Long-term Large-scale Mapping and Localization Using maplab

TL;DR

This paper demonstrates how the maplab framework enables large-scale, long-term mapping and localization by building consistent maps from multiple sessions, allowing reuse and registration of new trajectories months later.

Contribution

It introduces algorithms for building and maintaining consistent maps over time and shows their effectiveness in long-term localization scenarios.

Findings

Maps can be reused after several months for accurate localization

New trajectories can be registered within existing 3D models

The approach supports large-scale, long-term mapping and localization

Abstract

This paper discusses a large-scale and long-term mapping and localization scenario using the maplab open-source framework. We present a brief overview of the specific algorithms in the system that enable building a consistent map from multiple sessions. We then demonstrate that such a map can be reused even a few months later for efficient 6-DoF localization and also new trajectories can be registered within the existing 3D model. The datasets presented in this paper are made publicly available.