Energy-Efficient Path Planning and Task Allocation for Multi-Drone-Aided IoT Cluster-Based Data Collection
Guodong Zhao, Jingjing Wang, Zhijun Meng, Zichen Wang, Hang Fu, Chunxiao Jiang · IEEE Transactions on Aerospace and Electronic Systems · 2025
In cluster-based Internet of Things (IoT) environments, unmanned aerial vehicles (UAVs) are increasingly being deployed for data collection tasks due to their agility and flexibility. However, the limited energy capacity of UAVs remains a significant challenge. In this paper, we address the joint optimization problem of task allocation and path planning for multi-UAV swarms, aiming to minimize energy consumption while ensuring safe operations in dynamic, real-time environments. We decompose the problem into sub-tasks including task allocation among multiple types of UAVs, and safe, energy-efficient path planning. To solve these subtasks, we introduce a centralized transformation of the traveling salesman problem (TSP) combined with dynamic programmingbased method for task allocation that integrates data transmission considerations. For path planning and trajectory optimization, we leverage multi-agent deep reinforcement learning (RL) for safe waypoint planning and design an energy-optimal planner to minimize energy consumption. Theoretical analysis and simulation results demonstrate that the proposed approach significantly improves energy efficiency compared to existing methods.