CN110275526A - A kind of method for planning path for mobile robot based on improved adaptive GA-IAGA - Google Patents
A kind of method for planning path for mobile robot based on improved adaptive GA-IAGA Download PDFInfo
- Publication number
- CN110275526A CN110275526A CN201910407620.XA CN201910407620A CN110275526A CN 110275526 A CN110275526 A CN 110275526A CN 201910407620 A CN201910407620 A CN 201910407620A CN 110275526 A CN110275526 A CN 110275526A
- Authority
- CN
- China
- Prior art keywords
- path
- gen
- grid
- individual
- point
- 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
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- 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
- G05D1/0217—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with energy consumption, time reduction or distance reduction criteria
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
Abstract
The invention discloses a kind of method for planning path for mobile robot based on improved adaptive GA-IAGA, it includes the following steps: (1) environmental modeling: being pre-processed using Grid Method to map, environmental map is divided into rule and uniform grid;Step 2, the beginning and end for setting robot, beginning and end position is in free grid;Step 3 uses improved adaptive GA-IAGA planning robot's optimal path;Step 4, smooth paths determine that path point as control point, is smoothed optimal path using B-spline Curve, generates final path from the optimal path that algorithm generates;It solves the prior art and needs a large amount of iteration to solve optimal path for algorithm existing for mobile robot path planning, therefore low efficiency, convergence rate are slow, and easily fall into the technical problems such as local optimum.
Description
Technical field
The invention belongs to mobile robot path planning technical field more particularly to a kind of shiftings based on improved adaptive GA-IAGA
Mobile robot paths planning method.
Background technique
With the continuous development of science and technology, airmanship has become the research hotspot of robot field, and path
Planning algorithm is the important leverage for realizing Mobile Robotics Navigation.Path planning refers to robot according to certain criterion, in ring
In border search for one from starting point to target point, can be with the optimal path of avoiding obstacles.Traditional path planning algorithm someone
Work potential field method, simulated annealing, fuzzy control, neural network algorithm etc., but the computation complexity of these algorithms is larger,
Existing defects are applied under real scene.The intelligent bionics algorithm such as genetic algorithm, ant group algorithm, particle swarm algorithm needs a large amount of
Iteration solve optimal path, therefore low efficiency, convergence rate are slow, and easily fall into local optimum.
Summary of the invention
The technical problem to be solved by the present invention is providing a kind of mobile robot path planning based on improved adaptive GA-IAGA
Method needs a large amount of iteration to solve optimal road to solve the prior art for algorithm existing for mobile robot path planning
Diameter, therefore low efficiency, convergence rate are slow, and easily fall into the technical problems such as local optimum.
The technical scheme is that
A kind of method for planning path for mobile robot based on improved adaptive GA-IAGA, it includes:
Step 1, environmental modeling: being pre-processed using Grid Method to map, environmental map is divided into regular and uniform
Grid;
Step 2, the beginning and end for setting robot, beginning and end position is in free grid;
Step 3 uses improved adaptive GA-IAGA planning robot's optimal path;
Step 4, smooth paths determine path point as control point, using B sample three times from the optimal path that algorithm generates
Curve is smoothed optimal path, generates final path.
Grid described in step 1, each grid only occupies or free two states, and the grid for occupying state indicates obstacle
The grid of object, free state indicates robot walkable region.
Include: using the method for improved adaptive GA-IAGA planning robot's optimal path described in step 3
Step 3.1, setting population scale size M, initial temperature parameter T=T0, genetic algebra counter initialization gen=
0, maximum genetic algebra Maxgen=50, temperature terminal parameter ε=0.1;
Step 3.2 generates initial population P (gen), and M new individual is generated between robot motion's starting point S to terminal G;
Step 3.3, the fitness value for calculating all individuals, individual fitness evaluation function are as follows:
In formula, n is the grid number summation that the individual passes through, and D is the corresponding path length of the individual;
Step 3.4 executes selection, intersection, variation, insertion and delete operation.
