用大模型解析平面图，为视障者生成安全导航指令
LLM-Guided Agentic Floor Plan Parsing for Accessible Indoor Navigation of Blind and Low-Vision People
- 多智能体迭代纠错解析平面图，构建可检索的空间知识图谱
- 短/中/长路径成功率分别达92.31%/76.92%/61.54%（MP-1）
- 无需昂贵基建，适合实际建筑部署，尤其适合视障导航
室内导航对视障及低视力（BLV）人群仍是重大挑战，现有方案依赖高成本的每栋建筑基础设施。本文提出一种代理式框架，将单张平面图转化为结构化、可检索的知识库，以轻量级基础设施生成安全、无障碍的导航指令。系统分为两阶段：多智能体模块通过自纠正流程与迭代重试机制，将平面图解析为空间知识图谱；路径规划器生成无障碍导航指令，并由安全评估代理检测路线潜在风险。我们在真实建筑UMBC数学与心理学楼（楼层MP-1和MP-3）及CVC-FP基准上评估该系统。在MP-1上，短、中、长路径成功率达92.31%、76.92%、61.54%，优于最强单次调用基线（Claude 3.7 Sonnet）的84.62%、69.23%、53.85%。在MP-3上分别为76.92%、61.54%、38.46%，对比基线61.54%、46.15%、23.08%。结果表明，该工作流持续优于单次调用大模型基线，是面向视障人群的可扩展无障碍室内导航方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。