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
- pheromone
- 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.)
- Granted
Links
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 123
- 238000000034 method Methods 0.000 title claims abstract description 120
- 239000003016 pheromone Substances 0.000 claims abstract description 104
- 230000004888 barrier function Effects 0.000 claims abstract description 8
- 235000012907 honey Nutrition 0.000 claims description 38
- 230000008569 process Effects 0.000 claims description 31
- 241000257303 Hymenoptera Species 0.000 claims description 30
- 238000009826 distribution Methods 0.000 claims description 11
- 230000003044 adaptive effect Effects 0.000 claims description 9
- 238000011156 evaluation Methods 0.000 claims description 7
- 230000002688 persistence Effects 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 4
- 101100001677 Emericella variicolor andL gene Proteins 0.000 claims description 3
- 230000008034 disappearance Effects 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 230000006978 adaptation Effects 0.000 claims description 2
- 238000005457 optimization Methods 0.000 abstract description 25
- 238000005516 engineering process Methods 0.000 abstract description 14
- 230000008901 benefit Effects 0.000 abstract description 13
- 230000000694 effects Effects 0.000 description 9
- 230000006870 function Effects 0.000 description 6
- 239000002245 particle Substances 0.000 description 6
- 238000009825 accumulation Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 5
- 239000011664 nicotinic acid Substances 0.000 description 5
- 238000011160 research Methods 0.000 description 5
- 238000004088 simulation Methods 0.000 description 5
- 238000013461 design Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000002349 favourable effect Effects 0.000 description 3
- 235000013305 food Nutrition 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 101150019028 Antp gene Proteins 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 208000012661 Dyskinesia Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000003556 assay Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000002922 simulated annealing Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 230000003313 weakening effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—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 technical field of robots, and particularly relates to a robot path planning method and system (ABR) based on an ant-bee algorithm in a barrier environment.
Background
Path planning is the most critical technology of a mobile robot in the field of practical application, and refers to a continuous, collision-free, global optimal or suboptimal path from a starting point to a target point of the robot in a multi-barrier environment (Zhouz, Niey, MinG. EnhanceddAntColonyOptimization Algorithm for Global PathPath planning of Mobile Robots)
[J]Journal of NanchanghangHandkonguniversity, 2011: 698-. The problem of robot path planning has been proven to haveNPComplexity-based combinatorial optimization problem (HuanggB, KadaliR. dynamic modeling, predictiveControlandPerformancemonitoring [ M ]].SpringerLondon，2008.)。
The currently common robot path planning techniques can be divided into two categories (the robot path planning [ J ] of the uniform particle swarm and ant colony fusion algorithm, mechanical design and manufacture, 2017(7): 237-: (1) a traditional path planning method based on a mathematical concept. For example, a grid decoupling method, a visual graph method, a free space method, an artificial potential field method, a topological method and the like. With the increase of the complexity of the environment and the difficulty of the task to be optimized, the methods are difficult to obtain ideal effects in practical application. (2) A path planning method based on a bionic intelligent technology. Such as genetic algorithm, fuzzy control, neural network, particle swarm optimization algorithm, swarm algorithm, simulated annealing algorithm and the like. These methods can implement path optimization planning in a specific environment or in a real situation. However, the method has inherent defects in some complex and dynamic application environments. For example, in the application process of the standard ant colony algorithm facing the complex environment problem, the defects of low convergence speed, easy falling into local optimum and the like exist. And with the change of problem scale and dynamic environment, once ants fall into a local optimal solution, the ant colony is difficult to find other optimal paths due to the interference of the intensity of pheromones of local paths. Therefore, the application of the bionic intelligent technology to the path planning problem of the mobile robot still needs to be studied deeply.
Currently, in order to improve the search efficiency of the robot path planning technology, a plurality of researchers at home and abroad develop a robot path planning method research based on the bionic intelligent technology. From the current application effect, the ant colony algorithm has natural distributed parallel processing capability and has the path selection capability without taking the problem model as the interference, so that the ant colony algorithm is successfully applied to the combined optimization problem in a plurality of practical applications, particularly the successful application in the problem of a traveler, and the ant colony algorithm is better shown to be suitable for processing the problem with natural distributed parallel processing capability and the path selection capability without taking the problem model as the interferenceNPA distributed problem of complexity difficulty. Although the ant colony algorithm has the advantages of better pheromone positive feedback, parallelism, robustness and the like, with the continuous enhancement of problem environments or dynamic transformation, some aspects to be improved still exist: such as long search time, large calculation amount, easy trapping of local optimization and the like. In this regard, many scholars have proposed a number of positive improvements. For example, Dorigo et al propose an ant colony System Algorithm (ACS) (DorigoM, GambardellaM. Acooperivelevelearningapachpotothterrapvelingsalesanproplem [ J ]].IEEETransonEvolutionaryComputation，1997,1(1):53-66.). In the ACS path planning, only the pheromones on the paths traveled by the best individuals in each generation are updated, so that the algorithm convergence speed is accelerated. However, the problem is that although the feedback of the optimal pheromone on the path is strengthened, the stagnation phenomenon of the algorithm search is easily caused. Park et al propose a method for realizing path planning of robot by ant colony algorithm based on perception information clustering (Park JM, Savagaonkarr, ChongEKP, equivalent. effective resource utilization for QoSchannels in MF-TDMAsatellitems [ C)]// Milcom2000.
