无人机集群协同免疫自学习围捕策略研究  

Cooperative hunting strategy of UAV swarm based on immune self-learning

作　　者：孙红燕 周洁 陈超波[1] 高嵩[1] 赵素平 Sun Hongyan;Zhou Jie;Chen Chaobo;Gao Song;Zhao Suping(School of Electronics and Information Engineering,Xi’an Technological University,Xi’an 710021,China)

机构地区：[1]西安工业大学电子信息工程学院,西安710021

出　　处：《战术导弹技术》2023年第1期132-142,共11页Tactical Missile Technology

基　　金：陕西省技术创新引导专项(基金)计划项目(2022QFY01-16);陕西省科技厅基金(2022GY-236)。

摘　　要：针对非合作逃逸目标的围捕问题,提出了基于改进免疫自学习的协同策略。通过生物免疫系统机理与无人机集群协同围捕决策的映射关系,建立免疫自学习模型。仿照免疫应答的克隆选择、免疫记忆的过程,提出基于记忆总结、评价调节、学习进化的协同围捕算法CHS-IMEL。设计了综合围捕点分配与围捕无人机状态的抗体编码方式,构建包含围捕路径和包围效果的亲和度函数,迭代优化获得无人机的最佳航向角。仿真结果表明,在随机初始态势下,无人机集群能够利用所提策略通过协作实现对以不同策略逃逸的目标的围捕,且任务完成率最高提高11%,围捕成功时间减少了10.7%,证明了所提策略的有效性与优越性。Aiming at the hunting problem of non-cooperative escape targets,a cooperative strategy based on immune self-learning is proposed.Through the mapping relationship between the mechanism of the biological immune system and the cooperative hunting decision of UAV swarm,an immune self-learning model is established.Imitating the process of clonal selection and immune memory of immune response,a cooperative hunting algorithm CHS-IMEL (Cooperative Hunting Strategy Based on Immune Memory Summary-Evaluation Regulation-Learning Evolution) is proposed.The antibody coding method which integrates the distribution of hunting points and the state of the hunting UAVs is designed,the affinity function including the capture path and the encirclement effect is constructed,and the optimal heading angles of the hunting UAVs are obtained by iterative optimization.The simulation results show that under the random initial situation,the UAV swarm can make use of the proposed strategy to achieve the hunting of the targets escaped from different strategies,and the task completion rate increases by up to 11%,and the hunting completion time decreases by 10.7%.The effectiveness and superiority of the proposed strategy are proven.

关 键 词：协同围捕策略 免疫学习 无人机集群系统 非合作目标 逃逸策略 Apollonius圆 围捕点 

分 类 号：V279[航空宇航科学与技术—飞行器设计]