@article{BAI2025, 
author = {Hengzhi BAI and Haichao WANG and Rongrong HE and Jiatao DU and Guoxin LI and Yuhua XU and Yutao JIAO},
title = {Multi-hop UAV relay covert communication: A multi-agent reinforcement learning approach☆},
year = {2025},
journal = {Chinese Journal of Aeronautics},
volume = {38},
number = {10},
keywords = {Covert communication, Unmanned aerial vehicle (UAV), Power optimization, Trajectory planning, Multi-agent reinforcement learning (MARL)},
url = {https://www.sciopen.com/article/10.1016/j.cja.2025.103440},
doi = {10.1016/j.cja.2025.103440},
abstract = {Due to the characteristics of line-of-sight (LoS) communication in unmanned aerial vehicle (UAV) networks, these systems are highly susceptible to eavesdropping and surveillance. To effectively address the security concerns in UAV communication, covert communication methods have been adopted. This paper explores the joint optimization problem of trajectory and transmission power in a multi-hop UAV relay covert communication system. Considering the communication covertness, power constraints, and trajectory limitations, an algorithm based on multi-agent proximal policy optimization (MAPPO), named covert-MAPPO (C-MAPPO), is proposed. The proposed method leverages the strengths of both optimization algorithms and reinforcement learning to analyze and make joint decisions on the transmission power and flight trajectory strategies for UAVs to achieve cooperation. Simulation results demonstrate that the proposed method can maximize the system throughput while satisfying covertness constraints, and it outperforms benchmark algorithms in terms of system throughput and reward convergence speed.}
}