CenturyMilitarycommunications enhancements IEEE 2000: 645-. According to the method, breakpoint marking is carried out on the positions of the ant colony, which leave the nest or the food source, so that the convergence of the algorithm is ensured, however, the calculation amount of the method is increased rapidly along with the increase of the problem scale, and the deviation control performance of the path is not good easily. Aiming at the problem that the robot searches for the optimal path in the obstacle environment, the danton peak combines the advantages of a particle swarm algorithm and an ant colony algorithm, and utilizes an pheromone distribution improvement technology and a path selection technology mechanism to provide the ant colony particle swarm algorithm (danton peak, Zhangxuanping, Liuyanping). In addition, a large body of relevant literature (jingangcao. research of AntColonyAlgorithm for)
MobileRobotPathPlanning[J].JournalofComputer\s&\scommunications，2016 04(2): 11-19;
SaenphonT，PhimoltaresS，LursinsapC.CombiningnewFastOppositeGradientSearch
withAntColonyOptimizationforsolvingtravellingsalesmanproblem[J].EngineeringApplicationsofArtificialIntelligence，2014，35(2):324-334;ShuangB，ChenJ，LiZ.StudyonhybridPS-ACOalg
Research on ant colony algorithm [ J ] control and decision based on directional pheromone coordination, 2013(5):782 and 786) shows that by taking advantage of the technical advantages of other colony intelligent algorithms (such as a bee colony algorithm), the outstanding problem between convergence speed and local optimal solution in the ant colony algorithm can be effectively balanced, and the probability of converting the local optimal solution to global optimal solution is improved while the convergence speed is effectively accelerated, so that the hybrid algorithm can obtain the optimal solution more easily.
In summary, the application of the ant colony algorithm to the path planning process of the mobile robot has the key problems that: in the process of large-scale complex path environment application, the situations that the convergence speed is slow, the local optimum is easy to fall into exist. This is mainly because each ant needs to perform enhancement or attenuation operation on the path traveled by the ant after each round trip in the moving process of the ant. If the number of ants isANThe number of cities isCNThe time complexity of updating pheromone after the completion of each round trip of ants isO(AN×CN). Therefore, the pheromone updating time can show a line growth trend along with the continuous enhancement or dynamic transformation of the problem environment, which greatly influences the convergence speed of the global optimal path. In addition, ant colony is easy to fall into local optimal solution under the guidance of pheromone, which is mainly because in the path optimization process, ants select adjacent path points depending on the accumulation value of pheromone between the path points, and the accumulation intensity of the pheromone comes from two factors, namely the number of ants passing through the path; second is the persistence of the pheromone. This makes it easy to determine the next moving path point only by the intensity of pheromone between path points during the path selection process, which makes some ants have no successor point selectable. Therefore, the robot path planning can be deadlocked, and the whole robot path planning algorithm is in a stagnation state. Therefore, in order to improve the convergence speed of the ant colony algorithm path optimizing process, the path planning process is prevented from falling into the incoming optimal solution and causing deadlock.
At present, the robot technology is rapidly developed in the application fields of ground, underwater, air and the like, and gradually develops towards the direction of miniaturization and multi-robot cooperation. Along with the unknown detection of the universe planet of humans to the boundless countless countryside, the application field of the robot technology will focus more and more on autonomous path navigation of dyskinesia in rugged terrains of jungles and complex environments in mountainous areas. Meanwhile, in order to meet the requirement of rapid development of the robot technology, the path planning key planning technology is deeply designed towards swarm intelligence optimization based on the bionic intelligence technology, a good path can be found, and the path can be effectively executed, which is an important embodiment of robot intelligence, and particularly, the method based on the bionic intelligence technology and combined with other methods (such as ant colony optimization and bee colony system optimization provided by the invention) is a key point and a difficulty point of intensive research of the robot intelligence in the future and is one of the key point problems of the important research in the field of artificial intelligence.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a robot path planning method and system based on an ant-bee algorithm in a barrier environment. The invention firstly designs an optimization method of a bee colony algorithm applied to robot path planning, respectively takes bee colonies and honey sources as a starting point and an end point of a robot path planning process by using the optimization characteristic of the bee colony algorithm for reference, finally finds a global optimal planning path through close cooperation among different bee colonies, and correspondingly converts the global optimal planning path into an enhanced value of pheromones in a grid environment, thereby providing prior knowledge for effective search of the ant colony algorithm and weakening the blindness of the initial search stage of the ant colony algorithm.
Secondly, the invention designs a novel reliability evaluation scheme of the path points to be selected, and simultaneously, a reliability parameter is fused into the ant path point selection strategy. The path selection strategy is different from the past ant city selection strategy, and is novel in that pheromone intensity values and distance factors of path points to be selected are evaluated, reliability factors of the points to be selected are considered, and recognition and analysis capacity of ants on obstacles in an obstacle environment is enhanced.
Another important aspect of the present invention is a novel pheromone update strategy. Is different from the prior artThe novel pheromone updating strategy does not update pheromone of local paths represented by all ants but aims at local optimal paths represented by optimal antsp l Global optimal path represented by global optimal antsp g The pheromone is updated, so that the positive feedback effect of the pheromone in the path planning process is enhanced, and the separation of the global optimal path from a plurality of local optimal paths can be accelerated.
In the robot path planning method based on the ant colony algorithm in the obstacle environment, the bee colony algorithm and the ant colony algorithm are fused, an optimal planning path is preferentially found by the bee colony algorithm, and the optimal planning path is correspondingly converted into the distribution of pheromones in the grid environment, so that the prior knowledge is provided for the path optimizing process of the ant colony algorithm.
