CN109668573A - A kind of vehicle path planning method for improving RRT algorithm - Google Patents
A kind of vehicle path planning method for improving RRT algorithm Download PDFInfo
- Publication number
- CN109668573A CN109668573A CN201910008795.3A CN201910008795A CN109668573A CN 109668573 A CN109668573 A CN 109668573A CN 201910008795 A CN201910008795 A CN 201910008795A CN 109668573 A CN109668573 A CN 109668573A
- Authority
- CN
- China
- Prior art keywords
- node
- distance
- vehicle
- new
- path planning
- 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
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000012549 training Methods 0.000 claims abstract description 5
- 230000004888 barrier function Effects 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 5
- 230000007613 environmental effect Effects 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 3
- 238000002790 cross-validation Methods 0.000 claims 1
- 238000005259 measurement Methods 0.000 abstract description 7
- 238000002474 experimental method Methods 0.000 abstract 1
- 230000006870 function Effects 0.000 description 4
- 230000033001 locomotion Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 210000004209 hair Anatomy 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
-
- 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
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
- G01C21/343—Calculating itineraries, i.e. routes leading from a starting point to a series of categorical destinations using a global route restraint, round trips, touristic trips
-
- 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
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Abstract
The present invention relates to robot path planning's technical fields, and in particular to a kind of vehicle path planning method for improving RRT algorithm；In order to keep the RRT algorithm distance metric for applying to intelligent vehicle path planning more reasonable, evade simultaneously and accurately solves that optimal it is still necessary to cost bring computing costs, the kinematical constraint of present invention consideration vehicle, Dubins curve is introduced as distance metric, wherein Dubins curve corresponds to the shortest path of Dubins vehicle.Simultaneously as Dubins curve have it is non-linear, in order to accelerate to calculate, propose a kind of approximate method of supervised learning, using monitor model adjust the distance measurement carry out line under training learn, then applied to predict on line.Emulation experiment is carried out to the mentioned method of the present invention, it was confirmed that its superiority, validity have very strong application value.
Description
Technical field
The present invention relates to robot path planning's technical fields, and in particular to a kind of vehicle route rule for improving RRT algorithm
The method of drawing.
Background technique
Algorithm based on sampling is an effective tool (S for solving the problems, such as robot path planning
Lavalle.Planning Algorithms[M].Cambridge University Press,2006.).RRT algorithm (S M
LaValle.Rapidly-exploring random trees:A new tool forpathplanning[R].Ames,
USA:Iowa State University.Ames, USA:Iowa State University, 1998.) it is one singly to inquire
Planning algorithm is sampled, it is extended in configuration space using original state as root node, by tree construction, until reaching target-like
State.Distance metric is the key component of RRT algorithm.RRT algorithm needs to go selection nearest by distance metric in extension phase
Tree node, calculation times are as neighboring node number is in ratio growth.In state space distance metric ideal definition be from
It is still necessary to costs to dbjective state optimal for initial state.For the robot system with dynamics and kinematical constraint, determine
Optimal between two states is a two_point boundary value problem it is still necessary to cost, solve two_point boundary value problem at least with solve to transport
Dynamic planning problem is equally difficult.It is solved to simplify, LaVall and the Kuffner suggestion when proposing RRT algorithm are gone with alternative functions
For near-optimization it is still necessary to cost, alternative functions can be the function about path length, pose variable quantity.This optimal cost is approximate
Method is proved to that entire state space can be covered, and advantageously accounts for complicated motion planning problem (P Cheng and S
LaValle,“Reducing metric sensitivity in randomized trajectory design,”in
Int.Conf.on Intelligent Robots and Systems(IROS),San Francisco,USA,2001.)。
Intelligent vehicle is the robot with nonholonomic restriction, and it is still necessary to costs and its approximate function not to have for it optimal
Symmetry is not measurement truly, is generally called incomplete measurement (J P Laumond, S Sekhavat, F
