Global Path Planning of Mobile Robot Based on Improved Genetic Algorithm

Abstract

Aiming at the problems of genetic algorithm in path planning such as slow convergence speed,easy maturity and too many unnecessary turns,an improved genetic algorithm based on catastrophe strategy was proposed.A selection strategy of regional must pass points was designed to generate high-quality initial populations,which improved the convergence speed of the algorithm.The catastrophe strategy was introduced and improved to prevent premature maturity while increasing population diversity,reduce population size and increase calculation speed.A dynamic mutation operator embedded in A* algorithm was designed to improve the local search ability in the later stage of the algorithm.The fitness function with multiple constraints was used to improve the smoothness of the path.The simulation results proved that compared to GA,Improved Adaptive Genetic Algorithm (IAGA) and Heuristic communication Heterogeneous dual population Ant Colony Optimization algorithm (HHACO) algorithms,the improved algorithm could better avoid premature maturity,shorten the path finding time and search for better route.The proposed algorithm was applied to Robot Operating System (ROS) platform,and the navigation test proved that it was effective and feasible,and could significantly improve the stability and efficiency of the mobile robot.