Multi-Stage Data Collection and Path Planning for Multiple UAV-enabled Aerial REM Construction

An aerial Radio Environment Map (REM) characterizes the spatial distribution of Received Signal Strength (RSS) across a geographic space of interest, which is crucial for optimizing wireless communication network in the air. To address this issue, this paper proposes a multi-stage data collection and path planning algorithm with multiple Unmanned Aerial Vehicles (UAVs). Specifically, the UAV’s data collection task over the target area is divided into multiple stages. In each stage, collaboration among multiple UAVs is achieved by Voronoi diagram partitioning. Each UAV decides whether to adopt a more granular collecting strategy based on based on the degree of variation in the current RSS values. A Deep Reinforcement Learning (DRL) approach is proposed to design the shortest flight path for selected collecting points. Experimental results demonstrate that the proposed algorithm improves the accuracy of aerial REM construction, while efficiently planning the shortest paths for UAVs between collecting locations.