Robust SLAM Systems: Are We There Yet?

TL;DR

This paper systematically evaluates the robustness of leading SLAM algorithms under various challenging conditions, highlighting current limitations and the need for improved generalisation for long-term autonomous operation.

Contribution

It provides a comprehensive assessment of open-source SLAM systems' robustness across diverse perturbations and long-term scenarios, an area not thoroughly explored before.

Findings

SLAM algorithms show limited robustness to combined perturbations.

Performance degrades significantly under dynamic and non-uniform conditions.

Current methods lack strong generalisation for lifelong deployment.

Abstract

Progress in the last decade has brought about significant improvements in the accuracy and speed of SLAM systems, broadening their mapping capabilities. Despite these advancements, long-term operation remains a major challenge, primarily due to the wide spectrum of perturbations robotic systems may encounter. Increasing the robustness of SLAM algorithms is an ongoing effort, however it usually addresses a specific perturbation. Generalisation of robustness across a large variety of challenging scenarios is not well-studied nor understood. This paper presents a systematic evaluation of the robustness of open-source state-of-the-art SLAM algorithms with respect to challenging conditions such as fast motion, non-uniform illumination, and dynamic scenes. The experiments are performed with perturbations present both independently of each other, as well as in combination in long-term deployment settings in unconstrained environments (lifelong operation).