基于改进蚁群算法的 AGV 路径规划研究

针对传统蚁群算法在自动导引车(automated guided vehicle, AGV)路径规划研究中存在收敛速度慢、搜索能力差以及容易陷入局部最优等问题,文章提出一种改进蚁群算法。引入自适应启发式函数,增加蚁群寻优方向性;改进信息素更新策略,避免陷入局部最优解;动态调整信息素挥发系数,使其随着迭代时期而减小,从而提高算法搜索效率、加快算法收敛速度。仿真实验结果表明,相较于其他算法,在相同环境下文章所提改进蚁群算法具有较好的收敛性和较高的寻优能力。

This paper proposes an improved ant colony algorithm to address the problems of slow convergence, poor search capability and the tendency to fall into local optimum solutions in the traditional ant colony algorithm for automated guided vehicle (AGV) path planning. The paper introduces an adaptive heuristic function to increase the directionality of the ant colony search, improves the pheromone update strategy to avoid falling into local optimal solutions, and dynamically adjusts the pheromone volatility coefficient to decrease with the iteration period, so as to improve the search efficiency and accelerate the convergence speed of the algorithm. The simulation results show that the algorithm has better convergence and search ability compared with other algorithms in the same environment.