Scholarlink

<p>An Iterative Improved Salp Swarm Algorithm (IISSA) is proposed for solving the problem of poor stability and unsatisfactory optimization results in AUV global path planning. Firstly, in the population initialization stage, Tent chaotic mapping is introduced to enhance the diversity of the population, and theoretical evidence shows that this method can make the population closer to the optimal solution faster. Secondly, In the optimization phase, an iteratively improved leader structure is proposed, a leader iterative increase function is constructed, and the exploration and development capabilities of the algorithm are balanced by dynamically controlling the number of leaders. Again, an upper bound on the number of leaders is theoretically derived and the convergence of the IISSA algorithm is proved. Finally, an improved fitness function is proposed to model the marine environment using the raster method with coordinate transformation to apply IISSA to AUV global path planning. The simulation results show that compared with other intelligent bionic algorithms, IISSA has better optimization capabilities, better stability, and stronger robustness, and its path planning effect is more obvious when facing complex ocean environments. Compared with the comparison algorithm planning, the average path lengths are reduced by 44.2%, 47.5%, and 29.3% respectively.</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

Global path panning for AUV based on chaos mapping and iterative improved salp swarm algorithm

  • 期刊论文

  • 发表日期：

    2025年8月30日

查看全文
  • Zhaoye Chen,
  • Jiaqi Liu,
  • Lu Ding,
  • Zhihua Liu

摘要

An Iterative Improved Salp Swarm Algorithm (IISSA) is proposed for solving the problem of poor stability and unsatisfactory optimization results in AUV global path planning. Firstly, in the population initialization stage, Tent chaotic mapping is introduced to enhance the diversity of the population, and theoretical evidence shows that this method can make the population closer to the optimal solution faster. Secondly, In the optimization phase, an iteratively improved leader structure is proposed, a leader iterative increase function is constructed, and the exploration and development capabilities of the algorithm are balanced by dynamically controlling the number of leaders. Again, an upper bound on the number of leaders is theoretically derived and the convergence of the IISSA algorithm is proved. Finally, an improved fitness function is proposed to model the marine environment using the raster method with coordinate transformation to apply IISSA to AUV global path planning. The simulation results show that compared with other intelligent bionic algorithms, IISSA has better optimization capabilities, better stability, and stronger robustness, and its path planning effect is more obvious when facing complex ocean environments. Compared with the comparison algorithm planning, the average path lengths are reduced by 44.2%, 47.5%, and 29.3% respectively.