Decentralized Adaptive Formation via Consensus-Oriented Multi-Agent Communication

TL;DR

This paper introduces a decentralized multi-agent reinforcement learning framework that enables adaptive formation control through consensus-oriented communication, improving efficiency and stability in formation adjustments.

Contribution

It proposes a novel consensus-based multi-agent communication method and displacement-based formation approach for flexible, efficient, and stable multi-agent formations.

Findings

Achieved faster formation adjustments in simulations.

Demonstrated improved stability over existing methods.

Validated effectiveness through extensive experiments.

Abstract

Adaptive multi-agent formation control, which requires the formation to flexibly adjust along with the quantity variations of agents in a decentralized manner, belongs to one of the most challenging issues in multi-agent systems, especially under communication-limited constraints. In this paper, we propose a novel Consensus-based Decentralized Adaptive Formation (Cons-DecAF) framework. Specifically, we develop a novel multi-agent reinforcement learning method, Consensus-oriented Multi-Agent Communication (ConsMAC), to enable agents to perceive global information and establish the consensus from local states by effectively aggregating neighbor messages. Afterwards, we leverage policy distillation to accomplish the adaptive formation adjustment. Meanwhile, instead of pre-assigning specific positions of agents, we employ a displacement-based formation by Hausdorff distance to significantly improve the formation efficiency. The experimental results through extensive simulations validate that the proposed method has achieved outstanding performance in terms of both speed and stability.