Lamiraux.(1998)Guidelines in nonholonomic motion planning for mobile
robots.In:J P Laumond.(eds)Robot Motion Planning and Control,page 1-
53.Springer-Verlag,Berlin,1998.).Domestic and foreign scholars have carried out a large amount of research to incomplete measurement, with full
The different characteristics of sufficient planning algorithm.Euclidean distance and its variant are an important research directions of distance metric.Document (N
Amato,O Bayazit,L Dale,C Jones,and D Vallejo,"Choosing good distance metrics
and local planners for probabilistic roadmap methods,"IEEE Trans.on Robotics
And Automation (TRO), vol.16, no.4, pp.442-447, Aug 2000.) compared it is different in state space
Distance metric, it is indicated that although cum rights Euclidean distance is widely used in integrity constraint system, works as and be used for Nonholonomic Constraints Systems
State space is completely covered in Shi Buneng.(Du Mingbo, Mei Tao, Chen Jiajia wait the intelligence based on RRT algorithm under complex environment to document
Vehicle movement plan [J] robot, 2015,37 (4): 443-450.) in consider vehicle kinematics constraint, distance metric by
Euclidean distance and angle weight to obtain, but weighted factor is arranged by experience, do not have versatility.More accurate distance metric root
It is obtained according to optimum control.Document (E Glassman and R Tedrake, " A quadratic regulator-based
heuristic for rapidly exploring state space,"in Int.Conf.on Robotics and
Automation (ICRA), Anchorage, USA, 2010.) it goes to connect two shapes using optimum linearity secondary regulator (LQR)
State, this method linearize system dynamics in sector planning, then solve to obtain apart from degree by Lyu's Riccati equation
Amount.Similarly, document (D Webb and J van den Berg, " Kinodynamic RRT*:Asymptotically
optimal motionplanning for robots with linear dynamics,"in Int.Conf.on
Robotics and Automation (ICRA), Karlsruhe, Germany, 2013.) use time domain optimal controller as
Sector planning device.Although these optimal controllers can do a whole costing analysis to planning time and control force, calculate
Cost is too big, is unfavorable for calculating in real time.
Summary of the invention
In view of the deficiencies of the prior art, the invention discloses a kind of wiper switches, in order to make to apply to intelligent vehicle path
The RRT algorithm distance metric of planning is more reasonable, while evading and accurately solving that optimal it is still necessary to cost bring computing cost, this hairs
The bright kinematical constraint for considering vehicle introduces Dubins curve as distance metric, and wherein Dubins curve corresponds to Dubins
The shortest path of vehicle.Simultaneously as Dubins curve have it is non-linear, in order to accelerate to calculate, propose that a kind of supervised learning is close
As method, using monitor model adjust the distance measurement carry out line under training learn, then applied to predict on line.
The present invention is achieved by the following technical programs:
A kind of vehicle path planning method for improving RRT algorithm, including environmental map and auto model, starting point be
qstart, target point qgoal, which is characterized in that the paths planning method the following steps are included:
Step 1: initialization sample collection S；
Step 2: generating two state point q at random in vehicle-state space1And q2, calculate q1To q2Shortest path
Dubins length of curve c, by (q1,q2, c) and it is added to sample set S；
Step 3: repeat step 2 until in sample set S sample reach specified quantity；
Step 4: according to obtained sample set training regression model, wherein input is (q1,q2), it exports as c, passes through intersection
Verifying chooses that regression error is minimum and the smallest model F of predicted time, predicts the distance between two state points with this.
Step 5: setting target domain distance range thred, maximum number of iterations maxIter；
Step 6: initialization random tree T, by qstartAs root node；Initialize the number of iterations iter=0；
Step 7: judging whether the number of iterations iter is greater than maxIter；
Step 8: from vehicle free state space CfreeMiddle stochastical sampling state point qrand；The number of iterations iter=iter+1；
Step 9: traversal random tree T uses the model F prediction tree node and q in step 4randThe distance between, find away from
From qrandNearest node qnear；
Step 10: calculating from qnearTo qrandDubins curve, then random tree T is from qnearAlong Dubins curve to
qrandIt extends fixed step size step and reaches new node qnew；
Step 11: to q in step 8nearTo qnewSection curve carries out collision detection；
Step 12: calculate node qnewWith qgoalBetween distance D；
Step 13: from the node q for being located at target point fieldgoalStart, according to father node successively forward trace to starting point
qstart, obtain final path.