A series of generation method of new individual described in step 3.2 are as follows: with random selections, freedom, continuous or discontinuous grid
Lattice serial number connection source S to terminal G, these grid serial numbers just constitute a paths, and a paths are an individual, judge road
Whether the line of diameter coding intersects with barrier, gives up if intersecting and regenerates a new individual.
Selection, intersection, variation, insertion and the method for delete operation are executed described in step 3.4 includes:
Step 3.4.1, selection operation is executed to initial population P (gen) and obtains Ps(gen), selection operation is selected using ratio
Operator is selected, makes individual according to the probability directly proportional to fitness to next-generation population regularities;
Step 3.4.2, using single point crossing method to Ps(gen) it carries out crossover operation and obtains Pc(gen), when satisfaction is intersected
Two individuals are randomly selected when probability in population, selects the identical point of grid serial number to carry out crossover operation, works as coincidence point
When more than one, random selection one is intersected;When without coincidence point, without crossover operation;If Ps(gen) certain individual P insi
(gen) new individual after making a variation is Pci(gen), acceptance probability P is calculated according to Metroplis acceptance criteriai:
In formula (2), T (t) is Current Temperatures, and F (si) is individual Psi(gen) fitness value, F (ci)
For by Psi(gen) make a variation obtained new individual Pci(gen) fitness value;
Step 3.4.3, to the P of step 3.4.2c(gen) it carries out mutation operation and obtains Pm(gen);
Step 3.4.4, population Pm(gen) individual in executes insertion operation when there is interruption path, and interruption path is used
Free grid makes up, and becomes continuous path;
Step 3.4.5, identical together with two by the redundancy serial number in the population at individual of step 3.4.4 between two same sequence numbers
Any one in serial number is cast out together, to simplify path;
Step 3.4.6, Population Regeneration, gen=gen+1, return step 3.3 continues to evolve if gen < Maxgen, no
Then go to step 4;
Step 3.4.7, temperature termination condition judges: if Current Temperatures T (t) > ε, updates temperature by temperature renewal function
It spends parameter T (t), t ← t+1, turns to step 3.3;Otherwise algorithm terminates outgoing route, temperature renewal function are as follows:
T (t)=T0exp(-Ct1/M) (5)
T (t) indicates Current Temperatures, T in formula (5)0Indicate initial temperature, C is given constant, and t is the number of iterations, M be to
The number of inverted parameters calculates to simplify, and formula (5) are rewritten are as follows:
The value range of α is 0.7 < α < 1 in formula (6), and 1/M takes 0.5 in calculating.
Continuous path, judgment method described in step 3.4.4 are as follows: judge in individual that two is adjacent using following discriminates
Serial number Nk、Nk+1It is whether continuous:
Δ=max { abs (xk+1-xk),abs(yk+1-yk)} (3)
In formula, xk、yk、xk+1、yk+1Respectively Nk、Nk+1Corresponding rectangular co-ordinate,
If Δ=1, NkWith Nk+1Continuously, otherwise discontinuously;
When discontinuous, candidate insertion point is calculated by median method:
If the N ' being calculatedkFor free grid, then it is inserted directly into;If N 'kIt is obstacle grid, then selects one and N 'kAway from
From nearest free grid as new candidate insertion point, if can not find such candidate insertion point, i.e. declaration insertion operation is lost
It loses, casts out the individual;Otherwise N just is inserted into new candidate pointkWith Nk+1Between, above-mentioned insertion process repeats, until a
Body becomes continuously can be until pass.
Path point is determined described in step 4 from the optimal path that algorithm generates as control point, using B-spline Curve
The method for generating final path is smoothed to optimal path are as follows:
Relationship between B-spline Curve and control point are as follows:
T ∈ [0,1], P in formula (7)i、Pi+1、Pi+2、Pi+3For the control point of B-spline Curve, finally it is sequentially connected complete
3 rank B-spline curves section of portion generates final path.
