CN108036790A - Robot path planning method and system based on mutillid algorithm under a kind of obstacle environment - Google Patents
Robot path planning method and system based on mutillid algorithm under a kind of obstacle environment Download PDFInfo
- Publication number
- CN108036790A CN108036790A CN201711256105.3A CN201711256105A CN108036790A CN 108036790 A CN108036790 A CN 108036790A CN 201711256105 A CN201711256105 A CN 201711256105A CN 108036790 A CN108036790 A CN 108036790A
- Authority
- CN
- China
- Prior art keywords
- path
- ant
- algorithm
- point
- pheromones
- 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
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Manipulator (AREA)
Abstract
The invention belongs to robotic technology field; disclose the robot path planning method and system (ABR) under a kind of obstacle environment based on mutillid algorithm; with reference to the respective advantage of ant group algorithm and ant colony algorithm; based on grid modeling environment; it is distributed using the quick optimizing preferred plan path of ant colony algorithm and the corresponding ant group algorithm pheromones that are converted into, is conducive to accelerate speed of searching optimization of the ant group algorithm to Global motion planning path;Novel confidence level scheme clicks the application of strategy in path at the same time and the involvement of pheromone update strategy is advantageously implemented parallel search between ant, improves the precision of routing problem solution to be planned.Implementation result of the present invention shows that ABR can optimizing be a kind of novel robot path planning method with Jian Ming ﹑ universalities directly perceived to the path planning of global optimum effectively in complex barrier environment.
Description
Technical field
The invention belongs to the robot road based on mutillid algorithm under robotic technology field, more particularly to a kind of obstacle environment
Footpath method and system for planning(ABR).
Background technology
Path planning is mobile robot the most key technology in practical application area, is referred in more barrier things
In environment, robot by the collisionless global optimums of a Lian Xu ﹑ of starting point to target point or sub-optimal path (ZhouZ,
NieY, MinG. EnhancedAntColonyOptimizationAlgorithmfor
GlobalPathPlanningofMobileRobots
[J] .JournalofNanchangHangkongUniversity, 2011:698-701.).Robot path planning asks
Topic has proven to haveNPComplexity difficulty combinatorial optimization problem (HuangB, KadaliR.DynamicModeling,
PredictiveControlandPerformanceMonitoring [M] .SpringerLondon, 2008.).
Currently used robot path planning's technology can be divided into two classes (room moral monarch's uniform particle group's ant colony blending algorithms
Robot path planning [J] machine design and manufactures, 2017 (7):237-240.):(1) traditional road based on mathematics theory
Footpath planing method.Such as, grid decoupling Fa ﹑ Visual Graph Fa ﹑ free space Fa ﹑ Artificial Potential Field Fa ﹑ topological approach etc..These methods with
The complexity of environment and the increase for treating excellent solution task difficulty, it is more difficult to obtain preferable effect in practical applications.(2) it is based on
The paths planning method of bionic intelligence technology.Such as, Yi Chuan Suan Fa ﹑ Mo paste Kong ﹑ Shen through Wang Luo ﹑ particle group Youization Suan Fa ﹑ bee colonies
Algorithm and simulated annealing calculation etc..These methods can be planned in realizing route optimizing under specific environment or certain real conditions.However,
The defects of being also tended in some complicated changeable application environments of dynamic there is method inherently.Such as, standard ant group algorithm face
To in complex environment problem application process, exist as, the deficiencies of convergence rate compare Man ﹑ are easily absorbed in local optimum situation.And companion
With the change of problem scale and dynamic environment, once ant is absorbed in locally optimal solution, due to local path pheromones intensity
It is dry to scratch so that ant colony is difficult to optimizing to other optimal paths.Therefore, such bionic intelligence technology is applied to mobile robot path
Planning problem stills need people and continues deeper into research.
Currently, in order to improve the search efficiency of robot path planning's technology, lot of domestic and foreign scholar carries out one after another to be based on
The robot path planning method research of bionic intelligence technology.From the point of view of current application effect, ant group algorithm is due to natural
Distributed variable-frequencypump ability, and with not using problem model as the dry path selection capability scratched, be successfully applied to
Combinatorial optimization problem in many practical applications, the successful application particularly in traveling salesman problem, preferably indicates ant colony
Algorithm, which is suitable for processing, to be hadNPThe distributed problem of complexity difficulty.Although ant group algorithm possesses preferable pheromones positive feedback
The advantages that Xing ﹑ concurrencys and robustness, but with problem context constantly strengthen or dynamic mapping under, it is to be modified to still suffer from some
Aspect:The problems such as local optimum being easily absorbed in such as search time compare Chang ﹑ Ji calculation Liang great ﹑.In this regard, many scholars have been presented for much
The improved method of positive effect.Such as, Dorigo etc. propose ACS algorithm (ACS) (DorigoM,
GambardellaM.Acooperativelearningapproachtothetravelingsalesmanproblem[J]
.IEEETransonEvolutionaryComputation, 1997,1 (1):53-66.).In ACS path plannings, only to each
The pheromones on path that preferably individual is passed by generation are updated, so as to accelerate algorithm the convergence speed.Although but problem is
The feedback of optimal information element on path is enhanced, is also easy to the stagnation behavior for causing algorithm search.Park etc. proposes a kind of base
In perception information cluster ant group algorithm realize robot paths planning method (ParkJM, SavagaonkarUR,
ChongEKP, etal.EfficientresourceallocationforQoSchannelsinMF-
TDMAsatellitesystems[C]// Milcom2000.
CenturyMilitaryCommunicationsConferenceProceedings.IEEE,2000:645-
649vol.2.).This method leaves ant colony in nest or the position of food source carries out resolving punctuate, ensure that convergence of algorithm
Property, but this method calculation amount can be sharply increased with the increase of problem scale, be easy to cause the offset control performance in path bad.
Deng Gaofeng finds optimum path problems for robot under obstacle environment, combines the excellent of particle cluster algorithm and ant group algorithm
Point, is distributed improved technology using pheromones and skill mechanism is selected in path, it is proposed that robot path planning under a kind of obstacle environment
Ant colony particle cluster algorithm (the ant colony population of robot path planning under a kind of obstacle environment of Deng Gaofeng, Zhang Xueping, Liu Yan duckweed
Algorithm [J] control theories and application, 2009,26 (8):879-883.).In addition, relative literature
(JingangCao.ResearchofAntColonyAlgorithmfor
MobileRobotPathPlanning [J] .JournalofComputer s& scommunications, 2,016 04
(2): 11-19;
SaenphonT, PhimoltaresS, LursinsapC.CombiningnewFastOppositeGradientSearch
withAntColonyOptimizationforsolvingtravellingsalesmanproblem[J]
.EngineeringApplicationsofArtificialIntelligence, 2014,35 (2):324-334;ShuangB,
ChenJ, LiZ.StudyonhybridPS-ACOalg
Orithm [J] .AppliedIntelligence, 2011,34 (1):64-73;Meng Xiangping, million space of piece, Shen Zhongyu, waits bases
In ant group algorithm [J] controls and decision-making that directional information element is coordinated, 2013 (5):782-786.) research shows, uses for reference other
The technological merit of swarm intelligence algorithm (e.g., ant colony algorithm), can in efficient balance ant group algorithm convergence rate and locally optimal solution it
Between outstanding problem, while convergence rate is effectively accelerated, improve the probability that changes to globally optimal solution of locally optimal solution, from
And mingled algorithm is set to be more easy to obtain optimal solution.