Preferably, in the step 7, if iter > maxIter, EP (end of program), planning failure；If iter≤
MaxIter goes to step 8.
Preferably, in the step 11, if collided with barrier, step 7 is gone to, if do not occurred with barrier
Collision, by new node qnewAnd its corresponding curved section is added in tree T, qnewFather node be qnear。
Preferably, in the step 12, if distance D≤thred, determines qnewTarget point field is reached, step is gone to
13；If distance D > thred, goes to step 7.
The invention has the benefit that
Quick Extended random tree (RRT) algorithm is often taken in vehicle path planning, wherein distance metric is to realize the calculation
The key of method.And existing distance metric does not consider the kinematical constraint of vehicle, planning path cannot directly apply to reality
In environment.The present invention is directed to intelligent vehicle path planning problem, will meet the shortest path length of its kinematical constraint as away from
RRT algorithm is introduced from measurement, approximate distance metric of method using supervised learning is proposed, is replaced with the forward prediction of model multiple
Planning speed is accelerated in miscellaneous solving the shortest path operation.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is general flow chart of the invention；
Fig. 2 is auto model schematic diagram；
Fig. 3 is the schematic diagram of basic RRT algorithm；
Fig. 4 is Dubins curve synoptic diagram.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
A kind of vehicle path planning method of improvement RRT algorithm as shown in Figure 1 gives environmental map and auto model
(referring to fig. 2), starting point qstart, target point qgoal, it is characterised in that steps are as follows:
Step 1: initialization sample collection S；
Step 2: generating two state point q at random in vehicle-state space1And q2, calculate q1To q2Shortest path
Dubins length of curve c, by (q1,q2, c) and it is added to sample set S；
Step 3: repeat step 2 until in sample set S sample reach specified quantity；
Step 4: according to obtained sample set training regression model, wherein input is (q1,q2), it exports as c, passes through intersection
Verifying chooses that regression error is minimum and the smallest model F of predicted time, predicts the distance between two state points with this.
Step 5: setting target domain distance range thred, maximum number of iterations maxIter；
Step 6: initialization random tree T, by qstartAs root node；Initialize the number of iterations iter=0；
Step 7: judging whether the number of iterations iter is greater than maxIter；
Step 8: from vehicle free state space CfreeMiddle stochastical sampling state point qrand；The number of iterations iter=iter+1；
Step 9: traversal random tree T uses the model F prediction tree node and q in step 4randThe distance between, find away from
From qrandNearest node qnear；
Step 10: calculating from qnearTo qrandDubins curve, then random tree T is from qnearAlong Dubins curve to
qrandIt extends fixed step size step and reaches new node qnew；
Step 11: to q in step 8nearTo qnewSection curve carries out collision detection；
Step 12: calculate node qnewWith qgoalBetween distance D；
Step 13: from the node q for being located at target point fieldgoalStart, according to father node successively forward trace to starting point
qstart, obtain final path.
For Vehicle routing problem, in addition to the present invention uses the RRT algorithm (referring to Fig. 3) based on sampling, based on figure
The algorithm of search is also a kind of common method.Algorithm based on graph search has A*, Dijkstra etc., and this method needs first to
Discrete environmental map is grating map, and then building includes the discrete figure of beginning and end, by graph search algorithm in graph structure
In search out a paths, planning when be although able to satisfy real-time and optimality, but not consider vehicle it is incomplete
Property constraint, the path cooked up possibly can not execute.In addition, traditional paths planning method based on biological intelligence algorithm also by
Research extensively, such as genetic algorithm, ant group algorithm, these methods have certain superiority when solving simple planning problem,
But due to the modeling that it needs to be determined the barrier in environment, is solved very much under the complex environment of multi-obstacle avoidance and arrive machine
People's routing problem.