The beneficial effects of the present invention are:
A kind of method for planning path for mobile robot based on improved adaptive GA-IAGA is provided, by fast simulated annealing algorithm with
Genetic algorithm combines, which not only has stronger global and local search capability, but also it is existing to overcome genetic algorithm precocity
As, local optimal searching ability is poor the deficiencies of.And path is generated to algorithm using B-spline Curve and is smoothed, can have
Improve path planning quality in effect ground.
Advantages of the present invention:
(1) present invention optimizes genetic algorithm using the stronger fast simulated annealing algorithm of local search ability, adopts
Receive and give up new explanation with Metropolis criterion, so as to avoid genetic algorithm low efficiency, convergence is relatively slow, easily sunken people is local
The disadvantages of extreme point, so that genetic algorithm and fast simulated annealing algorithm achieve the purpose that mutual supplement with each other's advantages in path planning.
(2) not only global optimizing ability is strong for improved adaptive GA-IAGA of the invention, and search speed is fast, and to complex environment
It is adaptable, it can efficiently solve the problems, such as mobile robot path planning.
(3) present invention is smoothed using the path of B-spline Curve generated to innovatory algorithm, thus by road
Diameter becomes the smooth curve that robot can actually walk, and significantly improves path quality, so that the invention is easy to apply to machine
In the practical navigation of device people.
It solves the prior art and needs a large amount of iteration to solve most for algorithm existing for mobile robot path planning
Shortest path, therefore low efficiency, convergence rate are slow, and easily fall into the technical problems such as local optimum.
Specific embodiment
Step 1, environmental modeling: being pre-processed using Grid Method to map, environmental map is divided into regular and uniform
Grid.Each grid only occupies or free two states, and the grid for occupying state indicates barrier, the grid of free state
Indicate robot walkable region.
Step 2, the beginning and end for setting robot, beginning and end position must be in free grid;
Step 3, using improved adaptive GA-IAGA planning robot's optimal path, the innovatory algorithm includes:
Step 3.1, setting population scale size M, initial temperature parameter T=T0, genetic algebra counter initialization gen=
0, maximum genetic algebra Maxgen=50, temperature terminal parameter ε=0.1.
Step 3.2 generates initial population P (gen).Between robot motion's starting point S to terminal G, with a series of random
Selection, freely, not necessarily continuous grid serial number connects S to G, these grid serial numbers just constitute a paths, a paths
For an individual.Judge whether the line of path code intersects with barrier, give up if intersecting and regenerates new individual.When
Number of individuals performs the next step when being M.
Step 3.3, the fitness value for calculating all individuals, individual fitness evaluation function are as follows:
In formula (1), n is the grid number summation that the individual passes through, and D is the corresponding path length of the individual.It can by formula (1)
Know, ideal adaptation angle value is directly proportional to path length D, and it is most short to be excellent with path to evaluate path quality, therefore is generating novel species
The low individual of fitness value can be retained when group.
Step 3.4 executes selection, intersection, variation, insertion, delete operation.
Step 3.4.1, selection operation is executed to initial population P (gen) and obtains Ps(gen).Selection operation is selected using ratio
Operator is selected, makes individual according to the probability directly proportional to fitness to next-generation population regularities.
Step 3.4.2, using single point crossing method to Ps(gen) it carries out crossover operation and obtains Pc(gen).Intersect when meeting
Two individuals are randomly selected when probability in population, the identical point of grid serial number is selected to carry out crossover operation.Work as coincidence point
When more than one, random selection one is intersected;When without coincidence point, without crossover operation.If Ps(gen) certain individual in
Psi(gen) new individual after making a variation is Pci(gen), acceptance probability P is calculated according to Metroplis acceptance criteriai:
In formula (2), T (t) is Current Temperatures, and F (si) is individual Psi(gen) fitness value, F (ci) are by Psi
(gen) make a variation obtained new individual Pci(gen) fitness value.According to acceptance probability PiDetermine whether to receive new individual Pci
(gen)。
Step 3.4.3, to the P of step 3.4.2c(gen) it carries out mutation operation and obtains Pm(gen).Work as Pc(gen) individual in
It when meeting mutation probability, is randomly selected from individual a bit, another serial number being randomly generated replaces it.