In conclusion being applied to key issue existing for mobile robot path planning process using ant group algorithm is:Face
The deficiencies of in large-scale complex path circumstances application process, local optimum is easily absorbed in there is convergence rate compare Man ﹑ situation.This
Mainly due in ant moving process, after traveling round every time, every ant will make to believe to its paths traversed
Breath element implements enhancing or attenuation operations.If it is by ant numberAN, city number isCN, ant is traveled round every time terminates renewal
The time complexity of pheromones isO(AN×CN).As it can be seen that the time of Pheromone update constantly can strengthen or move with problem context
Outlet growth trend is presented in state conversion, this extreme influence the convergence rate in global optimum path.In addition, ant colony is in pheromones
It is also easy to be absorbed in locally optimal solution under guiding, this is primarily due to during optimum path search, and ant selects neighbouring path point
Depending on the accumulated value of pheromones between path point, and the integrated intensity of pheromones comes from two factors, first, by the path
The quantity of upper ant;Second, the persistence of pheromones.This is made it easy to so that in path selection process, only with information between path point
The power of element determines that the path point of next moved further is easy to cause some ants to occur without the follow-up optional situation of point.Such machine
Deadlock situation just occurs in people's path planning, causes whole Robot Path Planning Algorithm to sink into dead state.Therefore, in order to
The convergence rate of ant group algorithm optimizing path process is improved, prevents path planning process to be absorbed in into locally optimal solution and deadlock occur
State.
Now, the application fields such as ﹑ is aerial Xia robot technology Di Mian ﹑ Shui are quickly grown, and progressively towards micromation and
More device people cooperation directions are developed.With unknown detection of the mankind to vast universe celestial body, the application of robot technology
Field will increasingly pay attention to the autonomous path navigation of dyskinesia under mountain area jungle rugged topography and complex environment.Meanwhile
In order to meet the fast-developing needs of robot technology, the crucial stroke technology of its path planning will be towards based on bionic intelligence technology
Colony intelligence optimization direction go deep into, it is robot automtion that can find a good path and efficiently perform this paths
Important embodiment, be based particularly on bionic intelligence technology and combine other this method (e.g., ant group optimization joint proposed by the present invention
Bee colony system optimization) it would is that weight in the emphasis and difficult point, and artificial intelligence field that robot automtion will be furtherd investigate from now on
One of hot issue of point research.
The content of the invention
In view of the problems of the existing technology, the present invention provides the robot based on mutillid algorithm under a kind of obstacle environment
Paths planning method and system.The present invention devises the optimization method that ant colony algorithm is applied to robot path planning first, borrows
The characteristics of mirror ant colony algorithm optimizing, honeycomb and nectar source are respectively seen as to the beginning and end of robot path planning's process, passed through
Working closely between different bee colonies eventually finds global optimum's path planning, and correspondence is converted into pheromones in grid environment
Enhancement value, provide priori for effective search of ant group algorithm, weaken the blindness at ant group algorithm search initial stage.
Secondly, the present invention devises a kind of novel trust evaluation scheme to be selected for selecting path point, while on ant road
Confidence level parameter has been incorporated in the point selection strategy of footpath.Routing strategy ant city selection strategy different from the past, its is new
Clever part is not only to evaluate the pheromones intensity level to be selected for selecting path point and distance factor, while have also contemplated that and treat selected element
Confidence level factor, is conducive to strengthen identification and analysis ability of the ant to obstacle under obstacle environment.
Another important technology point of the present invention is novel pheromone update strategy.It is different from conventional ant colony Pheromone update plan
Slightly, designed novel pheromone update strategy does not carry out Pheromone update to the local path that all ants represent, but
The local optimum path represented for optimal antp l The global optimum path represented with global optimum antp g Pheromones carry out more
Newly, that is, be conducive to strengthen the positive feedback effect of pheromones during path planning, and global optimum path can be accelerated from numerous offices
Showing one's talent in portion's optimal path.
Under obstacle environment of the present invention in the robot path planning method based on mutillid algorithm:Ant colony algorithm and ant group algorithm
Fusion thought, an optimum programming path is preferentially found by ant colony algorithm, and corresponded to and be converted into information in grid environment
The distribution of element, so as to provide priori for the optimum path search process of ant group algorithm.
Confidence level numerical procedure in the routing strategy of the present invention, the numerical procedure have taken into full account routing to be selected
The accumulative effect of footpath point adjacent domain pheromones.Then contribute to optimal to wait to select based on the routing strategy constructed by the program
Path point is preferentially won.
The novel pheromone update strategy of the present invention, the local optimum path represented to optimal ant and global optimum ant
The pheromones in the global optimum path of representative are updated, and have abandoned all ant paths are updated in conventional pheromones
Thought, shortens the Pheromone update time, accelerates the search speed in global optimum path.
The present invention is achieved in that a kind of robot path planning method under obstacle environment based on mutillid algorithm and is
Unite, the robot path planning method based on mutillid algorithm includes under the obstacle environment:
Honeycomb and nectar source are respectively seen as to the beginning and end of robot path planning's process, looked for by the cooperation between different bee colonies
To global optimum's path planning, and the enhancement value for being converted into pheromones in grid environment is corresponded to, carried for ant group algorithm search
For priori;
The pheromones intensity level to be selected for selecting path point and distance factor are evaluated, while the confidence level factor of selected element is treated in analysis, into
Identification and analysis of the row ant to obstacle under obstacle environment;
The local optimum path represented to optimal antp l The global optimum path represented with global optimum antp g Pheromones into
Row renewal, the positive feedback to pheromones in the planning process of path scan for.
