Scholarlink

<p>To solve the path planning problem of multi-UAVs, the improved whale optimization algorithm based on Pareto strategy (IMOAP) is proposed in this paper. In order to optimize multiple objective functions at the same time, Pareto selection strategy is introduced to solve the “data explosion” problem in the multi-objective state, and Pareto ranking strategy is designed to achieve the finiteness and feasibility of the solution and ensure the population quantity. This paper constructs a synergy factor based on the fitness design value to improve the population diversity, convergence speed and accuracy of the algorithm, and the overall performance. Then, through convergence and complexity analysis, the feasibility and stability of the improved algorithm are proved. In addition, the Reynolds model of ground-to-air communication is used to realize the coordinated movement of UAV clusters. Across three path planning scenarios of varying complexity, compared with the baseline WOA, the proposed IWOAP algorithm achieved up to 50% shorter planning time, 55–65% lower energy consumption, and significantly improved convergence speed, while maintaining zero collisions across all three path planning scenarios, demonstrating superior stability, efficiency, and adaptability in complex environments.</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

Improved whale optimization path planning design for multi-UAVs based on Pareto strategy

  • 期刊论文

  • 发表日期：

    2025年12月1日

查看全文
  • Lingyu Cheng,
  • Fang Wang,
  • Chao Zhou

摘要

To solve the path planning problem of multi-UAVs, the improved whale optimization algorithm based on Pareto strategy (IMOAP) is proposed in this paper. In order to optimize multiple objective functions at the same time, Pareto selection strategy is introduced to solve the “data explosion” problem in the multi-objective state, and Pareto ranking strategy is designed to achieve the finiteness and feasibility of the solution and ensure the population quantity. This paper constructs a synergy factor based on the fitness design value to improve the population diversity, convergence speed and accuracy of the algorithm, and the overall performance. Then, through convergence and complexity analysis, the feasibility and stability of the improved algorithm are proved. In addition, the Reynolds model of ground-to-air communication is used to realize the coordinated movement of UAV clusters. Across three path planning scenarios of varying complexity, compared with the baseline WOA, the proposed IWOAP algorithm achieved up to 50% shorter planning time, 55–65% lower energy consumption, and significantly improved convergence speed, while maintaining zero collisions across all three path planning scenarios, demonstrating superior stability, efficiency, and adaptability in complex environments.