Scholarlink

<p>The goal of the path planning challenge is to assist the UAV in delineating a flight trajectory that minimizes overall overhead costs. This paper proposed a multi-strategy enhanced gorilla troops optimizer (MSIGTO). First, the integration of a gorilla memory mechanism enhances the quality of the population and improves the algorithm's exploitation capabilities by emulating the memory dynamics observed in gorillas. This process involved a meticulous comparison of current and previous positional data. Second, a differential evolution strategy is employed to prevent the algorithm from prematurely converging, addressing its tendency to settle on local optima. To validate the efficacy of the proposed MSIGTO, comparative analyses against a suite of 13 well-known metaheuristic algorithms, six CEC2022 benchmark functions is tested, the Wilcoxon rank-sum test’s significance threshold was established at 5%, if the p-value is less than 0.05. Friedman mean rank test findings with a 95% confidence level. The proposed MSIGTO algorithm is rank first. Finally, the proposed MSIGTO algorithm is applied to solve the 3D unmanned aerial vehicle (UAV) path planning problem. The experimental results show that the proposed algorithm can obtain shorter paths.</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 gorilla troops optimizer for global optimization and 3D UAV path planning

  • 期刊论文

  • 发表日期：

    2025年9月15日

查看全文
  • Yongquan Zhou,
  • Hongji Huang,
  • Yuanfei Wei,
  • Qifang Luo

摘要

The goal of the path planning challenge is to assist the UAV in delineating a flight trajectory that minimizes overall overhead costs. This paper proposed a multi-strategy enhanced gorilla troops optimizer (MSIGTO). First, the integration of a gorilla memory mechanism enhances the quality of the population and improves the algorithm's exploitation capabilities by emulating the memory dynamics observed in gorillas. This process involved a meticulous comparison of current and previous positional data. Second, a differential evolution strategy is employed to prevent the algorithm from prematurely converging, addressing its tendency to settle on local optima. To validate the efficacy of the proposed MSIGTO, comparative analyses against a suite of 13 well-known metaheuristic algorithms, six CEC2022 benchmark functions is tested, the Wilcoxon rank-sum test’s significance threshold was established at 5%, if the p-value is less than 0.05. Friedman mean rank test findings with a 95% confidence level. The proposed MSIGTO algorithm is rank first. Finally, the proposed MSIGTO algorithm is applied to solve the 3D unmanned aerial vehicle (UAV) path planning problem. The experimental results show that the proposed algorithm can obtain shorter paths.