The Benefits of Interaction Constraints in Distributed Autonomous Systems

TL;DR

This paper demonstrates that constraining interaction networks in distributed autonomous systems can significantly enhance collective learning performance, emphasizing that limited connectivity often outperforms physical network considerations.

Contribution

It introduces the idea that limiting agent interactions improves collective learning, challenging the focus on physical network connectivity in system design.

Findings

Interaction constraints improve collective learning performance.

Limited connectivity can outperform physical network influence.

Less interaction facilitates better information propagation.

Abstract

The design of distributed autonomous systems often omits consideration of the underlying network dynamics. Recent works in multi-agent systems and swarm robotics alike have highlighted the impact that the interactions between agents have on the collective behaviours exhibited by the system. In this paper, we seek to highlight the role that the underlying interaction network plays in determining the performance of the collective behaviour of a system, comparing its impact with that of the physical network. We contextualise this by defining a collective learning problem in which agents must reach a consensus about their environment in the presence of noisy information. We show that the physical connectivity of the agents plays a less important role than when an interaction network of limited connectivity is imposed on the system to constrain agent communication. Constraining agent interactions in this way drastically improves the performance of the system in a collective learning context. Additionally, we provide further evidence for the idea that `less is more' when it comes to propagating information in distributed autonomous systems for the purpose of collective learning.