CN109032149B - Multi-mobile-robot balance anti-deadlock path planning method based on grid map - Google Patents

Multi-mobile-robot balance anti-deadlock path planning method based on grid map Download PDF

Info

Publication number
CN109032149B
CN109032149B CN201811193879.0A CN201811193879A CN109032149B CN 109032149 B CN109032149 B CN 109032149B CN 201811193879 A CN201811193879 A CN 201811193879A CN 109032149 B CN109032149 B CN 109032149B
Authority
CN
China
Prior art keywords
grid
path
grid point
point
mobile
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.)
Active
Application number
CN201811193879.0A
Other languages
Chinese (zh)
Other versions
CN109032149A (en
Inventor
肖海宁
秦德金
张炯
楼佩煌
武星
钱晓明
曾勇
石陈陈
王龙军
郑竹安
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.)
Yancheng Institute of Technology
Original Assignee
Yancheng Institute of Technology
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 Yancheng Institute of Technology filed Critical Yancheng Institute of Technology
Priority to CN201811193879.0A priority Critical patent/CN109032149B/en
Publication of CN109032149A publication Critical patent/CN109032149A/en
Application granted granted Critical
Publication of CN109032149B publication Critical patent/CN109032149B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
    • 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
    • G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
    • 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
    • G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle

Landscapes

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

Abstract

The invention provides a multi-mobile-robot balance anti-deadlock path planning method based on a grid map, which is characterized in that before a path is planned for a mobile robot, the temporarily allowed running direction of each path is firstly identified according to a planned path library, all paths are guaranteed to be one-way paths, the deadlock phenomenon caused by the opposite conflict of the paths of two robots is avoided, and the overall efficiency and the intelligent level of a multi-mobile-robot system are further improved; during path planning, the invention comprehensively considers the routes, the turning times and the traffic flow of each grid point along the way, can effectively enhance the distribution balance of multiple AGV paths and reduce the probability of traffic jam.

