Research on Path Planning for Mobile Robots Based on Optimized Ant Colony Algorithm

To address the issues of traditional Ant Colony Optimization (ACO) in mobile robot path planning, such as blind searching, slow convergence, and susceptibility to local optima, an improved ACO algorithm is proposed. The improvement mainly focuses on the most critical part of the ACO algorithm—state transition rules. A pseudo-random state transition rule is adopted for path selection, and a dynamic selection factor is defined to update the selection ratio. Additionally, an adaptive weight factor is introduced to adjust the selection probability. Furthermore, different initial pheromone concentrations are assigned based on heuristic information to avoid blind searching in the early stage. The pheromone evaporation factor is then adaptively adjusted to enhance global optimization capability while improving convergence speed. Comparative simulation experiments are conducted on different two-dimensional static grid maps. Experimental verification demonstrates that the enhanced ACO method attains accelerated convergence rates, significantly enhances search efficiency, and exhibits better global search capability, verifying the practicality and superiority of the proposed algorithm.