CN108073176A - A kind of modified D*Lite vehicle dynamic path planing methods - Google Patents

A kind of modified D*Lite vehicle dynamic path planing methods Download PDF

Info

Publication number
CN108073176A
CN108073176A CN201810138594.0A CN201810138594A CN108073176A CN 108073176 A CN108073176 A CN 108073176A CN 201810138594 A CN201810138594 A CN 201810138594A CN 108073176 A CN108073176 A CN 108073176A
Authority
CN
China
Prior art keywords
vehicle
mrow
lite
path
modified
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
CN201810138594.0A
Other languages
Chinese (zh)
Other versions
CN108073176B (en
Inventor
孙宏滨
马荣波
吴金强
王潇
辛景民
郑南宁
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.)
WUFANG SMART CAR TECHNOLOGY Co.,Ltd.
Original Assignee
Xian Jiaotong University
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 Xian Jiaotong University filed Critical Xian Jiaotong University
Priority to CN201810138594.0A priority Critical patent/CN108073176B/en
Publication of CN108073176A publication Critical patent/CN108073176A/en
Application granted granted Critical
Publication of CN108073176B publication Critical patent/CN108073176B/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
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Economics (AREA)
  • Remote Sensing (AREA)
  • Strategic Management (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Operations Research (AREA)
  • Theoretical Computer Science (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

The invention discloses a kind of modified D*Lite vehicle dynamic path planing methods, comprise the following steps：1) vehicle's current condition and dbjective state are obtained, and obtains current environment cartographic information, morphological operation is reused and the barrier in current environment map is expanded；2) build vehicle operation and learn model；3) limitation based on vehicle kinematics model uses searching route on the environmental map of D*Lite algorithms upon inflation；4) vehicle is adjusted towards angle during according to Reeds Shepp curves to reaching home；5) the Reeds Shepp curves in the shortest path and step 4) that are generated according to step 3) build final path, then final path is carried out using energy function and gradient descent method smooth, complete the planning of modified D*Lite vehicle dynamic paths, this method can in the environment of dynamic realizing route planning.

