An A-guided Improved Ant Colony Optimization Algorithm for Mobile Robot Path Planning

To address the problems of slow convergence and susceptibility to local optima in traditional ant colony optimization (ACO) algorithms for global path planning of mobile robots, this paper proposes an improved ACO algorithm with three core methodological innovations: A*-guided differentiated pheromone initialization, a bidirectional A*-style heuristic factor, and strict line-of-sight (SLOS) path smoothing post-processing. Specifically, the proposed algorithm incorporates the A* algorithm to generate a prior path for targeted pheromone initialization, designs a bidirectional heuristic factor to strengthen global search guidance, and introduces a strict line-of-sight smoothing strategy to shorten the path while ensuring collision avoidance. Through simulation experiments on 20×20 and 30×30 grid maps, with the traditional ant colony algorithm as a benchmark for comparison, the results demonstrate that: the improved algorithm achieves an average runtime of only 0.67 seconds on the 20×20 map, representing a reduction of over 73.6% compared to the traditional algorithm; the average number of iterations decreases to 5.23, and the average path length is optimized to 29.36. The algorithm also maintains excellent performance on the 30×30 grid map with more complex environmental settings. This study validates that the proposed improvement strategies can significantly enhance the convergence speed, solution quality, and real-time performance of path planning. The proposed algorithm demonstrates broad practical applicability in mobile robot navigation. It provides an efficient and reliable path planning solution for intelligent robots deployed in intelligent manufacturing, autonomous warehouse handling, and unmanned patrol exploration.