Further, the robot path planning method based on mutillid algorithm specifically includes under the obstacle environment:
Step 1, parameter initialization, sets the parameter of ant colony algorithm;
Including population scaleSN, population maximum evolutionary generationMEN, the convergence of control algolithm, which changes, reaches numberlimit;Ant colony is set
The parameter of algorithm:Including ant quantityN a , Pheromone Dauerρ, path weight valuec 1Withc 2, weight coefficientα﹑βWithγ;
Step 2, the distribution of initialization context information;
Environment setting is carried out using Grid Method, initializes the pheromones on each grid point;
Step 3, a global optimum path is obtained using bee colony robot path planning method, and is converted into letter to the path
Cease the enhancement value of element, ant colony is then placed in starting pointS;
Step 4, performs the movement of ant colony path;
Each ant selects next path point according to path point selection strategy.If current grid is on its adjacent path point
Pheromones are 0, then ant continues to select other adjacent path points on current grid, will if periphery may be selected without path point
Current grid is set to obstacle grid, and returns to the path point of a search;
Step 5, repeat step four, until whole ant colony is all reached home;
Step 6, according to pheromone update strategy, the pheromones on each paths are updated by formula (9) and (10);
Step 7, if whole ant colony all converges to a paths or cycle-index reaches maximum, circulation terminates, entirely
Global optimum's path search process terminates, and exports global optimum road;Otherwise four are gone to step.
Further, individual fitness evaluation function is as follows in the ant colony algorithm:
In the system built using ant colony algorithm, each honeybee individual represents a path from initial point to terminating point,Represent a honeybee individual, wherein,DRepresent the dimension size of individual, individual every one-dimensional representation
One grid sequence number, and last 1 dimension of the 1st peacekeeping of individual represents the grid sequence number of initial point and terminating point respectively;By in individual
Every 1 dimension connects to form a path by origin-to-destination, and x=(1,2,5,9,10,20,21,27,40,45,60,78,
89,90,93,96,100) paths from 1 to 100 are represented, centre undergoes 2,5,9,10,20,21,27,40,45,60,78,
89,90,93,96 grid sequence numbers;Evaluation individualx i Quality in, be defined as follows individual fitness evaluation function;
Further, the bee colony robot global path planning algorithm comprises the following steps that:
1) environment setting is carried out using Grid Method, thus obtains the two-dimensional array of an expression environmental informationENV[][];
2)Parameter setting, population scale areSN, lead bee and observe the half that bee is population quantity, initial solution quantityFN=SN/
2, population maximum evolutionary generationMEN, the convergence of control algolithm, which changes, reaches numberlimit;
3)Random generation as followsSNIt is aDTie up feasible solution;
Wherein,ub j Withlb j It is respectivelyx ij The bound of value;
4)The adaptive value in each nectar source is calculated as follows;
Wherein,f i (x i ) be problem to be solved target function value;
5)Set cycle counterCount=1;Including:
a) bee is led in nectar sourcex i Adjacent domain searches for new nectar source, produces new solution according to the following formula, calculate adaptive value;
Wherein,kFor random generation, the random number between [- 1,1];
b) rightx i WithMake comparisons, lead bee using Greedy strategy selection nectar source;
c) observation bee calculate according to the following formula selection Mi Yuanx i ProbabilityP i ;
d) bee is observed according to probabilityP i Select nectar sourcex i , and new nectar source is produced near nectar source according to formula (4), calculate
New nectar sourceAdaptive value;
e) bee is observed according to Greedy strategy selection nectar source;
f) if there is the nectar source that need to be abandoned, a new Mi Yuan is randomly generated according to formula (2) at this time and substitutes it;
g) record this repeatedly reach interior optimal value, juxtapositionCount=Count+1;UntilMEN=Count;
h) output optimal solution.
Further, the mutillid algorithm is:
(1) expression of pheromones and path point power:
To each gridjIts corresponding confidence level of computation grid, concrete mode are:With gridjFor left upper apex, extract out byj
Neighbouring three raster combineds template;Each grid corresponds to a coefficient, and, by formula
(6) calculatejPheromones intensity in template,ForjConfidence value;
Wherein,It is correspondingtWhen inscribe path pointjWithkBetween pheromones value;
(2) path point selection strategy:
Exist according to transition probability by " roulette wheel method " selection path point, every anttMoment is moved to phase by some path point as the following formula
The probability of adjacent path point is:
Wherein,RepresenttMoment is by path pointiTo path pointjUpper remaining information content;D ij For path pointiWithjBetween
Euclidean distance;Path point is selected to be to be selectedjConfidence value;For the relative importance of pheromones,For two grids
(iWithj) between range information relative importance,For path pointjConfidence value;Three parameter amountsMeet
Relationship below:
(3)Pheromone update strategy:
More new strategy is stated shown in formula as follows:
Wherein,It is a constant between 0 and 1, represents the persistence of pheromones material;AndRepresent pheromones thing
The disappearance degree of matter;L c WithL w Local optimum path is represented respectivelyp l With global optimum pathp g Path length,QFor a constant;c 1Withc 2Local optimum path is represented respectivelyp l With global optimum pathp g Weight in Pheromone update, and meetc 1+c 2=1
(1>c 1, c 2>0).
Another object of the present invention is to provide the robot path planning system based on mutillid algorithm under a kind of obstacle environment
System.
Advantages of the present invention and good effect are:It is respective that the method for the present invention takes full advantage of ant colony algorithm and ant group algorithm etc.
Advantage, by having complementary advantages, overcomes respective shortcoming to find global optimum's path planning.Its advantage can be described as:By bee
Global optimum's path correspondence that group's algorithmic rule obtains is converted into the enhancement value of pheromones between path point, avoids conventional ant colony and calculates
Blindness when method progress optimum path search is initial, reduces the popularity of ant group algorithm search space.Secondly, with conventional ant city
Unlike city's selection strategy, confidence level is introduced in path point selection strategy, not only allows for the intensity of pheromones between waypoint
And distance factor, and the ant information content for treating selection path point adjacent domain is taken into full account, compared to ant group algorithm, energy
Enough successful cognitive disorders are simultaneously transferred to the selection of other path points.After ant is traveled round, pheromone update strategy is not
The local path represented to all ants is updated, but for the local optimum path that optimal ant representsp l With the overall situation most
The global optimum path that excellent ant representsp g Pheromones be updated, that is, be conducive to the positive feedback of pheromones, and can accelerate
Search speed of the algorithm to global optimum path.It is clear to by the effect of case study on implementation, is built by ant group algorithm and ant colony algorithm
Ant ColonySystem optimizes obtained global optimum path and is better than single path planning algorithm from time efficiency (in environment 1 and 2
In, 24.38% and 28.93%) is respectively increased compared to BCR, better than bee colony path planning algorithm (in environment 1 from the precision of solution
In 2,1.8% and 7.5%) has been respectively increased compared to APR, has been a kind of novel have the characteristics that Jian Ming ﹑ universalities solution directly perceived is excellent
The new method of change problem.
Brief description of the drawings
Fig. 1 is the robot path planning method flow chart based on mutillid algorithm under the obstacle environment that present invention implementation provides.
Fig. 2 is the robot path planning method and system based on mutillid algorithm under obstacle environment.
