DRL-Based Distributed Joint Serving and Charging Scheduling for UAV Swarm

Unmanned aerial vehicles (UAVs) have been applied to a wide range of applications. When planning a mission for battery-powered UAVs, energy replenishment is a factor that cannot be ignored. This paper considers a decentralized scheduling scheme for a swarm of UAVs for serving and charging activities, which is challenging because of the trade-off between service requirement and energy consumption as well as limited supply of charging facilities. We propose two decentralized schemes based on deep reinforcement learning (DRL) with partial observation that allow the UAV swarm to autonomously learn where to rest, provide service, or recharge. Although the learning model is for a single UAV, it applies to each UAV in the swarm. We conducted simulations for performance measurements. The results show that the proposed approaches are feasible for distributed serving and charging scheduling with multiple UAVs.