Description

Multi-mobile-robot balance anti-deadlock path planning method based on grid map
Technical Field
The invention relates to the field of mobile robots, in particular to a grid map-based multi-mobile-robot balance anti-deadlock path planning method which is applied to a grid map-based multi-mobile-robot system and used for solving the problem of unbalanced path distribution when multiple mobile robots share the same grid map.
Background
The path planning technology is a core technology for realizing autonomous movement of a mobile robot, the quality of the method directly influences the efficiency intelligent level of the mobile robot, at present, many domestic and foreign experts and scholars are dedicated to the research of a path planning algorithm of the mobile robot, but most of the methods aim at the path planning algorithm of a single mobile robot, the optimization goal is to minimize the total path or the travel time of the path of the single mobile robot, if the method is directly used for multiple mobile robots, imbalance of path distribution of the multiple mobile robots is easy to occur, local traffic jam occurs, deadlock caused by opposite path conflict among the mobile robots is not considered, and the overall efficiency and the intelligent level of a multiple mobile robot system are influenced.
Disclosure of Invention
The purpose of the invention is as follows: aiming at solving the technical problems that the paths of a plurality of mobile robots in the prior art are unevenly distributed and deadlock is easily caused by opposite path conflict
The technical scheme is as follows: in order to achieve the technical purpose, the technical scheme provided by the invention is as follows:
a grid map-based multi-mobile-robot balanced deadlock-proof path planning method, wherein a plurality of mobile robots use the same grid map, and the method comprises the following steps:
(1) acquiring a grid map and planned path information of each mobile robot, and preprocessing the grid map, wherein the preprocessing steps are as follows: numbering all grid points in the grid map; constructing a first-order adjacency matrix and an orientation matrix of grid points according to the encoding result;
the first order adjacency matrix is:
Figure BDA0001826617380000011
the orientation matrix is:
Figure BDA0001826617380000012
wherein i and j both represent the number of grid points, N is the total number of grid points in the grid map,
Figure BDA0001826617380000013
representing the shortest distance from grid point i to grid point j,
Figure BDA0001826617380000014
representing the azimuth angle between grid point i and grid point j;
Figure BDA0001826617380000015
the values of (A) are as follows:
Figure BDA0001826617380000021
Figure BDA0001826617380000022
the values of (A) are as follows:
Figure BDA0001826617380000023
(2) and (3) counting the traffic flow of each grid point to form a flow matrix:
F＝[f(i)]1×N
wherein f (i) represents the traffic flow at grid point i, i.e. the number of robots in the planned path that pass grid point i;
(3) resetting the first order adjacency matrix according to the planned path: when a path from grid point i to grid point j exists in the planned path, the elements in the first-order adjacency matrix are
Figure BDA0001826617380000024
The value of (d) is set to ∞;
(4) and planning an optimal path from the current position s of each mobile robot to a target grid point d for each mobile robot by adopting an improved Dijkstra algorithm according to the flow matrix and the reset adjacent matrix by taking the current position s of each mobile robot as a source point.
Further, the specific steps of performing path planning by using the improved Dijkstra algorithm in the step (4) are as follows:
1) setting parameters:setting a grid point set VSAnd VD，VD＝V/VSV is the set of all grid points; setting an optimal path matrix P, P ═ Psi]1×N，psiRepresenting the optimal path from the source point s to the grid point i; setting weight matrix T, T ═ Ti]1×N，tiThe weight values of the grid points i are represented,
Figure BDA0001826617380000025
2) initialization of parameters, initialization VS＝{s}，VDI | i ∈ V and i ≠ s }, pss＝{s}，
Figure BDA0001826617380000026
3) Search VDThe grid point k having the smallest weight in the grid,
Figure BDA0001826617380000027
grid point k is changed from VDMove into VSIn, i.e. update VS＝VS∪{k}，VD＝VD/{k}，psk＝{s，k}，
Figure BDA0001826617380000028
Turning to step 4);
4) update VDThe weight, the optimal path and the first-order adjacency matrix of each grid point n:
the weight value updating formula is as follows:
Figure BDA0001826617380000031
wherein theta is a steering coefficient, and the calculation formula of theta is as follows:
Figure BDA0001826617380000032
dmkis a path pskAzimuth angle between the last two grid points m, k; w is a steering time coefficient, w ═ TT/TD，TTAverage time for the robot to decelerate, turn and accelerate to rated speed at grid points, TDAverage time for the robot to pass a grid distance;
updating the optimal path p of a grid point nsnComprises the following steps:
Figure BDA0001826617380000033
5) after step 4), searching the updated VDIn the grid point k with the minimum weight, updating VS＝VS∪{k}，VD＝VD/{k}，
Figure BDA0001826617380000034
Judging whether k is satisfied, if so, outputting the optimal path psdEnding the path planning; otherwise, go to step 4).
Has the advantages that: compared with the prior art, the invention has the following advantages:
1. the method comprehensively considers the routes, the turning times and the traffic flow of each grid point along the way during path planning, can effectively enhance the distribution balance of multiple AGV paths, and reduces the probability of traffic jam;
2. before planning paths for the mobile robots, the temporarily allowed running directions of the paths are identified according to the planned path library, all the paths are guaranteed to be unidirectional paths, the deadlock phenomenon caused by the opposite conflict of the paths of the two robots is avoided, and the overall efficiency and the intelligent level of the multi-mobile robot system are improved.
Drawings
FIG. 1 is an overall flow chart of the present invention;
FIG. 2 is a schematic diagram of a grid map;
fig. 3 is a schematic diagram of deadlock caused by paths conflicting with each other between two robots.
Detailed Description
The present invention will be further described with reference to the accompanying drawings.