Step 3.4.4, the population P of step 3.4.3m(gen) individual in executes insertion operation when there is interruption path,
Interruption path is made up with free grid, makes continuous path.Two adjacent sequence in individual is judged using following discriminates
Number Nk、Nk+1It is whether continuous:
Δ=max { abs (xk+1-xk),abs(yk+1-yk)} (3)
In formula, xk、yk、xk+1、yk+1Respectively Nk、Nk+1Corresponding rectangular co-ordinate.If Δ=1, NkWith Nk+1Continuously,
Otherwise discontinuous.
When discontinuous, candidate insertion point is calculated by median method:
If the N ' being calculatedkFor free grid, then can be inserted directly into.If N 'kIt is obstacle grid, then selects one
With N 'kThe nearest free grid of distance is as new candidate insertion point, if can not find such candidate insertion point, i.e. declaration insertion
Operation failure casts out the individual, is otherwise just inserted into N with new candidate pointkWith Nk+1Between.Above-mentioned insertion process repeats,
Until individual become continuously can pass until.
Step 3.4.5, identical together with two by the redundancy serial number in the population at individual of step 3.4.4 between two same sequence numbers
One in serial number is cast out together, to simplify path.
Step 3.4.6, Population Regeneration, gen=gen+1.Return step 3.3 continues to evolve if gen < Maxgen, otherwise
Go to step 4.
Step 3.4.7, temperature termination condition judges.If Current Temperatures T (t) > ε, is updated by temperature renewal function
Temperature parameter T (t), t ← t+1 turn to step 3.3;Otherwise algorithm terminates outgoing route.Temperature renewal function are as follows:
T (t)=T0exp(-Ct1/M) (5)
T (t) indicates Current Temperatures, T in formula (5)0Indicate initial temperature.C is given constant, and t is the number of iterations, M be to
The number of inverted parameters.It is calculated to simplify, formula (5) is rewritten are as follows:
The value range of α is 0.7 < α < 1 in formula (6), and 1/M takes 0.5 in actually calculating.
Step 4, smooth paths.Path point is determined from the optimal path that algorithm generates as control point, using B sample three times
Curve is smoothed optimal path, to make path become the smooth curve that robot can actually walk, greatly
Improve path quality.Relationship between B spline curve and control point three times are as follows:
T ∈ [0,1], P in formula (7)i、Pi+1、Pi+2、Pi+3For the control point of B-spline Curve.It is finally sequentially connected complete
3 rank B-spline curves section of portion produces final path.
Claims (7)
1. a kind of method for planning path for mobile robot based on improved adaptive GA-IAGA, it includes:
Step 1, environmental modeling: being pre-processed using Grid Method to map, and environmental map is divided into rule and uniform grid
Lattice;
Step 2, the beginning and end for setting robot, beginning and end position is in free grid;
Step 3 uses improved adaptive GA-IAGA planning robot's optimal path;
Step 4, smooth paths determine path point as control point, using cubic B-spline song from the optimal path that algorithm generates
Line is smoothed optimal path, generates final path.
2. a kind of method for planning path for mobile robot based on improved adaptive GA-IAGA according to claim 1, feature
Be: grid described in step 1, each grid only occupies or free two states, and the grid for occupying state indicates barrier,
The grid of free state indicates robot walkable region.
