Online Global Loop Closure Detection for Large-Scale Multi-Session Graph-Based SLAM

TL;DR

This paper presents an online, scalable global loop closure detection method for large-scale multi-session SLAM, effectively managing memory and processing constraints during long-term indoor mapping with a robot.

Contribution

It introduces a graph-based SLAM system with a memory management approach that enables real-time global loop closure detection in large environments.

Findings

Successfully tested on five indoor mapping sessions

Handles unknown initial positioning and multi-session mapping

Maintains online processing efficiency

Abstract

For large-scale and long-term simultaneous localization and mapping (SLAM), a robot has to deal with unknown initial positioning caused by either the kidnapped robot problem or multi-session mapping. This paper addresses these problems by tying the SLAM system with a global loop closure detection approach, which intrinsically handles these situations. However, online processing for global loop closure detection approaches is generally influenced by the size of the environment. The proposed graph-based SLAM system uses a memory management approach that only consider portions of the map to satisfy online processing requirements. The approach is tested and demonstrated using five indoor mapping sessions of a building using a robot equipped with a laser rangefinder and a Kinect.