
2..., q
m, and with S
ifor the center of circle, with S
idistance to each sensing point is radius, does m concentric circles;
Step S022: adjustment sensing point position, finds the path key point on this scrolling windows;
Detect successively from first sensing point, first detect S
iq
1whether line is crossing with barrier, if non-intersect, then retains q
1point; If intersected, then at q
1non-barrier region in the segmental arc that place covering of the fan is corresponding, resets q
1point, until S
iq
1line and barrier non-intersect, or arrive maximum iteration time;
Detect q again
1q
2, according to adjustment location method adjustment q
2position, determines q
2behind position, then detect q
2q
3, determine q
3position, until detect q
mp
i, determine critical path point P
iposition.
In an embodiment of the present invention, the specific implementation of described step S03:
Step S031: whether effectively detect path key point.Detect each path key point successively whether in barrier, if in barrier, then remove this critical path point.
Step S032: FUZZY ALGORITHMS FOR CONTROL is applied between adjacent critical path point, completes global path planning.
The invention has the beneficial effects as follows: the present invention proposes the paths planning method merged based on deep search and the fuzzy control of scrolling windows, the method uses scrolling windows deep search method, find global path key point, ensure to there is feasible path, for Global motion planning provides guidance between the key point of path; Between key point, use fuzzy control simultaneously, complete global path planning.Based on the deep search of scrolling windows, method is simple, limits hunting zone more cleverly, raises the efficiency; Again itself and fuzzy control are merged, while global path planning, possess Real Time Obstacle Avoiding function.
Accompanying drawing explanation
Fig. 1 is path planning algorithm process flow diagram of the present invention.
Fig. 2 is environmental modeling schematic diagram of the present invention.
Fig. 3 is local rolling deep search path of the present invention key point.
Embodiment
For enabling above-mentioned purpose of the present invention, feature and advantage more become apparent, and are described in detail the specific embodiment of the present invention below in conjunction with accompanying drawing.
Set forth detail in the following description so that fully understand the present invention.But the present invention can be different from alternate manner described here to implement with multiple, those skilled in the art can when without prejudice to doing similar popularization when intension of the present invention.Therefore the present invention is not by the restriction of following public embodiment.
The paths planning method that the present embodiment provides a kind of deep search based on scrolling windows and fuzzy control to merge, is characterized in that comprising the following steps:
Step S01: environmental modeling, adopts polar coordinate mode;
Step S02: rolling optimization deep search finds path key point, with robot current location for the center of circle, with robot sensor distance for radius, do circular scrolling window, next step optimum sub-goal is calculated, i.e. way to acquire key point according to aiming spot and specific optimisation strategy;
Step S03: whether effectively detect path key point, use fuzzy control between path key point adjacent between two, find path, arrive impact point.
Refer to Fig. 1, below each step is specifically described.
(1) environmental modeling, as shown in Figure 2.
1. set the current location of robot as S
i, the distance of reaction of robot sensor is R, S
iand the distance of G is D between impact point; With S
ifor scrolling windows C is in the center of circle
iif, R≤D, then scrolling windows C
iradius is R, if R>D, then and scrolling windows C
iradius is D; With S
ifor ray starting point, do the ray being parallel to x-axis, using this ray as polar axis shaft;
2. the barrier in space represents with footpath, pole and polar angle;
3. by scrolling windows C
i, be divided into n sector region { d
1, d
2..., d
n, each fan-shaped angle is 360/n degree.
(2) local rolling deep search path key point, as shown in Figure 3.
Select a covering of the fan to search for, such as, at covering of the fan d according to local searching strategy at every turn
jinside search critical path point, then store this key point, if at d
jinside do not search critical path point, then search for next covering of the fan d
j+1, until find critical path point.Then scrolling windows moves to this critical path point, continues to explore next critical path point.
When scrolling windows radius is D, impact point is described just on scrolling windows, then the critical path point corresponding to this scrolling windows is exactly impact point G, does not need to search for this scrolling windows again.
Wherein, determine the local searching strategy of critical path point, specific as follows:
1. initialization m local is explored a little;
Connect robot current location S
iwith impact point G, line and scrolling windows C
iintersect at P
ipoint;
At S
ip
ion line segment, m sensing point { q is evenly set
1, q
2..., q
m, and with S
ifor the center of circle, with S
idistance to each sensing point is radius, does m concentric circles;
2. adjust sensing point position, find the path key point on this scrolling windows
Detect successively from first sensing point, first detect S
iq
1whether line is crossing with barrier, if non-intersect, then retains q
1point; If intersected, then at q
1non-barrier region in the segmental arc that place covering of the fan is corresponding, resets q
1point, until S
iq
1line and barrier non-intersect, or arrive maximum iteration time;
Detect q again
1q
2, according to adjustment location method adjustment q
2position, determines q
2behind position, then detect q
2q
3, determine q
3position, until detect q
mp
i, determine critical path point P
iposition.Wherein, i represents rolling sequence number; Initial machine people position is S
0, corresponding first scrolling windows C
0, correspondence obtains P
0point; Find next localized target point S
1, scrolling windows response rolls forward forms C
1, now correspondence obtains P
1point ... .. once analogize.
