现代信息科技2025，Vol.9Issue(19)：43-48,56,7.DOI:10.19850/j.cnki.2096-4706.2025.19.009
复杂环境下无人机集群的协同控制研究
Research on Cooperative Control of UAV Cluster for Complex Environment
摘要
Abstract
Facing the challenges of complex electromagnetic interference,dynamic obstacles and communication security,this paper proposes a hybrid framework of Bionic Hierarchical-Multi-Agent Reinforcement Learning(BioRL-Swarm).Through the collaborative control model of dynamic Hierarchical Network Coupling(HNC)and Multi-Agent Proximal Policy Optimization(MAPPO),it realizes the deep integration of distributed decision-making mechanism and survivability communication,and the cluster autonomy and environmental adaptability are significantly improved.Simulation results show that compared with the traditional algorithm,BioRL-Swarm improves the success rate of dynamic obstacle avoidance by 23.6%,reduces the communication packet loss rate to 1.2%,and shortens the task execution time by 37.4%,which shows significant advantages in many key indicators.It provides a solid theoretical basis and reliable technical verification for the engineering application of intelligent unmanned systems in military,agricultural and other fields.关键词
无人机集群/协同控制/深度强化学习/仿生层级网络Key words
UAV cluster/cooperative control/Deep Reinforcement Learning/bionic hierarchical network分类
信息技术与安全科学引用本文复制引用
舒健,韦雅文,吴佳豪,陆晨,孙自梅..复杂环境下无人机集群的协同控制研究[J].现代信息科技,2025,9(19):43-48,56,7.基金项目
南京工业大学浦江学院2024年度新质生产力创新人才"苗苗培育工程"项目(2024-6-11) （2024-6-11）
