Floorplan2Guide: LLM-Guided Floorplan Parsing for BLV Indoor Navigation

Floorplan2Guide system architecture showing a floorplan converted into a spatial knowledge graph and interpreted by a language model to produce indoor navigation instructions. — Figure 1. Architecture of the LLM-based indoor navigation system. Floorplans are parsed into a spatial knowledge graph, which the language model uses to generate navigation instructions from user queries. Original figure from the Floorplan2Guide arXiv preprint (CC BY 4.0).

Abstract

Indoor navigation remains a critical challenge for people with visual impairments. The current solutions mainly rely on infrastructure-based systems, which limit their ability to navigate safely in dynamic environments. We propose a novel navigation approach that utilizes a foundation model to transform floor plans into navigable knowledge graphs and generate human-readable navigation instructions. Floorplan2Guide integrates a large language model (LLM) to extract spatial information from architectural layouts, reducing the manual preprocessing required by earlier floorplan parsing methods. Experimental results indicate that few-shot learning improves navigation accuracy in comparison to zero-shot learning on simulated and real-world evaluations. Claude 3.7 Sonnet achieves the highest accuracy among the evaluated models, with 92.31%, 76.92%, and 61.54% on the short, medium, and long routes, respectively, under 5-shot prompting of the MP-1 floor plan. The success rate of graph-based spatial structure is 15.4% higher than that of direct visual reasoning among all models, which confirms that graphical representation and in-context learning enhance navigation performance and make our solution more precise for indoor navigation of Blind and Low Vision (BLV) users.

Framework

Floorplan parsing

Textual and geometric features are extracted from architectural layouts using OCR and visual analysis.

Spatial knowledge graph

The language model constructs and validates a graph of spatial entities and their connections, enriched with ArUco marker information.

Language-guided navigation

User queries are translated into step-by-step, context-aware indoor navigation instructions.

Route-aware localization

Marker-based localization supports route tracking and alerts users when they deviate from the planned route.

Resources

Published paper: IEEE Xplore
DOI: 10.1109/BigData66926.2025.11401868

BibTeX

@inproceedings{ayanzadeh2025floorplan2guide,
  title     = {Floorplan2Guide: LLM-Guided Floorplan Parsing for BLV Indoor Navigation},
  author    = {Ayanzadeh, Aydin and Oates, Tim},
  booktitle = {2025 IEEE International Conference on Big Data (BigData)},
  pages     = {7477--7485},
  year      = {2025},
  doi       = {10.1109/BigData66926.2025.11401868}
}