基于大语言模型的代理楼层计划解析用于视障和低视力人士的无障碍室内导航
LLM-Guided Agentic Floor Plan Parsing for Accessible Indoor Navigation of Blind and Low-Vision People
- University of Maryland, Baltimore County（马里兰大学巴尔的摩分校）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
本文提出一种基于代理的框架，将单张楼层平面图转换为结构化的知识库，生成安全的无障碍导航指令。系统通过多代理模块生成空间知识图谱，并通过路径规划器生成导航指令，实验结果显示在真实场景和基准数据集上均优于单次调用基线。
中文摘要 AI 辅助
室内导航仍是视障和低视力（BLV）人士的重要无障碍挑战，因为现有解决方案依赖于昂贵的建筑级基础设施。我们提出了一种代理框架，将单张楼层平面图转换为结构化、可检索的知识库，以生成安全、可访问的导航指令，使用轻量级基础设施。系统分为两个阶段：多代理模块通过自校正流程和迭代重试循环生成空间知识图谱；路径规划器生成可访问的导航指令，其中安全评估代理评估每条路径的潜在危险。我们评估了该系统在现实世界中的UMBC数学和心理学大楼（MP-1和MP-3楼层）以及CVC-FP基准数据集上的表现。在MP-1上，我们实现了短、中、长路线的成功率分别为92.31%、76.92%和61.54%，优于最强的单次调用基线（Claude 3.7 Sonnet）的84.62%、69.23%和53.85%。在MP-3上，我们达到了76.92%、61.54%和38.46%，相比最佳基线61.54%、46.15%和23.08%。这些结果表明在单次调用LLM基线上有持续的优势，并证明了我们的工作流程是无障碍室内导航的可扩展解决方案。
英文摘要
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.
