CN108762264A - The dynamic obstacle avoidance method of robot based on Artificial Potential Field and rolling window - Google Patents

The dynamic obstacle avoidance method of robot based on Artificial Potential Field and rolling window Download PDF

Info

Publication number
CN108762264A
CN108762264A CN201810496257.9A CN201810496257A CN108762264A CN 108762264 A CN108762264 A CN 108762264A CN 201810496257 A CN201810496257 A CN 201810496257A CN 108762264 A CN108762264 A CN 108762264A
Authority
CN
China
Prior art keywords
barrier
robot
current
dynamic
distance
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
Application number
CN201810496257.9A
Other languages
Chinese (zh)
Other versions
CN108762264B (en
Inventor
魏新
周详宇
张毅
王斌
方继康
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.)
Chongqing University of Post and Telecommunications
Original Assignee
Chongqing University of Post and Telecommunications
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 Chongqing University of Post and Telecommunications filed Critical Chongqing University of Post and Telecommunications
Priority to CN201810496257.9A priority Critical patent/CN108762264B/en
Publication of CN108762264A publication Critical patent/CN108762264A/en
Application granted granted Critical
Publication of CN108762264B publication Critical patent/CN108762264B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
    • G05D1/0238—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors
    • G05D1/024—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors in combination with a laser
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/20—Instruments for performing navigational calculations

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • General Physics & Mathematics (AREA)
  • Optics & Photonics (AREA)
  • Electromagnetism (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

The present invention relates to a kind of dynamic obstacle avoidance method of the robot based on Artificial Potential Field and rolling window, robot path planning's technical field, this method comprises the following steps S1：When robot motion is set and the distance D and location coordinate information X (x, y) of destination that is perfectly safe of barrier；S2：It is counted and current context information E by the history mileage of robot0iTo judge pose of the current robot in global coordinate systemS3：An optimal route S under current window is cooked up using A star pathfinding algorithmic preliminariesfirstAnd start to execute；S4：Using rolling window method, the moment is scanned and updates the real time environment information E under current window1i, the presence for whether having barrier in the environment in Δ t time windows calculated；S5：The distance of disturbance in judgement object whether setting being perfectly safe distance within；S6：Judge whether to have arrived at destination coordinate position X (x, y), terminates to navigate if reaching.The method of the present invention effectively improves global path planning optimality in dynamic.