3. a kind of method for planning path for mobile robot based on improved adaptive GA-IAGA according to claim 1, feature
It is: includes: using the method for improved adaptive GA-IAGA planning robot's optimal path described in step 3
Step 3.1, setting population scale size M, initial temperature parameter T=T0, genetic algebra counter initialization gen=0, most
Big genetic algebra Maxgen=50, temperature terminal parameter ε=0.1;
Step 3.2 generates initial population P (gen), and M new individual is generated between robot motion's starting point S to terminal G;
Step 3.3, the fitness value for calculating all individuals, individual fitness evaluation function are as follows:
In formula, n is the grid number summation that the individual passes through, and D is the corresponding path length of the individual;
Step 3.4 executes selection, intersection, variation, insertion and delete operation.
4. a kind of method for planning path for mobile robot based on improved adaptive GA-IAGA according to claim 3, feature
It is: the generation method of new individual described in step 3.2 are as follows: with a series of random selections, freedom, continuous or discontinuous grid sequence
Number connection source S to terminal G, these grid serial numbers just constitute a paths, and a paths are an individual, judge that path is compiled
Whether the line of code intersects with barrier, gives up if intersecting and regenerates a new individual.
5. a kind of method for planning path for mobile robot based on improved adaptive GA-IAGA according to claim 3, feature
Be: the method that selection, intersection, variation, insertion and delete operation are executed described in step 3.4 includes:
Step 3.4.1, selection operation is executed to initial population P (gen) and obtains Ps(gen), selection operation is calculated using ratio selection
Son makes individual according to the probability directly proportional to fitness to next-generation population regularities;
Step 3.4.2, using single point crossing method to Ps(gen) it carries out crossover operation and obtains Pc(gen), when meeting crossover probability
When randomly select two individuals in population, select the identical point of grid serial number to carry out crossover operation, when coincidence point is more than
At one, random selection one is intersected;When without coincidence point, without crossover operation;If Ps(gen) certain individual P insi
(gen) new individual after making a variation is Pci(gen), acceptance probability P is calculated according to Metroplis acceptance criteriai:
In formula (2), T (t) is Current Temperatures, and F (si) is individual Psi(gen) fitness value, F (ci) are by Psi(gen) it makes a variation
Obtained new individual Pci(gen) fitness value;
Step 3.4.3, to the P of step 3.4.2c(gen) it carries out mutation operation and obtains Pm(gen);
Step 3.4.4, population Pm(gen) individual in executes insertion operation when there is interruption path, interruption path free grid
Lattice make up, and become continuous path;
Step 3.4.5, by the redundancy serial number in the population at individual of step 3.4.4 between two same sequence numbers, together with two same sequence numbers
In any one cast out together, to simplify path;
Step 3.4.6, Population Regeneration, gen=gen+1, return step 3.3 continues to evolve if gen < Maxgen, otherwise goes to
Step 4;
Step 3.4.7, temperature termination condition judges: if Current Temperatures T (t) > ε, temperature ginseng is updated by temperature renewal function
Number T (t), t ← t+1 turn to step 3.3;Otherwise algorithm terminates outgoing route, temperature renewal function are as follows:
T (t)=T0exp(-Ct1/M) (5)
T (t) indicates Current Temperatures, T in formula (5)0Indicate initial temperature, C is given constant, and t is the number of iterations, and M is to join to inverting
Several numbers calculates to simplify, and formula (5) are rewritten are as follows:
The value range of α is 0.7 < α < 1 in formula (6), and 1/M takes 0.5 in calculating.
6. a kind of method for planning path for mobile robot based on improved adaptive GA-IAGA according to claim 5, feature
It is: continuous path, judgment method described in step 3.4.4 are as follows: two adjacent sequence in individual is judged using following discriminates
Number Nk、Nk+1It is whether continuous:
Δ=max { abs (xk+1-xk),abs(yk+1-yk)} (3)
In formula, xk、yk、xk+1、yk+1Respectively Nk、Nk+1Corresponding rectangular co-ordinate, if Δ=1, NkWith Nk+1Continuously, otherwise not
Continuously;
When discontinuous, candidate insertion point is calculated by median method:
If the N ' being calculatedkFor free grid, then it is inserted directly into;If N 'kIt is obstacle grid, then selects one and N 'kDistance is most
Close free grid is as new candidate insertion point, if can not find such candidate insertion point, i.e. declaration insertion operation failure, and house
Remove the individual;Otherwise N just is inserted into new candidate pointkWith Nk+1Between, above-mentioned insertion process repeats, until individual becomes
At continuously can be until pass.
