Multi-Robot Distributed Semantic Mapping in Unfamiliar Environments through Online Matching of Learned Representations

TL;DR

This paper introduces a multi-robot semantic mapping method that enables online learning of scene representations and robust label matching, resulting in significantly improved global map quality in unfamiliar environments.

Contribution

It proposes an online unsupervised learning and multiway matching approach for consistent semantic label fusion across multiple robots, addressing key limitations of prior methods.

Findings

20-60% higher global map quality

Robust label matching across robots

Maintains map quality as number of robots increases

Abstract

We present a solution to multi-robot distributed semantic mapping of novel and unfamiliar environments. Most state-of-the-art semantic mapping systems are based on supervised learning algorithms that cannot classify novel observations online. While unsupervised learning algorithms can invent labels for novel observations, approaches to detect when multiple robots have independently developed their own labels for the same new class are prone to erroneous or inconsistent matches. These issues worsen as the number of robots in the system increases and prevent fusing the local maps produced by each robot into a consistent global map, which is crucial for cooperative planning and joint mission summarization. Our proposed solution overcomes these obstacles by having each robot learn an unsupervised semantic scene model online and use a multiway matching algorithm to identify consistent sets of matches between learned semantic labels belonging to different robots. Compared to the state of the art, the proposed solution produces 20-60% higher quality global maps that do not degrade even as many more local maps are fused.