计算机工程与应用 ›› 2022, Vol. 58 ›› Issue (5): 287-295.DOI: 10.3778/j.issn.1002-8331.2108-0211

• 工程与应用 • 上一篇    下一篇

改进蚁群算法的移动机器人路径规划

唐旭晖,辛绍杰   

  1. 上海电机学院 机械学院,上海 201306
  • 出版日期:2022-03-01 发布日期:2022-03-01

Improved Ant Colony Algorithm for Mobile Robot Path Planning

TANG Xuhui, XIN Shaojie   

  1. College of Mechanical, Shanghai Dianji University, Shanghai 201306, China
  • Online:2022-03-01 Published:2022-03-01

摘要: 针对传统蚁群算法在路径规划中存在易陷入局部最优与收敛速度慢等问题,提出一种改进的蚁群算法。采用初始信息素差异化分布策略,增强目标点导向区的初始信息素浓度;基于回退策略与禁忌搜索结合分块优化,利用叉积运算进行局部折点优化;引入信息素自调节加强因子,改进信息素浓度更新公式;引入随机状态转移参数,增强全局搜索能力;将改进算法在多种地图环境下与传统蚁群算法、樽海鞘群算法进行比较,仿真结果证明了改进算法拥有较好的收敛性与稳定性。

关键词: 蚁群算法, 路径规划, 差异化分布策略, 叉积运算, 自调节加强因子, 随机状态转移参数

Abstract: An improved ant colony algorithm is proposed to address the problems of the traditional ant colony algorithm in path planning, such as the tendency to fall into local optimum and slow convergence speed. The initial pheromone concentration in the target point guidance area is enhanced by adopting the initial pheromone differential distribution strategy. The local fold optimization is carried out by using the fork product operation based on the backoff strategy and taboo search combined with chunking optimization. The pheromone self-adjustment enhancement factor is introduced to improve the pheromone concentration update formula. The random state transfer parameter is introduced to enhance the global search capability. The improved algorithm is compared with the traditional ant colony algorithm and the salp swarm algorithm in a variety of map environments. The simulation results prove that the improved algorithm has better convergence and stability in path planning.

Key words: ant colony algorithm, path planning, differential distribution strategy, fork product operation, self-adjustment enhancement factor, random state transfer parameter