Description

A kind of modified D*Lite vehicle dynamic path planing methods
Technical field
The invention belongs to pilotless automobile path planning fields, are related to a kind of modified D*Lite vehicle dynamic paths rule The method of drawing.
Background technology
The research origin of automatic driving vehicle in the 1960s, by vehicle body sensor information and environmental information, Have in the environment of barrier, complete positioning, avoidance, goal seeking etc. is a series of is automatically brought into operation process, be in recent years domestic and international Educational circles and business circles research hotspot.Unmanned technology mainly includes environment sensing, path planning, three parts of motion control. Wherein path planning is component very crucial in unmanned technology, plays to hold and open for environment sensing and motion control Under effect.Environmental data based on sensory perceptual system, vehicle is needed in complicated road environment, based on certain performance indicator Cook up safe and reliable, vehicle wheeled, from initial position to target location a most short collisionless path.
Common in unmanned vehicle path planning to have A* classes, D* class algorithms based on heuristic search algorithm, A* class algorithms are fitted For static environment, D* classes algorithm is suitable for dynamic environment.The environment moment residing for unmanned vehicle is changing, and this requires path weights The speed newly planned is sufficiently fast, and to meet the requirement of vehicle traveling real-time, this prevents A* class algorithms from meeting real-time road The requirement that lower vehicle is planned again.D* class algorithms are the improvement based on A* class algorithms, can be utilized when environment changes previous Search information improve this search efficiency, carried out with reusing A* classes algorithms compared with weight-normality draws, search efficiency higher, institute The active path planning for solving the problems, such as unmanned vehicle is more suitable for D* class algorithms.D*Lite algorithm principles are simple in D* class algorithms, hold It easily realizes, is particularly suited in the active path planning of unmanned vehicle.
However, in rasterizing environment, if directly A* classes, D* classes algorithm are applied in vehicle path planning, only Vehicle can be regarded to a point as, using the searching method searching route of four neighborhoods or eight neighborhood, the path so generated is uneven Sliding, from the limitation of vehicle kinematics, frequently resulting in path can not travel.
Chinese patent CN104590259 discloses a kind of A* algorithms based on vehicle kinematics model, lists vehicle fortune Dynamic side's differential equation, the kinematics model of vehicle is so just considered when using A* algorithm search paths, is finally obtained Path must be feasible.But method used in the patent can be only applied in static environment, if environment changes, It then needs to travel through whole map and plan again, be not suitable for the planning under dynamic environment, and the environment residing for unmanned vehicle is not Disconnected variation, so the algorithm is not appropriate for the real-time route planning of unmanned vehicle.In addition, the patent propose method due to only Vehicle kinematics model is used, so vehicle towards angle approximate can only reach dbjective state when reaching home, error depends on In the size towards angular resolution, this under unstructured moving grids (such as parking lot) is unpractical.
The content of the invention
The shortcomings that it is an object of the invention to overcome the above-mentioned prior art, provides a kind of modified D*Lite vehicles dynamic Paths planning method, this method can in the environment of dynamic realizing route planning.
In order to achieve the above objectives, modified D*Lite vehicle dynamic paths planing method of the present invention includes following step Suddenly：
1) vehicle's current condition and dbjective state are obtained, and obtains current environment cartographic information, reuses morphological operation Barrier in current environment map is expanded；
2) build vehicle operation and learn model；
3) limitation based on vehicle kinematics model, it is most short using being generated on the environmental map of D*Lite algorithms upon inflation Path；
4) vehicle is adjusted towards angle during according to Reeds-Shepp curves to reaching home；
5) the Reeds-Shepp curves in the shortest path and step 4) that are generated according to step 3) build final path, so Carry out smooth, completion modified D*Lite vehicle dynamic path rule to final path using energy function and gradient descent method afterwards It draws.
The concrete operations of step 2) are：
If vehicle is limited in plane motion, and wheel will not skid on the ground, then vehicle operation model is：
Wherein, x is state of motion of vehicle, and (x, y) is the position coordinates of vehicle, and θ is the course angle of vehicle, and v is vehicle Speed, δ be vehicle front-wheel corner, l be the distance between automobile front-axle and rear axle,AndX, y and θ are corresponded to respectively First derivation.
Energy function in step 5) is：
Wherein, N be path point quantity, Δ xi+1=xi+1-xi,Δxi=xi-xi-1。
During D*Lite algorithm expanding nodes, the son that different position and different directions are generated according to vehicle kinematics model saves Then the child node of generation is inserted in the drawing up in table of D*Lite by point.
The invention has the advantages that：
Modified D*Lite vehicle dynamic paths planing method of the present invention is in concrete operations, based on vehicle movement The limitation of model is learned, using shortest path is generated on the environmental map of D*Lite algorithms upon inflation, so as in dynamic environment Be quickly found out a shortest path, in addition, the present invention according to Reeds-Shepp curves to reaching home when vehicle towards angle into Row adjustment realizes that vehicle towards the adjustment at angle, recycles smooth function and gradient descent method to final road when being up to terminal Footpath carries out smooth, completes under dynamic environment vehicle accurate path planning in real time, convenient and simple for operation.
Description of the drawings
Fig. 1 is the flow chart of the present invention；
Fig. 2 is the D*Lite expanding node figures based on vehicle kinematics model in the present invention；
Fig. 3 is the path profile generated using D*Lite and Reeds-Shepp curves；
Fig. 4 is the comparison diagram using smooth paths function anterior-posterior approach.
Specific embodiment
The present invention is described in further detail below in conjunction with the accompanying drawings：
With reference to figure 1, modified D*Lite vehicle dynamic path planing methods of the present invention comprise the following steps：
1) vehicle's current condition and dbjective state are obtained, and obtains current environment cartographic information, reuses morphological operation Barrier in current environment map is expanded；
2) build vehicle operation and learn model；
The concrete operations of step 2) are：
If vehicle is limited in plane motion, and wheel will not skid on the ground, then have vehicle operation to learn model and be：