Description

The dynamic obstacle avoidance method of robot based on Artificial Potential Field and rolling window
Technical field
The invention belongs to robot path planning's technical fields, are related to a kind of machine based on Artificial Potential Field and rolling window The dynamic obstacle avoidance method of people.
Background technology
Path planning is one of key element of autonomous mobile robot, it is desirable to which mobile robot can as possible quick and precisely Ground arrives at, while being also required to robot and can safely and effectively hide barrier in environment.In known static ring It safely and effectively avoiding barrier and accurately arrives at destination in border and has had more preferable solution.But in environment Present in barrier be movement, and the Position And Velocity moment of barrier, all when changing, this is just to robot Navigation procedure obstacle avoidance algorithm real-time and accuracy all than the requirement higher in static environment, if being continuing with static state Algorithm in environment carries out navigation and the avoidance of dynamic environment, then greatly may be such that avoidance unsuccessfully causes finally to navigate Failure.
Research for the dynamic obstacle avoidance of mobile robot mainly to carry out effectively detecting to barrier and collision is hided Control algorithm design is kept away, allows the robot to quickly and accurately complete navigation task.For the detection to barrier, need to utilize The measurement sensor of institute of robot itself band, to barrier into the measurement of row distance and position and the judgement of motion state.Mesh The preceding use for this kind of sensor generally has ultrasonic sensor, infrared sensor, laser sensor, visual sensor etc..
In the research of dynamic obstacle avoidance algorithm, more commonly used method have Artificial Potential Field Method, VFH classes algorithm, neural network, Genetic algorithm, fuzzy logic method and rolling window method etc..
Artificial Potential Field Method is that a kind of Virtual space conference and barrier generate one and make robot and barrier to the repulsion of robot Hinder object that safe distance, target point is kept to generate the gravitation to robot so that robot drives towards target point, gravitation and repulsion Resultant force decide the direction of motion and speed of robot, the small real-time of this method calculation amount is good, but is susceptible to local minimum Value point.
Rolling window method is a kind of environmental information using in sensor moment detection robot window to carry out pair Barrier is hidden and navigates, and rolling window active path planning is a kind of paths planning method of real-time online, not into The offline path planning of row, only determines its direction of advance by the window specific item punctuate of each step-length；And specific item punctuate is By avoiding static, dynamic barrier in window, and to the target point shortest distance come what is determined, this method is not considered global Optimization aim.If applying the method in complicated wide environment, obtained global optimization result can be very undesirable.
Invention content
In view of this, the present invention in the state-detection of dynamic barrier using laser sensor come real time scan moving machine Environmental information in device people navigation is stored in a static global information first, then to Artificial Potential Field in dynamic obstacle avoidance control algolithm Method is combined control method with rolling window method, provides a kind of dynamic obstacle avoidance of the robot based on Artificial Potential Field and rolling window Method.
In order to achieve the above objectives, the present invention provides the following technical solutions：
The dynamic obstacle avoidance method of robot based on Artificial Potential Field and rolling window, this method comprise the following steps
S1：When robot motion is set and the distance D and location coordinate information X of destination that is perfectly safe of barrier (x, y)；
S2：It is counted and current context information E by the history mileage of robot0iTo judge that current robot is sat in the overall situation Pose in mark system
S3：According to current robot pose, current environmental characteristic information, destination coordinate and world coordinates information profit The initial optimal path route S of a static state is obtained with A star pathfinding algorithmsfirst, and start to execute；
S4：Using rolling window method, the moment is scanned and updates the real time environment information E under current window1i, calculate in real time Whether there is the presence of barrier in environment in Δ t time windows, and determines whether there is barrier：
