Application of Improved Ant Colony Algorithm in the Path Planning Problem of Mobile Robot

In this study, we present an advanced approach to global path planning for mobile robots, grounded in the refinement of the ant colony algorithm. The conventional implementation of this algorithm often encounters the “stalemate” issue and struggles to attain the globally optimal solution. By strategically modifying the transition probabilities of ants within the traditional framework, we mitigate the frequency of “stalemate” occurrences. Furthermore, we incorporate the roulette wheel selection methodology from genetic algorithms, thereby circumventing the tendency towards local optimization inherent in the ant colony algorithm. Through rigorous simulation experiments, we have optimized and identified the most suitable parameter combination for the refined ant colony algorithm, enhancing its applicability and performance. Finally, it proves that the improved ant colony algorithm can greatly improve the path planning efficiency through Matlab2016b.