Distributed Data Storage and Fusion for Collective Perception in Resource-Limited Mobile Robot Swarms

TL;DR

This paper presents a decentralized data storage and fusion method for collective perception in resource-limited robot swarms, enabling efficient semantic classification despite limited resources.

Contribution

It introduces a novel decentralized data structure and a voting-based algorithm tailored for low-resource mobile robots to improve collective perception accuracy.

Findings

Efficient storage and retrieval of semantic data in resource-limited robots

Decentralized voting algorithm reduces classification variance

Extensive simulations demonstrate improved perception accuracy

Abstract

In this paper, we propose an approach to the distributed storage and fusion of data for collective perception in resource-limited robot swarms. We demonstrate our approach in a distributed semantic classification scenario. We consider a team of mobile robots, in which each robot runs a pre-trained classifier of known accuracy to annotate objects in the environment. We provide two main contributions: (i) a decentralized, shared data structure for efficient storage and retrieval of the semantic annotations, specifically designed for low-resource mobile robots; and (ii) a voting-based, decentralized algorithm to reduce the variance of the calculated annotations in presence of imperfect classification. We discuss theory and implementation of both contributions, and perform an extensive set of realistic simulated experiments to evaluate the performance of our approach.