If existed without barrier, S is continued to executefirst, update and preserve current context information data E0i=E1i (i1,2,3..., n), wherein n is positive integer, and executes S6；
If there is barrier exists, then S5 is executed；
S5：Whether the distance of disturbance in judgement object is within the being perfectly safe distance of setting, if not executing S6 if；
If within the distance that is perfectly safe, handles laggard walking along the street diameter and plan update S againfirst, then execute S2；
S6：Judge whether to have arrived at destination coordinate position X (x, y), terminates this navigation if reaching, if do not had There is arrival, then returns to S2 and continue to execute.
Further, step S2 is specifically, the history mileage by robot is counted in conjunction with current context information E0iWith ground Figure environmental model is matched, pose of the positioning current robot in global coordinate system
According to EtiWithJudge the world coordinates of the barrier in t moment environment for Ooti(Xti, Xti), meet：
Wherein, (xt, yt) be t moment robot world coordinates, d0iFor the distance of i-th of barrier to machine, θtFor machine Device people's t moment pose angle, k are the angles between barrier and robot pose direction.
Further, step S5 is specially：
S51：According to obstacle article coordinate Oo0i(X0i, Y0i) and Oo1i(X1i, Y1i) barrier in current environment is divided Class meets：
Wherein, Zso0iIndicate static-obstacle thing, Zdo0iIndicate that dynamic barrier, l+m≤n, Δ S indicate barrier in the t times Interior changed distance, Δ S=S1i-S0i,Indicate the position of barrier t moment, S0iAt the beginning of indicating barrier Beginning moment position；
S52：Judged according to obstacle identity, it, then will be between static-obstacle thing and robot if static-obstacle thing Distance dsoDistance D is compared with being perfectly safe, Δ d=dso- D continues the route S according to planning if Δ d > 0first Advance, if Δ d < 0, plan S againnew, static-obstacle thing is avoided, S is updatedfirst=Snew；
If dynamic barrier, then according to the motion state v of current dynamic barrier1With SfirstJudge the dynamic barrier It is whether dangerous to route that robot is current, if there is no danger, continue the route S according to planningfirstAdvance, if depositing In danger, then S is planned according to influence situation againnew, avoiding dynamic barrier, update Sfirst=Snew。
Further, according to the motion state v of current dynamic barrier in step S521With SfirstJudge the dynamic barrier Whether dangerous to route that robot is current be specially：
If the movement track parameters equation of dynamic barrier is：
Present navigation route SfirstThe movement track parameters equation of lower robot is：
Simultaneous equations fo(t) and Equation fr(t) it is solved, and is judged：
Show that two equations have intersection point (x if equation group has solutioni,yi,ti) (i=0,1 ...), i.e., in t=ti(i=0, 1 ...) two equations are in point (xi,yi) (i=0,1 ...) intersection, robot will collide with dynamic barrier, then currently Route is dangerous, needs to plan again；
Show that two equations do not have intersection point if equation group is without solution, i.e., there is no danger for current route, will not hinder with dynamic Object is hindered to collide.
Further, it if current route is dangerous, needs to plan again, the specific method that avoiding obstacles are planned again is full Foot：When possible dangerous intersection point (xi,yi) after (i=0,1 ...) be updated in original static map, obtain one it is new Then static map utilizes Artificial Potential Field Method, first obtains local optimum direction, A star pathfinding algorithms are used then along this direction Obtain new path planning Snew, update Sfirst=Snew。
The beneficial effects of the present invention are：
The present invention provides a kind of mobile robots being combined with dynamic window based on the Artificial Potential Field of laser sensor Dynamic obstacle avoidance method adds global static information, lacks global information to compensate in the navigation of local dynamic station avoidance and leads The local optimum of cause and poor disadvantage of overall importance, part are combined with the overall situation, effectively improve global path rule in dynamic Draw optimality.
Description of the drawings
In order to keep the purpose of the present invention, technical solution and advantageous effect clearer, the present invention provides following attached drawing and carries out Explanation：
Fig. 1 is flow chart of the present invention.
Specific implementation mode
Below in conjunction with attached drawing, the preferred embodiment of the present invention is described in detail.
As shown in Figure 1, before carrying out step S1, it would be desirable to be built and be deposited the static map characteristic information of environment It stores up inside mobile robot.
