Learning Decentralized Controllers for Robot Swarms with Graph Neural Networks

TL;DR

This paper introduces a method to learn decentralized robot swarm controllers using graph neural networks, enabling robots to make local decisions based on limited communication while maintaining coordinated behaviors.

Contribution

It extends aggregation graph neural networks to handle time-varying signals and network support, allowing a single local controller to utilize multi-hop information in dynamic environments.

Findings

Effective flocking achieved with local communication

Multi-hop information improves control in fast-moving, sparsely connected networks

Controller adapts to changing communication ranges and robot velocities

Abstract

We consider the problem of finding distributed controllers for large networks of mobile robots with interacting dynamics and sparsely available communications. Our approach is to learn local controllers that require only local information and communications at test time by imitating the policy of centralized controllers using global information at training time. By extending aggregation graph neural networks to time varying signals and time varying network support, we learn a single common local controller which exploits information from distant teammates using only local communication interchanges. We apply this approach to the problem of flocking to demonstrate performance on communication graphs that change as the robots move. We examine how a decreasing communication radius and faster velocities increase the value of multi-hop information.