The invention provides a multi-mobile-robot balance deadlock-proof path planning method based on a grid map, the overall flow of the method is shown in figure 1, the method mainly comprises three parts of grid map preprocessing, data statistics of a mobile robot with a planned path and balance path planning, and the schemes of the three parts are respectively described in detail below.
(1) Grid map preprocessing
The method comprises the following steps:
step 1: encoding N grid point presses in a given grid map (as shown in FIG. 2);
step 2: obtaining a 1 st order adjacency matrix of a grid map
Figure BDA0001826617380000041
Wherein i and j both represent the number of grid points, N is the total number of grid points in the grid map,
Figure BDA0001826617380000042
representing the shortest distance from grid point i to grid point j,
Figure BDA0001826617380000043
the values of (A) are as follows:
Figure BDA0001826617380000044
that is, when
Figure BDA0001826617380000045
When the value is 1, the distance between the grid point i and the grid point j is 1 grid; when in use
Figure BDA0001826617380000046
When the value is 0, the grid point i and the grid point j are the same grid point; when in use
Figure BDA0001826617380000047
When the value is infinity, the grid point i and the grid point j are not adjacent or one grid point is definedThe obstacle is occupied.
Step 3: obtaining an orientation matrix between grid points
Figure BDA0001826617380000048
Wherein
Figure BDA0001826617380000049
The azimuth angle between grid point i and grid point j is represented as follows:
Figure BDA00018266173800000410
and waiting for a new path planning task after the preprocessing is finished.
(2) Data statistics
The method comprises the following steps:
step 4: counting the traffic flow of each grid point to form a flow matrix F ═ F (i)]1×NWhere N is the total number of grid points of the grid map given in fig. 2; f (i) represents the traffic flow at grid point i, i.e. the number of robots in the planned path that pass grid point i.
The paths of three robots in the planned path library are assumed to be:
PR1＝{1，2，7，8，13，14}，PR2＝{3，8，13}，PR4＝{4，3，8，13}，
then f (1) is 1, f (2) is 1, f (3) is 2, f (4) is 1, f (7) is 1, f (8) is 3, f (13) is 3, and f (14) is 1.
Step 5: according to the path identification method, the operation direction allowed by each path is identified according to the path of each mobile robot in the path library, the phenomenon that the mobile robot about to plan the path and the robot with the planned path conflict in opposite directions as shown in figure 3 to cause deadlock is avoided, and the identification method comprises the following steps: if the path { i, j } is already in the path library, then the corresponding element in the 1 st order adjacency matrix is set
Figure BDA0001826617380000051
Avoiding the occurrence of paths { j, i } in the path of the robot to be planned, and ensuring the placeThe paths are all unidirectional paths, so that the deadlock phenomenon caused by the opposite conflict of the paths of the two robots is avoided.
(3) Balanced path planning
According to the received robot path planning task, comprehensively considering the adjacency matrix
Figure BDA0001826617380000052
And the flow matrix F ═ F (i)]1×NAnd planning an optimal path from the current position s of the robot to a target grid point d by adopting an improved Dijkstra algorithm. The classic Dijkstra algorithm is a greedy algorithm and can obtain the shortest path and the shortest path between a source point and other grid points.
The basic idea of the third part of path planning is as follows: set V of two grid pointsSAnd VD＝V/VSV is the set of all grid points, set VSThe grid points of the searched optimal path with the source point (the current position s of the robot) are stored in a set VDAnd grid points which are required to be searched for and have the smallest source point weight (including grid number, turning times and traffic flow of all grid points along the way) are stored in the storage. At the beginning of VSIn the middle, only the active point s, then continuously from VDSelecting the grid point (such as k) with the minimum s weight value to add into VSIn, set VSUpdate the source points s to V each time a new grid point is addedDThe weights of all grid points in the list. Adding V until target grid point dSIn (1). The path planning method comprises the following specific steps:
step 6: setting parameters: setting a grid point set VSAnd VD，VD＝V/VSV is the set of all grid points; setting an optimal path matrix P, P ═ Psi]1×N，psiRepresenting the optimal path from the source point s to the grid point i; setting weight matrix T, T ═ Ti]1×N，tiThe weight values of the grid points i are represented,
Figure BDA0001826617380000053
initialization of parameters, initialization VS＝{s}，VDI | i ∈ V and i ≠ s }, pss＝{s}，
Figure BDA0001826617380000061
Step 7: search VDThe grid point k having the smallest weight in the grid,
Figure BDA0001826617380000062
grid point k is changed from VDMove into VSIn, i.e. update VS＝VS∪{k}，VD＝VD/{k}，psk＝{s，k}，
Figure BDA0001826617380000063
Go to Step 8;
step 8: update VDThe weight, the optimal path and the first-order adjacency matrix of each grid point in the method are updated as follows, and V is assumedDAny grid point in the grid points is n, and the weight value updating formula of n is as follows:
Figure BDA0001826617380000064
wherein theta is a steering coefficient, and the calculation method of theta is as follows:
Figure BDA0001826617380000065
wherein d ismkIs a path pskAzimuth angle between the last two grid points m and k; w is a steering time coefficient, w ═ TT/TD，TTAverage time for the robot to decelerate, turn and accelerate to rated speed at grid points, TDAverage time for the robot to pass a grid distance;
optimal path psnAlso according to tnAnd synchronously updating, wherein the updating method comprises the following steps:
Figure BDA0001826617380000066
proceed to Step 9.
Step 9: search VDThe grid point with the minimum weight is not set as the grid point k, and k is set from VDMove into VSIn, i.e. VS＝VS∪{k}，VD＝VD/{ k }, and sets a first-order adjacency matrix
Figure BDA0001826617380000067
Ensuring that all paths are unidirectional paths, judging whether k is equal to d, if so, searching an optimal path, and outputting an optimal path psdEnding the path planning; otherwise, go to Step 8.
The above description is only of the preferred embodiments of the present invention, and it should be noted that: it will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the principles of the invention and these are intended to be within the scope of the invention.