S1：Carry out parameter input, i.e., be perfectly safe distance D and the target point of navigation between mobile robot and barrier Coordinate information X (x, y) in the map of structure.
S2：It is counted according to the mileage at the moment of historical data, that is, ∞ → 0 of the odometer of robot, then in conjunction with laser The environmental characteristic information E that sensor scans at this time0i(i=1,2 ..., n) is matched with map environment model, orients machine The current pose of people
By Eti(i=1,2 ..., n) withIt may determine that the world coordinates of the barrier in t moment environment is Ooti(Xti, Yti)：
In formula, (xt,yt) be t moment robot world coordinates, doiIt is distance of i-th of barrier to machine, θtIt is machine Device people's t moment pose angle, k are the angles between barrier and robot pose direction.
It then can be by E0i(i=1,2 ..., n) withThe world coordinates for calculating the barrier in t=0 moment environment is Oo0i(X0i,Y0i) (i=1,2 ..., n).
S3：According to current robot poseCurrent environmental characteristic information E0i(i=1,2 ..., n), destination coordinate X And global map information preliminary planning goes out an optimal route S under current windowfirst(assuming that dynamic barrier is not present), And start to execute Sfirst。
S4, the environmental data information E in the current window that laser scanning obtains1i(i=1,2 ..., n), when judging Δ t Between whether there are obstacles in window：The optimal path S under current window is updated if without barrierfirst, update simultaneously And current environmental information data are preserved, even E0i=E1i(i=1,2 ..., n) then jumps to step S6 and continues to execute；If There is barrier to then follow the steps S5.
S5, according to barrier z1iThe coordinate of (i=1,2 ..., n)With barrier z0i(i =1,2 ..., n) coordinateJudge the static-obstacle thing Z in current environmentso0i(i= 1,2 ..., l；L+m≤n) and dynamic barrier Zdo0j(j=1,2 ..., m；L+m≤n) be respectively：
Assuming that barrier i does uniformly accelerated motion within a short period, then t moment can be obtained by kinematics formula Speed and the distance moved in 0~t times are respectively vti=v0i+aiT withΔ S=S1i-S0i。
It is judged respectively further according to obstacle identity：
1) static-obstacle thing situation：By barrier and robot distance dsoBe perfectly safe distance D will compared with Δ d= dso- D continues if Δ d >=0 according to path planning S beforefirstAdvance, when Δ d < 0 then need to be advised again Draw Snew, current barrier is got around, and update Sfirst=Snew；
2) dynamic barrier situation：According to the motion state v of obtained current barrier1, by v1With SfirstJudge this Whether dynamic barrier is dangerous to route that robot is current,
If the movement track parameters equation of barrier isMachine under Present navigation route Sfirst The movement track parameters equation of people isSo, to equation fo (t) and Equation fr(t) simultaneous equations are carried out Group is solved：
Show that two equations have intersection point (x if equation group has solutioni,yi,ti) (i=0,1 ...), i.e., in t=ti(i= 0,1 ...) two equations are in point (xi,yi) (i=0,1 ...) intersection, robot will collide with dynamic barrier, currently Route is dangerous, needs to plan again；
Show that two equations do not have intersection point if equation group is without solution, i.e., there is no danger for current route, will not be with dynamic Barrier collides.
If route SfirstIt is dangerous, then it needs to plan route again：The intersection point acquired according to equation group (xi,yi) (i=0,1 ...), it is substituted into obstacle object point in original static map information, then avoiding obstacles carry out again Path planning.The specific method that avoiding obstacles are planned again：When possible dangerous intersection point (xi,yi) (i=0,1 ...) After being updated in original static map, a new static map is obtained, Artificial Potential Field Method is then utilized, first obtains part Optimal direction obtains new path planning S then along this direction using A star pathfinding algorithmsnew, update Sfirst=Snew。
S6：According to the current pose of robotJudge changing coordinates xt(xt,yt) whether be equal to coordinate of ground point X (x, y)：It is equal, show to have arrived at, terminates this time to navigate；It is unequal, it does not reach, return to step S2 is continued to execute, until reaching Target.
Finally illustrate, preferred embodiment above is only to illustrate the technical solution of invention and unrestricted, although passing through Above preferred embodiment is described in detail the present invention, however, those skilled in the art should understand that, can be in shape Various changes are made in formula and to it in details, without departing from claims of the present invention limited range.

