Motion-Bias-Free Feature-Based SLAM

TL;DR

This paper identifies and addresses the motion bias in feature-based SLAM systems, proposing improvements that enhance consistency and accuracy across forward and reverse traversals in real-world environments.

Contribution

The paper introduces methods to eliminate motion bias in feature-based SLAM, significantly improving trajectory consistency and accuracy in ORB-SLAM2 across multiple datasets.

Findings

Reduced forward-reverse trajectory bias

Improved overall trajectory error

Enhanced performance consistency

Abstract

For SLAM to be safely deployed in unstructured real world environments, it must possess several key properties that are not encompassed by conventional benchmarks. In this paper we show that SLAM commutativity, that is, consistency in trajectory estimates on forward and reverse traverses of the same route, is a significant issue for the state of the art. Current pipelines show a significant bias between forward and reverse directions of travel, that is in addition inconsistent regarding which direction of travel exhibits better performance. In this paper we propose several contributions to feature-based SLAM pipelines that remedies the motion bias problem. In a comprehensive evaluation across four datasets, we show that our contributions implemented in ORB-SLAM2 substantially reduce the bias between forward and backward motion and additionally improve the aggregated trajectory error. Removing the SLAM motion bias has significant relevance for the wide range of robotics and computer vision applications where performance consistency is important.