Claims (2)

1. A multi-mobile-robot balance deadlock-proof path planning method based on a grid map is characterized in that the multi-mobile robot uses the same grid map, and the method comprises the following steps:
(1) acquiring a grid map and planned path information of each mobile robot, and preprocessing the grid map, wherein the preprocessing steps are as follows: numbering all grid points in the grid map; constructing a first-order adjacency matrix and an orientation matrix of the grid points according to the numbering result;
the first order adjacency matrix is:
Figure FDA0002736041450000011
the orientation matrix is:
Figure FDA0002736041450000012
wherein i and j both represent the number of grid points, N is the total number of grid points in the grid map,
Figure FDA0002736041450000013
representing the shortest distance from grid point i to grid point j,
Figure FDA0002736041450000014
representing the azimuth angle between grid point i and grid point j;
Figure FDA0002736041450000015
the values of (A) are as follows:
Figure FDA0002736041450000016
Figure FDA0002736041450000017
the values of (A) are as follows:
Figure FDA0002736041450000018
(2) and (3) counting the traffic flow of each grid point to form a flow matrix:
F＝[f(i)]1×N
wherein f (i) represents the traffic flow at grid point i, i.e. the number of mobile robots in the planned path that pass grid point i;
(3) resetting the first order adjacency matrix according to the planned path: when a path from grid point i to grid point j exists in the planned path, the elements in the first-order adjacency matrix are
Figure FDA0002736041450000019
The value of (d) is set to ∞;
(4) and planning an optimal path from the current position s of each mobile robot to a target grid point d for each mobile robot by adopting an improved Dijkstra algorithm according to the flow matrix and the reset first-order adjacent matrix by taking the current position s of each mobile robot as a source point.
2. The grid map-based multi-mobile-robot balanced deadlock-proof path planning method according to claim 1, wherein the path planning in step (4) by using an improved Dijkstra algorithm comprises the following specific steps:
1) setting parameters: setting a grid point set VSAnd VD，VD＝V/VSV is the set of all grid points; setting an optimal path matrix P, P ═ Psi]1×N，psiRepresenting the optimal path from the source point s to the grid point i; setting weight matrix T, T ═ Ti]1×N，tiThe weight values of the grid points i are represented,
Figure FDA0002736041450000021
2) initialization of parameters, initialization VS＝{s}，VDI | i ∈ V and i ≠ s }, pss＝{s}，
Figure FDA0002736041450000022
3) Search VDThe grid point k having the smallest weight in the grid,
Figure FDA0002736041450000023
grid point k is changed from VDMove into VSIn, i.e. update VS＝VS∪{k}，VD＝VD/{k}，psk＝{s,k}，
Figure FDA0002736041450000024
Turning to step 4);
4) update VDThe weight, the optimal path and the first-order adjacency matrix of each grid point n:
the weight value updating formula is as follows:
Figure FDA0002736041450000025
wherein theta is a steering coefficient, and the calculation formula of theta is as follows:
Figure FDA0002736041450000026
Figure FDA0002736041450000027
is a path pskAzimuth angle between the last two grid points m, k; w is a steering time coefficient, w ═ TT/TD,TTFor the average time, T, that each mobile robot decelerates, turns and accelerates to the rated speed at the grid pointDAverage time for each mobile robot to pass a grid distance;
optimal path p according to grid point nsnComprises the following steps:
Figure FDA0002736041450000028
5) after step 4), searching the updated VDIn the grid point k with the minimum weight, updating VS＝VS∪{k}，VD＝VD/{k}，
Figure FDA0002736041450000029
Judging whether k is satisfied, if so, outputting the optimal path psdEnding the path planning; otherwise, go to step 4).
CN201811193879.0A 2018-10-12 2018-10-12 Multi-mobile-robot balance anti-deadlock path planning method based on grid map Active CN109032149B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811193879.0A CN109032149B (en) 2018-10-12 2018-10-12 Multi-mobile-robot balance anti-deadlock path planning method based on grid map

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811193879.0A CN109032149B (en) 2018-10-12 2018-10-12 Multi-mobile-robot balance anti-deadlock path planning method based on grid map

Publications (2)

Publication Number Publication Date
CN109032149A CN109032149A (en) 2018-12-18
CN109032149B true CN109032149B (en) 2020-12-11

Family

ID=64612818

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811193879.0A Active CN109032149B (en) 2018-10-12 2018-10-12 Multi-mobile-robot balance anti-deadlock path planning method based on grid map

Country Status (1)