7. a kind of method for planning path for mobile robot based on improved adaptive GA-IAGA according to claim 1, feature
It is: determines path point described in step 4 from the optimal path that algorithm generates as control point, using B-spline Curve pair
Optimal path is smoothed the method for generating final path are as follows:
Relationship between B-spline Curve and control point are as follows:
T ∈ [0,1], P in formula (7)i、Pi+1、Pi+2、Pi+3For the control point of B-spline Curve, it is finally sequentially connected all 3 rank B
Spline curve section generates final path.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910407620.XA CN110275526A (en) | 2019-05-16 | 2019-05-16 | A kind of method for planning path for mobile robot based on improved adaptive GA-IAGA |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910407620.XA CN110275526A (en) | 2019-05-16 | 2019-05-16 | A kind of method for planning path for mobile robot based on improved adaptive GA-IAGA |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110275526A true CN110275526A (en) | 2019-09-24 |
Family
ID=67959060
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910407620.XA Pending CN110275526A (en) | 2019-05-16 | 2019-05-16 | A kind of method for planning path for mobile robot based on improved adaptive GA-IAGA |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110275526A (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110823238A (en) * | 2019-11-05 | 2020-02-21 | 湖南大学 | Improved cubic spline interpolation curve path point fitting method |
CN111445093A (en) * | 2020-04-23 | 2020-07-24 | 长春工程学院 | Power transmission line emergency repair path optimization system and method |
CN111780759A (en) * | 2020-05-28 | 2020-10-16 | 南京邮电大学 | Mobile robot path planning method based on improved genetic algorithm |
CN111897328A (en) * | 2020-07-17 | 2020-11-06 | 武汉理工大学 | Path planning method, device and equipment based on improved artificial potential field method |
CN112327862A (en) * | 2020-11-16 | 2021-02-05 | 北京理工大学 | Path planning method for multi-robot collaborative search in uncertain environment |
CN112650248A (en) * | 2020-12-23 | 2021-04-13 | 齐鲁工业大学 | Routing inspection robot path planning method and system based on improved genetic algorithm |
CN112686429A (en) * | 2020-12-16 | 2021-04-20 | 天津城建大学 | Mobile robot and path planning method thereof based on adaptive genetic algorithm |
CN112734878A (en) * | 2020-12-31 | 2021-04-30 | 南昌工学院 | Method, equipment and storage medium for detecting connectivity between two points of large grid map |
CN112947490A (en) * | 2021-04-09 | 2021-06-11 | 京东数科海益信息科技有限公司 | Path smoothing method, device, equipment, storage medium and product |
CN113635296A (en) * | 2021-06-30 | 2021-11-12 | 苏州艾吉威机器人有限公司 | Method for tracking arbitrary curve path |
CN114323055A (en) * | 2022-03-15 | 2022-04-12 | 北京航空航天大学 | Robot weak rejection area path planning method based on improved genetic algorithm |
CN114995391A (en) * | 2022-05-10 | 2022-09-02 | 安徽工程大学 | 4-order B spline curve path planning method for improving A-star algorithm |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102136104A (en) * | 2011-03-22 | 2011-07-27 | 西安电子科技大学 | Load balance and Lin-Kernighan (LK) algorithm based vehicle route planning method |
CN102169347A (en) * | 2011-03-08 | 2011-08-31 | 浙江工业大学 | Multi-robot path planning system based on cooperative co-evolution and multi-population genetic algorithm |
CN102809718A (en) * | 2012-07-25 | 2012-12-05 | 华南理工大学 | Ultra-high-frequency partial discharge signal identification method for gas insulated switchgear (GIS) |
