云南民族大学学报（自然科学版）2025，Vol.34Issue(6)：713-722,10.DOI:10.3969/j.issn.1672-8513.2025.06.010
基于多目标规划的MO-MATD3算法的多无人机编队控制
Multi-UAV formation control based on MO-MATD3 algorithm with multi-objective planning
摘要
Abstract
Aiming at the cooperative control problem of multi-UAV formation maintenance and target navigation in complex dynamic obstacle environments,a multi-objective multi-agent twin delayed deep deterministic policy gradient(MO-MATD3)algorithm based on a virtual center control architecture is proposed.First,a continuous dense reward function is constructed based on artificial potential field theory to improve the learning efficiency of complex behavioral strategies and accelerate training convergence.Second,a mode-switching mechanism for formation navigation and obstacle avoidance is designed using multi-objective planning principles,with agents granting priority to avoidance strategies during obstacle encounters.This enables multi-agent systems to switch strategies amid conflicting objectives including formation maintenance,navigation,and obstacle avoidance,thereby ensuring safe completion of formation navigation tasks.Finally,the effectiveness of the algorithm is verified through comparative experiments,its generalization capability is tested in diverse environments,and system robustness is validated through parameter perturbation.关键词
多智能体强化学习/人工势场法/多目标规划/编队控制/MATD3Key words
multi-agent reinforcement learning/artificial potential field method/multi-objective planning/formation control/MATD3分类
信息技术与安全科学引用本文复制引用
LI Jun-ze,LIANG Cheng-qing,YAN Dong-mei,LIU Lei..基于多目标规划的MO-MATD3算法的多无人机编队控制[J].云南民族大学学报（自然科学版）,2025,34(6):713-722,10.基金项目
航空科学基金(2024Z071108001) （2024Z071108001）
中央高校业务费(B240203012). （B240203012）
