TOL: Textual Localization with OpenStreetMap

2026-04-02

AI Summary

This work proposes a novel task of text-to-OpenStreetMap (T2O) global localization, aiming to achieve high-precision 2D positioning in urban environments using only natural language descriptions, without geometric observations or GNSS priors. To facilitate systematic exploration of this task, the authors introduce TOL, a large-scale benchmark spanning multiple cities across continents, comprising 121,000 textual queries paired with corresponding OpenStreetMap tiles. They further present TOLoc, a coarse-to-fine localization framework that explicitly models semantic information of surrounding objects and their directional relationships through direction-aware feature extraction, global descriptor matching, and text-to-local-map alignment modules. Experiments demonstrate that TOLoc outperforms the current state-of-the-art by 6.53%, 9.93%, and 8.31% at localization thresholds of 5m, 10m, and 25m, respectively, and exhibits strong generalization capability in unseen cities.

Technology Category

Intelligent Robots: Localization, Mapping, and NavigationSearch and Optimization: Local SearchNatural Language Processing: Sentence-level Semantics, Textual Inference, etc.

Application Category

Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and servicesSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingGraph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Natural language provides an intuitive way to express spatial intent in geospatial applications. While existing localization methods often rely on dense point cloud maps or high-resolution imagery, OpenStreetMap (OSM) offers a compact and freely available map representation that encodes rich semantic and structural information, making it well suited for large-scale localization. However, text-to-OSM (T2O) localization remains largely unexplored. In this paper, we formulate the T2O global localization task, which aims to estimate accurate 2 degree-of-freedom (DoF) positions in urban environments from textual scene descriptions without relying on geometric observations or GNSS-based initial location. To support the proposed task, we introduce TOL, a large-scale benchmark spanning multiple continents and diverse urban environments. TOL contains approximately 121K textual queries paired with OSM map tiles and covers about 316 km of road trajectories across Boston, Karlsruhe, and Singapore. We further propose TOLoc, a coarse-to-fine localization framework that explicitly models the semantics of surrounding objects and their directional information. In the coarse stage, direction-aware features are extracted from both textual descriptions and OSM tiles to construct global descriptors, which are used to retrieve candidate locations for the query. In the fine stage, the query text and top-1 retrieved tile are jointly processed, where a dedicated alignment module fuses textual descriptor and local map features to regress the 2-DoF pose. Experimental results demonstrate that TOLoc achieves strong localization performance, outperforming the best existing method by 6.53%, 9.93%, and 8.31% at 5m, 10m, and 25m thresholds, respectively, and shows strong generalization to unseen environments. Dataset, code and models will be publicly available at: https://github.com/WHU-USI3DV/TOL.

Problem

• text-to-OSM localization
• global localization
• natural language
• OpenStreetMap
• 2-DoF pose estimation

Innovation

• Text-to-Map Localization
• OpenStreetMap
• Natural Language Spatial Reasoning
• Coarse-to-Fine Localization
• Geospatial Benchmark