Team Orienteering and Scheduling Algorithms for Collaborative UAV-UGV Area Coverage with Battery Constraints

This paper proposes a FOV-aware, area-based coordination framework for UAV-UGV collaborative surveillance under real-world constraints such as limited battery capacity and road-constrained UGV mobility. Unlike traditional point-based reconnaissance approaches, our method discretizes the surveillance region into realistic grid cells based on UAV camera footprints and guides UAVs to maximize coverage using heading-constrained field-of-view (FOV) planning. A single UGV navigates a predefined fixed route extracted from GeoJSON road data and serves as a mobile charging station with two wireless pads. We formulate the task as a Team Orienteering Problem (TOP) and address it using a structured meta-heuristic algorithm. Key innovations include heading-aware path construction, dynamic reward reinitialization to prevent local stagnation, and tight synchronization with an ILP-based UAV scheduling algorithm that considers operational flight time and charging constraints. UAVs autonomously select their next positions within <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathrm{a}\pm 5^{\circ}$</tex> heading cone to optimize new area coverage while minimizing redundant overlap. Simulation results conducted over the Texas A&M campus demonstrate that our method achieves up to 19% higher area coverage, reduces redundancy by 11.3%, and lowers UAV charging delays compared to point-based and naive area-based baselines. These findings validate the effectiveness of integrating FOV-driven spatial planning with temporal scheduling and adaptive reward modeling, offering a scalable and robust framework for autonomous persistent surveillance missions.