Learning Connectivity-Maximizing Network Configurations

TL;DR

This paper introduces a CNN-based method for quickly optimizing robot team connectivity, enabling real-time configurations for larger teams than traditional optimization methods.

Contribution

It presents a scalable, data-driven approach to maximize network connectivity in robot teams using supervised learning with CNNs, suitable for online applications.

Findings

CNN achieves over tenfold speedup compared to optimization.

Method successfully generalizes to larger, unseen teams.

Effective in dynamic, simulated robot environments.

Abstract

In this letter we propose a data-driven approach to optimizing the algebraic connectivity of a team of robots. While a considerable amount of research has been devoted to this problem, we lack a method that scales in a manner suitable for online applications for more than a handful of agents. To that end, we propose a supervised learning approach with a convolutional neural network (CNN) that learns to place communication agents from an expert that uses an optimization-based strategy. We demonstrate the performance of our CNN on canonical line and ring topologies, 105k randomly generated test cases, and larger teams not seen during training. We also show how our system can be applied to dynamic robot teams through a Unity-based simulation. After training, our system produces connected configurations over an order of magnitude faster than the optimization-based scheme for teams of 10-20 agents.