Scholarlink

<p>When AUV is tasked with planning paths in irregular regions with obstacles, it faces challenges such as low coverage, failure to avoid obstacles, and high energy consumption from redundant paths. This study proposed Spider Monkey Optimization Based on Repulsive Field (RF-SMO) to address these issues. Firstly, an obstacle influence factor is proposed to guide the AUV in avoiding obstacles. Secondly, an inertia weight factor is introduced, and an adaptive step size is utilized instead of a random step size, expanding the solution space and enhancing search capability. The theory proves that the RF-SMO algorithm converges rapidly compared to the SMO algorithm. Finally, simulation results indicate that RF-SMO plans less full-coverage path length than the OA-SMT and IBINN algorithms while minimizing energy consumption. Under five different region shapes, RF-SMO significantly improves both coverage and the success rate of obstacle avoidance compared to the OA-SMT and IBINN algorithms.</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

Full-coverage obstacle avoidance path planning based on RF-SMO for AUV in irregular regions

  • 期刊论文

  • 发表日期：

    2025年9月19日

查看全文
  • Jiaxing Chen,
  • Xiaoqian Liu,
  • Jiaqi Liu,
  • Mengnan Hao,
  • Zhihua Liu

摘要

When AUV is tasked with planning paths in irregular regions with obstacles, it faces challenges such as low coverage, failure to avoid obstacles, and high energy consumption from redundant paths. This study proposed Spider Monkey Optimization Based on Repulsive Field (RF-SMO) to address these issues. Firstly, an obstacle influence factor is proposed to guide the AUV in avoiding obstacles. Secondly, an inertia weight factor is introduced, and an adaptive step size is utilized instead of a random step size, expanding the solution space and enhancing search capability. The theory proves that the RF-SMO algorithm converges rapidly compared to the SMO algorithm. Finally, simulation results indicate that RF-SMO plans less full-coverage path length than the OA-SMT and IBINN algorithms while minimizing energy consumption. Under five different region shapes, RF-SMO significantly improves both coverage and the success rate of obstacle avoidance compared to the OA-SMT and IBINN algorithms.