Submap-based Pose-graph Visual SLAM: A Robust Visual Exploration and Localization System

TL;DR

This paper introduces a submap-based VSLAM system that enhances robustness in visual localization, especially under challenging conditions like textureless environments and motion blur, by using a submap back-end and visual front-end.

Contribution

It presents a novel submap-based VSLAM system that significantly improves robustness and accuracy over existing methods in difficult scenarios.

Findings

Compared to state-of-the-art, our system shows higher average tracking percentage.

Achieves lower ATE RMSE indicating improved localization accuracy.

Demonstrates effective solution to the 'kidnapped' robot problem.

Abstract

For VSLAM (Visual Simultaneous Localization and Mapping), localization is a challenging task, especially for some challenging situations: textureless frames, motion blur, etc.. To build a robust exploration and localization system in a given space or environment, a submap-based VSLAM system is proposed in this paper. Our system uses a submap back-end and a visual front-end. The main advantage of our system is its robustness with respect to tracking failure, a common problem in current VSLAM algorithms. The robustness of our system is compared with the state-of-the-art in terms of average tracking percentage. The precision of our system is also evaluated in terms of ATE (absolute trajectory error) RMSE (root mean square error) comparing the state-of-the-art. The ability of our system in solving the `kidnapped' problem is demonstrated. Our system can improve the robustness of visual localization in challenging situations.