The reliability calculation scheme in the path selection strategy fully considers the accumulation effect of pheromones in the adjacent areas of the path points to be selected. The path selection strategy constructed based on the scheme is favorable for the preferential winning of the optimal path selection point.
The novel pheromone updating strategy updates the pheromones of the local optimal path represented by the optimal ant and the global optimal path represented by the global optimal ant, abandons the idea of updating all ant paths in the prior pheromone, shortens the pheromone updating time and accelerates the searching speed of the global optimal path.
The invention is realized in such a way, and provides a robot path planning method and a system based on an ant-bee algorithm in a barrier environment, wherein the robot path planning method based on the ant-bee algorithm in the barrier environment comprises the following steps:
respectively taking a honeycomb and a honey source as a starting point and an end point of a robot path planning process, finding a global optimal planning path through cooperation among different bee colonies, and correspondingly converting the global optimal planning path into an enhanced value of pheromones in a grid environment to provide prior knowledge for searching an ant colony algorithm;
evaluating the pheromone intensity value and distance factors of the path point to be selected, analyzing the reliability factor of the point to be selected, and identifying and analyzing the obstacle in the obstacle environment by the ant;
local optimal path represented for optimal antsp l Global optimal path represented by global optimal antsp g And updating the pheromone, and searching positive feedback of the pheromone in the path planning process.
Further, the robot path planning method based on the ant-bee algorithm in the obstacle environment specifically includes:
initializing parameters, and setting parameters of a swarm algorithm;
including population sizeSNPopulation maximum evolution algebraMENControlling the convergence overlap of the algorithmlimit(ii) a Setting parameters of the ant colony algorithm: including the number of antsN a Pheromone persistenceρPath weightc 1Andc 2coefficient of weightα﹑βAndγ；
initializing environmental information distribution;
setting an environment by using a grid method, and initializing pheromones on grid points;
step three, obtaining a global optimal path by using a swarm robot path planning method, and converting the path into an enhanced value of the pheromoneSubsequently placing the ant colony at the starting pointS；
Step four, executing ant colony path movement;
and each ant selects the next path point according to the path point selection strategy. If the pheromone from the current grid to the adjacent path point is 0, the ant continuously selects other adjacent path points on the current grid, if no path point is available on the periphery, the current grid is set as an obstacle grid, and the ant returns to the last searched path point;
step five, repeating the step four until the whole ant colony reaches the end point;
step six, updating pheromones on each path according to formulas (9) and (10) according to the pheromone updating strategy;
step seven, if the whole ant colony converges to a path or the cycle times reach the maximum value, the cycle is ended, the whole global optimal path searching process is ended, and a global optimal path is output; otherwise, turning to the step four.
Further, the evaluation function of the individual adaptive value in the bee colony algorithm is as follows:
in the system constructed by using the swarm algorithm, each bee individual represents a path from an initial point to a final point,represents an individual bee, wherein,Dthe dimension of the individual is represented, each dimension of the individual represents a grid serial number, and the 1 st dimension and the last 1 st dimension of the individual respectively represent the grid serial numbers of an initial point and a terminal point; connecting every 1-dimension in the individual to form a path from a starting point to an end point, wherein x = (1,2,5,9,10,20,21,27,40,45,60,78,89,90,93,96,100) represents a path from 1 to 100, and the intermediate passes through 2,5,9,10,20,21,27,40,45,60,78,89,90,93,96 grid serial numbers; evaluating an individualx i Defining an individual fitness value evaluation function as follows;
further, the global path planning algorithm for the swarm robots comprises the following specific steps:
1) environmental setting using grid methodThereby obtaining a two-dimensional array representing the environment informationENV[][]；
2) Setting parameters of a population scale ofSNLeading bees and observing bees are half of population quantity, and initial solution quantityFN=SN(v 2) population maximum evolution algebraMENControlling the convergence overlap of the algorithmlimit；
3) Is randomly generated according to the following formulaSNAnDMaintaining a feasible solution;
wherein,ub j andlb j are respectivelyx ij Upper and lower limits of value;
4) calculating the adaptive value of each honey source according to the following formula;
wherein,f i (x i ) Is the objective function value of the problem to be solved;
5) setting a cycle counterCount= 1; the method comprises the following steps:
a) Leading bees to the honey sourcex i The neighboring area searches for a new source of honey, and a new solution is generated according to the following formulaCalculating an adaptive value;
wherein,kfor random generation, is [ -1,1 [)]A random number in between;
b) To pairx i Andcomparing, and leading the bees to select honey sources by adopting a greedy strategy;
c) The observation bee selects a dense source according to the following formulax i Probability of (2)P i ；
d) Observing bee according to probabilityP i Selecting honey sourcex i And generating a new honey source near the honey source according to the formula (4)Calculating new honey sourceAn adaptation value of;
e) Selecting a honey source by the observation bees according to a greedy strategy;
f) If the honey source needing to be abandoned exists, a new honey source is randomly generated according to the formula (2) to replace the honey source;
g) Recording the optimal value in the current iteration, and juxtaposingCount=Count+ 1; up toMEN=Count；
h) And outputting the optimal solution.
