UAV Swarm Deployment and Trajectory for 3D Area Coverage via Reinforcement Learning

TL;DR

This paper presents a hierarchical UAV swarm deployment and trajectory optimization framework using reinforcement learning to enhance 3D area coverage amidst obstacles, demonstrating improved efficiency over existing methods.

Contribution

It introduces a novel hierarchical framework and a Q-learning based algorithm for efficient UAV swarm deployment and trajectory planning in complex 3D environments.

Findings

The proposed method outperforms existing approaches in simulation.

Hierarchical clustering improves coverage efficiency.

Q-learning accelerates solution convergence.

Abstract

Unmanned aerial vehicles (UAVs) are recognized as promising technologies for area coverage due to the flexibility and adaptability. However, the ability of a single UAV is limited, and as for the large-scale three-dimensional (3D) scenario, UAV swarms can establish seamless wireless communication services. Hence, in this work, we consider a scenario of UAV swarm deployment and trajectory to satisfy 3D coverage considering the effects of obstacles. In detail, we propose a hierarchical swarm framework to efficiently serve the large-area users. Then, the problem is formulated to minimize the total trajectory loss of the UAV swarm. However, the problem is intractable due to the non-convex property, and we decompose it into smaller issues of users clustering, UAV swarm hovering points selection, and swarm trajectory determination. Moreover, we design a Q-learning based algorithm to accelerate the solution efficiency. Finally, we conduct extensive simulations to verify the proposed mechanisms, and the designed algorithm outperforms other referred methods.