FRAME: Fast and Robust Autonomous 3D point cloud Map-merging for Egocentric multi-robot exploration

TL;DR

This paper introduces FRAME, a fast and robust 3D point cloud map-merging framework for multi-robot exploration that does not require prior pose knowledge, using learned descriptors for overlap detection and efficient registration.

Contribution

The paper presents a novel map-merging approach that combines learned descriptors for overlap detection with Fast-GICP for alignment, eliminating manual initialization and global feature matching.

Findings

Effective in underground multi-robot exploration scenarios

Compatible with heterogeneous robot sensor configurations

Achieves fast and robust map merging without prior pose info

Abstract

This article presents a 3D point cloud map-merging framework for egocentric heterogeneous multi-robot exploration, based on overlap detection and alignment, that is independent of a manual initial guess or prior knowledge of the robots' poses. The novel proposed solution utilizes state-of-the-art place recognition learned descriptors, that through the framework's main pipeline, offer a fast and robust region overlap estimation, hence eliminating the need for the time-consuming global feature extraction and feature matching process that is typically used in 3D map integration. The region overlap estimation provides a homogeneous rigid transform that is applied as an initial condition in the point cloud registration algorithm Fast-GICP, which provides the final and refined alignment. The efficacy of the proposed framework is experimentally evaluated based on multiple field multi-robot exploration missions in underground environments, where both ground and aerial robots are deployed, with different sensor configurations.