Fig. 3 is the distribution map for the pheromones that the present invention implements offer.
Fig. 4 is the template distribution map that the present invention implements to provide.
Fig. 5 is present invention implementation offer based on the simulation result figure between environment once distinct methods.
In figure:(a), more obstacle grid environment under 20 × 20 environment;(b), the global optimum that once searches of BCR environment
Path planning;(c)Global optimum's path planning that APR environment once searches;(d), ABR environment once search it is global most
Excellent path planning.
Fig. 6 is present invention implementation offer based on the simulation result figure between two times distinct methods of environment.
In figure:(a), more obstacle grid environment under 30 × 30 environment;(b), the global optimum that once searches of BCR environment
Path planning;(c)Global optimum's path planning that APR environment once searches;(d), ABR environment once search it is global most
Excellent path planning.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to embodiments, the present invention is carried out
It is further described.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not used to limit
The present invention.
The present invention devises a kind of novel routing strategy, the confidence level of path point has been incorporated in the strategy, on road
During the point selection of footpath, it is comprehensive examine it is to be selected select path point away from breath element ﹑ confidence levels etc. are believed from ﹑, preferentially selecting road
While the point of footpath, and it is avoided that optimizing is absorbed in locally optimal solution.Meanwhile before ant group algorithm optimizing, it is excellent using bee colony system
To change obtained path planning can strengthen the convergence efficiency of ant group algorithm, and the pheromone update strategy proposed only travels round ant
The element enhancing operation of optimal path execution information.Case study on implementation the result shows that:Compared with other correlation techniques, present invention design carries
Robot path planning method and system based on mutillid algorithm under the obstacle environment gone out, while ensureing to solve quality, more
Be conducive to the convergence rate of quickening system optimizing, in same time planning scale, be more advantageous to showing one's talent for optimal path.
The application principle of the present invention is further described below in conjunction with the accompanying drawings.
As shown in Figure 1, the present invention provides the robot path planning method bag based on mutillid algorithm under a kind of obstacle environment
Include following steps:
S101, parameter initialization, sets the parameter of ant colony algorithm;
Including population scale SN, population maximum evolutionary generationMEN, the convergence of control algolithm, which changes, reaches numberlimit;Ant colony is set
The parameter of algorithm:Including ant quantityN a , Pheromone Dauerρ, path weight valuec 1Withc 2, weight coefficientα﹑βWithγ。
S102, the distribution of initialization context information;
Environment setting is carried out using Grid Method, initializes the pheromones on each grid point.
S103, a global optimum path is obtained using bee colony robot path planning method, and the path is converted into
The enhancement value of pheromones, ant colony is then placed in starting pointS;
S104, performs ant colony path movement scheme;
Each ant selects next path point according to path point selection strategy.If current grid is on its adjacent path point
Pheromones are 0, then ant continues to select other adjacent path points on current grid, will if periphery may be selected without path point
Current grid is set to obstacle grid, and returns to the path point of a search.
S105, repeat step S104, until whole ant colony all reaches terminal;
S106, according to pheromone update strategy, the pheromones on each paths are updated by formula (9) and (10);
S107, if whole ant colony all converges to a paths or cycle-index reaches maximum, circulation terminates, whole complete
Office's optimum route search process terminates, and exports global optimum road;Otherwise S104 is gone to step.
Fig. 3 is the distribution map for the pheromones that the present invention implements offer.
With reference to concrete analysis, the invention will be further described.
Individual fitness evaluation function is as follows in ant colony algorithm provided by the invention:
1st, using in the system of ant colony algorithm structure, each honeybee individual represents a path from initial point to terminating point,Represent a honeybee individual, wherein,DRepresent the dimension size of individual, individual every one-dimensional representation
One grid sequence number, and the 1st dimension of individualWith last 1 dimensionThe grid sequence number of initial point and terminating point is represented respectively;Will be a
Every 1 dimension connects to form a path by origin-to-destination in body, and x=(1,2,5,9,10,20,21,27,40,45,60,
78,89,90,93,96,100) paths from 1 to 100 are represented, centre undergoes 2,5,9,10,20,21,27,40,45,60,
78,89,90,93,96 grid sequence numbers;Evaluation individualx i Quality in, be defined as follows individual fitness evaluation function:
。
2nd, bee colony robot global path planning algorithm provided by the invention comprises the following steps that:
Step2.1 carries out environment setting using Grid Method, thus obtains the two-dimensional array of an expression environmental informationENV[][].
Step2.2 parameter settings, population scale areSN, lead bee and observe the half that bee is population quantity, i.e., initial skill
AmountFN=SN/ 2 population maximum evolutionary generationsMEN,The convergence of control algolithm repeatedly reaches numberlimit。
Step2.3 is generated at random as followsSNIt is aDTie up feasible solution
Wherein,ub j Withlb j It is respectivelyx ij The bound of value.
Step2.4 calculates the adaptive value in each nectar source as follows
.
Wherein,f i (x i ) be problem to be solved target function value.
Step2.5 sets cycle counterCount=1;
Repeat
Step2.5.1 leads bee in nectar sourceAdjacent domain searches for new nectar source, produces new solution according to the following formula, calculate suitable
Should value
Wherein,kGenerated to be random,Random number between [- 1,1].
Step2.5.2 pairsWithMake comparisons, lead bee using Greedy strategy selection nectar source (retaining preferable solution).
Step2.5.3 observation bees calculate selection Mi Yuan according to the following formulax i ProbabilityP i
Step2.5.4 observes bee according to probabilityP i Select nectar sourcex i , and new nectar source is produced near nectar source according to formula (4), calculate new nectar sourceAdaptive value.
Step2.5.5 observes bee and selects nectar source according to Greedy strategy.
If there is the nectar source that need to be abandoned, (i.e. nectar source exists Step2.5.6 according to formula (4)limitNothing changes in number
Become), a new Mi Yuan is randomly generated according to formula (2) at this time and substitutes it.
Step2.5.7 records this and repeatedly reaches interior optimal value, juxtapositionCount=Count+1.
until MEN=Count
Step2.6 exports optimal solution.
3rd, with reference to mutillid algorithm, the invention will be further described.
The mutillid algorithm is:
Mutillid algorithm is a kind of mingled algorithm for having used for reference the respective advantage of ant group algorithm and ant colony algorithm.Ant colony algorithm finds food
The process of material resource is exactly to find the process of food source to be optimized, and cooperating with each other between different role honeybee promotes bee colony can be with quickly
Speed convergence is in globally optimal solution.However, in more obstacle complex environments, barrier may not necessarily be effectively avoided.Thus, obtain
Global path may not necessarily effective guidance machine people mobile route planning process.And ant colony passes through the accumulation to pheromones in path
Analysis, can not only obtain global optimum path, and have certain identification and analysis ability to barrier, this master benefits from ant
City routing strategy.But it is that the accumulated time of pheromones is long in place of the weak tendency of ant group algorithm, so as to can cause complete
The search speed of office's optimal path is excessively slow, and as the increase of problem scale, efficiency can be seriously low, is unfavorable for being applied to city
Large-scale complex type problem.
