Scholarlink

Automated Guided Vehicles (AGVs) play an irreplaceable role in intelligent production workshops. This paper proposes a method that combines the improved ACO algorithm with the improved DWA algorithm, namely IACO-DWA. Addressing the limitations of the traditional ant colony algorithm, this paper uses a pheromone map based on obstacle density as the initial pheromone distribution, adds distance heuristic factors and direction heuristic factors to the heuristic function, and adopts a hierarchical pheromone update strategy to generate a global planning path for the improved DWA algorithm. The speed evaluation function of the traditional DWA is improved, and a target deviation evaluation is added, enhancing the smooth operation of AGV vehicles while dynamically avoiding obstacles. This paper aims to improve the efficiency and accuracy of AGV vehicle path planning by combining the ACO and DWA algorithms. The effectiveness of the proposed algorithm is verified through comparative experiments, and the proposed algorithm is applied to intelligent production processes.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Research on Single-Agent Path Planning Based on the Improved ACO-DWA Algorithm

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Zeyu Zhang,
  • Xuezhi Wen,
  • Yihang Ma,
  • Yefeng Liu

摘要

Automated Guided Vehicles (AGVs) play an irreplaceable role in intelligent production workshops. This paper proposes a method that combines the improved ACO algorithm with the improved DWA algorithm, namely IACO-DWA. Addressing the limitations of the traditional ant colony algorithm, this paper uses a pheromone map based on obstacle density as the initial pheromone distribution, adds distance heuristic factors and direction heuristic factors to the heuristic function, and adopts a hierarchical pheromone update strategy to generate a global planning path for the improved DWA algorithm. The speed evaluation function of the traditional DWA is improved, and a target deviation evaluation is added, enhancing the smooth operation of AGV vehicles while dynamically avoiding obstacles. This paper aims to improve the efficiency and accuracy of AGV vehicle path planning by combining the ACO and DWA algorithms. The effectiveness of the proposed algorithm is verified through comparative experiments, and the proposed algorithm is applied to intelligent production processes.