Detecting Invalid Map Merges in Lifelong SLAM

TL;DR

This paper presents methods to detect and undo invalid map merges in Lifelong SLAM caused by relocalization errors, using scan comparison and change detection techniques evaluated on multiple datasets.

Contribution

It introduces novel detection techniques for invalid map merges in Lifelong SLAM, improving robustness against relocalization failures and perceptual aliasing.

Findings

Methods perform well in flat and office environments

Real-time execution with reasonable computational cost

Effective detection of invalid map merges

Abstract

For Lifelong SLAM, one has to deal with temporary localization failures, e.g., induced by kidnapping. We achieve this by starting a new map and merging it with the previous map as soon as relocalization succeeds. Since relocalization methods are fallible, it can happen that such a merge is invalid, e.g., due to perceptual aliasing. To address this issue, we propose methods to detect and undo invalid merges. These methods compare incoming scans with scans that were previously merged into the current map and consider how well they agree with each other. Evaluation of our methods takes place using a dataset that consists of multiple flat and office environments, as well as the public MIT Stata Center dataset. We show that methods based on a change detection algorithm and on comparison of gridmaps perform well in both environments and can be run in real-time with a reasonable computational cost.