CAPRICORN: Communication Aware Place Recognition using Interpretable Constellations of Objects in Robot Networks

TL;DR

This paper introduces CAPRICORN, a communication-aware place recognition method for robot networks that uses interpretable constellations of objects to improve robustness and reduce bandwidth in decentralized loop closure verification.

Contribution

The paper presents a novel approach combining compact semantic constellation descriptors with a two-step decentralized verification process, enhancing interpretability and efficiency over existing methods.

Findings

Reduces communication bandwidth in multi-robot mapping.

Maintains robustness to illumination changes and dynamic elements.

Validated on TUM RGB-D SLAM sequence with improved performance.

Abstract

Using multiple robots for exploring and mapping environments can provide improved robustness and performance, but it can be difficult to implement. In particular, limited communication bandwidth is a considerable constraint when a robot needs to determine if it has visited a location that was previously explored by another robot, as it requires for robots to share descriptions of places they have visited. One way to compress this description is to use constellations, groups of 3D points that correspond to the estimate of a set of relative object positions. Constellations maintain the same pattern from different viewpoints and can be robust to illumination changes or dynamic elements. We present a method to extract from these constellations compact spatial and semantic descriptors of the objects in a scene. We use this representation in a 2-step decentralized loop closure verification: first, we distribute the compact semantic descriptors to determine which other robots might have seen scenes with similar objects; then we query matching robots with the full constellation to validate the match using geometric information. The proposed method requires less memory, is more interpretable than global image descriptors, and could be useful for other tasks and interactions with the environment. We validate our system's performance on a TUM RGB-D SLAM sequence and show its benefits in terms of bandwidth requirements.