Wherein, x is state of motion of vehicle, and (x, y) is the position coordinates of vehicle, and θ is the course angle of vehicle, and v is vehicle Speed, δ be vehicle front-wheel corner, l be the distance between automobile front-axle and rear axle,AndX, y and θ are corresponded to respectively First derivation.
3) limitation based on vehicle kinematics model, using searching for road on the environmental map of D*Lite algorithms upon inflation Footpath；
According to the limitation of vehicle kinematics model, D*Lite algorithms are improved, the input of the D*Lite algorithms is one Open the rasterizing map after barrier expansion, vehicle starting pose XS=(xS,yS,θS) and object pose XG=(xG,yG,θG) defeated It is a path for meeting the limitation of vehicle kinematics model to go out, which is represented by a series of continuous vehicle poses.
The heuristic searching function of D*Lite algorithms is：
F (p)=g (p)+h (p)
Wherein, f (p) be the node cost value, g (p) be starting point arrive arbitrary node n minimum cost value, h (p) for The cost inspiration value of destination node n.
The shortest path information, each drawn up in table storage and have each node on path planning to destination node of D*Lite Father node, f (p), g (p), h (p) and the father node of node are to the track of present node.
When extending child node from father node, each node of conventional method only includes the coordinate information of vehicle, is saved with father Centered on point (x, y), toward upper and lower, 4 directions of left and right or upper and lower, left and right, upper left, lower-left, upper right and the direction of bottom right 8 Extension child node (x ', y '), it finally searches for obtained path and does not account for vehicle kinematics model, it is possible that racing, original It turns around to wait the behavior that can not possibly make of vehicles in ground.
And when considering the limitation extension child node of vehicle kinematics model, each node includes coordinate information and the court of vehicle To information, start from father node (x, y, θ), with fixed speed by different steering angles by certain time, arrival is owned Next node (x ', y ', θ ') it is extended, it finally searches for obtained path and meets vehicle kinematics model, vehicle can be direct Traveling.
Specifically search process is：
Since present node, being moved forward and backward one section of set time of traveling with vehicle kinematics model, steering angle is more, Then generated state is also more, and obtained path is also more smooth.Steering angle is very little, then can cause to can not find path, turns to Angle can cause calculation amount to increase too much, therefore it is critically important to choose moderate steering angle quantity.Turned according to the maximum of vehicle in practice To angle, as shown in Fig. 2, using 10 steering angles, i.e. vehicle moves forward and backward each five steering angles (- 35 ° -20 ° 0 ° 20 ° 35 °), Vehicle-state after one section of set time.
After having extended a node, judge either with or without barrier, if without barrier, to retain on the track of its generation The paths, and by the terminal state insertion Open tables of this paths, if there is barrier, give up.
Therefore several new nodes can all be obtained by often extending a node, and the path between node and node is then basis Vehicle is generated with model is learned, and when so using D*Lite algorithm search to certain point, his father's section is found as long as being upsided down along the point Point, then the father node of father node is found, and so on, until starting point stops.All path points are determined and then found out to be saved from father Point arrives the path of child node, you can one path under the limitation of vehicle kinematics model of generation.
In discrete D*Lite, when search, is inserted into the grid extended in Open tables, but is limited in vehicle kinematics model In D*Lite under system, since position coordinates is continuous, any position in grid can be appeared in, if do not processed straight When patching in Open chained lists, there will be infinite various states, it is therefore desirable to which installation position resolution ratio and towards resolution ratio then exists Two nodes under same resolution ratio are considered as same state.
4) vehicle is adjusted towards angle during according to Reeds-Shepp curves to reaching home；
When D*Lite algorithm search path is to close to land, Reeds-Shepp curves searching D*Lite is used It is attached between rope point and terminal.
When only using D*Lite algorithm search to terminal, due to the direction without considering terminal in search process, vehicle cannot Terminal is driven into correct posture, this is just not suitable for for this environment especially sensitive to angle in parking lot；Near terminal In region introduce Reeds-Shepp curves, can effectively solve the problems, such as close to during terminal towards angle.Reeds-Shepp curves are in vehicle It can move backward and in the case that min. turning radius and speed determine, two pose (x can be generated1,y1,θ1) and (x2,y2, θ2) between shortest path.
When D*Lite search nodes enter Reeds-Shepp route searching regions, terminal is generated to from present node Reeds-Shepp curves, if there is no barrier on the curve, the success of Reeds-Shepp coordinates measurements；If there is barrier on the curve Hinder object, then Reeds-Shepp coordinates measurements fail, then extend child node from present node, continue to be generated to terminal from child node Reeds-Shepp curves, so cycle, until there is no barrier on the curve, until coordinates measurement success.In extension son section Increase the number of steering angle during point, to generate more child status, increase searches out the possibility in Reeds-Shepp paths Property.
Then final path is formed by D*Lite paths and Reeds-Shepp curve matchings.Fig. 3 is final path schematic diagram.
5) the Reeds-Shepp curves in the shortest path and step 4) that are generated according to step 3) build final path, so Carry out smooth, completion modified D*Lite vehicle dynamic path rule to final path using energy function and gradient descent method afterwards It draws.
Energy function is：
Wherein, N be path point quantity, Δ xi+1=xi+1-xi,Δxi=xi-xi-1。
Using gradient descent method, energy is made to share in each path point；First seek the first derivative of each path point：
Then a constant μ is selected, is calculated：
Repeat above-mentioned two cycle, until the value of a preceding energy function and the value of a rear energy function subtract each other it is absolute Until value is less than preset value ε.
Comparison before and after path smooth is as shown in Figure 4.It can be seen that although original path is based on vehicle kinematics model , but local fluctuation concussion is relatively more, and do not meet behavior of the people when driving vehicle.And smoothed path is without local Concussion, curve become very smooth.
In addition, vehicle according to generation track travel, when environmental information changes, if on new ground path in graphs still without Barrier, original route is still feasible, then does not re-start the planning in path；If original path is now infeasible, carry out D*Lite algorithms pick up a collisionless path, to be rapidly completed planning and dynamic obstacle avoidance in real time.

