Technical Report: A Hierarchical Dynamically Weighting Deep Reinforcement Learning Method for Multi-UAV Multi-Task Coordination

2026-05-08

AI Summary

This work addresses the coordination challenge of heterogeneous multi-agent tasks—such as aerial imaging and communication—in infrastructure-free emergency scenarios by proposing a hierarchical dynamic weighting deep reinforcement learning framework. The approach innovatively integrates episode-level global task preferences with step-level real-time environmental feedback through a dual-layer weighting mechanism, enhancing dynamic responsiveness while preserving decision stability. Experimental results demonstrate that the proposed framework achieves faster convergence and improved training stability compared to conventional methods, significantly boosting the efficiency of multi-task execution in complex, dynamic environments.

Abstract

This paper investigates the multi-UAV multi-task coordination problem in infrastructure-less emergency scenarios, where UAVs collaboratively are required to jointly perform aerial image acquisition and ground-user communication. To tackle the challenge of balancing heterogeneous tasks within dynamic environments, we propose a hierarchical dynamic weighting Deep Reinforcement Learning (DRL) framework. Specifically, an episode-level module is introduced to capture global task preferences, while a step-level module adaptively adjusts the objective weights according to real-time system conditions. By integrating global and instantaneous weights, the proposed framework improves decision stability and responsiveness during task execution. Simulation results demonstrate that the proposed method achieves faster convergence, more stable training, and higher task completion efficiency than conventional works.

Problem

• multi-UAV coordination
• multi-task coordination
• emergency scenarios
• heterogeneous tasks
• dynamic environments

Innovation

• Hierarchical Dynamic Weighting
• Deep Reinforcement Learning
• Multi-UAV Coordination
• Multi-Task Optimization
• Adaptive Task Balancing