基于ROC理论的多UUV协同探雷任务分配方法研究  

Study on Task Assignment of Multi-UUV Coordination Mine Detection Based on ROC Theory

作　　者：范学满 刘星璇 薛昌友[1] FAN Xueman;LIU Xingxuan;XUE Changyou(Navy Submarine Academy,Qingdao 266199,China)

机构地区：[1]海军潜艇学院,山东青岛266199

出　　处：《火力与指挥控制》2022年第11期64-70,共7页Fire Control & Command Control

摘　　要：时间受限条件下,传统计划搜索和随机搜索模式难以满足多UUV协同探查水雷任务的效率需求。针对多UUV协同探雷的任务分配问题,为了充分利用各UUV的探测资源,在尽可能短的时间内获得尽可能精确的水雷分布概率图,提出一种基于ROC理论的最小权重算法。该算法通过优化搜索通道、引入变深惩罚项以及考虑距离代价等措施,提高了算法的鲁棒性和环境适应能力。进行了仿真验证和算法性能对比分析。Under time constraints,the traditional planned search and random search modes are difficult to meet the efficiency requirements of multiple unmanned underwater vehicle(multi-UUV)coordination mine detection task. Aiming at the task allocation problem of multi UUV coordination mine detection,in order to make full use of the detection resources of each UUV and to obtain the mine distribution probability map as accurate as possible in the shortest possible time,a minimum weight algorithm based on ROC theory is proposed. By optimizing the search channel,introducing the variable depth penalty term and considering the distance cost and other measures,the algorithm improves the robustness and environmental adaptability of the algorithm. Finally,the simulation verification and the performance comparison of the algorithm are carried out.

关 键 词：多无人潜航器 探查水雷 任务分配 ROC曲线 信息增益 

分 类 号：TJ61[兵器科学与技术—武器系统与运用工程]