In the present embodiment, n is general, and value is greater than 6, is less than 12.The value of n determines the scope (scrolling windows is divided into n part) of a Local Search, and it is large that n gets, then the scope of a Local Search is little; N obtains little, then the scope of a Local Search is large.M is general, and value is greater than 5, is less than 10.Concrete condition, determines according to scrolling windows size, and scrolling windows radius is large, then m value is large; Radius is little, then m value is little.
(3) between critical path point, use fuzzy control, complete global path planning.
1. whether effectively path key point is detected.Detect each path key point successively whether in barrier, if in barrier, then remove this critical path point.
2. FUZZY ALGORITHMS FOR CONTROL is applied between adjacent critical path point, completes global path planning.
By the paths planning method merged based on polar coordinates particle cluster algorithm and the fuzzy control of scrolling windows, find path, Real Time Obstacle Avoiding, finally arrive impact point.
Although the present invention with preferred embodiment openly as above; but it is not for limiting the present invention; any those skilled in the art without departing from the spirit and scope of the present invention; the Method and Technology content of above-mentioned announcement can be utilized to make possible variation and amendment to technical solution of the present invention; therefore; every content not departing from technical solution of the present invention; the any simple modification done above embodiment according to technical spirit of the present invention, equivalent variations and modification, all belong to the protection domain of technical solution of the present invention.The foregoing is only preferred embodiment of the present invention, all equalizations done according to the present patent application the scope of the claims change and modify, and all should belong to covering scope of the present invention.
Claims (4)
1., based on the paths planning method that deep search and the fuzzy control of scrolling windows are merged, it is characterized in that comprising the following steps:
Step S01: environmental modeling, adopts polar coordinate mode;
Step S02: rolling optimization deep search finds path key point, with robot current location for the center of circle, with robot sensor distance for radius, do circular scrolling window, next step optimum sub-goal is calculated, i.e. way to acquire key point according to aiming spot and specific optimisation strategy;
Step S03: whether effectively detect path key point, use fuzzy control between path key point adjacent between two, find path, arrive impact point.
2. the paths planning method that merges of the deep search based on scrolling windows according to claim 1 and fuzzy control, is characterized in that: the specific implementation of described step S01:
Step S011: set the current location of robot as S
i, the distance of reaction of robot sensor is R, S
iand the distance of G is D between impact point; With S
ifor scrolling windows C is in the center of circle
iif, R≤D, then scrolling windows C
iradius is R, if R>D, then and scrolling windows C
iradius is D; With S
ifor ray starting point, do the ray being parallel to x-axis, using this ray as polar axis shaft;
Step S012: the barrier in space represents with footpath, pole and polar angle;
Step S013: by scrolling windows C
i, be divided into n sector region { d
1, d
2..., d
n, each fan-shaped angle is 360/n degree.
3. the paths planning method that merges of the deep search based on scrolling windows according to claim 1 and fuzzy control, is characterized in that: the specific implementation of described step S02:
Step S021: initialization m local is explored a little;
Connect robot current location S
iwith impact point G, line and scrolling windows C
iintersect at P
ipoint;
At S
ip
ion line segment, m sensing point { q is evenly set
1, q
2..., q
m, and with S
ifor the center of circle, with S
idistance to each sensing point is radius, does m concentric circles;
Step S022: adjustment sensing point position, finds the path key point on this scrolling windows;
Detect successively from first sensing point, first detect S
iq
1whether line is crossing with barrier, if non-intersect, then retains q
1point; If intersected, then at q
1non-barrier region in the segmental arc that place covering of the fan is corresponding, resets q
1point, until S
iq
1line and barrier non-intersect, or arrive maximum iteration time;
Detect q again
1q
2, according to adjustment location method adjustment q
2position, determines q
2behind position, then detect q
2q
3, determine q
3position, until detect q
mp
i, determine critical path point P
iposition.