Further, the ant-bee algorithm is as follows:
(1) and (3) representation of intensity of pheromone and path point:
for each gridjCalculating the corresponding credibility of the grid in a specific mode: by a gridjFor the upper left vertex, extractjThe template is combined by adjacent three grids, and each grid corresponds to a coefficientAnd is andcalculated according to the formula (6)jThe intensity of the pheromone within the template,is composed ofjA confidence value of;
wherein,correspond totTime down path pointjAndkpheromone values in between;
(2) route point selection strategy:
selecting path points according to the "bet round method" according to the transition probability, each ant is intThe probability of a time moving from a certain waypoint to an adjacent waypoint is as follows:
wherein,is shown intThe time of day is determined by the waypointiTo the path pointjThe amount of information remaining;D ij as a waypointiAndjthe Euclidean distance between;for the path point to be selectedjA confidence value of;to the relative degree of importance of the pheromone,is two grids (iAndj) The relative degree of importance of the distance information between,as a waypointjA confidence value of; three parametersThe following relation is satisfied:
(3) pheromone update strategy:
the update strategy is shown in the following formula:
wherein,is a constant between 0 and 1, indicating the persistence of the pheromone substance; whileIndicating the degree of disappearance of the pheromone substance;L c andL w respectively representing locally optimal pathsp l And global optimal pathp g The length of the path of (a) is,Qis a constant;c 1andc 2respectively representing locally optimal pathsp l And global optimal pathp g Weight in pheromone update, and satisfyc 1+c 2=1（1>c 1,c 2>0）。
The invention further aims to provide a robot path planning system based on the ant-bee algorithm in the obstacle environment.
The invention has the advantages and positive effects that: the method of the invention fully utilizes respective advantages of the bee colony algorithm, the ant colony algorithm and the like, and overcomes respective disadvantages to find a global optimal planning path through advantage complementation. The advantages can be described as: the global optimal path obtained by the bee colony algorithm planning is correspondingly converted into the enhancement value of the pheromone between the path points, so that the blindness of the conventional ant colony algorithm in the initial path optimization is avoided, and the universality of the ant colony algorithm search space is reduced. Secondly, different from the traditional ant city selection strategy, the reliability is introduced into the path point selection strategy, the intensity and distance factors of pheromones among the path points are considered, the ant information quantity of the adjacent area of the path point to be selected is fully considered, and compared with an ant colony algorithm, obstacles can be successfully identified and other path points can be successfully selected. When the round trip of the ants is finished, the pheromone updating strategy does not update the local paths represented by all the ants, but aims at the local optimal path represented by the optimal antp l Global optimal path represented by global optimal antsp g The pheromone is updated, so that the positive feedback of the pheromone is facilitated, and the searching speed of the algorithm on the global optimal path can be increased. The implementation case has obvious effects, the global optimal path obtained by the ant colony system optimization constructed by the ant colony algorithm and the bee colony algorithm is superior to a single planning path algorithm in time efficiency (in environments 1 and 2, the optimal path is respectively improved by 24.38% and 28.93% compared with BCR), the solution precision is superior to the bee colony planning path algorithm (in environments 1 and 2, the optimal path is respectively improved by 1.8% and 7.5% compared with APR), and the method is a novel method for solving the optimization problem with the characteristics of intuition and universality.
Drawings
Fig. 1 is a flowchart of a robot path planning method based on an ant-bee algorithm in an obstacle environment provided by the implementation of the present invention.
Fig. 2 is a robot path planning method and system based on the ant-bee algorithm in a barrier environment.
FIG. 3 is a distribution diagram of pheromones provided by practice of the present invention.
FIG. 4 is a template profile provided by the practice of the present invention.
FIG. 5 is a diagram of simulation results between different methods provided by the present invention based on the environment.
In the figure: (a) a multi-obstacle grid environment under a 20 × 20 environment; (b) the global optimal planning path searched in the BCR environment is obtained; (c) searching a global optimal planning path in an APR environment; (d) and searching the global optimal planning path in the ABR environment.
FIG. 6 is a diagram of simulation results between different methods based on environment two provided by the present invention.
In the figure: (a) a multi-obstacle grid environment under a 30 × 30 environment; (b) the global optimal planning path searched in the BCR environment is obtained; (c) searching a global optimal planning path in an APR environment; (d) and searching the global optimal planning path in the ABR environment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The invention designs a novel path selection strategy, the credibility of path points is integrated into the strategy, and the aspects of the distance, the pheromone, the credibility and the like of the path points to be selected are comprehensively considered in the path point selection process, so that the path points can be selected preferentially, and the situation that the optimization is trapped in a local optimal solution can be avoided. Meanwhile, before the ant colony algorithm is optimized, the convergence efficiency of the ant colony algorithm can be enhanced by using a planned path obtained by optimizing the bee colony system, and the provided pheromone updating strategy only executes pheromone enhancement operation on the optimal path of ant circumambulation. The results of the examples show that: compared with other related methods, the robot path planning method and system based on the ant-bee algorithm in the obstacle environment, which are provided by the invention, are more favorable for accelerating the convergence speed of system optimization while ensuring the solving quality, and are more favorable for the optimal path to be taken out of sight within the same time planning scale.
The application of the principles of the present invention will now be further described with reference to the accompanying drawings.
As shown in fig. 1, the method for planning a robot path based on an ant-bee algorithm in an obstacle environment provided by the invention comprises the following steps:
s101, initializing parameters, and setting parameters of a swarm algorithm;
including population scale SN, population maximum evolutionary algebraMENControlling the convergence overlap of the algorithmlimit(ii) a Setting parameters of the ant colony algorithm: including the number of antsN a Pheromone persistenceρPath weightc 1Andc 2coefficient of weightα﹑βAndγ。
s102, initializing environmental information distribution;
and (4) setting an environment by using a grid method, and initializing pheromones on grid points.
