SignLoc: Robust Localization Using Navigation Signs and Public Maps
Nicky Zimmerman, Joel Loo, Ayush Agrawal, David Hsu
Abstract
Navigation signs and maps, such as floor plans and street maps, are widely available and serve as ubiquitous aids for way-finding in human environments. Yet, they are rarely used by robot systems. This paper presents <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"/><bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SignLoc</b><italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"/>, a global localization method that leverages navigation signs to localize the robot on publicly available maps—specifically floor plans and OpenStreetMap (OSM) graphs–without prior sensor-based mapping. <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SignLoc</b> first extracts a navigation graph from the input map. It then employs a probabilistic observation model to match directional and locational cues from the detected signs to the graph, enabling robust topo-semantic localization within a Monte Carlo framework. We evaluated <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SignLoc</b> in diverse large-scale environments: part of a university campus, a shopping mall, and a hospital complex. Experimental results show that <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SignLoc</b> reliably localizes the robot after observing only one to two signs.
BibTeX
@inproceedings{ral2026_signlocrobustloc,
title = {SignLoc: Robust Localization Using Navigation Signs and Public Maps},
author = {Nicky Zimmerman and Joel Loo and Ayush Agrawal and David Hsu},
booktitle = {RA-L 2026},
year = {2026}
}