Lightweight Decentralized Neural Network-Based Strategies for Multi-Robot Patrolling

TL;DR

This paper introduces two lightweight neural network strategies for decentralized multi-robot patrolling, outperforming traditional methods in minimizing idleness and resisting intruders, with analysis of robustness to communication failures.

Contribution

The paper presents novel neural network-based strategies for multi-robot patrolling, improving performance over existing hand-designed approaches and analyzing robustness to communication issues.

Findings

Neural strategies outperform traditional methods in idleness minimization.

Strategies effectively counter intelligent intruders.

Robustness to communication failure is demonstrated.

Abstract

The problem of decentralized multi-robot patrol has previously been approached primarily with hand-designed strategies for minimization of 'idlenes' over the vertices of a graph-structured environment. Here we present two lightweight neural network-based strategies to tackle this problem, and show that they significantly outperform existing strategies in both idleness minimization and against an intelligent intruder model, as well as presenting an examination of robustness to communication failure. Our results also indicate important considerations for future strategy design.