S103, obtaining a global optimal path by using a swarm robot path planning method, and converting the path into pheromonesEnhancement valueSubsequently placing the ant colony at the starting pointS；
S104, executing an ant colony path moving scheme;
and each ant selects the next path point according to the path point selection strategy. If the pheromone from the current grid to the adjacent path point is 0, the ant continuously selects other adjacent path points on the current grid, if no path point is available on the periphery, the current grid is set as an obstacle grid, and the ant returns to the last searched path point.
S105, repeating the step S104 until the whole ant colony reaches the end point;
s106, updating pheromones on each path according to formulas (9) and (10) according to the pheromone updating strategy;
s107, if the whole ant colony converges to a path or the cycle times reach the maximum value, the cycle is ended, the whole global optimal path searching process is ended, and a global optimal path is output; otherwise, go to step S104.
FIG. 3 is a distribution diagram of pheromones provided by practice of the present invention.
The invention is further described below with reference to specific assays.
The evaluation function of the individual adaptive value in the bee colony algorithm provided by the invention is as follows:
1. in the system constructed by using the swarm algorithm, each bee individual represents a path from an initial point to a final point,represents an individual bee, wherein,Drepresenting the dimension size of the individual, each dimension of the individual representing a grid number, and the 1 st dimension of the individualAnd last 1 dimensionThe grid serial numbers respectively represent the initial point and the terminal point; connecting every 1-dimension in the individual to form a path from a starting point to an end point, wherein x = (1,2,5,9,10,20,21,27,40,45,60,78,89,90,93,96,100) represents a path from 1 to 100, and the intermediate passes through 2,5,9,10,20,21,27,40,45,60,78,89,90,93,96 grid serial numbers; evaluating an individualx i In the above (1), the following individual fitness value evaluation functions are defined:
。
2. the invention provides a global path planning algorithm for a swarm robot, which comprises the following specific steps:
step2.1 uses a grid method to set environment, thereby obtaining a two-dimensional array representing environment informationENV[][].
Step2.2 parameter set, population size isSNThe number of leading bees and observation bees is half of the population number, i.e. the initial number of solutionsFN=SN/2 maximum evolutionary algebra of populationMEN,Control algorithm convergence overlap timeslimit。
Step2.3 was randomly generated as followsSNAnDSolution to problem of maintenance
Wherein,ub j andlb j are respectivelyx ij Upper and lower limits of the values.
Step2.4 the fitness value of each honey source was calculated according to the following formula.
.
Wherein,f i (x i ) Is the objective function value of the problem to be solved.
Step2.5 set Loop counterCount=1;
Repeat
Step2.5.1 leading bees to the honey sourceThe neighboring area searches for a new source of honey, and a new solution is generated according to the following formulaAnd calculating an adaptive value.
Wherein,kin order to generate the information at random,is [ -1,1 [ ]]A random number in between.
Step2.5.2 pairsAndfor comparison, the lead bee selects the honey source by adopting a greedy strategy (namely, a better solution is kept).
Step2.5.3 Observation bees select dense sources according to the following formulax i Probability of (2)P i
Step2.5.4 Observation of bees according to probabilityP i Selecting honey sourcex i And generating a new honey source near the honey source according to the formula (4)Calculating new honey sourceThe adaptive value of (a).
Step2.5.5 the observer bees select honey sources according to a greedy strategy.
Step2.5.6 if there is a honey source to be discarded (i.e. the honey source is according to equation (4))limitNo change in number) at which point a new secret source is randomly generated to replace it according to equation (2).
Step2.5.7 records the optimal value in the iterative and juxtaposesCount=Count+1.
untilMEN=Count
And outputting the optimal solution by Step2.6.
3. The present invention is further described below in conjunction with the ant algorithm.
The ant-bee algorithm is as follows:
the ant-bee algorithm is a mixed algorithm which references the respective advantages of the ant colony algorithm and the bee colony algorithm. The process of searching the food source by the swarm algorithm is the process of searching the food source to be optimized, and mutual cooperation among bees in different roles promotes the swarm to converge on the global optimal solution at a high speed. However, in a multi-obstacle complex environment, obstacles may not be effectively avoided. Thus, the obtained global path may not effectively guide the movement path planning process of the robot. The ant colony can obtain a global optimal path through accumulated analysis of pheromones in the path, has certain identification and analysis capacity on obstacles, and mainly benefits from an ant city path selection strategy. However, the ant colony algorithm has the disadvantages that the accumulation time of pheromones is too long, so that the search speed of the global optimal path is too slow, the efficiency is seriously low along with the increase of the problem scale, and the ant colony algorithm is not suitable for being applied to large-scale and complex problems in cities.
(1) Representation of intensity of pheromone and path point
For a given gridiThe pheromone distribution of the grid is distributed on the paths of eight adjacent grids, and each grid is assumed to be a square grid with the side length of 1; as shown in fig. 3;
grid (C)iThe grids (1-8) adjacent to the grid have pheromone distribution, and the pheromone is distributedv ij (j=1, 2., 8) depends on the pheromone accumulation effect of the ant colony on the path, and numbers 1 to 8 also indicate the moving direction of the robot. Path pointi(i.e. grid)i) In the planning process of selecting the adjacent path points, each path point to be selectedj(jNeighboring pheromone distribution of =1, 2., 8) to the path point to be selectedjThe choice of (a) has an important influence. Obviously, if the distribution of the neighboring pheromones is strong, the to-be-selected path point has more information communication with the neighboring area, the intensity of the pheromone left by the ants in the area is strong, and the probability that the to-be-selected path point is selected as the next moving path point is high. Therefore, in the present invention, for each gridjThe reliability value is calculated in the following specific mode: by a gridjFor the upper left vertex, extractjThe template is assembled adjacent to three grids as shown in fig. 3. In this case, each grid corresponds to a coefficientAnd is andcalculated according to the formula (6)jIntensity of pheromone in the template, i.e.jA confidence value of (2).
