Multi-Agent Deep Reinforcement Learning-Based Multi-UAV Path Planning for Wireless Data Collection and Energy Transfer

In this paper, we propose the wireless energy transfer and data collection system for multi-unmanned aerial vehicles (UAVs). This system enables multiple UAVs to transfer energy to and collect data from internet of things (IoT) devices, and to recharge their batteries at a central charging station when their batteries are low. In this paper, we propose a multi-UAV path algorithm based on distributed multi-agent deep Q-network (MADQN) to minimize the overall age-of-information (AoI) of IoT devices. The numerical results demonstrate that our proposed algorithm outperforms the benchmark scheme in terms of AoI enables to prolong data collection by continuously charging the battery of both IoT devices and UAVs.