Joint trajectory design and radio resource management for multi UAV-aided vehicular networks

In recent years, the integration of unmanned aerial vehicles (UAVs) into wireless networks has emerged as a promising solution to enhance coverage, optimize resourse allocation, and improve network performance in both uplink (UL) and downlink (DL) scenarios. This paper proposes a novel multi-agent deep reinforcement learning (MADRL) approach that combines UAV trajectory design with radio resource management (RRM). Our system adapts dynamically to user demands and network conditions, incorporating an interference management strategy and continuous service approach to enhance quality of experience (QoE) across multiple time instants. Experimental results demonstrate that our algorithm outperforms traditional placement strategies, achieving significant improvements in network performance, user satisfaction, and robustness under varying demand conditions. This work offers a practical solution for deploying UAVs in dense, real-world scenarios that require continuous and reliable connectivity.