Scholarlink

<p>The pursuit-evasion game is a current research hotspot in the field of intelligent swarm robotics. Existing solutions often rely on unrealistic assumptions, such as fully known environmental information, complete communication capabilities between pursuers, and centralized coordination systems. Moreover, these methods mostly overlook the search process of the evader. To address these challenges, we propose a self-organizing pursuit strategy in an unknown environment. This strategy divides the evader search and capture task into two stages: In the search stage, various pheromone-based improvements to the inverse ant colony algorithm are introduced to assist the pursuers in collaborative environmental exploration. In the pursuit stage, the integration of the improved A* algorithm and the improved APF enables online path planning in complex dynamic environments, significantly improving the pursuit efficiency. Simulation results show that the proposed algorithm outperforms traditional methods in terms of performance.</p>

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

Self-organizing pursuit strategy in an unknown environment

  • 期刊论文

  • 发表日期：

    2025年8月19日

查看全文
  • Ruizhen Gao,
  • Yubo Wang,
  • Xiaofan Bai,
  • Zhilong Zhu

摘要

The pursuit-evasion game is a current research hotspot in the field of intelligent swarm robotics. Existing solutions often rely on unrealistic assumptions, such as fully known environmental information, complete communication capabilities between pursuers, and centralized coordination systems. Moreover, these methods mostly overlook the search process of the evader. To address these challenges, we propose a self-organizing pursuit strategy in an unknown environment. This strategy divides the evader search and capture task into two stages: In the search stage, various pheromone-based improvements to the inverse ant colony algorithm are introduced to assist the pursuers in collaborative environmental exploration. In the pursuit stage, the integration of the improved A* algorithm and the improved APF enables online path planning in complex dynamic environments, significantly improving the pursuit efficiency. Simulation results show that the proposed algorithm outperforms traditional methods in terms of performance.