Quick Extended random tree (RRT) algorithm is often taken in vehicle path planning, wherein distance metric is to realize the calculation
The key of method.And existing distance metric does not consider the kinematical constraint of vehicle, planning path cannot directly apply to reality
In environment.The present invention is directed to intelligent vehicle path planning problem, will meet the shortest path length of its kinematical constraint as away from
RRT algorithm is introduced from measurement, approximate distance metric of method using supervised learning is proposed, is replaced with the forward prediction of model multiple
Planning speed is accelerated in miscellaneous solving the shortest path operation.
The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although with reference to the foregoing embodiments
Invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each implementation
Technical solution documented by example is modified or equivalent replacement of some of the technical features；And these modification or
Replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution.
Claims (4)
1. a kind of vehicle path planning method for improving RRT algorithm, including environmental map and auto model, starting point be
qstart, target point qgoal, which is characterized in that the paths planning method the following steps are included:
Step 1: initialization sample collection S；
Step 2: generating two state point q at random in vehicle-state space1And q2, calculate q1To q2Shortest path Dubins it is bent
Line length c, by (q1,q2, c) and it is added to sample set S；
Step 3: repeat step 2 until in sample set S sample reach specified quantity；
Step 4: according to obtained sample set training regression model, wherein input is (q1,q2), it exports as c, passes through cross validation
It chooses that regression error is minimum and the smallest model F of predicted time, the distance between two state points is predicted with this.
Step 5: setting target domain distance range thred, maximum number of iterations maxIter；
Step 6: initialization random tree T, by qstartAs root node；Initialize the number of iterations iter=0；
Step 7: judging whether the number of iterations iter is greater than maxIter；
Step 8: from vehicle free state space CfreeMiddle stochastical sampling state point qrand；The number of iterations iter=iter+1；
Step 9: traversal random tree T uses the model F prediction tree node and q in step 4randThe distance between, find distance
qrandNearest node qnear；
Step 10: calculating from qnearTo qrandDubins curve, then random tree T is from qnearAlong Dubins curve to qrandExtension
Fixed step size step reaches new node qnew；
Step 11: to q in step 8nearTo qnewSection curve carries out collision detection；
Step 12: calculate node qnewWith qgoalBetween distance D；
Step 13: from the node q for being located at target point fieldgoalStart, according to father node successively forward trace to starting point qstart, obtain
To final path.
2. the vehicle path planning method according to claim 1 for improving RRT algorithm, which is characterized in that the step 7
In, if iter > maxIter, EP (end of program), planning failure；If iter≤maxIter goes to step 8.