CN103324982A (en) * | 2013-06-07 | 2013-09-25 | 银江股份有限公司 | Path planning method based on genetic algorithm |
CN103941737A (en) * | 2014-05-09 | 2014-07-23 | 济南大学 | Motion planning and controlling method for tractor-trailer mobile robot in complex environment |
CN106843211A (en) * | 2017-02-07 | 2017-06-13 | 东华大学 | A kind of method for planning path for mobile robot based on improved adaptive GA-IAGA |
EP3213974A1 (en) * | 2016-03-03 | 2017-09-06 | Thales Deutschland GmbH | Method for controlling vehicles in case of a conflict situation and decision support system |
CN107368077A (en) * | 2017-08-15 | 2017-11-21 | 西京学院 | A kind of robot path planning method based on GACA algorithm |
-
2019
- 2019-05-16 CN CN201910407620.XA patent/CN110275526A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102169347A (en) * | 2011-03-08 | 2011-08-31 | 浙江工业大学 | Multi-robot path planning system based on cooperative co-evolution and multi-population genetic algorithm |
CN102136104A (en) * | 2011-03-22 | 2011-07-27 | 西安电子科技大学 | Load balance and Lin-Kernighan (LK) algorithm based vehicle route planning method |
CN102809718A (en) * | 2012-07-25 | 2012-12-05 | 华南理工大学 | Ultra-high-frequency partial discharge signal identification method for gas insulated switchgear (GIS) |
CN103324982A (en) * | 2013-06-07 | 2013-09-25 | 银江股份有限公司 | Path planning method based on genetic algorithm |
CN103941737A (en) * | 2014-05-09 | 2014-07-23 | 济南大学 | Motion planning and controlling method for tractor-trailer mobile robot in complex environment |
EP3213974A1 (en) * | 2016-03-03 | 2017-09-06 | Thales Deutschland GmbH | Method for controlling vehicles in case of a conflict situation and decision support system |
CN106843211A (en) * | 2017-02-07 | 2017-06-13 | 东华大学 | A kind of method for planning path for mobile robot based on improved adaptive GA-IAGA |
CN107368077A (en) * | 2017-08-15 | 2017-11-21 | 西京学院 | A kind of robot path planning method based on GACA algorithm |
Non-Patent Citations (2)
Title |
---|
张杰: ""移动机器人路径规划策略研究"", 《研究与设计》 * |
裴以建等: ""基于一种混合遗传算法的移动机器人路径规划"", 《现代电子技术》 * |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110823238A (en) * | 2019-11-05 | 2020-02-21 | 湖南大学 | Improved cubic spline interpolation curve path point fitting method |
CN111445093A (en) * | 2020-04-23 | 2020-07-24 | 长春工程学院 | Power transmission line emergency repair path optimization system and method |
CN111445093B (en) * | 2020-04-23 | 2023-04-07 | 长春工程学院 | Power transmission line emergency repair path optimization system and method |
CN111780759A (en) * | 2020-05-28 | 2020-10-16 | 南京邮电大学 | Mobile robot path planning method based on improved genetic algorithm |
CN111780759B (en) * | 2020-05-28 | 2023-11-28 | 南京邮电大学 | Mobile robot path planning method based on improved genetic algorithm |
CN111897328A (en) * | 2020-07-17 | 2020-11-06 | 武汉理工大学 | Path planning method, device and equipment based on improved artificial potential field method |
CN111897328B (en) * | 2020-07-17 | 2022-02-15 | 武汉理工大学 | Path planning method, device and equipment based on improved artificial potential field method |
CN112327862A (en) * | 2020-11-16 | 2021-02-05 | 北京理工大学 | Path planning method for multi-robot collaborative search in uncertain environment |
CN112686429A (en) * | 2020-12-16 | 2021-04-20 | 天津城建大学 | Mobile robot and path planning method thereof based on adaptive genetic algorithm |
CN112686429B (en) * | 2020-12-16 | 2022-07-29 | 天津城建大学 | Mobile robot and path planning method thereof based on adaptive genetic algorithm |
CN112650248A (en) * | 2020-12-23 | 2021-04-13 | 齐鲁工业大学 | Routing inspection robot path planning method and system based on improved genetic algorithm |
