Optimizing Risk-Aware Task Migration Algorithm Among Multiplex UAV Groups Through Hybrid Attention Multi-Agent Reinforcement Learning  

作　　者：Yuanshuang Jiang Kai Di Ruiyi Qian Xingyu Wu Fulin Chen Pan Li Xiping Fu Yichuan Jiang 

机构地区：[1]School of Computer Science and Engineering,Southeast University,Nanjing 211189 [2]School of Software Engineering,Southeast University,Nanjing 211189 [3]School of Cyber Science and Engineering,Southeast University,Nanjing 211189 [4]PredictHQ,Auckland 1010,New Zealand

出　　处：《Tsinghua Science and Technology》2025年第1期318-330,共13页清华大学学报自然科学版(英文版)

基　　金：supported by the Key Research and Development Program of Jiangsu Province of China(No.BE2022157);the National Natural Science Foundation of China(Nos.62303111,62076060,and 61932007);the Defense Industrial Technology Development Program(No.JCKY2021214B002);the Fellowship of China Postdoctoral Science Foundation(No.2022M720715).

摘　　要：Recently,with the increasing complexity of multiplex Unmanned Aerial Vehicles(multi-UAVs)collaboration in dynamic task environments,multi-UAVs systems have shown new characteristics of inter-coupling among multiplex groups and intra-correlation within groups.However,previous studies often overlooked the structural impact of dynamic risks on agents among multiplex UAV groups,which is a critical issue for modern multi-UAVs communication to address.To address this problem,we integrate the influence of dynamic risks on agents among multiplex UAV group structures into a multi-UAVs task migration problem and formulate it as a partially observable Markov game.We then propose a Hybrid Attention Multi-agent Reinforcement Learning(HAMRL)algorithm,which uses attention structures to learn the dynamic characteristics of the task environment,and it integrates hybrid attention mechanisms to establish efficient intra-and inter-group communication aggregation for information extraction and group collaboration.Experimental results show that in this comprehensive and challenging model,our algorithm significantly outperforms state-of-the-art algorithms in terms of convergence speed and algorithm performance due to the rational design of communication mechanisms.

关 键 词：Unmanned Aerial Vehicle(UAV) multiplex UAV group structures task migration multi-agent reinforcement learning 

分 类 号：V27[航空宇航科学与技术—飞行器设计]