Floorplan2Guide: LLM-Guided Floorplan Parsing for BLV Indoor Navigation
This addresses the problem of safe indoor navigation for blind and low vision users, offering an incremental improvement over existing methods by reducing manual preprocessing.
The paper tackled indoor navigation for people with visual impairments by using a large language model to parse floor plans into knowledge graphs and generate navigation instructions, achieving up to 92.31% accuracy on short routes with few-shot learning and a 15.4% higher success rate using graph-based representations.
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.