Wherein,correspond totTime down path pointjAndkpheromone values in between.
(2) Path point selection strategy
During the movement of each step of the ant, only the path point of each step of movement is selected from the adjacent grids. Thus, each grid has equal chance of being chosen as a place for ants to move next, where path points are chosen according to the transition probability in a "round of bet" manner, with each ant attThe time being represented by a certain path point (grid)i) Moving adjacent path points (grids)j) The probability of (c) is:
wherein,is shown intThe time of day is determined by the waypointiTo the path pointjThe amount of information remaining;D ij as a waypointiAndjthe Euclidean distance between;for the path point to be selectedjA confidence value of (2).To the relative degree of importance of the pheromone,is two grids (iAndj) The relative degree of importance of the distance information between,as a waypointjA confidence value of (2). Three parametersThe following relation is satisfied:
different from the path selection strategy of the standard ant algorithm, the formula (6) analyzes pheromone and distance between adjacent path points and simultaneously comprehensively considers the path pointsjA confidence value of (2). This is because, in the course of selecting ant paths, there are some paths and their neighboring area paths are likely to have the phenomenon that pheromones are weak or even 0.
(3) Pheromone update strategy
And in the process that the ant colony moves from the starting point to the end point, selecting the path point of each movement according to the intensity of the pheromone on the path and the reliability value of the adjacent point. In the invention, after the ant colony completes one round trip, the pheromone updating strategy does not update the local paths represented by all ants, but timely aims at the local optimal path represented by the optimal antp l Global optimal path represented by global optimal antsp g The pheromone is updated, so that the positive feedback effect of the pheromone is enhanced, and the searching speed of the algorithm on the global optimal path can be increased. Here, the update strategy is shown by the following formula:
wherein,is a constant between 0 and 1, indicating the persistence of the pheromone substance; and 1-Indicating the degree of disappearance of the pheromone substance;L c andL w respectively representing locally optimal pathsp l And global optimal pathp g The length of the path of (a) is,Qis a constant; respectively representing locally optimal pathsp l And global optimal pathp g Weight in pheromone update, and satisfyc 1+c 2=1(1>c 1,c 2>0)。
4. The invention is further described with reference to specific examples.
Example (b):
the robot path planning method and system based on the ant-bee algorithm in the obstacle environment are abbreviated as ABR, and in order to effectively describe the high efficiency of the robot path planning method and system in the robot path planning process, the multi-obstacle grid environment in 20 × 20 environment and 30 × 30 environment is used in implementation. In addition, in order to better compare the validity of the simulation result of the ABR, the invention respectively compares the method with a bee colony robot path planning method (BCR for short) and an ant colony-swarm algorithm machine path planning method (dune et al, an ant colony-swarm algorithm control theory and application of robot path planning in an obstacle environment, 2009, 26(8): 879-.
The parameters in the implementation process of the invention are respectively as follows: (1) parameter setting of ABR method, (1.1) parameter setting of bee colony algorithm, bee colony scaleSN=40, maximum evolutionary algebra of populationMEN=2000,Control algorithm convergence overlap timeslimit=20; (1.2) parameters of the ant colony algorithm: number of antsN a =30, pheromone persistence=0.1, path weightc 2=c 1=0.5, constantQ=50, weight coefficient=0.4﹑=0.3 andand = 0.3. (2) Parameter setting of APR method, (2.1) ant numberN a =30, pheromone persistence=0.1, path weightc 1=c 2=0.5, weight coefficient=1﹑=2, constantQ=100, (2.2) particle swarm algorithm parameter settings, the number of particles is 30, the maximum iteration number is 50,c 2=c 1=2, initial inertial weightwLinearly decreasing from 0.9 to 0.4 with the number of iterationsV max =10.
The simulation result in the environment one is shown in fig. 5, and global optimal planning paths searched in the environment by three methods, namely ABR, BCR, APR and the like.
From the planned path analysis depicted in fig. 5, it can be seen that: the path planned by the BCR method passes through 27 path points from the starting point to the end point, 11 path points walking along the direction 1 and 16 path points walking along the direction 2 or 8 in the moving process, and the total length of the path isThe path obtained by the APR method passes through 25 path points from the starting point to the end point, and the path walks along the direction 1 in the moving processThere are 13 points and 12 path points running along direction 2 or 8, and the optimal path length isThe path planned by the ABR method passes 24 path points in total from the starting point to the end point, 14 path points are traveled along the direction 1, 10 path points are traveled along the directions 2 or 8 in the moving process, and the total length of the path is equal to= 29.80. Therefore, the global optimal path planned by the ABR method of the invention has fewer path points than BCR and APR in the moving process of the robot, and the length of the path is relatively slightly smaller.
