Font Size: a A A

Research On Path Planning Optimization Algorithm For Mobile Robots In Complex Environments

Posted on:2020-09-24Degree:MasterType:Thesis
Country:ChinaCandidate:Z K TangFull Text:PDF
GTID:2428330605980569Subject:Electronic and communication engineering
Abstract/Summary:PDF Full Text Request
With the rapid development of modern science and technology,researchers have begun extensive research on mobile robot technology.At the same time,robots have also gone out of laboratories and been applied in a wider range of fields,such as military defense,medical rehabilitation,rescue and relief mission,life services and other aspects.As one of the key technologies in mobile robot research,path planning has also become a hotspot.Planning a safe and collision-free shortest path in a complex environment is an important guarantee for mobile robots to move safely,quickly and efficiently.The main content of this thesis is the path planning research based on genetic algorithm,ant colony algorithm,and artificial potential field method.In this thesis,the global path planning problem of mobile robots in static known environment and the local path planning problem in dynamic obstacle environment were studied,and the above three algorithms were improved respectively to solve the problems existing in traditional algorithms.The main research work of this thesis is as follows:In order to solve the problem of global path planning,grid method was used to establish an environment model in this thesis,an improved genetic algorithm and an improved ant colony algorithm were used to solve the problem of global path planning.The traditional genetic algorithm has the defects of slow convergence speed and it is easy to fall into a local optimal solution.In this thesis,column scanning and interpolation were used to produce the initial population,and a new fitness function was adopted.Adaptive crossover and adaptive mutation probability coefficient were used to improve the performance of the algorithm.Simulation results show that the performance of the algorithm was improved.The traditional ant colony algorithm has the defects of lack of directionality and instability in search,so the transfer function was improved and the adaptive heuristic function was added.At the same time,the pheromone distribution system was improved and a reward system was implemented.The number of ants,pheromone volatilization coefficient,pheromone heuristic factor,and expected heuristic factor were analyzed in this thesis,and the best parameters were selected.Since the two improved algorithms were still insufficient,a genetic ant colony fusion algorithm was proposed in this thesis.The global search ability has been enhanced in the improved genetic algorithm,and the results of the algorithm were used to provide initial pheromone for the improved ant colony algorithm.The genetic algorithm was used to process the search results of the ant colony to promote the evolution of the results.Compared with the improved genetic algorithm and the improved ant colony algorithm,the fusion algorithm proposed was optimal in global path search results,algorithm stability,and convergence speed through simulation experiments,which shows that the algorithm designed is feasible and superior in this thesis.To solve the problem of dynamic obstacles in the environment,an improved artificial potential field method was proposed in this thesis.The gravitational field of the global path is established,and the global path is divided into several line segments.So that the endpoints of the line segments and the line segments generate gravitational fields respectively.And the local path planning is completed step by step.In this thesis,the velocity field and acceleration field of relative motion obstacles were added to the repulsive force potential field,and the method to solve the minimum trap was given.Simulation results show that the improved artificial potential field algorithm can effectively deal with static and dynamic obstacles.
Keywords/Search Tags:Path planning, Algorithm integration, Genetic algorithm, Ant colony algorithm, Artificial potential field
PDF Full Text Request
Related items