Claims (4)

1. a kind of modified D*Lite vehicle dynamic path planing methods, which is characterized in that comprise the following steps：
1) vehicle's current condition and dbjective state are obtained, and obtains current environment cartographic information, reuses morphological operation to working as Barrier in preceding environmental map is expanded；
2) build vehicle operation and learn model；
3) limitation based on vehicle kinematics model, using searching for shortest path on the environmental map of D*Lite algorithms upon inflation Footpath；
4) vehicle is adjusted towards angle during according to Reeds-Shepp curves to reaching home；
5) the Reeds-Shepp curves in the shortest path and step 4) that are generated according to step 3) build final path, then make Final path is carried out with energy function and gradient descent method smoothly, to complete the planning of modified D*Lite vehicle dynamic paths.
2. modified D*Lite vehicle dynamic path planing methods according to claim 1, which is characterized in that step 2) Concrete operations are：
If vehicle is limited in plane motion, and wheel will not skid on the ground, then vehicle operation model is：
<mrow> <mover> <mi>x</mi> <mo>&amp;CenterDot;</mo> </mover> <mo>=</mo> <mi>v</mi> <mi>c</mi> <mi>o</mi> <mi>s</mi> <mrow> <mo>(</mo> <mi>&amp;theta;</mi> <mo>+</mo> <mi>&amp;delta;</mi> <mo>)</mo> </mrow> </mrow>
<mrow> <mover> <mi>y</mi> <mo>&amp;CenterDot;</mo> </mover> <mo>=</mo> <mi>v</mi> <mi>s</mi> <mi>i</mi> <mi>n</mi> <mrow> <mo>(</mo> <mi>&amp;theta;</mi> <mo>+</mo> <mi>&amp;delta;</mi> <mo>)</mo> </mrow> </mrow>
<mrow> <mover> <mi>&amp;theta;</mi> <mo>&amp;CenterDot;</mo> </mover> <mo>=</mo> <mfrac> <mrow> <mi>v</mi> <mi>s</mi> <mi>i</mi> <mi>n</mi> <mi>&amp;delta;</mi> </mrow> <mi>l</mi> </mfrac> </mrow>
Wherein, x is state of motion of vehicle, and (x, y) is the position coordinates of vehicle, and θ is the course angle of vehicle, and v is the speed of vehicle, δ be vehicle front-wheel corner, l be the distance between automobile front-axle and rear axle,AndThe single order of x, y and θ are corresponded to respectively Derivation.
3. modified D*Lite vehicle dynamic path planing methods according to claim 1, which is characterized in that in step 5) Energy function be：
<mrow> <mi>T</mi> <mo>=</mo> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mrow> <mi>N</mi> <mo>-</mo> <mn>1</mn> </mrow> </munderover> <msup> <mrow> <mo>(</mo> <msub> <mi>&amp;Delta;x</mi> <mrow> <mi>i</mi> <mo>+</mo> <mn>1</mn> </mrow> </msub> <mo>-</mo> <msub> <mi>&amp;Delta;x</mi> <mrow> <mi>i</mi> <mo>-</mo> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> </mrow>
Wherein, N be path point quantity, Δ xi+1=xi+1-xi,Δxi=xi-xi-1。
4. modified D*Lite vehicle dynamic path planing methods according to claim 1, which is characterized in that D*Lite is calculated During method expanding node, the child node of different position and different directions is generated according to vehicle kinematics model, then by the son of generation Node is inserted in the drawing up in table of D*Lite.
CN201810138594.0A 2018-02-10 2018-02-10 Improved D star Lite vehicle dynamic path planning method Active CN108073176B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810138594.0A CN108073176B (en) 2018-02-10 2018-02-10 Improved D star Lite vehicle dynamic path planning method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810138594.0A CN108073176B (en) 2018-02-10 2018-02-10 Improved D star Lite vehicle dynamic path planning method

