自主水下航行器群探测行为关键技术分析  

Analysis on key technologies of collective detection behavior by autonomous underwater vehicles

作　　者：余敏 刘浩煜 张文凯 汤奇荣[1] YU Min;LIU Haoyu;ZHANG Wenkai;TANG Qirong(Laboratory of Robotics and Multibody System,School of Mechanical Engineering,Tongji University,Shanghai 201804,China)

机构地区：[1]同济大学机械与能源工程学院机器人技术与多体系统实验室,上海201804

出　　处：《舰船科学技术》2025年第3期111-116,共6页Ship Science and Technology

基　　金：国家自然科学基金项目(62373285);上海市产业协同创新项目(产业发展类,HCXBCY-2022-051);机器人技术与系统全国重点实验室开放基金(SKLRS-2024-KF-04);某部基础科研计划项目(XXXX2022YYYC133)。

摘　　要：自主水下航行器协同技术发展需求日益迫切,研究多航行器协同探测技术能够提高未知海洋环境下作业效率、避免人员生命安全问题,在海洋资源探测、海洋搜救等应用中发挥着重要作用。在复杂未知水下环境中,通过多航行器协同行为实现对特定目标物的高效探测是一项巨大挑战。对水下群探测行为的关键技术进行研究,分析了基于图论、仿生模型、动力学模型和学习模型的水下群探测行为建模方法,分析了有组织和自组织群行为规划方法,分析了动力学模型、数据驱动的群体协同控制方法。研究结果表明,探测信息沟联的水下群体交互、可解释性强的学习类协同探测行为策略、动力学模型与数据相结合的行为控制方法是未来水下群探测行为技术的重要发展趋势。Collective autonomous underwater vehicle(AUV)technology is in sore need.Researches on collective AUV technology can improve the operation efficiency of unknow ocean environment and avoid the human safety problem,which plays a significant role in applications such as ocean resource exploration and ocean search and rescue.High-efficient detec-tion of specific targets via collective behavior of multi-AUV is a great challenge under the unknown,complex underwater en-vironment.Key technologies on the underwater collective detecting behavior are studied,in which topological,biological,dynamical,and learning-based modelling methods,organized and self-organized collective behavior planning methods,as well as model and data-driven collaborative control methods are analyzed.Analysis results indicates that underwater collect-ive interaction linked with detecting information,collective detecting behavior strategy via strong interpretable learning method,and behavior control combining dynamic models and data are important developing trends.

关 键 词：群体智能 水下机器人 行为规划与控制 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置]