4. the paths planning method that merges of the deep search based on scrolling windows according to claim 1 and fuzzy control, is characterized in that: the specific implementation of described step S03:
Step S031: whether effectively detect path key point.Detect each path key point successively whether in barrier, if in barrier, then remove this critical path point.
Step S032: FUZZY ALGORITHMS FOR CONTROL is applied between adjacent critical path point, completes global path planning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510193519.0A CN104765371A (en) | 2015-04-22 | 2015-04-22 | Route planning method based on rolling window deep searching and fuzzy control fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510193519.0A CN104765371A (en) | 2015-04-22 | 2015-04-22 | Route planning method based on rolling window deep searching and fuzzy control fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104765371A true CN104765371A (en) | 2015-07-08 |
Family
ID=53647277
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510193519.0A Pending CN104765371A (en) | 2015-04-22 | 2015-04-22 | Route planning method based on rolling window deep searching and fuzzy control fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104765371A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106598055A (en) * | 2017-01-19 | 2017-04-26 | 北京智行者科技有限公司 | Intelligent vehicle local path planning method, device thereof, and vehicle |
| CN106774329A (en) * | 2016-12-29 | 2017-05-31 | 大连理工大学 | A kind of robot path planning method based on oval tangent line construction |
| CN107133917A (en) * | 2017-05-04 | 2017-09-05 | 天津大学 | Search merging method for drawing effective and safe region in Safe firing zone figure automatically |
| CN107798861A (en) * | 2017-11-30 | 2018-03-13 | 湖北汽车工业学院 | A kind of vehicle cooperative formula formation running method and system |
| CN108917770A (en) * | 2018-07-25 | 2018-11-30 | 重庆交通大学 | A kind of industrial robot route searching optimization method |
| CN109520507A (en) * | 2018-12-05 | 2019-03-26 | 智灵飞（北京）科技有限公司 | A kind of unmanned plane real-time route planing method based on improvement RRT |
| CN109669446A (en) * | 2017-10-13 | 2019-04-23 | 苏州宝时得电动工具有限公司 | Return guide line finding method, device and automatic mobile device |
| CN112083724A (en) * | 2020-08-31 | 2020-12-15 | 南京凌华微电子科技有限公司 | Remote control system and method for service robot |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008234447A (en) * | 2007-03-22 | 2008-10-02 | Yaskawa Electric Corp | Movable body control device and movable body equipped with the same |
| CN101604166A (en) * | 2009-07-10 | 2009-12-16 | 杭州电子科技大学 | A kind of method for planning path for mobile robot based on particle swarm optimization algorithm |
| CN101738195A (en) * | 2009-12-24 | 2010-06-16 | 厦门大学 | Method for planning path for mobile robot based on environmental modeling and self-adapting window |
| CN103605368A (en) * | 2013-12-04 | 2014-02-26 | 苏州大学张家港工业技术研究院 | Method and device for route programming in dynamic unknown environment |
| CN103823466A (en) * | 2013-05-23 | 2014-05-28 | 电子科技大学 | Path planning method for mobile robot in dynamic environment |
-
2015
- 2015-04-22 CN CN201510193519.0A patent/CN104765371A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008234447A (en) * | 2007-03-22 | 2008-10-02 | Yaskawa Electric Corp | Movable body control device and movable body equipped with the same |
| CN101604166A (en) * | 2009-07-10 | 2009-12-16 | 杭州电子科技大学 | A kind of method for planning path for mobile robot based on particle swarm optimization algorithm |
| CN101738195A (en) * | 2009-12-24 | 2010-06-16 | 厦门大学 | Method for planning path for mobile robot based on environmental modeling and self-adapting window |
| CN103823466A (en) * | 2013-05-23 | 2014-05-28 | 电子科技大学 | Path planning method for mobile robot in dynamic environment |
| CN103605368A (en) * | 2013-12-04 | 2014-02-26 | 苏州大学张家港工业技术研究院 | Method and device for route programming in dynamic unknown environment |
Non-Patent Citations (4)
| Title |
|---|
| QUNJIE DUAN ET AL.: "Research on Real Time Path Planning Method for the Underwater Robot in Unknown Environment with Random Shape Obstacle", 《PROCEEDINGS OF THE 2006 IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS AND AUTOMATION JUNE 25 - 28, 2006, LUOYANG, CHINA》 * |
| 杜宇上: "一种基于模糊逻辑的滚动窗口路径规划方法", 《现代电子技术》 * |
| 罗竹青 等: "同心圆策略下机器人路径滚动规划遗传算法", 《电脑知识与技术》 * |
