Have I been here before? Learning to Close the Loop with LiDAR Data in Graph-Based SLAM

TL;DR

This paper enhances graph-based SLAM by integrating 3D LiDAR data through global descriptors and a robust loop detection method, significantly improving loop closure accuracy in changing environments and demonstrating broad applicability.

Contribution

It introduces a novel loop detection extension for graph-based SLAM that leverages 3D LiDAR descriptors and extensive verification, improving robustness and applicability.

Findings

Improved loop closure detection in changing environments.

Enhanced SLAM robustness with LiDAR data.

Comparable performance to state-of-the-art methods like LOAM.

Abstract

This work presents an extension of graph-based SLAM methods to exploit the potential of 3D laser scans for loop detection. Every high-dimensional point cloud is replaced by a compact global descriptor, whereby a trained detector decides whether a loop exists. Searching for loops is performed locally in a variable space to consider the odometry drift. Since closing a wrong loop has fatal consequences, an extensive verification is performed before acceptance. The proposed algorithm is implemented as an extension of the widely used state-of-the-art library RTAB-Map, and several experiments show the improvement: During SLAM with a mobile service robot in changing indoor and outdoor campus environments, our approach improves RTAB-Map regarding total number of closed loops. Especially in the presence of significant environmental changes, which typically lead to failure, localization becomes possible by our extension. Experiments with a car in traffic (KITTI benchmark) show the general applicability of our approach. These results are comparable to the state-of-the-art LiDAR method LOAM. The developed ROS package is freely available.