系统工程与电子技术 ›› 2025, Vol. 47 ›› Issue (11): 3708-3720.doi: 10.12305/j.issn.1001-506X.2025.11.19

• 系统工程 • 上一篇    

基于聚类优化算法的多无人艇协同任务规划

余文瞾1,2,3,4, 乔靖超1,2, 杜哲1,2,*(), 邢著楷5, 万芯源2   

  1. 1. 武汉理工大学高性能船舶技术教育部重点实验室,湖北 武汉 430062
    2. 武汉理工大学船海与能源动力工程学院,湖北 武汉 430062
    3. 新加坡国立大学工业系统工程与管理系下一代港口建模与仿真卓越中心,新加坡市 119077
    4. 武汉理工大学三亚科教创新园,海南 三亚 572000
    5. 大连理工大学船舶工程学院,辽宁 大连 116024
  • 收稿日期:2025-04-30 出版日期:2025-11-25 发布日期:2025-12-08
  • 通讯作者: 杜哲 E-mail:duzhe@whut.edu.cn
  • 作者简介:余文瞾(1989—),男,副研究员,博士,主要研究方向为海洋多智能体航行与协同控制、无人系统智能容错控制、智能船舶航行运动控制、船舶动力定位控制系统
    乔靖超(2001—),男,硕士研究生,主要研究方向为无人系统协同决策与路径规划
    邢著楷(2002—),男,硕士研究生,主要研究方向为无人系统路径规划与航迹预测
    万芯源(2001—),男,主要研究方向为无人系统路径规划
  • 基金资助:
    国家自然科学基金(52201373);中国国家留学基金青年骨干教师出国研修项目(202306950131);国家大学生创新创业训练计划(S202310497067);中央高校基本科研业务费专项资金(WUT: 2024IVA018)资助课题

Multi-USV cooperative task planning based on clustering optimization algorithm

Wenzhao YU1,2,3,4, Jingchao QIAO1,2, Zhe DU1,2,*(), Zhukai XING5, Xinyuan WAN2   

  1. 1. Key Laboratory of High Performance Ship Technology of Ministry of Education,Wuhan University of Technology,Wuhan 430062,China
    2. School of Naval Architecture,Ocean and Energy Power Engineering,Wuhan University of Technology,Wuhan 430062,China
    3. Centre of Excellence in Modelling and Simulation for Next Generation Ports,Department of Industrial Systems Engineering and Management,National University of Singapore,Singapore City 119077,Singapore
    4. Sanya Science and Education Innovation Park,Wuhan University of Technology,Sanya 572000,China
    5. School of Ship Engineering,Dalian University of Technology,Dalian 116024,China
  • Received:2025-04-30 Online:2025-11-25 Published:2025-12-08
  • Contact: Zhe DU E-mail:duzhe@whut.edu.cn

摘要:

针对多无人艇(unmanned surface vessel, USV)集群协同任务分配及安全路径规划问题,面向USV设计运动转艏约束条件与评价指标,提出基于密度的噪声应用空间聚类(density-based spatial clustering of applications with noise, DBSCAN)的改进分工蚁群任务分配算法。路径规划方面,先应用改进人工势场(artificial potential field, APF)法,后考虑USV操纵约束,通过三次Hermite曲线与USV操纵模型约束其航速与切向量。仿真实验表明,在搜索角约束下,3艘USV能够比较有效地减少转向,预设路径无交叉碰撞;三次Hermite曲线优化后的路径能够避开障碍物,且使USV艏向角变化趋于平缓,满足其运动约束。因此,所提方法能够给出更符合USV操纵特性的分配与规划方案。

关键词: 多无人艇任务分配, 路径规划, 基于密度的噪声应用空间聚类, 蚁群优化算法, 三次Hermite曲线

Abstract:

Aiming at the problem of collaborative task allocation and safe path planning for unmanned surface vessel (USV) cluster, an improved ant colony task allocation algorithm based on density-based spatial clustering of applications with noise (DBSCAN) is proposed to design motion turning constraints and evaluation indicators for USVs. In terms of path planning, the improved artificial potential field (APF) method is applied firstly, followed by consideration of USV manipulation constraints. The ship speed and tangent vector are constrained through a cubic Hermite curve and USV manipulation model. Simulation experiments show that in the constraint of search angle, three USVs can effectively reduce turning and have no cross collision on the preset path. The path optimized by the cubic Hermite curve can avoid obstacles and make the USV bow angle change tend to be gentle, satisfying its motion constraints. Therefore, the proposed method can provide allocation and planning schemes that are more in line with the maneuverability of USVs.

Key words: multi-unmanned surface vessel (USV) task allocation, path planning, density-based spatial clustering of applications with noise (DBSCAN), ant colony optimization (ACO) algorithm, cubic Hermite curve

中图分类号: