Research On Global Path Planning Algorithm For Mobile Robot Based On Fusion Of Ant Colony Optimization And Genetic Algorithm

Under the circumstance that all the robot's working environment are all known,the global path planning of mobile robot is guided by reasonable planning algorithm,starting from the starting point and avoiding all the obstacles in the working environment to find an optimal path to the end point.In the research of the global path planning of mobile robots,although some important research results have been obtained,there is still a lack of theoretical research.The related technologies in solving practical problems need to be improved.In the global path planning,the path optimization algorithm is the core of path planning,so how to improve the planning algorithm has been one of the hot topics in the research.As the pheromone accumulates,the ant colony optimization possesses the positive feedback characteristic,which makes the algorithm converge more quickly towards the optimal solution and can search more points in the solution space.Its robustness and searching ability are better than other algorithms.In the genetic algorithm,the individuals in the population continuously carry out genetic operations,so that the individuals in the population continue to evolve toward the global optimal solution,covering a relatively large area in the search space and having the ability of concurrent search.In this paper,we combine the advantages of the two algorithms,propose two algorithms to integrate the improved strategy,and successfully apply the improved algorithm to the global path planning of mobile robots.(1)In this paper,we propose to use genetic algorithm to search the path search,and find the optimal part of the search algorithm as the value of the initial pheromone of the ant colony optimization to make up for the ant colony optimization in the initial stage of the algorithm search pheromone Lack of deficiency(2)In this paper,a strategy is proposed to mix and update the global optimal path and the current iterative optimal path when the ant colony optimization pheromone is updated,and an ant colony bidirectional search scheme is proposed in order to improve and improve the searching speed of the algorithm.(3)In the path search of ant colony optimization,this paper proposes to cross-interchange the global optimal path with the intersection point and the optimal path of the current iterative search through the cross-operation of the simulated genetic algorithm The optimalpath to speed up the search speed of ant colony optimization.In the end,this paper verifies the improved fusion algorithm by Matlab simulation.By setting up three grid maps representing different environments,this algorithm is compared with the two algorithms of the basic genetic algorithm and the maximum and minimum ant colony system.The results show that the improved algorithm is effective.It proves that the improved algorithm is better than the other three algorithms in the speed and quality of path optimization.The TurtleBot mobile robot is used for physical verification.The improved fusion algorithm,the basic genetic algorithm and the maximum and minimum ant colony system are applied to the TurtleBot mobile robot respectively.The results show that the improved fusion algorithm is better than the unmodified algorithm.