paper-with-me

홈 › Papers

LLM-Guided Agentic Floor Plan Parsing for Accessible Indoor Navigation of Blind and Low-Vision People

2026-04-27 · Aydin Ayanzadeh, Tim Oates arxiv

Indoor navigation remains a critical accessibility challenge for the blind and low-vision (BLV) individuals, as existing solutions rely on costly per-building infrastructure. We present an agentic framework that converts a single floor plan image into a structured, retrievable knowledge base to generate safe, accessible navigation instructions with lightweight infrastructure. The system has two phases: a multi-agent module that parses the floor plan into a spatial knowledge graph through a self-correcting pipeline with iterative retry loops and corrective feedback; and a Path Planner that generates accessible navigation instructions, with a Safety Evaluator agent assessing potential hazards along each route. We evaluate the system on the real-world UMBC Math and Psychology building (floors MP-1 and MP-3) and on the CVC-FP benchmark. On MP-1, we achieve success rates of 92.31%, 76.92%, and 61.54% for short, medium, and long routes, outperforming the strongest single-call baseline (Claude 3.7 Sonnet) at 84.62%, 69.23%, and 53.85%. On MP-3, we reach 76.92%, 61.54%, and 38.46%, compared to the best baseline at 61.54%, 46.15%, and 23.08%. These results show consistent gains over single-call LLM baselines and demonstrate that our workflow is a scalable solution for accessible indoor navigation for BLV individuals.

📄 PDF Abstract BibTeX arXiv:2604.23970

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Floorplan2Guide: LLM-Guided Floorplan Parsing for BLV Indoor Navigation

2025-12-13 · Aydin Ayanzadeh, Tim Oates arxiv

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. …

Zero-Shot LearningFew-Shot LearningKnowledge GraphsVisual Reasoning

FloVerse: Floor Plan-Guided Multi-Modal Navigation

2026-06-12 · Weiqi Huang, Shuangyi Dong, Jiaxin Li, Yifei Guo 외 arxiv

Floor plans encapsulate compact spatial priors, enabling agents to navigate unseen scenes more efficiently. While prior work has explored floor plan-guided navigation, it has focused mainly on PointNav and a limited set …

Floor Plan Image Segmentation Via Scribble-Based Semi-Weakly Supervised Learning: A Style and Category-Agnostic Approach

2024-02-15 · N.A. 2024 2 · Jielin CHEN;Rudi STOUFFS

The field of architectural design is experiencing a transformative shift towards the integration of advanced computational methodologies, aiming to revolutionize traditional practices through automation. A pivotal aspect…

Image SegmentationSegmentationSemantic SegmentationSemi-Supervised Semantic Segmentation+2

Parsing Line Segments of Floor Plan Images Using Graph Neural Networks

2023-03-07 · Mingxiang Chen, Cihui Pan

In this paper, we present a GNN-based Line Segment Parser (GLSP), which uses a junction heatmap to predict line segments' endpoints, and graph neural networks to extract line segments and their categories. Different from…

Line Segment DetectionSemantic Segmentation

Vision Language Models Can Parse Floor Plan Maps

2024-09-19 · David Defazio, Hrudayangam Mehta, Jeremy Blackburn, Shiqi Zhang

Vision language models (VLMs) can simultaneously reason about images and texts to tackle many tasks, from visual question answering to image captioning. This paper focuses on map parsing, a novel task that is unexplored …

Image CaptioningQuestion AnsweringVisual Question Answering