Publications (2)

Publication Number Publication Date
CN108073176A true CN108073176A (en) 2018-05-25
CN108073176B CN108073176B (en) 2020-08-18

Family

ID=62155142

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810138594.0A Active CN108073176B (en) 2018-02-10 2018-02-10 Improved D star Lite vehicle dynamic path planning method

Country Status (1)

Country Link
CN (1) CN108073176B (en)

Cited By (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108983781A (en) * 2018-07-25 2018-12-11 北京理工大学 A kind of environment detection method in unmanned vehicle target acquisition system
CN109141441A (en) * 2018-07-19 2019-01-04 北京汽车集团有限公司 The obstacle analysis method and apparatus of vehicle
CN109270933A (en) * 2018-10-11 2019-01-25 中国科学院深圳先进技术研究院 Unmanned barrier-avoiding method, device, equipment and medium based on conic section
CN109916400A (en) * 2019-04-10 2019-06-21 上海大学 A kind of unmanned boat barrier-avoiding method combined based on gradient descent algorithm with VO method
CN109945885A (en) * 2019-04-16 2019-06-28 清华大学 The dynamic barrier obstacle-avoiding route planning calculation method of unmanned motor
CN109990796A (en) * 2019-04-23 2019-07-09 成都信息工程大学 Intelligent vehicle paths planning method based on two-way extension random tree
CN110614631A (en) * 2018-06-19 2019-12-27 北京京东尚科信息技术有限公司 Method and device for determining target point, electronic equipment and computer readable medium
CN110728398A (en) * 2019-09-27 2020-01-24 东南大学 Articulated engineering vehicle path planning method based on support vector machine
CN110806218A (en) * 2019-11-29 2020-02-18 北京京东乾石科技有限公司 Parking path planning method, device and system
CN110836671A (en) * 2019-11-14 2020-02-25 北京京邦达贸易有限公司 Trajectory planning method, trajectory planning device, storage medium, and electronic apparatus
CN111060108A (en) * 2019-12-31 2020-04-24 江苏徐工工程机械研究院有限公司 Path planning method and device and engineering vehicle
CN111176286A (en) * 2020-01-06 2020-05-19 重庆邮电大学 Mobile robot path planning method and system based on improved D-lite algorithm
CN111176288A (en) * 2020-01-07 2020-05-19 深圳南方德尔汽车电子有限公司 Reedsshepp-based global path planning method and device, computer equipment and storage medium
CN111220160A (en) * 2020-02-27 2020-06-02 智慧航海（青岛）科技有限公司 Autonomous driving ship route planning method based on D-Lite optimization algorithm
CN111426330A (en) * 2020-03-24 2020-07-17 江苏徐工工程机械研究院有限公司 Path generation method and device, unmanned transportation system and storage medium
CN111897365A (en) * 2020-08-27 2020-11-06 中国人民解放军国防科技大学 Autonomous vehicle three-dimensional path planning method for contour line guide line
CN112148002A (en) * 2020-08-31 2020-12-29 西安交通大学 Local trajectory planning method, system and device
CN113286985A (en) * 2020-09-17 2021-08-20 华为技术有限公司 Path planning method and path planning device
CN113341999A (en) * 2021-06-29 2021-09-03 河南科技大学 Forklift path planning method and device based on optimized D-x algorithm
CN113495566A (en) * 2021-08-21 2021-10-12 福州大学 Curvature constraint fusion potential field method-based D × Lite unmanned vehicle local path planning method
CN113670305A (en) * 2020-05-13 2021-11-19 长沙智能驾驶研究院有限公司 Parking trajectory generation method and device, computer equipment and storage medium
CN113885501A (en) * 2021-10-09 2022-01-04 江苏金陵智造研究院有限公司 Trajectory planning method for unmanned parking position posture adjustment
CN117075620A (en) * 2023-10-18 2023-11-17 华东交通大学 Multi-task navigation scheduling method and system for multi-inspection robot