3. the vehicle path planning method according to claim 1 for improving RRT algorithm, which is characterized in that the step 11
In, if collided with barrier, step 7 is gone to, if do not collided with barrier, by new node qnewAnd its it is corresponding
Curved section be added to tree T in, qnewFather node be qnear。
4. the vehicle path planning method according to claim 1 for improving RRT algorithm, which is characterized in that the step 12
In, if distance D≤thred, determines qnewTarget point field is reached, step 13 is gone to；If distance D > thred, goes to
Step 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910008795.3A CN109668573A (en) | 2019-01-04 | 2019-01-04 | A kind of vehicle path planning method for improving RRT algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910008795.3A CN109668573A (en) | 2019-01-04 | 2019-01-04 | A kind of vehicle path planning method for improving RRT algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109668573A true CN109668573A (en) | 2019-04-23 |
Family
ID=66149087
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910008795.3A Pending CN109668573A (en) | 2019-01-04 | 2019-01-04 | A kind of vehicle path planning method for improving RRT algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109668573A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110081889A (en) * | 2019-06-11 | 2019-08-02 | 广东工业大学 | A kind of robot path planning method based on stochastical sampling and intensified learning |
| CN110262473A (en) * | 2019-04-29 | 2019-09-20 | 上海交通大学 | A kind of unmanned boat automatic Collision Avoidance method based on improvement Bi-RRT algorithm |
| CN110285802A (en) * | 2019-06-11 | 2019-09-27 | 安徽理工大学 | Quick Extended random tree path smoothing method |
| CN110531770A (en) * | 2019-08-30 | 2019-12-03 | 的卢技术有限公司 | One kind being based on improved RRT paths planning method and system |
| CN111397598A (en) * | 2020-04-16 | 2020-07-10 | 苏州大学 | Mobile robot path planning and sampling method and system in man-machine co-fusion environment |
| CN111523719A (en) * | 2020-04-16 | 2020-08-11 | 东南大学 | Hybrid path planning method based on articulated vehicle kinematic constraint |
| CN113095537A (en) * | 2020-01-09 | 2021-07-09 | 北京京东乾石科技有限公司 | Path planning method and device |
| CN113108806A (en) * | 2021-05-13 | 2021-07-13 | 重庆紫光华山智安科技有限公司 | Path planning method, device, equipment and medium |
| CN113219998A (en) * | 2021-06-15 | 2021-08-06 | 合肥工业大学 | Improved bidirectional-RRT-based vehicle path planning method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106056152A (en) * | 2016-05-27 | 2016-10-26 | 大连楼兰科技股份有限公司 | System and method for establishing target division remote damage assessment of different vehicle types based on artificial intelligence semi-supervised learning BIRCH method |
| CN106446754A (en) * | 2015-08-11 | 2017-02-22 | 阿里巴巴集团控股有限公司 | Image identification method, metric learning method, image source identification method and devices |
| CN107943053A (en) * | 2017-12-15 | 2018-04-20 | 陕西理工大学 | A kind of paths planning method of mobile robot |
| CN108958292A (en) * | 2018-08-23 | 2018-12-07 | 北京理工大学 | A kind of aircraft based on RRT* algorithm is dashed forward anti-method for planning track |
-
2019
- 2019-01-04 CN CN201910008795.3A patent/CN109668573A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106446754A (en) * | 2015-08-11 | 2017-02-22 | 阿里巴巴集团控股有限公司 | Image identification method, metric learning method, image source identification method and devices |
| CN106056152A (en) * | 2016-05-27 | 2016-10-26 | 大连楼兰科技股份有限公司 | System and method for establishing target division remote damage assessment of different vehicle types based on artificial intelligence semi-supervised learning BIRCH method |
| CN107943053A (en) * | 2017-12-15 | 2018-04-20 | 陕西理工大学 | A kind of paths planning method of mobile robot |
| CN108958292A (en) * | 2018-08-23 | 2018-12-07 | 北京理工大学 | A kind of aircraft based on RRT* algorithm is dashed forward anti-method for planning track |
Non-Patent Citations (2)
| Title |
|---|
| 于飞: "基于距离学习的集成KNN分类器的研究", 《万方数据库》 * |
| 张煜等: "基于改进RRT算法的预警机实时航迹规划", 《计算机仿真》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110262473B (en) * | 2019-04-29 | 2021-09-14 | 上海交通大学 | Unmanned ship automatic collision avoidance method based on improved Bi-RRT algorithm |
