A UAV-UGV Cooperative System: Patrolling and Energy Management for Urban Monitoring

Abstract

Urban monitoring in 6th Generation (6 G) networks is vital for ensuring smart city security and efficiency. Traditional methods rely on either standalone Unmanned Aerial Vehicles (UAVs) or Unmanned Ground Vehicles (UGVs), often suffering from limited coverage, intermittent connectivity, and inefficient energy management. Recent works have explored UAV-UGV collaboration to enhance surveillance and communication; however, they lack dynamic communication optimization and energy-efficient coordination. To address these gaps, we propose a novel cooperative framework integrating UAVs equipped with Reconfigurable Intelligent Surfaces (RIS) and UGVs for real-time monitoring. Unlike prior approaches, our system optimizes UAV flight paths and recharging schedules using Deep Reinforcement Learning (DRL) while refining UGV patrol routes with a Genetic Algorithm (GA), ensuring adaptive and continuous surveillance. Additionally, we employ Differential Evolution (DE) for RIS configuration, enhancing data transmission and mitigating urban signal degradation. UAVs further support UGVs by wirelessly recharging them via energy beamforming, reducing dependency on fixed charging stations. By leveraging AI-driven coordination, RIS-assisted communication, and real-time energy optimization, our framework ensures seamless data transmission, reduces latency, and maximizes energy efficiency. Simulation results demonstrate that our approach significantly improves communication reliability, monitoring coverage, and energy consumption compared to existing methods, making it a promising solution for next-generation urban monitoring.