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108827311B (en) * 2018-08-02 2021-09-21 大连理工江苏研究院有限公司 Route planning method for unmanned carrying system in manufacturing workshop

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7447593B2 (en) * 2004-03-26 2008-11-04 Raytheon Company System and method for adaptive path planning
EP2182419A1 (en) * 2008-11-04 2010-05-05 Saab Ab Avoidance manoeuvre generator for an aircraft
US20130103249A1 (en) * 2011-10-25 2013-04-25 Jaybridge Robotics, Inc. Method and system for dynamically positioning a vehicle relative to another vehicle in motion
CN104008392A (en) * 2014-05-09 2014-08-27 南京邮电大学 Multi-objective tracking method based on continuous minimum-energy appearance model
CN104238560A (en) * 2014-09-26 2014-12-24 深圳市科松电子有限公司 Method and system for planning nonlinear paths
CN105549597A (en) * 2016-02-04 2016-05-04 同济大学 Unmanned vehicle dynamic path programming method based on environment uncertainty
CN106767860A (en) * 2016-11-21 2017-05-31 江苏大学 A kind of method that intelligent automobile path planning search time is shortened based on heuristic search algorithm
CN106843216A (en) * 2017-02-15 2017-06-13 北京大学深圳研究生院 A kind of complete traverse path planing method of biological excitation robot based on backtracking search
CN106989748A (en) * 2017-05-16 2017-07-28 南京农业大学 A kind of Agriculture Mobile Robot man-computer cooperation paths planning method based on cloud model
CN107168344A (en) * 2017-05-17 2017-09-15 哈尔滨工程大学 A kind of UUV approaches air route generation method during seabed operation
CN107631734A (en) * 2017-07-21 2018-01-26 南京邮电大学 A kind of dynamic smoothing paths planning method based on D*_lite algorithms

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7447593B2 (en) * 2004-03-26 2008-11-04 Raytheon Company System and method for adaptive path planning
EP2182419A1 (en) * 2008-11-04 2010-05-05 Saab Ab Avoidance manoeuvre generator for an aircraft
US20130103249A1 (en) * 2011-10-25 2013-04-25 Jaybridge Robotics, Inc. Method and system for dynamically positioning a vehicle relative to another vehicle in motion
CN104008392A (en) * 2014-05-09 2014-08-27 南京邮电大学 Multi-objective tracking method based on continuous minimum-energy appearance model
CN104238560A (en) * 2014-09-26 2014-12-24 深圳市科松电子有限公司 Method and system for planning nonlinear paths
CN105549597A (en) * 2016-02-04 2016-05-04 同济大学 Unmanned vehicle dynamic path programming method based on environment uncertainty
CN106767860A (en) * 2016-11-21 2017-05-31 江苏大学 A kind of method that intelligent automobile path planning search time is shortened based on heuristic search algorithm
CN106843216A (en) * 2017-02-15 2017-06-13 北京大学深圳研究生院 A kind of complete traverse path planing method of biological excitation robot based on backtracking search
CN106989748A (en) * 2017-05-16 2017-07-28 南京农业大学 A kind of Agriculture Mobile Robot man-computer cooperation paths planning method based on cloud model
CN107168344A (en) * 2017-05-17 2017-09-15 哈尔滨工程大学 A kind of UUV approaches air route generation method during seabed operation
CN107631734A (en) * 2017-07-21 2018-01-26 南京邮电大学 A kind of dynamic smoothing paths planning method based on D*_lite algorithms

