Multi-Session Ground Texture SLAM in Low-Dynamic Environments

TL;DR

This paper evaluates techniques for improving SLAM accuracy in multi-session, low-dynamic ground texture environments, highlighting the effectiveness of Kullback-Leibler Divergence and providing a new dataset.

Contribution

It introduces an analysis of three techniques for trajectory estimation in multi-session ground texture SLAM and presents a new dataset with multi-session images and high-accuracy poses.

Findings

Kullback-Leibler Divergence improves loop closure confidence.

Analysis shows the impact of different similarity measures on SLAM accuracy.

The new dataset enables evaluation of SLAM systems in changing ground textures.

Abstract

The simultaneous localization and mapping community has introduced a growing number of systems adapted for multi-session operations where the operational environment features low-dynamic changes that impact mapping, such as surface wear, weather phenomena, or seasonal change. These systems allow for lifelong operations by a robot within these environments. There is also growing interest in operations in environments where the unique ground texture is the only mapping feature available for use. These ground texture systems are not yet targeted for multi-session low-dynamic-change environments though. This work explores the impact of three different techniques on trajectory estimation accuracy in these multi-session low-dynamic ground texture environments. Of the three, the use of Kullback-Leibler Divergence, as a similarity score and a bias influencing loop closure confidence, is found to have the most success. We show an analysis of all three methods and a deeper exploration of the impact of Kullback-Leibler Divergence. We also introduce a dataset for use by the robotics community that contains multi-session images where the ground changes between sessions and also high-accuracy pose information for use in evaluation.