(1) expression of pheromones and path point power
For a given gridi, its pheromones, which is distributed, to be present in its adjacent eight raster path, and each grid assumes
It is the square grid of the length of side 1;As shown in Figure 3;
GridiGrid (1 ~ 8) adjacent thereto has pheromones distribution, its pheromonesv ij (j=1,2 ..., 8) distribution power
Depending on the pheromones accumulative effect of ant colony on the path, here, sequence number 1 ~ 8 also illustrates that the moving direction of robot.Path
Pointi(i.e. gridi)In the planning process for selecting its adjacent path point, each is to be selected to select path pointj(j=1,2 ..., 8)
Neighbor information element distribution to be selected selects path point to thisjSelection have important influence.Obviously, if neighbor information element distribution compared with
By force, then there is more information interchange in path point adjacent region to be selected of selecting, and the pheromones that the ant in the region leaves are strong
Spend it is larger, this is to be selected select path point be selected as next step mobile route point possibility it is larger.Therefore, it is right in the present invention
Each gridjIts confidence value is calculated, concrete mode is:With gridjFor left upper apex, extract out byjNeighbouring three grids
The template of combination, as shown in Figure 3.Here, each grid corresponds to a coefficient, and, by formula
(6) calculatejPheromones intensity in template, isjConfidence value.
Wherein,It is correspondingtWhen inscribe path pointjWithkBetween pheromones value.
(2) path point selection strategy
In the moving process that ant often walks, the path point of every moved further is only selected from its adjacent cells.Therefore, each grid
Lattice have equal chance to be selected the position as moved further under ant, here, according to transition probability by " roulette wheel method " selection path
Point, every ant existtMoment is as the following formula by some path point (gridi) the adjacent path point (grid of movementj) probability be:
Wherein,RepresenttMoment is by path pointiTo path pointjUpper remaining information content;D ij For path pointiWithjBetween
Euclidean distance;Path point is selected to be to be selectedjConfidence value.For the relative importance of pheromones,For two grids
(iWithj) between range information relative importance,For path pointjConfidence value.Three parameter amountsMeet
Relationship below:
Unlike the routing strategy of standard ant algorithm, formula (6) between adjacent path point is analyzed pheromones and away from
From while, also considered path pointjConfidence value.This is because in ant path selection process, some paths
The adjacent zone routing point of point is likely to deposit pheromones even 0 phenomenon on the weak side.
(3) pheromone update strategy
Ant colony, into terminal moving process, selects every from starting point according to the pheromones power on path and the confidence value of neighbor point
The path point of secondary movement.In the present invention, after ant colony is completed once to travel round, pheromone update strategy does not represent all ants
Local path be updated, but in time for optimal ant represent local optimum pathp l With global optimum's ant representative
Global optimum pathp g Pheromones are updated, that is, are conducive to the positive feedback effect of enhancement information element, and can accelerate algorithm pair
The search speed in global optimum path.Here, more new strategy is stated shown in formula as follows:
Wherein,It is a constant between 0 and 1, represents the persistence of pheromones material;And 1-Represent pheromones
The disappearance degree of material;L c WithL w Local optimum path is represented respectivelyp l With global optimum pathp g Path length,QIt is normal for one
Number;Local optimum path is represented respectivelyp l With global optimum pathp g Weight in Pheromone update, and meetc 1+c 2=1(1>c 1, c 2>0)。
4th, with reference to specific embodiment, the invention will be further described.
Embodiment:
Robot path planning method and system under a kind of obstacle environment proposed by the present invention based on mutillid algorithm are referred to as
ABR, in order to effectively describe high efficiency of the present invention during robot path planning, has used 20 × 20 respectively in implementation
With more obstacle grid environment under 30 × 30 two kinds of environment.In addition, be the validity of the preferably simulation result of contrast ABR, this
In invention respectively with bee colony robot path planning method (abbreviation BCR) and a kind of ant colony particle cluster algorithm machine path planning side
Method (the ant colony particle cluster algorithm control theory of robot path planning and application under a kind of obstacle environment of the such as Deng, 2009,26
(8):879-883. this method is referred to as APR) etc. be respectively compared.
Parameter in implementation process of the present invention is respectively:(1) parameter setting of ABR methods, (1.1) ant colony algorithm
Parameter setting, bee colony scaleSN=40, population maximum evolutionary generationMEN=2000,The convergence of control algolithm repeatedly reaches numberlimit=20;(1.2) parameter of ant group algorithm:Ant quantityN a =30, Pheromone Dauer=0.1, path weight valuec 2=c 1=
0.5, constantQ=50, weight coefficient=0.4 ﹑=0.3 He=0.3.(2) parameter setting of APR methods, (2.1) ant quantityN a =30, Pheromone Dauer=0.1, path weight valuec 1=c 2=0.5, weight coefficient=1 ﹑=2, constantQ=100;(2.2) grain
Swarm optimization parameter setting, number of particles 30, maximum iteration 50,c 2=c 1=2, initial inertia weightwBy 0.9 with
Repeatedly up to number linear decrease to 0.4, maximal rateV max =10.
Environment simulation result once as shown in figure 5, three kinds of methods such as ABR ﹑ BCR ﹑ APR environment once search it is global most
Excellent path planning.
It was found from the path planning analysis described in Fig. 5:The path of BCR methods planning experienced 27 roads from starting point altogether
Footpath point is reached home, and in moving process, the path point walked along direction 1 has 11, and the path point walked along direction 2 or 8 has
16, path total length is;The path that APR methods obtain experienced 25 roads by starting point
Footpath point is reached home, and in moving process, the path point walked along direction 1 has 13, and the path point walked along direction 2 or 8 has 12
A, optimal path length at this time is=30.38;And the path of ABR methods planning is undergone altogether from starting point
24 path points are reached home, and in moving process, the path point walked along direction 1 has 14, walks along direction 2 or 8
Path point has 10, and path total length is=29.80.It can be seen from the above that planned by the method for the present invention ABR
To the path point that is undergone in robot moving process of global optimum path will be few than BCR and APR, and the path length undergone
Degree is also relatively smaller.