| 肖本贤 等: "以期望方向角为优化目标的机器人滚动路径规划", 《PROCEEDINGS OF THE 27TH CHINESE CONTROL CONFERENCE》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106774329A (en) * | 2016-12-29 | 2017-05-31 | 大连理工大学 | A kind of robot path planning method based on oval tangent line construction |
| CN106774329B (en) * | 2016-12-29 | 2019-08-13 | 大连理工大学 | A kind of robot path planning method based on oval tangent line construction |
| CN106598055A (en) * | 2017-01-19 | 2017-04-26 | 北京智行者科技有限公司 | Intelligent vehicle local path planning method, device thereof, and vehicle |
| CN106598055B (en) * | 2017-01-19 | 2019-05-10 | 北京智行者科技有限公司 | A kind of intelligent vehicle local paths planning method and its device, vehicle |
| CN107133917A (en) * | 2017-05-04 | 2017-09-05 | 天津大学 | Search merging method for drawing effective and safe region in Safe firing zone figure automatically |
| CN107133917B (en) * | 2017-05-04 | 2019-11-08 | 天津大学 | For drawing the search merging method in effective and safe region in Safe firing zone figure automatically |
| CN109669446A (en) * | 2017-10-13 | 2019-04-23 | 苏州宝时得电动工具有限公司 | Return guide line finding method, device and automatic mobile device |
| CN109669446B (en) * | 2017-10-13 | 2022-04-15 | 苏州宝时得电动工具有限公司 | Regression guide line searching method and device and automatic moving equipment |
| CN107798861A (en) * | 2017-11-30 | 2018-03-13 | 湖北汽车工业学院 | A kind of vehicle cooperative formula formation running method and system |
| CN108917770A (en) * | 2018-07-25 | 2018-11-30 | 重庆交通大学 | A kind of industrial robot route searching optimization method |
| CN109520507A (en) * | 2018-12-05 | 2019-03-26 | 智灵飞（北京）科技有限公司 | A kind of unmanned plane real-time route planing method based on improvement RRT |
| CN109520507B (en) * | 2018-12-05 | 2021-05-07 | 智灵飞（北京）科技有限公司 | Unmanned aerial vehicle real-time path planning method based on improved RRT |
| CN112083724A (en) * | 2020-08-31 | 2020-12-15 | 南京凌华微电子科技有限公司 | Remote control system and method for service robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104765371A (en) | Route planning method based on rolling window deep searching and fuzzy control fusion | |
| Zhen et al. | Rotary unmanned aerial vehicles path planning in rough terrain based on multi-objective particle swarm optimization | |
| CN101604166B (en) | Path planning method for mobile robots based on particle swarm optimization algorithm | |
| CN108827309B (en) | Robot path planning method and dust collector with same | |
| CN111610786B (en) | Mobile robot path planning method based on improved RRT algorithm | |
| CN108983777A (en) | A kind of autonomous exploration and barrier-avoiding method based on the selection of adaptive forward position goal seeking point | |
| CN102541057A (en) | Moving robot obstacle avoiding method based on laser range finder | |
| CN106774329A (en) | A kind of robot path planning method based on oval tangent line construction | |
| CN104375505A (en) | Robot automatic road finding method based on laser ranging | |
| CN103455034A (en) | Avoidance path planning method based on closest distance vector field histogram | |
| KR101450843B1 (en) | Group Robot System and Control Method thereof | |
| CN107357295B (en) | Path searching method and chip based on grid map and robot | |
| CN108873915B (en) | Dynamic obstacle avoidance method and omnidirectional security robot thereof | |
| CN113359756B (en) | Method for realizing real-time planning of obstacle avoidance path of omnidirectional mobile robot based on grid method | |
| CN104932494A (en) | Probability type indoor barrier distribution map establishing mechanism | |
| CN108445894A (en) | A kind of secondary paths planning method considering unmanned boat movenent performance | |
| CN108917770A (en) | A kind of industrial robot route searching optimization method | |
| CN114755373B (en) | Air pollution source early warning positioning method based on multi-robot formation | |
| CN114610076B (en) | Flight path planning method combining artificial potential field method and A-star algorithm angle constraint | |
| Ying et al. | Path planning of mobile robot based on Improved RRT Algorithm | |
| CN108227718B (en) | Self-adaptive switching automatic carrying trolley path planning method | |
| Guan et al. | Robot dynamic path planning based on improved A* and DWA algorithms | |
| Chen et al. | A novel navigation system for an autonomous mobile robot in an uncertain environment | |
| Lu et al. | Path planning based on double-layer genetic algorithm | |
| Li et al. | Dynamic algorithm for safe and reachable frontier point generation for robot exploration |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150708 |