3D Radio Map Reconstruction and Trajectory Optimization for Cellular-Connected UAVs

This paper introduces an innovative approach to address the trajectory optimization challenge for cellular-connected unmanned aerial vehicles (UAVs) operating in three-dimensional (3D) space. In most cases, optimizing UAV trajectories necessitates ensuring reliable network connectivity. However, achieving dependable connectivity in 3D space poses a significant challenge due to terrestrial base stations primarily designed for ground users. Additionally, UAVs possess network information only for the areas they have visited, with global network information being inaccessible. To address this issue, we propose a collaborative approach in which multiple UAVs create a global model of outage probability using federated learning, enabling more precise and effective trajectory design. Building upon the constructed global information, we conduct the trajectory design. Initially, we introduce A-star (A∗) algorithm for trajectory design in small-scale scenarios. Nevertheless, recognizing the limitations of A∗ algorithm in large-scale scenarios, we further introduce improved rapidly-exploring random trees (RRTs) algorithm for weighted path optimization. Simulation results are provided to validate the effectiveness of the proposed algorithms.