Claims (5)

1. the dynamic obstacle avoidance method of the robot based on Artificial Potential Field and rolling window, it is characterised in that：This method includes as follows Step
S1：When robot motion is set and the distance D and location coordinate information X (x, y) of destination that is perfectly safe of barrier；
S2：It is counted and current context information E by the history mileage of robot0iTo judge current robot in global coordinate system In pose
S3：According to current robot pose, current environmental characteristic information, destination coordinate and world coordinates use of information A Star pathfinding algorithm obtains the initial optimal path route S of a static statefirst, and start to execute；
S4：Using rolling window method, the moment is scanned and updates the real time environment information F under current window1i, Δ t is calculated in real time Whether there is the presence of barrier in environment in time window, and determines whether there is barrier：
If existed without barrier, S is continued to executefirst, update and preserve current context information data E0i=E1i(i1,2, 3..., n), wherein n is positive integer, and executes S6；
If there is barrier exists, then S5 is executed；
S5：Whether the distance of disturbance in judgement object is within the being perfectly safe distance of setting, if not executing S6 if；
If within the distance that is perfectly safe, handles laggard walking along the street diameter and plan update S againfirst, then execute S2；
S6：Judge whether to have arrived at destination coordinate position X (x, y), terminates this navigation if reaching, if do not arrived It reaches, then returns to S2 and continue to execute.
2. the dynamic obstacle avoidance method of the robot according to claim 1 based on Artificial Potential Field and rolling window, feature It is：Step S2 is specifically, the history mileage by robot is counted in conjunction with current context information E0iWith map environment model It is matched, pose of the positioning current robot in global coordinate system
According to EtiWithJudge the world coordinates of the barrier in t moment environment for Ooti(Xti, Yti), meet：
Wherein, (xt, yt) be t moment robot world coordinates, d0iFor the distance of i-th of barrier to machine, θtFor robot T moment pose angle, k are the angles between barrier and robot pose direction.
3. the dynamic obstacle avoidance method of the robot according to claim 2 based on Artificial Potential Field and rolling window, feature It is：Step S5 is specially：
S51：According to obstacle article coordinate Oo0i(X0i, Y0i) and Oo1i(X1i, Y1i) classify to the barrier in current environment, it is full Foot：
Wherein, Zso0iIndicate static-obstacle thing, Zdo0iIndicate that dynamic barrier, l+m≤n, Δ S indicate barrier institute within the t times The distance of variation, Δ S=S1i-S0i,Indicate the position of barrier t moment, S0iWhen indicating that barrier is initial Carve position；
S52：Judged according to obstacle identity, if static-obstacle thing, then by between static-obstacle thing and robot away from From dsoDistance D is compared with being perfectly safe, Δ d=dso- D continues the route S according to planning if Δ d > 0firstAdvance, If Δ d < 0, plan S againnew, static-obstacle thing is avoided, S is updatedfirsT=Snew；
If dynamic barrier, then according to the motion state v of current dynamic barrier1With SfirstWhether judge the dynamic barrier It is dangerous to the route that robot is current, if there is no danger, continue the route S according to planningfirstAdvance, if there is danger S is then planned in danger again according to influence situationnew, avoiding dynamic barrier, update Sfirst=Snew。
4. the dynamic obstacle avoidance method of the robot according to claim 3 based on Artificial Potential Field and rolling window, feature It is：According to the motion state v of current dynamic barrier in step S521With SfirstJudge the dynamic barrier whether to machine The current route of people is dangerous to be specially：
If the movement track parameters equation of dynamic barrier is：
Present navigation route SfirstThe movement track parameters equation of lower robot is：
Simultaneous equations fo(t) and Equation fr(t) it is solved, and is judged：
Show that two equations have intersection point (x if equation group has solutioni,yi,ti) (i=0,1 ...), i.e., in t=ti(i=0,1 ...) Two equations are in point (xi,yi) (i=0,1 ...) intersection, robot will collide with dynamic barrier, then current route is deposited In danger, need to plan again；
Show that two equations do not have intersection point if equation group is without solution, i.e. current route, will not be with dynamic barrier there is no danger It collides.
5. the dynamic obstacle avoidance method of the robot according to claim 4 based on Artificial Potential Field and rolling window, feature It is：If current route is dangerous, need to plan again, the specific method that avoiding obstacles are planned again meets：When handle can Dangerous intersection point (the x of energyi,yi) after (i=0,1 ...) be updated in original static map, a new static map is obtained, Then Artificial Potential Field Method is utilized, local optimum direction is first obtained, new road is obtained using A star pathfinding algorithms then along this direction Diameter plans Snew, update Sfirst=Snew。
CN201810496257.9A 2018-05-22 2018-05-22 Dynamic obstacle avoidance method of robot based on artificial potential field and rolling window Active CN108762264B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810496257.9A CN108762264B (en) 2018-05-22 2018-05-22 Dynamic obstacle avoidance method of robot based on artificial potential field and rolling window

