发表机构
Trier University of Applied Sciences; University of Luxembourg（特里尔应用技术大学; 卢森堡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出利用LLM融合VLM输出、OpenStreetMap数据及传感器信息，实现移动机器人场景解读的物理-地理空间接地，在校园测试中建筑接地F1为0.83。
AI 中文摘要
深度学习的最新进展使机器人代理能够与动态和非结构化环境进行交互。特别令人感兴趣的是将物理-地理空间世界知识整合到此类系统中，可通过使用物理感知的机器学习模型、用于建模关系的知识图谱或时空与逻辑推理来实现。在本工作中，我们提出了一种方法，通过整合语义描述、OpenStreetMap建筑数据和街道信息，以及从我们的传感系统获得的位置、时间和度量信息，利用LLM融合这些信息，来增强用于场景解读的预训练、未修改的VLM的输出。我们将此概念应用于大学校园内的户外记录，在我们的试点评估集上，在建筑接地任务中实现了0.83的F1分数，在路径表面接地任务中实现了0.64的F1分数。结果证明了所提出方案在提供物理-地理空间接地的自然语言描述方面的概念能力。代码和结果可在以下https URL获取。
英文摘要
Recent advancements in deep learning allow robotic agents to interact with dynamic and unstructured environments. Of special interest is the integration of physico-geospatial world knowledge into such systems, either by using physics-aware machine learning models, knowledge graphs to model relationships or spatio-temporal and logical reasoning. In the present work, we introduce an approach to augment the output of pre-trained, unmodified VLMs used for scene interpretation by integrating semantic descriptions, OpenStreetMap building data and street information with positional, temporal and metric information obtained from our sensory systems, fusing this information using LLMs. We apply this concept to an outdoor recording within a university campus, achieving an F1-Score of 0.83 in the task of grounding buildings and 0.64 for path surface grounding on our pilot evaluation set. The results demonstrate the conceptual capability of the proposed solution to deliver physico-geospatial grounded natural language descriptions. Code and results are available at https://datahub.rz.rptu.de/hstr-csrl-public/publications/physico-geospatial-grounded-scene-interpretation
Comments9 pages, 3 figures, 3 table; accepted for International Conference on FutureTech 2026 (ICFT), AMMAN, JORDAN October 18-22 2026