Simulation result under environment two is as shown in Figure 6;
Fig. 6 (a) is increasingly complex relative to Fig. 5 (a) obstacle environment, and obstacle distribution is more and need to be carried out by starting point to the end more
The selection course of path point.Optimum programming path analysis described in Fig. 6 is understood:The path of BCR methods planning is total to from starting point
It experienced 46 path points to reach home, in moving process, the path point walked along direction 1 has 12, along 2 or 8 row of direction
The path point walked has 34, and path total length is=50.97;The path that APR methods obtain is passed through by starting point
Go through 39 path points to reach home, in moving process, the path point walked along direction 1 there are 19, walks along direction 2 or 8
Path point has 20, and optimal path length at this time is=46.87;And ABR methods planning path from
Starting point experienced 33 path points and reach home, and in moving process, the path point walked along direction 1 has 25, along direction 2
Or 8 walking path point have 8, path total length is=43.36.It can be seen from the above that in barrier barrier environment more
In complicated situation, road that the global optimum path planned by the method for the present invention ABR is undergone in robot moving process
Footpath point can be considerably less than BCR and APR, and the path length undergone is also considerably less than other two methods.
The experimental data obtained under two kinds of environment of summary, introduces performance and compares time data factor, investigate the present invention
Searching efficiency between method and other two kinds of comparative approach, as shown in table 1.
The experimental data obtained under two kinds of environment of summary, introduces performance and compares time data factor, investigate the present invention
Searching efficiency between method and other two kinds of comparative approach, as shown in table 1.
By in above-mentioned table 1 as it can be seen that average operating time of the method for the present invention on optimum programming path is solved is superior to other two
Kind comparative approach.And be stepped up with problem context complexity, the method for the present invention will be less than global optimum's path planning
Two kinds of comparative approach of APR and BCR.
Robot path planning method and system under a kind of obstacle environment that the present invention describes based on mutillid algorithm can
With the change of environment, there is the ability for planning global optimum path in real time.The method of the present invention is by two kinds of algorithms (ant group algorithm and bees
Group's algorithm) merged, respective advantage is used for reference, while the they affect of respective algorithm is also reduced, constructed mutillid machine
People's paths planning method not only in time better than single two kinds by comparative approach, and be also better than from solution efficiency by than
Compared with two methods, be a kind of robot global path planning new method of two kinds of algorithms of novel synthesis, reached the time with
Two-win effect in path optimization's performance.The effect of implementation shows that in theory, the method for the present invention can also further improve depth
Enter to be applied to other fields, e.g., the excellent Wen Ti ﹑ city logistics optimum path search Wen Ti ﹑ wireless sensers of urban traffic network path Xun
The actual optimization problem such as network path optimizing.These problems can be converted into the similar problem of robot path optimizing, be adapted to
Solved in method proposed by the present invention.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
All any modification, equivalent and improvement made within refreshing and principle etc., should all be included in the protection scope of the present invention.
Claims (6)
- A kind of 1. robot path planning method based on mutillid algorithm under obstacle environment, it is characterised in that the obstacle environment Under the robot path planning method based on mutillid algorithm include:Honeycomb and nectar source are respectively seen as to the beginning and end of robot path planning's process, looked for by the cooperation between different bee colonies To global optimum's path planning, and the enhancement value for being converted into pheromones in grid environment is corresponded to, carried for ant group algorithm search For priori;The pheromones intensity level to be selected for selecting path point and distance factor are evaluated, while the confidence level factor of selected element is treated in analysis, into Identification and analysis of the row ant to obstacle under obstacle environment;The local optimum path represented to optimal antp l The global optimum path represented with global optimum antp g Pheromones carry out Renewal, the positive feedback to pheromones in the planning process of path scan for.
- 2. the robot path planning method based on mutillid algorithm under obstacle environment as claimed in claim 1, it is characterised in that The robot path planning method based on mutillid algorithm specifically includes under the obstacle environment:Step 1, parameter initialization, sets the parameter of ant colony algorithm;Including population scaleSN, population maximum evolutionary generationMEN, the convergence of control algolithm, which changes, reaches numberlimit;Ant colony is set The parameter of algorithm:Including ant quantityN a , Pheromone Dauerρ, path weight valuec 1Withc 2, weight coefficientα﹑βWithγ;Step 2, the distribution of initialization context information;Environment setting is carried out using Grid Method, initializes the pheromones on each grid point;Step 3, a global optimum path is obtained using bee colony robot path planning method, and is converted into letter to the path Cease the enhancement value of element, ant colony is then placed in starting point S;Step 4, performs the movement of ant colony path;Each ant selects next path point according to path point selection strategy;If the pheromones on current grid to its adjacent path point are 0, ant continues to select other adjacent on current grid Path point, if periphery may be selected without path point, obstacle grid is set to by current grid, and returns to the path of a search Point;Step 5, repeat step four, until whole ant colony is all reached home;Step 6, according to pheromone update strategy, the pheromones on each paths are updated by formula (9) and (10);Step 7, if whole ant colony all converges to a paths or cycle-index reaches maximum, circulation terminates, entirely Global optimum's path search process terminates, output global optimum path;Otherwise four are gone to step.
- 3. the robot path planning method based on mutillid algorithm under obstacle environment as claimed in claim 2, it is characterised in that Individual fitness evaluation function is as follows in the ant colony algorithm:In the system built using ant colony algorithm, each honeybee individual represents a path from initial point to terminating point,Represent a honeybee individual, wherein,DRepresent the dimension size of individual, individual every one-dimensional representation One grid sequence number, and the 1st dimension of individualWith last 1 dimensionThe grid sequence number of initial point and terminating point is represented respectively;Will be a Every 1 dimension connects to form a path by origin-to-destination in body, and x=(1,2,5,9,10,20,21,27,40,45,60, 78,89,90,93,96,100) paths from 1 to 100 are represented, centre undergoes 2,5,9,10,20,21,27,40,45,60, 78,89,90,93,96 grid sequence numbers;Evaluation individualx i Quality in, be defined as follows individual fitness evaluation function;。
- 4. the robot path planning method based on mutillid algorithm under obstacle environment as claimed in claim 2, it is characterised in that The bee colony robot global path planning algorithm comprises the following steps that:1)Environment setting is carried out using Grid Method, thus obtains the two-dimensional array ENV [] [] of an expression environmental information;2)Parameter setting, population scale areSN, lead bee and observe the half that bee is population quantity, initial solution quantityFN=SN/ 2, population maximum evolutionary generationMEN, the convergence of control algolithm, which changes, reaches numberlimit;3)Random generation as followsSNIt is aDTie up feasible solution;Wherein,ub j Withlb j It is respectivelyx ij The bound of value;4 )The adaptive value in each nectar source is calculated as follows;Wherein,f i (x i ) be problem to be solved target function value;5)Set cycle counterCount=1;Including:a) bee is led in nectar sourcex i Adjacent domain searches for new nectar source, produces new solution according to the following formula, calculate adaptive value;Wherein,kGenerated to be random,Random number between [- 1,1];b) rightx i WithMake comparisons, lead bee using Greedy strategy selection nectar source;c) observation bee calculate according to the following formula selection Mi Yuanx i ProbabilityP i ;d) bee is observed according to probabilityP i Select nectar sourcex i , and new nectar source is produced near nectar source according to formula (4), calculate new Nectar sourceAdaptive value;e) bee is observed according to Greedy strategy selection nectar source;f) if there is the nectar source that need to be abandoned, a new Mi Yuan is randomly generated according to formula (2) at this time and substitutes it;g) record this repeatedly reach interior optimal value, juxtapositionCount=Count+1;UntilMENIt is equal toCount;h) output optimal solution.