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810496257.9A CN108762264B (en) 2018-05-22 2018-05-22 Dynamic obstacle avoidance method of robot based on artificial potential field and rolling window

Publications (2)

Publication Number Publication Date
CN108762264A true CN108762264A (en) 2018-11-06
CN108762264B CN108762264B (en) 2021-05-04

Family

ID=64008600

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810496257.9A Active CN108762264B (en) 2018-05-22 2018-05-22 Dynamic obstacle avoidance method of robot based on artificial potential field and rolling window

Country Status (1)

Country Link
CN (1) CN108762264B (en)

Cited By (31)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109445440A (en) * 2018-12-13 2019-03-08 重庆邮电大学 The dynamic obstacle avoidance method with improvement Q learning algorithm is merged based on sensor
CN109828588A (en) * 2019-03-11 2019-05-31 浙江工业大学 Paths planning method in a kind of robot chamber based on Multi-sensor Fusion
CN109976343A (en) * 2019-03-26 2019-07-05 电子科技大学 A kind of automatic obstacle avoidance method based on dynamic window method
CN110221613A (en) * 2019-06-12 2019-09-10 北京洛必德科技有限公司 Robot path planning method and device based on modified Artificial Potential Field Method
CN110345948A (en) * 2019-08-16 2019-10-18 重庆邮智机器人研究院有限公司 Dynamic obstacle avoidance method based on neural network in conjunction with Q learning algorithm
CN111121804A (en) * 2019-12-03 2020-05-08 重庆邮电大学 Intelligent vehicle path planning method and system with safety constraint
CN111338359A (en) * 2020-04-30 2020-06-26 武汉科技大学 Mobile robot path planning method based on distance judgment and angle deflection
CN111381589A (en) * 2018-12-29 2020-07-07 沈阳新松机器人自动化股份有限公司 Robot path planning method
CN111633646A (en) * 2020-05-22 2020-09-08 北京理工大学 Robot motion planning method based on DMPs and modified obstacle avoidance algorithm
CN112013866A (en) * 2020-08-31 2020-12-01 电子科技大学 Path planning method based on intelligent navigation system
CN112099486A (en) * 2020-08-04 2020-12-18 西安电子科技大学 Method, system, equipment and application for controlling formation of multi-robot formation at any position
CN112099501A (en) * 2020-09-15 2020-12-18 哈尔滨工程大学 Unmanned ship path planning method based on potential field parameter optimization
CN112130559A (en) * 2020-08-21 2020-12-25 同济大学 Indoor pedestrian following and obstacle avoiding method based on UWB and laser radar
CN112130562A (en) * 2020-09-04 2020-12-25 浙江嘉蓝海洋电子有限公司 Multi-rolling-window-based artificial potential field unmanned surface vessel obstacle avoidance method
CN112269381A (en) * 2020-10-20 2021-01-26 安徽工程大学 Mobile robot path planning method based on improved artificial fish swarm algorithm
CN112378408A (en) * 2020-11-26 2021-02-19 重庆大学 Path planning method for realizing real-time obstacle avoidance of wheeled mobile robot
CN112540609A (en) * 2020-07-30 2021-03-23 深圳优地科技有限公司 Path planning method and device, terminal equipment and storage medium
CN112665592A (en) * 2020-12-16 2021-04-16 郑州大学 Space-time path planning method based on multiple intelligent agents
CN112731944A (en) * 2021-01-15 2021-04-30 同济大学 Autonomous obstacle avoidance method for unmanned road roller
CN112859866A (en) * 2021-01-18 2021-05-28 西安电子科技大学 Robot rolling path planning method, system, storage medium, equipment and application
CN113034579A (en) * 2021-03-08 2021-06-25 江苏集萃微纳自动化系统与装备技术研究所有限公司 Dynamic obstacle track prediction method of mobile robot based on laser data
CN113515131A (en) * 2021-08-27 2021-10-19 苏州大学 Mobile robot obstacle avoidance method and system based on condition variation automatic encoder
CN113778119A (en) * 2021-09-26 2021-12-10 江西理工大学 Unmanned aerial vehicle control path optimization method
CN113848933A (en) * 2021-10-11 2021-12-28 徐州徐工环境技术有限公司 Omnibearing obstacle avoidance method and device for cleaning robot
CN113934219A (en) * 2021-12-16 2022-01-14 宏景科技股份有限公司 Robot automatic obstacle avoidance method, system, equipment and medium
CN114035568A (en) * 2021-03-27 2022-02-11 浙江大学 Method for planning path of stratum drilling robot in combustible ice trial production area
CN114136318A (en) * 2020-08-13 2022-03-04 科沃斯商用机器人有限公司 Intelligent navigation method and device for machine
CN114879701A (en) * 2022-06-23 2022-08-09 池州市安安新材科技有限公司 Robot track obstacle avoidance method and system
CN114995421A (en) * 2022-05-31 2022-09-02 重庆长安汽车股份有限公司 Automatic driving obstacle avoidance method, device, electronic device, storage medium, and program product
CN115755890A (en) * 2022-11-01 2023-03-07 南京傲翼飞控智能科技有限公司 Weeding task path planning method and device based on data processing
CN116307334A (en) * 2023-05-17 2023-06-23 广州一链通互联网科技有限公司 Dynamic programming method, system and computer equipment for internal trade gathering and transportation route

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
CN105717929A (en) * 2016-04-29 2016-06-29 中国人民解放军国防科学技术大学 Planning method for mixed path of mobile robot under multi-resolution barrier environment
US20160209849A1 (en) * 2015-01-15 2016-07-21 William Dale Arbogast System and method for decentralized, multi-agent unmanned vehicle navigation and formation control
CN107015563A (en) * 2016-12-29 2017-08-04 北京航空航天大学 Method for planning path for mobile robot and device
CN107091643A (en) * 2017-06-07 2017-08-25 旗瀚科技有限公司 A kind of indoor navigation method based on many 3D structure lights camera splicings
CN107883962A (en) * 2017-11-08 2018-04-06 南京航空航天大学 A kind of dynamic Route planner of multi-rotor unmanned aerial vehicle under three-dimensional environment

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
US20160209849A1 (en) * 2015-01-15 2016-07-21 William Dale Arbogast System and method for decentralized, multi-agent unmanned vehicle navigation and formation control
CN105717929A (en) * 2016-04-29 2016-06-29 中国人民解放军国防科学技术大学 Planning method for mixed path of mobile robot under multi-resolution barrier environment
CN107015563A (en) * 2016-12-29 2017-08-04 北京航空航天大学 Method for planning path for mobile robot and device
CN107091643A (en) * 2017-06-07 2017-08-25 旗瀚科技有限公司 A kind of indoor navigation method based on many 3D structure lights camera splicings
CN107883962A (en) * 2017-11-08 2018-04-06 南京航空航天大学 A kind of dynamic Route planner of multi-rotor unmanned aerial vehicle under three-dimensional environment

