Research On Path Planning Of Mobile Robot Based On Improved Ant Colony Algorithm

With the continuous development of technologies such as artificial intelligence and machine learning,mobile robots have become intelligent systems that can handle various complex tasks,and their ability to navigate autonomously in complex environments has become increasingly important.Compared with other swarm intelligence optimization algorithms,the ant colony algorithm is often used to deal with complex path planning problems because of its robustness,simplicity and ease of implementation.But the ant colony algorithm itself has certain problems,so this paper proposes an improved ant colony algorithm and pelican optimization algorithm fusion model to make up for the defects of the ant colony algorithm.The main content of the paper is as follows:(1)This paper proposes an adaptive ant colony algorithm.First,the visibility of the current node is enhanced,and a scaling factor is introduced to adaptively control the influence degree of searching the heuristic information function value in each period.Secondly,the search state of the algorithm is dynamically adjusted using pseudo-random state transition rules.Finally,the global optimal path of each iteration is used as the heuristic path for the next search,and the moving direction of the robot is no longer limited to its adjacent free grids,making the generated path smoother and shorter.The simulation experiment proves that the improved ant colony algorithm can plan a more excellent path.(2)This paper first improves the performance of the Pelican optimization algorithm,and then integrates it with the improved ant colony algorithm.First,introduce the balance pool strategy in the EO algorithm,make full use of the high-quality solutions in the algorithm,and improve the instability caused by the random selection of individuals by the Pelican optimization algorithm.Secondly,a nonlinear inertia factor is introduced to balance the global search ability and local search ability of each stage of the algorithm.Finally,the t-distribution adaptive perturbation strategy is used to update the population position to enhance the ability of the algorithm to jump out of the local optimal solution.In order to verify the performance of the improved Pelican optimization algorithm,10 unimodal and multimodal functions were selected for testing and comparison experiments.The results show that the improved Pelican algorithm has greatly improved the optimization ability and convergence speed.(3)The improved ant colony algorithm is relatively blind in its early search and incorporates the improved Pelican optimization algorithm to further enhance the effectiveness of the ant colony algorithm.First,the improved Pelican algorithm is used to generate a suboptimal path,according to which the initial pheromone concentration distribution of the ant colony algorithm is updated to guide the initial search of the ant colony,and the path is used as the heuristic path of the first search of the ant colony to achieve multi-step movement.Secondly,the improved ant colony algorithm is used to complete the secondary path planning.Finally,the superiority of the fusion algorithm was verified through simulation experiments.