6G-Assisted UAV-Truck Networks: Toward Efficient Essential Services Delivery

Energy consumption is a critical constraint for Unmanned Aerial Vehicles (UAVs) delivery operations to achieve their full potential of providing fast delivery, reducing cost, and cutting emissions. In this article, we propose a synchronized delivery mechanism that employs trucks and UAVs to construct an energy efficient essential service delivery model using Multi-Swarm UAV-Truck (MSUT) framework in a sixth generation (6G) assisted environment. Firstly, we introduce an efficient Brain Storm Optimization (BSO) algorithm that determines the optimal placement location for the trucks and the number of UAV launch sites, given the delivery requirements for optimal delivery of essentials to the target destination. Further, a Multi-Agent Reinforcement Learning (MARL) model, namely Multi-Agent Advantage Actor Critic (MAAC), is employed on UAVs in a swarm for route optimization and efficient energy consumption while en route to the destination. We further investigate the reduced overall delivery time and energy metrics for the proposed UAV-truck network by comparing it with existing Deep Reinforcement Learning (DRL) delivery models.