Collisionless Pattern Discovery in Robot Swarms Using Deep Reinforcement Learning

TL;DR

This paper introduces a deep reinforcement learning framework that enables robot swarms to autonomously discover collision-free gathering and visibility patterns from arbitrary initial configurations.

Contribution

The work presents a novel RL-based approach for pattern discovery in robot swarms, focusing on collision avoidance and mutual visibility without predefined patterns.

Findings

Robots successfully discover collision-less trajectories.

Patterns for gathering and visibility are effectively learned.

The framework adapts to various initial configurations.

Abstract

We present a deep reinforcement learning-based framework for automatically discovering patterns available in any given initial configuration of fat robot swarms. In particular, we model the problem of collision-less gathering and mutual visibility in fat robot swarms and discover patterns for solving them using our framework. We show that by shaping reward signals based on certain constraints like mutual visibility and safe proximity, the robots can discover collision-less trajectories leading to well-formed gathering and visibility patterns.