The focus on cellular-connected unmanned aerial vehicles (UAVs) has been growing due to their ability to enhance conventional UAV capabilities by utilizing existing cellular infrastructure for reliable communication with base stations. These UAVs have been utilized in various applications such as weather forecasting and search and rescue operations. However, in extreme weather conditions like rainfall, designing the trajectory for cellular UAVs becomes challenging due to weak coverage regions in the sky, limitations in flying time, and signal attenuation caused by raindrops.
To address this challenge, this paper introduces a physics-based trajectory design approach for cellular-connected UAVs in rainy environments. The approach utilizes a physics-based electromagnetic simulator to consider detailed environment information and the impact of rain on radio wave propagation. The trajectory optimization problem is formulated to jointly consider UAV flying time and signal-to-interference ratio. This problem is then solved using a Markov decision process with deep reinforcement learning algorithms based on multi-step learning and double Q-learning.
The paper compares optimal UAV trajectories in examples with homogeneous atmosphere medium and rain medium. It also provides a comprehensive study on how varying weather conditions affect trajectory design and discusses the impact of weight coefficients in the problem formulation. The proposed approach showcases significant potential for designing UAV trajectories in rainy weather conditions.