Long-Term Localization using Semantic Cues in Floor Plan Maps

TL;DR

This paper presents a semantic cue-based long-term indoor localization method that leverages sparse CAD floor plans and object detection to improve robustness against environmental changes, demonstrated through experiments in office environments.

Contribution

The paper introduces a novel long-term localization approach using semantic cues and a semantic map, reducing reliance on detailed geometric maps and enabling adaptation to environmental changes.

Findings

Robust localization despite structural changes in indoor environments

Effective integration of semantic cues with Monte Carlo localization

Open source implementation available for deployment and further research

Abstract

Lifelong localization in a given map is an essential capability for autonomous service robots. In this paper, we consider the task of long-term localization in a changing indoor environment given sparse CAD floor plans. The commonly used pre-built maps from the robot sensors may increase the cost and time of deployment. Furthermore, their detailed nature requires that they are updated when significant changes occur. We address the difficulty of localization when the correspondence between the map and the observations is low due to the sparsity of the CAD map and the changing environment. To overcome both challenges, we propose to exploit semantic cues that are commonly present in human-oriented spaces. These semantic cues can be detected using RGB cameras by utilizing object detection, and are matched against an easy-to-update, abstract semantic map. The semantic information is integrated into a Monte Carlo localization framework using a particle filter that operates on 2D LiDAR scans and camera data. We provide a long-term localization solution and a semantic map format, for environments that undergo changes to their interior structure and detailed geometric maps are not available. We evaluate our localization framework on multiple challenging indoor scenarios in an office environment, taken weeks apart. The experiments suggest that our approach is robust to structural changes and can run on an onboard computer. We released the open source implementation of our approach written in C++ together with a ROS wrapper.