- 5. the robot path planning method based on mutillid algorithm under obstacle environment as claimed in claim 2, it is characterised in that The mutillid algorithm is:(1)The expression of pheromones and path point power:To each gridjThe confidence value of computation grid, concrete mode are:With gridjFor left upper apex, extract out byjNeighbour The template of nearly three raster combineds;Each grid corresponds to a coefficient, wherein,k=1,2,3, and, by formula (6) CalculatejPheromones intensity in template, isjConfidence value;Wherein,It is correspondingtWhen inscribe path pointjWithkBetween pheromones value;(2)Path point selection strategy:Exist according to transition probability by " roulette wheel method " selection path point, every anttMoment is moved adjacent by some path point as the following formula The probability of path point is:Wherein,RepresenttMoment is by path pointiTo path pointjUpper remaining information content;D ij For path pointiWithjBetween Euclidean distance;Path point is selected to be to be selectedjConfidence value;For the relative importance of pheromones,For two grids (i Withj) between range information relative importance,For path pointjConfidence value;Three parameter amountsMeet with Lower relational expression:(3)Pheromone update strategy:More new strategy is stated shown in formula as follows:Wherein,It is a constant between 0 and 1, represents the persistence of pheromones material;AndRepresent pheromones thing The disappearance degree of matter;L c WithL w Local optimum path is represented respectivelyp l With global optimum pathp g Path length,QFor a constant; Local optimum path is represented respectivelyp l With global optimum pathp g Weight in Pheromone update, and meetc 1+c 2=1, wherein, 1>c 1, c 2>0。
- A kind of 6. robot path planning's system based on mutillid algorithm under obstacle environment as claimed in claim 1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711256105.3A CN108036790B (en) | 2017-12-03 | 2017-12-03 | Robot path planning method and system based on ant-bee algorithm in obstacle environment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711256105.3A CN108036790B (en) | 2017-12-03 | 2017-12-03 | Robot path planning method and system based on ant-bee algorithm in obstacle environment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108036790A true CN108036790A (en) | 2018-05-15 |
CN108036790B CN108036790B (en) | 2020-06-02 |
Family
ID=62095517
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711256105.3A Active CN108036790B (en) | 2017-12-03 | 2017-12-03 | Robot path planning method and system based on ant-bee algorithm in obstacle environment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108036790B (en) |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108958238A (en) * | 2018-06-01 | 2018-12-07 | 哈尔滨理工大学 | A kind of robot area Dian Dao paths planning method based on covariant cost function |
CN109002923A (en) * | 2018-07-23 | 2018-12-14 | 宁波大学 | A kind of intercity multimode travel route planing method |
CN109164810A (en) * | 2018-09-28 | 2019-01-08 | 昆明理工大学 | It is a kind of based on the adaptive dynamic path planning method of ant colony-clustering algorithm robot |
CN109213157A (en) * | 2018-08-28 | 2019-01-15 | 北京秦圣机器人科技有限公司 | Data center's crusing robot paths planning method based on improved Ant Colony System |
CN109282815A (en) * | 2018-09-13 | 2019-01-29 | 天津西青区瑞博生物科技有限公司 | Method for planning path for mobile robot based on ant group algorithm under a kind of dynamic environment |
CN109506655A (en) * | 2018-10-19 | 2019-03-22 | 哈尔滨工业大学(威海) | Improvement ant colony path planning algorithm based on non-homogeneous modeling |
CN109855640A (en) * | 2019-01-29 | 2019-06-07 | 北京航空航天大学 | A kind of paths planning method based on free space and artificial bee colony algorithm |
CN109945881A (en) * | 2019-03-01 | 2019-06-28 | 北京航空航天大学 | A kind of method for planning path for mobile robot of ant group algorithm |
CN109977455A (en) * | 2019-01-30 | 2019-07-05 | 广东工业大学 | It is a kind of suitable for the ant group optimization path construction method with terrain obstruction three-dimensional space |
CN110702121A (en) * | 2019-11-23 | 2020-01-17 | 赣南师范大学 | Optimal path fuzzy planning method for hillside orchard machine |
CN110990769A (en) * | 2019-11-26 | 2020-04-10 | 厦门大学 | Posture migration algorithm framework suitable for multi-degree-of-freedom robot |
CN112461247A (en) * | 2020-12-16 | 2021-03-09 | 广州大学 | Robot path planning method based on self-adaptive sparrow search algorithm |
CN112486185A (en) * | 2020-12-11 | 2021-03-12 | 东南大学 | Path planning method based on ant colony and VO algorithm in unknown environment |
CN114169560A (en) * | 2020-12-22 | 2022-03-11 | 四川合纵药易购医药股份有限公司 | Material scheduling control method for stereoscopic warehouse |
CN115609595A (en) * | 2022-12-16 | 2023-01-17 | 北京中海兴达建设有限公司 | Trajectory planning method, device and equipment of mechanical arm and readable storage medium |
CN117550273A (en) * | 2024-01-10 | 2024-02-13 | 成都电科星拓科技有限公司 | Multi-transfer robot cooperation method based on bee colony algorithm and transfer robot |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100088146A1 (en) * | 2002-08-22 | 2010-04-08 | United Parcel Service Of America, Inc. | Core Area Territory Planning for Optimizing Driver Familiarity and Route Flexibility |
CN105509749A (en) * | 2016-01-04 | 2016-04-20 | 江苏理工学院 | Mobile robot path planning method and system based on genetic ant colony algorithm |
CN106225788A (en) * | 2016-08-16 | 2016-12-14 | 上海理工大学 | The robot path planning method of ant group algorithm is expanded based on path |
-
2017
- 2017-12-03 CN CN201711256105.3A patent/CN108036790B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100088146A1 (en) * | 2002-08-22 | 2010-04-08 | United Parcel Service Of America, Inc. | Core Area Territory Planning for Optimizing Driver Familiarity and Route Flexibility |
CN105509749A (en) * | 2016-01-04 | 2016-04-20 | 江苏理工学院 | Mobile robot path planning method and system based on genetic ant colony algorithm |
CN106225788A (en) * | 2016-08-16 | 2016-12-14 | 上海理工大学 | The robot path planning method of ant group algorithm is expanded based on path |
Non-Patent Citations (1)
Title |
---|
汤可宗等: "一种求解旅行商问题的改进蚁群算法", 《东华理工学院学报》 * |
