Team Assignment for Heterogeneous Multi-Robot Sensor Coverage through Graph Representation Learning

TL;DR

This paper introduces a graph representation learning approach to optimize team assignments in heterogeneous multi-robot systems for enhanced sensor coverage, considering complex relationships among robots.

Contribution

It formulates the multi-robot sensor coverage problem as a graph learning task and proposes a regularized optimization method for effective team assignment.

Findings

Effective team assignment in simulated multi-robot systems

Successful physical multi-robot system case study

Improved sensor coverage through learned representations

Abstract

Sensor coverage is the critical multi-robot problem of maximizing the detection of events in an environment through the deployment of multiple robots. Large multi-robot systems are often composed of simple robots that are typically not equipped with a complete set of sensors, so teams with comprehensive sensing abilities are required to properly cover an area. Robots also exhibit multiple forms of relationships (e.g., communication connections or spatial distribution) that need to be considered when assigning robot teams for sensor coverage. To address this problem, in this paper we introduce a novel formulation of sensor coverage by multi-robot systems with heterogeneous relationships as a graph representation learning problem. We propose a principled approach based on the mathematical framework of regularized optimization to learn a unified representation of the multi-robot system from the graphs describing the heterogeneous relationships and to identify the learned representation's underlying structure in order to assign the robots to teams. To evaluate the proposed approach, we conduct extensive experiments on simulated multi-robot systems and a physical multi-robot system as a case study, demonstrating that our approach is able to effectively assign teams for heterogeneous multi-robot sensor coverage.