The simulation result under the environment two is shown in fig. 6;
fig. 6(a) is more complex than fig. 5(a), and more obstacles are distributed and more path points are selected from the starting point to the ending point. As can be seen from the optimal planned path analysis depicted in fig. 6: the path planned by the BCR method passes through 46 path points from the starting point to the end point, in the moving process, 12 path points walking along the direction 1 and 34 path points walking along the direction 2 or 8 are provided, and the total length of the path is=50.97, the path obtained by the APR method passes through 39 path points from the starting point to the end point, during the movement, there are 19 path points walking along the direction 1 and 20 path points walking along the direction 2 or 8, and the optimal path length is at this time=46.87, and the path planned by the ABR method passes 33 path points from the starting point to the end point, and during the moving process, there are 25 path points walking along the direction 1 and 8 path points walking along the directions 2 or 8, and the total length of the path is= 43.36. It can be seen that in the situation where the obstacle environment is more complex, the global optimal path planned by the ABR method of the present invention may experience significantly fewer path points than the BCR and the APR during the movement of the robot, and the length of the path experienced may also be significantly shorter than those of the other two methods.
The experimental data obtained in the two environments are combined, a performance comparison time data factor is introduced, and the optimization efficiency between the method and other two comparison methods is examined, as shown in table 1.
The experimental data obtained in the two environments are combined, a performance comparison time data factor is introduced, and the optimization efficiency between the method and other two comparison methods is examined, as shown in table 1.
As can be seen from table 1 above, the average running time of the method of the present invention in solving the optimal planned path is superior to the other two comparison methods. And along with the gradual increase of the complexity of the problem environment, the global optimal planning path is less than two comparison methods of APR and BCR.
The robot path planning method and system based on the ant-bee algorithm in the obstacle environment can change along with the environment and have the capability of planning the global optimal path in real time. The method disclosed by the invention integrates two algorithms (an ant colony algorithm and a bee colony algorithm), the respective advantages are used for reference, the weak point influence of the respective algorithms is weakened, the established ant-bee robot path planning method is superior to two independent compared methods in time, and is superior to the two compared methods in solving efficiency, so that the method is a novel robot global path planning new method integrating the two algorithms, and the win-win effect on time and path optimization performance is achieved. The implementation effect shows that theoretically, the method can be further improved and deeply applied to other fields, such as urban traffic network path optimization problem, urban logistics path optimization problem, wireless sensor network path optimization and other practical optimization problems. These problems can be translated into similar problems to robot path optimization and are suitable for solving with the method proposed by the present invention.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (6)
1. A robot path planning method based on an ant-bee algorithm in a barrier environment is characterized by comprising the following steps:
respectively taking a honeycomb and a honey source as a starting point and an end point of a robot path planning process, finding a global optimal planning path through cooperation among different bee colonies, and correspondingly converting the global optimal planning path into an enhanced value of pheromones in a grid environment to provide prior knowledge for searching an ant colony algorithm;
evaluating the pheromone intensity value and distance factors of the path point to be selected, analyzing the reliability factor of the point to be selected, and identifying and analyzing the obstacle in the obstacle environment by the ant;
local optimal path represented for optimal antsp l Global optimal path represented by global optimal antsp g And updating the pheromone, and searching positive feedback of the pheromone in the path planning process.
2. The method for robot path planning based on the ant-bee algorithm in the obstacle environment according to claim 1, wherein the method for robot path planning based on the ant-bee algorithm in the obstacle environment specifically includes:
initializing parameters, and setting parameters of a swarm algorithm;
including population sizeSNPopulation maximum evolution algebraMENControlling the convergence overlap of the algorithmlimit(ii) a Setting parameters of the ant colony algorithm: including the number of antsN a Pheromone persistenceρPath weightc 1Andc 2coefficient of weightα﹑βAndγ；
initializing environmental information distribution;
setting an environment by using a grid method, and initializing pheromones on grid points;
step three, obtaining a global optimal path by using a swarm robot path planning method, and converting the path into an enhanced value of the pheromoneSubsequently, the ant colony is placed at the starting point S;
step four, executing ant colony path movement;
each ant selects the next path point according to the path point selection strategy;
if the pheromone from the current grid to the adjacent path point is 0, the ant continuously selects other adjacent path points on the current grid, if no path point is available on the periphery, the current grid is set as an obstacle grid, and the ant returns to the last searched path point;
step five, repeating the step four until the whole ant colony reaches the end point;
step six, updating pheromones on each path according to formulas (9) and (10) according to the pheromone updating strategy;
step seven, if the whole ant colony converges to a path or the cycle times reach the maximum value, the cycle is ended, the whole global optimal path searching process is ended, and a global optimal path is output; otherwise, turning to the step four.