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
YI ZHANG: "Dynamic Obstacle avoidance based on multi-sensor fusion and Q-learning Algorithm", 《ITNEC》 *
ZHIYU ZHOU: "Tangent navigated robot path planning strategy using particle swarm optimized artificial potential field", 《OPTIK》 *
史进 等: "移动机器人动态路径规划方法的研究与实现", 《计算机应用》 *
张毅 等: "基于改进遗传算法的移动机器人路径规划", 《计算机测量与控制》 *

Cited By (40)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109445440A (en) * 2018-12-13 2019-03-08 重庆邮电大学 The dynamic obstacle avoidance method with improvement Q learning algorithm is merged based on sensor
CN109445440B (en) * 2018-12-13 2022-03-22 重庆邮电大学 Dynamic obstacle avoidance method based on sensor fusion and improved Q learning algorithm
CN111381589A (en) * 2018-12-29 2020-07-07 沈阳新松机器人自动化股份有限公司 Robot path planning method
CN109828588A (en) * 2019-03-11 2019-05-31 浙江工业大学 Paths planning method in a kind of robot chamber based on Multi-sensor Fusion
CN109976343A (en) * 2019-03-26 2019-07-05 电子科技大学 A kind of automatic obstacle avoidance method based on dynamic window method
CN110221613A (en) * 2019-06-12 2019-09-10 北京洛必德科技有限公司 Robot path planning method and device based on modified Artificial Potential Field Method
CN110221613B (en) * 2019-06-12 2020-04-17 北京洛必德科技有限公司 Robot path planning method and device based on improved artificial potential field method
CN110345948A (en) * 2019-08-16 2019-10-18 重庆邮智机器人研究院有限公司 Dynamic obstacle avoidance method based on neural network in conjunction with Q learning algorithm
CN111121804A (en) * 2019-12-03 2020-05-08 重庆邮电大学 Intelligent vehicle path planning method and system with safety constraint
CN111121804B (en) * 2019-12-03 2023-09-26 重庆邮电大学 Intelligent vehicle path planning method and system with safety constraint
CN111338359A (en) * 2020-04-30 2020-06-26 武汉科技大学 Mobile robot path planning method based on distance judgment and angle deflection
CN111633646A (en) * 2020-05-22 2020-09-08 北京理工大学 Robot motion planning method based on DMPs and modified obstacle avoidance algorithm
CN111633646B (en) * 2020-05-22 2021-08-27 北京理工大学 Robot motion planning method based on DMPs and modified obstacle avoidance algorithm
CN112540609A (en) * 2020-07-30 2021-03-23 深圳优地科技有限公司 Path planning method and device, terminal equipment and storage medium
CN112099486A (en) * 2020-08-04 2020-12-18 西安电子科技大学 Method, system, equipment and application for controlling formation of multi-robot formation at any position
CN114136318A (en) * 2020-08-13 2022-03-04 科沃斯商用机器人有限公司 Intelligent navigation method and device for machine
CN112130559A (en) * 2020-08-21 2020-12-25 同济大学 Indoor pedestrian following and obstacle avoiding method based on UWB and laser radar
CN112013866A (en) * 2020-08-31 2020-12-01 电子科技大学 Path planning method based on intelligent navigation system
CN112130562A (en) * 2020-09-04 2020-12-25 浙江嘉蓝海洋电子有限公司 Multi-rolling-window-based artificial potential field unmanned surface vessel obstacle avoidance method
CN112099501A (en) * 2020-09-15 2020-12-18 哈尔滨工程大学 Unmanned ship path planning method based on potential field parameter optimization
CN112099501B (en) * 2020-09-15 2022-10-28 哈尔滨工程大学 Unmanned ship path planning method based on potential field parameter optimization
CN112269381A (en) * 2020-10-20 2021-01-26 安徽工程大学 Mobile robot path planning method based on improved artificial fish swarm algorithm
CN112378408A (en) * 2020-11-26 2021-02-19 重庆大学 Path planning method for realizing real-time obstacle avoidance of wheeled mobile robot
CN112665592A (en) * 2020-12-16 2021-04-16 郑州大学 Space-time path planning method based on multiple intelligent agents
CN112731944A (en) * 2021-01-15 2021-04-30 同济大学 Autonomous obstacle avoidance method for unmanned road roller
CN112859866A (en) * 2021-01-18 2021-05-28 西安电子科技大学 Robot rolling path planning method, system, storage medium, equipment and application
CN113034579B (en) * 2021-03-08 2023-11-24 江苏集萃微纳自动化系统与装备技术研究所有限公司 Dynamic obstacle track prediction method of mobile robot based on laser data
CN113034579A (en) * 2021-03-08 2021-06-25 江苏集萃微纳自动化系统与装备技术研究所有限公司 Dynamic obstacle track prediction method of mobile robot based on laser data
CN114035568A (en) * 2021-03-27 2022-02-11 浙江大学 Method for planning path of stratum drilling robot in combustible ice trial production area
CN113515131A (en) * 2021-08-27 2021-10-19 苏州大学 Mobile robot obstacle avoidance method and system based on condition variation automatic encoder
CN113778119B (en) * 2021-09-26 2022-10-21 江西理工大学 Unmanned aerial vehicle control path optimization method
CN113778119A (en) * 2021-09-26 2021-12-10 江西理工大学 Unmanned aerial vehicle control path optimization method
CN113848933A (en) * 2021-10-11 2021-12-28 徐州徐工环境技术有限公司 Omnibearing obstacle avoidance method and device for cleaning robot
CN113848933B (en) * 2021-10-11 2024-04-26 徐州徐工环境技术有限公司 All-dimensional obstacle avoidance method and device for cleaning robot
CN113934219A (en) * 2021-12-16 2022-01-14 宏景科技股份有限公司 Robot automatic obstacle avoidance method, system, equipment and medium
CN114995421A (en) * 2022-05-31 2022-09-02 重庆长安汽车股份有限公司 Automatic driving obstacle avoidance method, device, electronic device, storage medium, and program product
CN114879701A (en) * 2022-06-23 2022-08-09 池州市安安新材科技有限公司 Robot track obstacle avoidance method and system
CN115755890A (en) * 2022-11-01 2023-03-07 南京傲翼飞控智能科技有限公司 Weeding task path planning method and device based on data processing
CN116307334A (en) * 2023-05-17 2023-06-23 广州一链通互联网科技有限公司 Dynamic programming method, system and computer equipment for internal trade gathering and transportation route
CN116307334B (en) * 2023-05-17 2023-08-15 广州一链通互联网科技有限公司 Dynamic programming method, system and computer equipment for internal trade gathering and transportation route

