Scholarlink

<p>Path planning is essential for an autonomous underwater vehicle (AUV) to efficiently perform underwater missions. To address the challenges of energy-efficient three-dimensional path planning under multiple constraints, this study proposes a synergistic differential evolution (SDE) algorithm. First, a comprehensive underwater environment model is developed, including a path encoding model and a deterministic pathevaluation method. Second, a synergistic evolution mechanism is introduced to improve global exploration by adaptively sharing the evolutionary information of two synergistic populations. Third, evolutionary guidance is proposed to refine the search direction by integrating successful population movements based on fitness improvements and positional correlations. Finally, a cosine-based strategy is employed to adjust the population size by eliminating low-quality solutions. Compared to state-of-the-art methods, the proposed algorithm achieves average improvements of 2.37% in best fitness, 15.99% in mean fitness, 13.42% in median fitness, 80.69% in standard deviation, 66.65% in convergence quality, and 39.91% in runtime. In addition, AUV field tests further validate the feasibility and reliability of the SDE-based pathplanning approach.</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

Energy-Efficient AUV Path Planning Under Multiple Constraints Using a Synergistic Differential Evolution Algorithm

  • 期刊论文

  • 发表日期：

    2025年12月3日

查看全文
  • Jiehui Tan,
  • Yushan Sun,
  • Kaiqian Cai,
  • Yinghao Zhang,
  • Liwen Zhang

摘要

Path planning is essential for an autonomous underwater vehicle (AUV) to efficiently perform underwater missions. To address the challenges of energy-efficient three-dimensional path planning under multiple constraints, this study proposes a synergistic differential evolution (SDE) algorithm. First, a comprehensive underwater environment model is developed, including a path encoding model and a deterministic pathevaluation method. Second, a synergistic evolution mechanism is introduced to improve global exploration by adaptively sharing the evolutionary information of two synergistic populations. Third, evolutionary guidance is proposed to refine the search direction by integrating successful population movements based on fitness improvements and positional correlations. Finally, a cosine-based strategy is employed to adjust the population size by eliminating low-quality solutions. Compared to state-of-the-art methods, the proposed algorithm achieves average improvements of 2.37% in best fitness, 15.99% in mean fitness, 13.42% in median fitness, 80.69% in standard deviation, 66.65% in convergence quality, and 39.91% in runtime. In addition, AUV field tests further validate the feasibility and reliability of the SDE-based pathplanning approach.