Multi-Robot Coverage and Exploration using Spatial Graph Neural Networks

TL;DR

This paper introduces a Graph Neural Network-based controller for multi-robot coverage and exploration, demonstrating superior generalization to larger maps and teams, and outperforming traditional planning methods in exploration tasks.

Contribution

The paper presents a novel GNN controller that leverages spatial equivariance for multi-robot coverage, enabling scalable and effective exploration beyond traditional planning approaches.

Findings

GNN controller generalizes to larger maps and more robots.

The approach surpasses planning-based methods in exploration tasks.

Effective in simulation of ten quadrotors and multiple buildings.

Abstract

The multi-robot coverage problem is an essential building block for systems that perform tasks like inspection or search and rescue. We discretize the coverage problem to induce a spatial graph of locations and represent robots as nodes in the graph. Then, we train a Graph Neural Network controller that leverages the spatial equivariance of the task to imitate an expert open-loop routing solution. This approach generalizes well to much larger maps and larger teams that are intractable for the expert. In particular, the model generalizes effectively to a simulation of ten quadrotors and dozens of buildings. We also demonstrate the GNN controller can surpass planning-based approaches in an exploration task.