发表机构
University of California at Irvine; Indian Institute of Technology Bombay（加州大学尔湾分校; 印度理工学院孟买分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
CORNAV利用蓝图和进度感知，结合开放词汇场景图与LLM安全模块，提升活跃工地机器人导航成功率至72.2%，消除区域违规。
AI 中文摘要
建筑行业面临持续劳动力短缺、低生产率（每年给全球经济造成超过1.6万亿美元的损失）以及主要行业中最高的事故率之一。这些因素促使使用自主机器人来提高效率和工人安全。然而，现有的基于语言的导航系统仅依赖语义场景理解，缺乏对建筑特定上下文（如建筑平面图、不断变化的工作进度和安全约束）的访问。因此，它们对永久性建筑特征的定位不可靠，且无法在活跃工地安全导航。我们提出CORNAV，一种基于蓝图、进度感知的导航框架，它仅从2D CAD图纸和项目进度运行，无需建筑信息模型。CORNAV将建筑蓝图与分层开放词汇3D场景图对齐，以锚定对象查询，将项目进度转换为随时间变化的导航约束，并通过基于LLM的安全模块验证请求，该模块在规划前升级危险区域。随后，A*规划器强制执行强制排除区域，同时优先避开高风险区域。在室内办公室和真实建筑工地中，蓝图锚定将任务成功率从13.0%提升至72.2%（相对于纯语义检索），进度感知消除了所有硬性区域违规，安全模块正确拒绝了因错误标记项目进度而产生的危险请求。
英文摘要
The construction industry faces persistent labor shortages, low productivity that costs the global economy over $1.6 trillion annually, and one of the highest injury rates among major industries. These factors motivate the use of autonomous robots to improve efficiency and worker safety. Existing language-grounded navigation systems, however, rely on semantic scene understanding alone and lack access to construction-specific context such as architectural plans, evolving work schedules, and safety constraints. As a result, they localize permanent building features unreliably and cannot safely navigate active jobsites. We present CORNAV, a blueprint-grounded, schedule-aware navigation framework that operates from 2D CAD drawings and project schedules without requiring a Building Information Model. CORNAV aligns architectural blueprints against hierarchical open-vocabulary 3D scene graphs to ground object queries, converts project schedules into time-varying navigation constraints, and validates requests through an LLM-based safety module that escalates hazardous zones before planning. An A* planner then enforces mandatory exclusion zones while preferentially avoiding higher-risk areas. Across an indoor office and a real construction site, blueprint grounding raises task success from 13.0% to 72.2% over semantic retrieval alone, schedule awareness eliminates all hard-zone violations, and the safety module correctly rejects hazardous requests arising from mislabeled project schedules.