Country Link
CN (1) CN109032149B (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111833593B (en) * 2019-04-18 2022-12-27 北京京东乾石科技有限公司 Method and device for controlling vehicle, control method executed by vehicle and vehicle
CN110530388B (en) * 2019-09-05 2021-08-27 苏宁云计算有限公司 Multi-AGV path planning method and system
CN111573126B (en) * 2020-05-11 2022-04-05 盐城工学院 Modular intelligent logistics system material distribution path planning method based on omnidirectional wheel
CN113762575B (en) * 2020-12-02 2024-05-21 北京京东乾石科技有限公司 Conveying line path optimization method and device
CN112817316B (en) * 2021-01-04 2022-03-15 浙江大学 Multi-robot path planning method and device

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20110026776A (en) * 2009-09-08 2011-03-16 부산대학교 산학협력단 Method for path-planning for actual robots
CN102566576A (en) * 2012-02-24 2012-07-11 山东鲁能智能技术有限公司 Multiple inspection robot cooperative operation method for substation sequence control system
CN104537834A (en) * 2014-12-21 2015-04-22 北京工业大学 Intersection identification and intersection trajectory planning method for intelligent vehicle in urban road running process
CN105955280A (en) * 2016-07-19 2016-09-21 Tcl集团股份有限公司 Mobile robot path planning and obstacle avoidance method and system
CN105955258A (en) * 2016-04-01 2016-09-21 沈阳工业大学 Robot global grid map construction method based on Kinect sensor information fusion

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20110026776A (en) * 2009-09-08 2011-03-16 부산대학교 산학협력단 Method for path-planning for actual robots
CN102566576A (en) * 2012-02-24 2012-07-11 山东鲁能智能技术有限公司 Multiple inspection robot cooperative operation method for substation sequence control system
CN104537834A (en) * 2014-12-21 2015-04-22 北京工业大学 Intersection identification and intersection trajectory planning method for intelligent vehicle in urban road running process
CN105955258A (en) * 2016-04-01 2016-09-21 沈阳工业大学 Robot global grid map construction method based on Kinect sensor information fusion
CN105955280A (en) * 2016-07-19 2016-09-21 Tcl集团股份有限公司 Mobile robot path planning and obstacle avoidance method and system

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
自动导引车系统单双向混合路径规划和交通管理技术研究;王江华;《中国优秀硕士学位论文全文数据库》;20160315;24-35 *

Also Published As

Publication number Publication date
CN109032149A (en) 2018-12-18

Similar Documents

Publication Publication Date Title
CN109032149B (en) Multi-mobile-robot balance anti-deadlock path planning method based on grid map
CN111352417B (en) Rapid generation method of heterogeneous multi-unmanned aerial vehicle cooperative path
CN111785045B (en) Distributed traffic signal lamp combined control method based on actor-critic algorithm
CN110308740B (en) Unmanned aerial vehicle cluster dynamic task allocation method for tracking moving target
CN102810118B (en) A kind of change weighs net K nearest neighbor search method
CN111024080B (en) Unmanned aerial vehicle group-to-multi-mobile time-sensitive target reconnaissance path planning method
CN109724612A (en) A kind of AGV paths planning method and equipment based on topological map
CN110530369A (en) AGV method for scheduling task based on time window
CN102735239B (en) Navigation device, method and system
CN109357678B (en) Multi-unmanned aerial vehicle path planning method based on heterogeneous pigeon swarm optimization algorithm
CN110471417B (en) Multi-AGV collision prevention method based on load balancing
CN110782086A (en) Rescue vehicle distribution path optimization method and system with unmanned aerial vehicle
CN113758494B (en) Navigation path planning method, device, equipment and storage medium
CN110487290B (en) Unmanned vehicle local path planning method based on variable step size A star search
CN104199878A (en) Game engine shortest path search method and game engine system
CN110531782A (en) Unmanned aerial vehicle flight path paths planning method for community distribution
CN109115220A (en) A method of for parking system path planning
CN112819211A (en) Multi-region scheduling route planning method based on ant colony iterative algorithm
CN111310992A (en) Multi-unmanned aerial vehicle path optimization method for rapid evaluation after earthquake disaster
CN116720642A (en) Method and system for optimizing path of cooperative distribution of vehicle and unmanned aerial vehicle
CN114967680A (en) Mobile robot path planning method based on ant colony algorithm and convolutional neural network
CN114169628B (en) Shipboard aircraft scheduling optimization method and system based on A-star algorithm and genetic algorithm
CN112558601A (en) Robot real-time scheduling method and system based on Q-learning algorithm and water drop algorithm
CN112346480B (en) Indoor unmanned aerial vehicle, control method thereof and computer-readable storage medium
Huang et al. Robot path planning using improved ant colony algorithm in the environment of internet of things

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