3. The method for robot path planning based on ant-bee algorithm in obstacle environment according to claim 2, wherein the evaluation function of individual adaptive value in the bee colony algorithm is as follows:
in the system constructed by using the swarm algorithm, each bee individual represents a path from an initial point to a final point,represents an individual bee, wherein,Drepresenting the dimension size of the individual, each dimension of the individual representing a grid number, and the 1 st dimension of the individualAnd last 1 dimensionThe grid serial numbers respectively represent the initial point and the terminal point; connecting every 1-dimension in the individual to form a path from a starting point to an end point, wherein x = (1,2,5,9,10,20,21,27,40,45,60,78,89,90,93,96,100) represents a path from 1 to 100, and the intermediate passes through 2,5,9,10,20,21,27,40,45,60,78,89,90,93,96 grid serial numbers; evaluating an individualx i Defining an individual fitness value evaluation function as follows;
。
4. the robot path planning method based on the ant-bee algorithm in the obstacle environment according to claim 2, wherein the bee colony robot global path planning algorithm comprises the following specific steps:
1) setting an environment by using a grid method, thereby obtaining a two-dimensional array ENV [ ] [ ] representing environment information;
2) setting parameters of a population scale ofSNLeading bees and observing bees are half of population quantity, and initial solution quantityFN=SN(v 2) population maximum evolution algebraMENControlling the convergence overlap of the algorithmlimit；
3) Is randomly generated according to the following formulaSNAnDMaintaining a feasible solution;
wherein,ub j andlb j are respectivelyx ij Upper and lower limits of value;
4) Calculating the adaptive value of each honey source according to the following formula;
wherein,f i (x i ) Is the objective function value of the problem to be solved;
5) setting a cycle counterCount= 1; the method comprises the following steps:
a) Leading bees to the honey sourcex i The neighboring area searches for a new source of honey, and a new solution is generated according to the following formulaCalculating an adaptive value;
wherein,kin order to generate the information at random,is [ -1,1 [ ]]A random number in between;
b) To pairx i Andcomparing, and leading the bees to select honey sources by adopting a greedy strategy;
c) The observation bee selects a dense source according to the following formulax i Probability of (2)P i ；
d) Observing bee according to probabilityP i Selecting honey sourcex i And generating a new honey source near the honey source according to the formula (4)Calculating new honey sourceAn adaptation value of;
e) Selecting a honey source by the observation bees according to a greedy strategy;
f) If the honey source needing to be abandoned exists, a new honey source is randomly generated according to the formula (2) to replace the honey source;
g) Recording the optimal value in the current iteration, and juxtaposingCount=Count+ 1; up toMENIs equal toCount；
h) And outputting the optimal solution.
5. The method for robot path planning based on the ant-bee algorithm in the obstacle environment according to claim 2, wherein the ant-bee algorithm is as follows:
(1) and (3) representation of intensity of pheromone and path point:
for each gridjCalculating the reliability value of the grid in a specific mode of: by a gridjFor the upper left vertex, extractjThe template is combined by adjacent three grids, and each grid corresponds to a coefficientWhereink=1,2,3, andcalculated according to the formula (6)jIntensity of pheromone in the template, i.e.jA confidence value of;
wherein,correspond totTime down path pointjAndkpheromone values in between;
(2) route point selection strategy:
selecting path points according to the "bet round method" according to the transition probability, each ant is intThe probability of a time moving from a certain waypoint to an adjacent waypoint is as follows:
wherein,is shown intThe time of day is determined by the waypointiTo the path pointjThe amount of information remaining;D ij as a waypointiAndjthe Euclidean distance between;for the path point to be selectedjA confidence value of;to the relative degree of importance of the pheromone,is two grids (iAndj) The relative degree of importance of the distance information between,as a waypointjA confidence value of; three parametersThe following relation is satisfied:
(3) pheromone update strategy:
the update strategy is shown in the following formula:
wherein,is a constant between 0 and 1, indicating the persistence of the pheromone substance; whileIndicating the degree of disappearance of the pheromone substance;L c andL w respectively representing locally optimal pathsp l And global optimal pathp g The length of the path of (a) is,Qis a constant; respectively representing locally optimal pathsp l And global optimal pathp g Weight in pheromone update, and satisfyc 1+c 2=1, wherein 1>c 1,c 2>0。
6. An ant-bee algorithm based robot path planning system in a barrier environment according to 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 |
|---|---|---|
| CN108036790B (en) | Robot path planning method and system based on ant-bee algorithm in obstacle environment | |
| CN113110592B (en) | Unmanned aerial vehicle obstacle avoidance and path planning method | |
| CN109945881B (en) | Mobile robot path planning method based on ant colony algorithm | |
| Zhao et al. | Survey on computational-intelligence-based UAV path planning | |
| CN110750096B (en) | Mobile robot collision avoidance planning method based on deep reinforcement learning in static environment | |
| Wang et al. | Autonomous robotic exploration by incremental road map construction | |
| CN108664022B (en) | Robot path planning method and system based on topological map | |
| CN110794842A (en) | Reinforced learning path planning algorithm based on potential field | |
| CN111610786A (en) | Mobile robot path planning method based on improved RRT algorithm | |
| CN110488859A (en) | A kind of Path Planning for UAV based on improvement Q-learning algorithm | |
| CN108985516A (en) | Indoor paths planning method based on cellular automata | |
| Bai et al. | Adversarial examples construction towards white-box q table variation in dqn pathfinding training | |
| CN114167865A (en) | Robot path planning method based on confrontation generation network and ant colony algorithm | |
| CN117556979B (en) | Unmanned plane platform and load integrated design method based on group intelligent search | |
| CN110045738A (en) | Robot path planning method based on ant group algorithm and Maklink figure | |
| CN109683630A (en) | Unmanned aerial vehicle flight path planing method based on population and PRM algorithm | |
| CN112484732A (en) | IB-ABC algorithm-based unmanned aerial vehicle flight path planning method | |
| Qiming et al. | A review of intelligent optimization algorithm applied to unmanned aerial vehicle swarm search task | |
| Wu et al. | Global and local moth-flame optimization algorithm for UAV formation path planning under multi-constraints | |
| Su et al. | Robot path planning based on random coding particle swarm optimization | |
| Ammar et al. | Hybrid metaheuristic approach for robot path planning in dynamic environment | |
| CN111080035A (en) | Global path planning method based on improved quantum particle swarm optimization algorithm | |
| CN114815801A (en) | Adaptive environment path planning method based on strategy-value network and MCTS | |
| Tian et al. | Multi-UAV Reconnaissance Task Allocation in 3D Urban Environments | |
| Zhang et al. | A multi-goal global dynamic path planning method for indoor mobile robot |
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 |