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
DMITRI DOLGOV，ECT.: "Practical Search Techniques in Path Planning for Autonomous Driving", 《AAAI WORKSHOP ARTIFICIAL INTELLIGENCE AND ROBOTICS》 *
ROBIN HESS,ECT.: "Trajectory Planning for Car-Like Robots using Rapidly Exploring Random Trees", 《IFAC SYMPOSIUM ON TELEMATICS APPLICATIONS》 *
余冬冬: "移动机器人避障与轨迹规划", 《万方数据在线》 *
王龙等: "基于最短路径的变半径泊车路径规划研究", 《汽车科技》 *

Cited By (36)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110614631A (en) * 2018-06-19 2019-12-27 北京京东尚科信息技术有限公司 Method and device for determining target point, electronic equipment and computer readable medium
CN110614631B (en) * 2018-06-19 2021-05-25 北京京东乾石科技有限公司 Method and device for determining target point, electronic equipment and computer readable medium
CN109141441A (en) * 2018-07-19 2019-01-04 北京汽车集团有限公司 The obstacle analysis method and apparatus of vehicle
CN108983781B (en) * 2018-07-25 2020-07-07 北京理工大学 Environment detection method in unmanned vehicle target search system
CN108983781A (en) * 2018-07-25 2018-12-11 北京理工大学 A kind of environment detection method in unmanned vehicle target acquisition system
CN109270933A (en) * 2018-10-11 2019-01-25 中国科学院深圳先进技术研究院 Unmanned barrier-avoiding method, device, equipment and medium based on conic section
CN109916400A (en) * 2019-04-10 2019-06-21 上海大学 A kind of unmanned boat barrier-avoiding method combined based on gradient descent algorithm with VO method
CN109945885A (en) * 2019-04-16 2019-06-28 清华大学 The dynamic barrier obstacle-avoiding route planning calculation method of unmanned motor
CN109990796A (en) * 2019-04-23 2019-07-09 成都信息工程大学 Intelligent vehicle paths planning method based on two-way extension random tree
CN110728398A (en) * 2019-09-27 2020-01-24 东南大学 Articulated engineering vehicle path planning method based on support vector machine
CN110728398B (en) * 2019-09-27 2023-05-16 东南大学 Hinge engineering vehicle path planning method based on support vector machine
CN110836671A (en) * 2019-11-14 2020-02-25 北京京邦达贸易有限公司 Trajectory planning method, trajectory planning device, storage medium, and electronic apparatus
CN110836671B (en) * 2019-11-14 2021-09-14 北京京邦达贸易有限公司 Trajectory planning method, trajectory planning device, storage medium, and electronic apparatus
CN110806218A (en) * 2019-11-29 2020-02-18 北京京东乾石科技有限公司 Parking path planning method, device and system
CN110806218B (en) * 2019-11-29 2021-09-07 北京京东乾石科技有限公司 Parking path planning method, device and system
CN111060108B (en) * 2019-12-31 2021-10-12 江苏徐工工程机械研究院有限公司 Path planning method and device and engineering vehicle
CN111060108A (en) * 2019-12-31 2020-04-24 江苏徐工工程机械研究院有限公司 Path planning method and device and engineering vehicle
CN111176286A (en) * 2020-01-06 2020-05-19 重庆邮电大学 Mobile robot path planning method and system based on improved D-lite algorithm
CN111176288A (en) * 2020-01-07 2020-05-19 深圳南方德尔汽车电子有限公司 Reedsshepp-based global path planning method and device, computer equipment and storage medium
CN111220160A (en) * 2020-02-27 2020-06-02 智慧航海（青岛）科技有限公司 Autonomous driving ship route planning method based on D-Lite optimization algorithm
CN111220160B (en) * 2020-02-27 2023-07-04 智慧航海（青岛）科技有限公司 Autonomous driving ship route planning method based on D-Lite optimization algorithm
CN111426330A (en) * 2020-03-24 2020-07-17 江苏徐工工程机械研究院有限公司 Path generation method and device, unmanned transportation system and storage medium
CN113670305A (en) * 2020-05-13 2021-11-19 长沙智能驾驶研究院有限公司 Parking trajectory generation method and device, computer equipment and storage medium
CN111897365A (en) * 2020-08-27 2020-11-06 中国人民解放军国防科技大学 Autonomous vehicle three-dimensional path planning method for contour line guide line
CN111897365B (en) * 2020-08-27 2022-09-02 中国人民解放军国防科技大学 Autonomous vehicle three-dimensional path planning method for contour line guide line
CN112148002B (en) * 2020-08-31 2021-12-28 西安交通大学 Local trajectory planning method, system and device
CN112148002A (en) * 2020-08-31 2020-12-29 西安交通大学 Local trajectory planning method, system and device
CN113286985A (en) * 2020-09-17 2021-08-20 华为技术有限公司 Path planning method and path planning device
WO2022056770A1 (en) * 2020-09-17 2022-03-24 华为技术有限公司 Path planning method and path planning apparatus
CN113341999A (en) * 2021-06-29 2021-09-03 河南科技大学 Forklift path planning method and device based on optimized D-x algorithm
CN113495566A (en) * 2021-08-21 2021-10-12 福州大学 Curvature constraint fusion potential field method-based D × Lite unmanned vehicle local path planning method
CN113495566B (en) * 2021-08-21 2023-03-31 福州大学 Curvature constraint fusion potential field method-based D × Lite unmanned vehicle local path planning method
CN113885501A (en) * 2021-10-09 2022-01-04 江苏金陵智造研究院有限公司 Trajectory planning method for unmanned parking position posture adjustment
CN113885501B (en) * 2021-10-09 2024-05-03 南京晨光集团有限责任公司 Track planning method for unmanned vehicle pose adjustment
CN117075620A (en) * 2023-10-18 2023-11-17 华东交通大学 Multi-task navigation scheduling method and system for multi-inspection robot
CN117075620B (en) * 2023-10-18 2024-01-16 华东交通大学 Multi-task navigation scheduling method and system for multi-inspection robot

