MAPPO-Based Cooperative UAV Trajectory Design with Long-Range Emergency Communications in Disaster Areas

This paper investigates the cooperative real-time trajectory design issue for multiple unmanned aerial vehicles (UAVs) to support long-range emergency communications in disaster areas. To quickly restore the communication links between mobile users (MUs) and base stations, UAVs equipped with a radio frequency (RF) module and a free space optical (FSO) module serve as relay nodes. Given the difficulty of setting up a central controller for UAVs and the urgency of emergency communication, the UAV trajectory design issue is formulated as a distributed cooperative optimization problem. A collaborative multi-UAV trajectory design method based on multi-agent proximal policy optimization (MAPPO) is adopted to improve RF/FSO channel throughput. Compared with the state-of-the-art DRL methods, MAPPO can achieve higher RF allocation efficiency and increase the FSO communication backhaul capacity.