CN112734878A (en) * | 2020-12-31 | 2021-04-30 | 南昌工学院 | Method, equipment and storage medium for detecting connectivity between two points of large grid map |
CN112734878B (en) * | 2020-12-31 | 2023-06-20 | 南昌工学院 | Method, equipment and storage medium for detecting connectivity between two points of large grid map |
CN112947490A (en) * | 2021-04-09 | 2021-06-11 | 京东数科海益信息科技有限公司 | Path smoothing method, device, equipment, storage medium and product |
CN113635296A (en) * | 2021-06-30 | 2021-11-12 | 苏州艾吉威机器人有限公司 | Method for tracking arbitrary curve path |
CN114323055B (en) * | 2022-03-15 | 2022-06-07 | 北京航空航天大学 | Robot weak rejection area path planning method based on improved genetic algorithm |
CN114323055A (en) * | 2022-03-15 | 2022-04-12 | 北京航空航天大学 | Robot weak rejection area path planning method based on improved genetic algorithm |
CN114995391A (en) * | 2022-05-10 | 2022-09-02 | 安徽工程大学 | 4-order B spline curve path planning method for improving A-star algorithm |
CN114995391B (en) * | 2022-05-10 | 2024-04-09 | 安徽工程大学 | 4-order B spline curve path planning method for improving A-algorithm |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110275526A (en) | A kind of method for planning path for mobile robot based on improved adaptive GA-IAGA | |
CN106444755B (en) | Method for planning path for mobile robot based on improved adaptive GA-IAGA | |
CN111785045B (en) | Distributed traffic signal lamp combined control method based on actor-critic algorithm | |
CN112462803B (en) | Unmanned aerial vehicle path planning method based on improved NSGA-II | |
CN105527964B (en) | A kind of robot path planning method | |
CN105589461A (en) | Parking system path planning method on the basis of improved ant colony algorithm | |
CN110347151B (en) | Robot path planning method fused with Bezier optimization genetic algorithm | |
CN112489464B (en) | Crossing traffic signal lamp regulation and control method with position sensing function | |
CN109945881A (en) | A kind of method for planning path for mobile robot of ant group algorithm | |
CN110220525A (en) | A kind of paths planning method based on potential field ant group algorithm | |
CN105430706A (en) | WSN (Wireless Sensor Networks) routing optimization method based on improved PSO (particle swarm optimization) | |
CN112686429B (en) | Mobile robot and path planning method thereof based on adaptive genetic algorithm | |
CN109932903A (en) | The air-blower control Multipurpose Optimal Method of more parent optimization networks and genetic algorithm | |
CN108413963A (en) | Bar-type machine people's paths planning method based on self study ant group algorithm | |
CN111562785A (en) | Path planning method and system for collaborative coverage of cluster robots | |
CN109035767A (en) | A kind of tide lane optimization method considering Traffic Control and Guidance collaboration | |
CN109213169A (en) | The paths planning method of mobile robot | |
CN108803332A (en) | Based on the paths planning method for improving biogeography | |
CN111337931A (en) | AUV target searching method | |
CN114161416B (en) | Robot path planning method based on potential function | |
CN104679947A (en) | Automatic generation method of cable component optimizing structure of mechanical and electrical product | |
CN107490959A (en) | A kind of efficient robotic path planning system | |
CN110906936A (en) | Underwater robot path planning method | |
CN105704025B (en) | Routing optimization method based on Chaos Search and Artificial Immune Algorithm | |
Hawari et al. | Industry 4.0 with intelligent manufacturing 5G mobile robot based on genetic algorithm |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190924 |