Also Published As

Publication number Publication date
CN108073176B (en) 2020-08-18

Similar Documents

Publication Publication Date Title
CN108073176A (en) A kind of modified D*Lite vehicle dynamic path planing methods
Zhang et al. Trajectory planning and tracking for autonomous vehicle based on state lattice and model predictive control
Yang et al. Spline-based RRT path planner for non-holonomic robots
CN108519773A (en) The paths planning method of automatic driving vehicle under a kind of structured environment
CN106371445A (en) Unmanned vehicle planning control method based on topology map
CN104298239B (en) A kind of indoor mobile robot strengthens map study paths planning method
CN110361013B (en) Path planning system and method for vehicle model
CN108088456A (en) A kind of automatic driving vehicle local paths planning method with time consistency
CN107643752A (en) Omni-directional mobile robots path planning algorithm based on pedestrian track prediction
WO2018176596A1 (en) Unmanned bicycle path planning method based on weight-improved particle swarm optimization algorithm
Zhao et al. Dynamic motion planning for autonomous vehicle in unknown environments
CN105857306A (en) Vehicle autonomous parking path programming method used for multiple parking scenes
Bae et al. Path generation and tracking based on a Bezier curve for a steering rate controller of autonomous vehicles
Liu et al. The role of model fidelity in model predictive control based hazard avoidance in unmanned ground vehicles using LIDAR sensors
CN104029203A (en) Path planning method for implementation of obstacle avoidance for space manipulators
JP7130062B2 (en) Route determination method
CN110908386B (en) Layered path planning method for unmanned vehicle
Zhuge et al. A novel dynamic obstacle avoidance algorithm based on collision time histogram
CN104897168A (en) Intelligent vehicle path search method and system based on road risk assessment
Hu et al. Integrated path planning for unmanned differential steering vehicles in off-road environment with 3D terrains and obstacles
WO2022142893A1 (en) Path planning method and apparatus for biped robot, and biped robot
Fuji et al. Trajectory planning for automated parking using multi-resolution state roadmap considering non-holonomic constraints
Arnay et al. Safe and reliable path planning for the autonomous vehicle verdino
Yi et al. Smooth path planning for autonomous parking system
CN107289938A (en) A kind of unmanned ground vehicle local paths planning method

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
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20221207

Address after: No. 2, Yunshen Road, Changshu Hi tech Industrial Development Zone, Suzhou City, Jiangsu Province, 215506

Patentee after: WUFANG SMART CAR TECHNOLOGY Co.,Ltd.

Address before: Beilin District Xianning West Road 710049, Shaanxi city of Xi'an province No. 28

Patentee before: XI'AN JIAOTONG University