AC-MASAC: An Attentive Curriculum Learning Framework for Heterogeneous UAV Swarm Coordination

TL;DR

This paper introduces AC-MASAC, a novel attentive curriculum learning framework for heterogeneous UAV swarm coordination, effectively modeling asymmetric dependencies and improving training stability in multi-agent reinforcement learning.

Contribution

It proposes a role-aware attention mechanism and a structured curriculum strategy to enhance cooperative path planning in heterogeneous UAV swarms.

Findings

Significant improvements in Success Rate over existing methods

Enhanced Formation Keeping Rate in simulations

Reduced Success-weighted Mission Time

Abstract

Cooperative path planning for heterogeneous UAV swarms poses significant challenges for Multi-Agent Reinforcement Learning (MARL), particularly in handling asymmetric inter-agent dependencies and addressing the risks of sparse rewards and catastrophic forgetting during training. To address these issues, this paper proposes an attentive curriculum learning framework (AC-MASAC). The framework introduces a role-aware heterogeneous attention mechanism to explicitly model asymmetric dependencies. Moreover, a structured curriculum strategy is designed, integrating hierarchical knowledge transfer and stage-proportional experience replay to address the issues of sparse rewards and catastrophic forgetting. The proposed framework is validated on a custom multi-agent simulation platform, and the results show that our method has significant advantages over other advanced methods in terms of Success Rate, Formation Keeping Rate, and Success-weighted Mission Time. The code is available at \textcolor{red}{https://github.com/Wanhao-Liu/AC-MASAC}.