Evaluation of RGB-D SLAM in Large Indoor Environments

TL;DR

This paper empirically evaluates two RGB-D SLAM methods, RTAB-Map and Voxgraph, in large indoor environments, analyzing their performance, strengths, and weaknesses under varying odometry noise conditions.

Contribution

It provides a comparative analysis of RTAB-Map and Voxgraph in large-scale indoor environments, highlighting their performance differences and limitations.

Findings

Both methods produce high-quality maps with low odometry noise.

Voxgraph has lower relative trajectory error and memory usage.

Both methods struggle with high odometry noise.

Abstract

Simultaneous localization and mapping (SLAM) is one of the key components of a control system that aims to ensure autonomous navigation of a mobile robot in unknown environments. In a variety of practical cases a robot might need to travel long distances in order to accomplish its mission. This requires long-term work of SLAM methods and building large maps. Consequently the computational burden (including high memory consumption for map storage) becomes a bottleneck. Indeed, state-of-the-art SLAM algorithms include specific techniques and optimizations to tackle this challenge, still their performance in long-term scenarios needs proper assessment. To this end, we perform an empirical evaluation of two widespread state-of-the-art RGB-D SLAM methods, suitable for long-term navigation, i.e. RTAB-Map and Voxgraph. We evaluate them in a large simulated indoor environment, consisting of corridors and halls, while varying the odometer noise for a more realistic setup. We provide both qualitative and quantitative analysis of both methods uncovering their strengths and weaknesses. We find that both methods build a high-quality map with low odometry noise but tend to fail with high odometry noise. Voxgraph has lower relative trajectory estimation error and memory consumption than RTAB-Map, while its absolute error is higher.