| CN110262473A (en) * | 2019-04-29 | 2019-09-20 | 上海交通大学 | A kind of unmanned boat automatic Collision Avoidance method based on improvement Bi-RRT algorithm |
| CN110285802A (en) * | 2019-06-11 | 2019-09-27 | 安徽理工大学 | Quick Extended random tree path smoothing method |
| CN110081889A (en) * | 2019-06-11 | 2019-08-02 | 广东工业大学 | A kind of robot path planning method based on stochastical sampling and intensified learning |
| CN110285802B (en) * | 2019-06-11 | 2022-09-16 | 安徽理工大学 | Method for rapidly expanding path smoothing of random tree |
| CN110531770A (en) * | 2019-08-30 | 2019-12-03 | 的卢技术有限公司 | One kind being based on improved RRT paths planning method and system |
| CN113095537A (en) * | 2020-01-09 | 2021-07-09 | 北京京东乾石科技有限公司 | Path planning method and device |
| CN111523719A (en) * | 2020-04-16 | 2020-08-11 | 东南大学 | Hybrid path planning method based on articulated vehicle kinematic constraint |
| CN111397598B (en) * | 2020-04-16 | 2022-02-01 | 苏州大学 | Mobile robot path planning and sampling method and system in man-machine co-fusion environment |
| CN111397598A (en) * | 2020-04-16 | 2020-07-10 | 苏州大学 | Mobile robot path planning and sampling method and system in man-machine co-fusion environment |
| CN111523719B (en) * | 2020-04-16 | 2024-03-15 | 东南大学 | Hybrid path planning method based on kinematic constraint of articulated vehicle |
| CN113108806A (en) * | 2021-05-13 | 2021-07-13 | 重庆紫光华山智安科技有限公司 | Path planning method, device, equipment and medium |
| CN113108806B (en) * | 2021-05-13 | 2024-01-19 | 重庆紫光华山智安科技有限公司 | Path planning method, device, equipment and medium |
| CN113219998A (en) * | 2021-06-15 | 2021-08-06 | 合肥工业大学 | Improved bidirectional-RRT-based vehicle path planning method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109668573A (en) | A kind of vehicle path planning method for improving RRT algorithm | |
| Stahl et al. | Multilayer graph-based trajectory planning for race vehicles in dynamic scenarios | |
| CN108153153B (en) | Learning variable impedance control system and control method | |
| Han et al. | Actor-critic reinforcement learning for control with stability guarantee | |
| Juang et al. | Reinforcement ant optimized fuzzy controller for mobile-robot wall-following control | |
| CN101943916B (en) | Kalman filter prediction-based robot obstacle avoidance method | |
| Bharatheesha et al. | Distance metric approximation for state-space RRTs using supervised learning | |
| Depraetere et al. | Comparison of model-free and model-based methods for time optimal hit control of a badminton robot | |
| Jiang et al. | A dynamic motion planning framework for autonomous driving in urban environments | |
| Han et al. | Obstacle avoidance based on deep reinforcement learning and artificial potential field | |
| Yoshimura et al. | Iterative transportation planning of multiple objects by cooperative mobile robots | |
| Xin et al. | Distributed model predictive contouring control for real-time multi-robot motion planning | |
| Rosolia et al. | Learning model predictive control for iterative tasks | |
| Laouici et al. | Hybrid method for the navigation of mobile robot using fuzzy logic and spiking neural networks | |
| CN114167872A (en) | Robot obstacle avoidance method and system, computer and robot | |
| Kon et al. | Model predictive based multi-vehicle formation control with collision avoidance and localization uncertainty | |
| Wan et al. | Predictive motion control of a mirosot mobile robot | |
| Liu et al. | Model-free and model-based time-optimal control of a badminton robot | |
| Li et al. | A new hybrid algorithm of dynamic obstacle avoidance based on dynamic rolling planning and RBFNN | |
| Armesto et al. | Mobile robot obstacle avoidance based on quasi-holonomic smooth paths | |
| Zhou et al. | Research on the fuzzy algorithm of path planning of mobile robot | |
| Fu et al. | Global Dynamic Path Planning based on Fusion Improved A-star And Dynamic Window Method | |
| Paykari et al. | Design of MIMO mamdani fuzzy logic controllers for wall following Mobile robot | |
| Doshi et al. | Towards reduced-order models for online motion planning and control of UAVs in the presence of wind | |
| Jiang et al. | Obstacle Avoidance Algorithm Based on Human Experience Knowledge |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190423 |
|
| RJ01 | Rejection of invention patent application after publication |