Collaborative Robot Mapping using Spectral Graph Analysis

TL;DR

This paper introduces a spectral graph analysis-based framework for multi-robot SLAM that enhances global map consistency and reduces drift by exploiting structural differences between robot and server graphs.

Contribution

It presents a novel spectral graph analysis method to generate constraints for improving multi-robot pose graph optimization in a centralized SLAM system.

Findings

Achieved up to 90% improvement in onboard system accuracy.

Validated effectiveness through real-world multi-robot deployments.

Enhanced global map consistency and robustness.

Abstract

In this paper, we deal with the problem of creating globally consistent pose graphs in a centralized multi-robot SLAM framework. For each robot to act autonomously, individual onboard pose estimates and maps are maintained, which are then communicated to a central server to build an optimized global map. However, inconsistencies between onboard and server estimates can occur due to onboard odometry drift or failure. Furthermore, robots do not benefit from the collaborative map if the server provides no feedback in a computationally tractable and bandwidth-efficient manner. Motivated by this challenge, this paper proposes a novel collaborative mapping framework to enable accurate global mapping among robots and server. In particular, structural differences between robot and server graphs are exploited at different spatial scales using graph spectral analysis to generate necessary constraints for the individual robot pose graphs. The proposed approach is thoroughly analyzed and validated using several real-world multi-robot field deployments where we show improvements of the onboard system up to 90%.