Scholarlink

<p>This study proposes a three-dimensional path planning method for UAV swarms using the Multi-Strategy Improved Crested Porcupine Optimizer (ICPO), designed to enable UAVs to more effectively avoid obstacles and optimize flight paths. This study integrates tent mapping with the reverse refraction learning strategy to enhance the diversity of the algorithm’s population. Inspired by animal escape behavior, the first defense strategy is replaced with a moving escape strategy to expand the global search. The fourth defense strategy is improved using a Cauchy distribution, making the probability distribution independent of the global optimal solution, thereby rendering the search process independent and flexible while reducing computational complexity. To avoid getting stuck in local optima later in the process, a Cauchy-Gaussian mutation strategy was introduced, enabling the algorithm to better escape local optima. Simulations were conducted on the 2005 and 2022 test sets, and the results demonstrated that ICPO exhibits superior robustness and stability. In 3D terrain simulations, the ICPO algorithm proved its effectiveness in path planning.</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

Multi-Strategy optimisation algorithm for multi-UAV path planning in complex mountainous environments

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月1日

查看全文
  • Xinrong Zhang,
  • Zhe Cheng,
  • Zhicong Zheng

摘要

This study proposes a three-dimensional path planning method for UAV swarms using the Multi-Strategy Improved Crested Porcupine Optimizer (ICPO), designed to enable UAVs to more effectively avoid obstacles and optimize flight paths. This study integrates tent mapping with the reverse refraction learning strategy to enhance the diversity of the algorithm’s population. Inspired by animal escape behavior, the first defense strategy is replaced with a moving escape strategy to expand the global search. The fourth defense strategy is improved using a Cauchy distribution, making the probability distribution independent of the global optimal solution, thereby rendering the search process independent and flexible while reducing computational complexity. To avoid getting stuck in local optima later in the process, a Cauchy-Gaussian mutation strategy was introduced, enabling the algorithm to better escape local optima. Simulations were conducted on the 2005 and 2022 test sets, and the results demonstrated that ICPO exhibits superior robustness and stability. In 3D terrain simulations, the ICPO algorithm proved its effectiveness in path planning.