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108958238A (en) * | 2018-06-01 | 2018-12-07 | 哈尔滨理工大学 | A kind of robot area Dian Dao paths planning method based on covariant cost function |
CN108958238B (en) * | 2018-06-01 | 2021-05-07 | 哈尔滨理工大学 | Robot point-to-area path planning method based on covariant cost function |
CN109002923A (en) * | 2018-07-23 | 2018-12-14 | 宁波大学 | A kind of intercity multimode travel route planing method |
CN109213157A (en) * | 2018-08-28 | 2019-01-15 | 北京秦圣机器人科技有限公司 | Data center's crusing robot paths planning method based on improved Ant Colony System |
CN109282815A (en) * | 2018-09-13 | 2019-01-29 | 天津西青区瑞博生物科技有限公司 | Method for planning path for mobile robot based on ant group algorithm under a kind of dynamic environment |
CN109164810A (en) * | 2018-09-28 | 2019-01-08 | 昆明理工大学 | It is a kind of based on the adaptive dynamic path planning method of ant colony-clustering algorithm robot |
CN109164810B (en) * | 2018-09-28 | 2021-08-10 | 昆明理工大学 | Robot self-adaptive dynamic path planning method based on ant colony-clustering algorithm |
CN109506655A (en) * | 2018-10-19 | 2019-03-22 | 哈尔滨工业大学(威海) | Improvement ant colony path planning algorithm based on non-homogeneous modeling |
CN109506655B (en) * | 2018-10-19 | 2023-05-05 | 哈尔滨工业大学(威海) | Improved ant colony path planning algorithm based on non-uniform modeling |
CN109855640B (en) * | 2019-01-29 | 2021-03-02 | 北京航空航天大学 | Path planning method based on free space and artificial bee colony algorithm |
CN109855640A (en) * | 2019-01-29 | 2019-06-07 | 北京航空航天大学 | A kind of paths planning method based on free space and artificial bee colony algorithm |
CN109977455B (en) * | 2019-01-30 | 2022-05-13 | 广东工业大学 | Ant colony optimization path construction method suitable for three-dimensional space with terrain obstacles |
CN109977455A (en) * | 2019-01-30 | 2019-07-05 | 广东工业大学 | It is a kind of suitable for the ant group optimization path construction method with terrain obstruction three-dimensional space |
CN109945881A (en) * | 2019-03-01 | 2019-06-28 | 北京航空航天大学 | A kind of method for planning path for mobile robot of ant group algorithm |
CN110702121A (en) * | 2019-11-23 | 2020-01-17 | 赣南师范大学 | Optimal path fuzzy planning method for hillside orchard machine |
CN110702121B (en) * | 2019-11-23 | 2023-06-23 | 赣南师范大学 | Optimal path fuzzy planning method for hillside orchard machine |
CN110990769B (en) * | 2019-11-26 | 2021-10-22 | 厦门大学 | Attitude migration algorithm system suitable for multi-degree-of-freedom robot |
CN110990769A (en) * | 2019-11-26 | 2020-04-10 | 厦门大学 | Posture migration algorithm framework suitable for multi-degree-of-freedom robot |
CN112486185A (en) * | 2020-12-11 | 2021-03-12 | 东南大学 | Path planning method based on ant colony and VO algorithm in unknown environment |
CN112461247A (en) * | 2020-12-16 | 2021-03-09 | 广州大学 | Robot path planning method based on self-adaptive sparrow search algorithm |
CN112461247B (en) * | 2020-12-16 | 2023-05-23 | 广州大学 | Robot path planning method based on self-adaptive sparrow search algorithm |
CN114169560A (en) * | 2020-12-22 | 2022-03-11 | 四川合纵药易购医药股份有限公司 | Material scheduling control method for stereoscopic warehouse |
CN115609595A (en) * | 2022-12-16 | 2023-01-17 | 北京中海兴达建设有限公司 | Trajectory planning method, device and equipment of mechanical arm and readable storage medium |
CN117550273A (en) * | 2024-01-10 | 2024-02-13 | 成都电科星拓科技有限公司 | Multi-transfer robot cooperation method based on bee colony algorithm and transfer robot |
CN117550273B (en) * | 2024-01-10 | 2024-04-05 | 成都电科星拓科技有限公司 | Multi-transfer robot cooperation method based on bee colony algorithm |
Also Published As
Publication number | Publication date |
---|---|
CN108036790B (en) | 2020-06-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108036790A (en) | Robot path planning method and system based on mutillid algorithm under a kind of obstacle environment | |
Zhang et al. | An improved ant colony algorithm for path planning in one scenic area with many spots | |
Fang et al. | Particle swarm optimization with simulated annealing for TSP | |
CN106444755A (en) | Mobile robot path planning method and system based on improved genetic algorithm | |
CN101520858B (en) | Ant colony optimization-differential evolution fusion method for solving traveling salesman problems | |
Fang et al. | A survey of algorithms, applications and trends for particle swarm optimization | |
CN111562785A (en) | Path planning method and system for collaborative coverage of cluster robots | |
CN106525047A (en) | Unmanned aerial vehicle path planning method based on floyd algorithm | |
Rai et al. | Bio-inspired optimization techniques: a critical comparative study | |
Mohammed et al. | Particle swarm optimization for facility layout problems FLP—A comprehensive study | |
Chen et al. | Ant colony optimization with tabu table to solve TSP problem | |
CN110045738A (en) | Robot path planning method based on ant group algorithm and Maklink figure | |
Su et al. | Robot path planning based on random coding particle swarm optimization | |
Chen et al. | Ant colony algorithm with Stackelberg game and multi-strategy fusion | |
Juntao et al. | Study on robot path collision avoidance planning based on the improved ant colony algorithm | |
Singh et al. | Artificial bee colony algorithm with uniform mutation | |
Alsawy et al. | Fuzzy-based ant colony optimization algorithm | |
Liu et al. | A novel evolutionary membrane algorithm for global numerical optimization | |
Peng et al. | Cooperative area search for multiple UAVs based on RRT and decentralized receding horizon optimization | |
Jiang | Discrete bat algorithm for traveling salesman problem | |
Zhang et al. | A multi-goal global dynamic path planning method for indoor mobile robot | |
Lee et al. | Enhancement of ant colony optimization in multi-robot source seeking coordination | |
CN110097076A (en) | A kind of vector road network matching parallel calculating method and device based on GPU architecture | |
Zhang et al. | A Variable-step Two Synchronous Artificial Bee Colony Algorithm for mobile Robot Path Planning | |
Wang et al. | Welding robot path optimization based on hybrid discrete PSO |
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 |