AI-Empowered UAV Trajectory Optimization in 6G Aerial Networks

Recently, Unmanned Aerial Vehicles (UAVs) have been deployed in various logistics and surveillance applications. Sixth-Generation (6G) cellular networks can further enhance communications to provide ubiquitous coverage, low-latency control, and seamless connectivity among the UAVs. However, achieving constant and end-to-end 3D coverage for user devices is demanding. UAV s have limited battery capacity; thus, energy consumption should be efficiently managed. Optimizing the UAV trajectories improves network performance by diminishing Base Station (BS) load or covering areas with limited radio access. Hence, we propose a Swarm Clustering and Double-Deep-Q-Network (SC-DDQN) framework for efficient communication in aerial networks. The framework constitutes a novel SC- Particle Swarm Optimization (SC-PSO) to improve intra-UAV communication and an Intelligent Trajectory Optimization (ITO) sub-component to optimize Air-to-Ground (A2G) trajectories. The results show that the proposed SC-DDQN framework achieves 40 % faster clustering and a 1.2 % failure probability of reaching a destination compared to the conventional systems, thus providing optimal clustering and trajectory for UAV communications.