Also Published As

Publication number Publication date
CN108762264B (en) 2021-05-04

Similar Documents

Publication Publication Date Title
CN108762264A (en) The dynamic obstacle avoidance method of robot based on Artificial Potential Field and rolling window
CN106444769B (en) A kind of optimum path planning method of indoor mobile robot increment type environmental information sampling
CN107450535B (en) A kind of intelligence carrying robot optimal path combination chart discusses controlling planning method
CN110502032A (en) A kind of unmanned plane cluster formation flight method of Behavior-based control control
CN110333714A (en) A kind of pilotless automobile paths planning method and device
CN105629974B (en) A kind of robot path planning method and system based on modified Artificial Potential Field Method
CN107894773A (en) A kind of air navigation aid of mobile robot, system and relevant apparatus
CN106873599A (en) Unmanned bicycle paths planning method based on ant group algorithm and polar coordinate transform
CN109318890A (en) A kind of unmanned vehicle dynamic obstacle avoidance method based on dynamic window and barrier potential energy field
CN109445440A (en) The dynamic obstacle avoidance method with improvement Q learning algorithm is merged based on sensor
CN104501816A (en) Multi-unmanned aerial vehicle coordination and collision avoidance guide planning method
CN103558856A (en) Service mobile robot navigation method in dynamic environment
CN106708059A (en) Channel selection-based real-time motion planning method for mobile robot
WO2020136978A1 (en) Path determination method
CN108873915A (en) Dynamic obstacle avoidance method and its omnidirectional&#39;s security robot
Chen et al. Tracking with UAV using tangent-plus-Lyapunov vector field guidance
CN111506063A (en) Mobile robot map-free navigation method based on layered reinforcement learning framework
Chen et al. Collision-free UAV navigation with a monocular camera using deep reinforcement learning
CN110032189A (en) A kind of intelligent storage method for planning path for mobile robot not depending on map
López et al. A new approach to local navigation for autonomous driving vehicles based on the curvature velocity method
Wu et al. Vision-based target detection and tracking system for a quadcopter
CN112631269A (en) Autonomous mobile robot and control program for autonomous mobile robot
CN114564008A (en) Mobile robot path planning method based on improved A-Star algorithm
CN110442014A (en) A kind of location-based mobile robot RFID servo method
JP2020149095A (en) Inverted pendulum robot

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant