本研究聚焦建築營運與維護階段，回應設施管理在人力巡檢不足、監視系統割裂以及現場資訊難以與BIM與數位孿生整合之問題。為此，本研究提出結合BIM與數位孿生之前導性智慧巡檢系統，稱之為SAFER-RoBIM。系統以自主移動機器人系統為核心，透過2D雷射與深度相機兩者感測器，建立機器人室內導航與環境感測能力，並在邊緣運算平台（Jetson Orin Nano）上部署輕量化的物件偵測模型，用以偵測火災徵兆、積水、結構損傷、人員跌倒、抽菸行為及可移除障礙物等10類室內危險事件。為了使機器人具備初步的推理與通報能力，本研究進一步將其所紀錄的危險事件，包括座標位置、事件類型與影像證據等資訊，自動整合並觸發告警電子郵件的發送機制。最後，將事件座標與災害資訊即時回寫至Autodesk Platform Services (APS)數位孿生平台，除了可視化自主移動機器人的巡檢軌跡外，亦在既有的模型語意資訊中標示各危險事件，協助設施管理人員迅速掌握危險位置與事件資訊。
為評估自主巡檢機器人「從偵測到決策」之實際表現，本研究採腳本化場景設計，分別於小型PoC 場域與正式實驗場域實施巡檢任務，並以事件級區段混淆矩陣作為核心評估指標。在小型 PoC 場域中，共執行19次單一腳本化巡檢，結果獲得11次正確偵測（TP）、5次誤報（FP）與3次漏報（FN），整體precision約64.3%、recall約75.0%、F1-score約 69.2%，顯示系統多數情況能正確察覺危險事件，惟對「無事件背景」仍存在偏高誤判率。在正式實驗場域中，21次巡檢共計累積84筆事件觀測，分析顯示跌倒、抽菸、可移除障礙物、積水與交通錐等外觀明顯類別表現較佳；火災徵兆與細部結構裂縫等目標尺寸較小或特徵不明顯之類別則易發生漏報，整體傾向謹慎發報之保守策略。
藉由上述系統整合流程，SAFER-RoBIM證實將自主移動機器人、邊緣端AI推理與BIM/APS 整合於同一工作流程中的可行性，並建構從危險徵兆辨識、位姿對齊、事件級紀錄到自動告警的資料管線。SAFER-RoBIM不僅可作為室內安全巡檢與維運管理之實務參考，亦提供一套腳本化實驗設計與事件級評估框架，作為後續多機器人協作、異質感測器融合及大型視覺語言模型導入等研究延伸與複現之基礎。

To address critical challenges in Facility Management (FM), such as labor shortages and fragmented surveillance systems, this study proposes SAFER-RoBIM, a pilot intelligent inspection system. The framework integrates Autonomous Mobile Robots (AMR), Edge AI, and Digital Twin technologies to establish a closed-loop decision-making mechanism. Built upon ROS 2 middleware, the system utilizes a multi-sensor fusion approach for indoor navigation and employs a lightweight object detection model to identify ten categories of indoor hazards. Crucially, the system bridges the gap between robotic perception and building management by synchronizing event coordinates and visual evidence with the Autodesk Platform Services (APS) in real-time, thereby facilitating rapid situational awareness.
The system’s "detection-to-decision" performance was validated through rigorous scripted scenarios in both a Proof of Concept (PoC) site and a formal experimental environment. Results indicate that while the system effectively identifies distinct hazards (e.g., falls and obstacles) with high precision (0.91 in formal tests), it adopts a conservative reporting strategy for subtle anomalies. Ultimately, SAFER-RoBIM demonstrates the feasibility of combining AMRs and BIM into a unified O&M workflow, providing a scalable data pipeline for future research in multi-agent collaboration and semantic spatial reasoning.

1. 朱國權-佈線與時BIM進，透視建築智慧！. (2022, July 30).
2.醫院數位孿生技術協助提升營運效率與病患體驗—AnyLogic. (2022). https://www.anylogic.com/resources/case-studies/hospital-digital-twin-to-improve-operations-and-enhance-patient-experience/?utm_source=chatgpt.com
3.Beatty, R., Eastman, C., Kim, K., & Fang, Y. (2013). Case study 2: Texas A&M health science center-a case study of BIM and COBie for facility management (pp. 164–184). Wiley-Academy. https://research.monash.edu/en/publications/case-study-2-texas-aampm-health-science-center-a-case-study-of-bi
4.Cai, W., Huang, L., & Zou, Z. (2023). Actively-exploring thermography-enabled autonomous robotic system for detecting and registering HVAC thermal leaks. Automation in Construction, 152, 104901. https://doi.org/10.1016/J.AUTCON.2023.104901
5.Chen, J., Xiao, Y., Guo, Y., Li, M., Li, X., Zhang, X., Hao, F., Pu, X., & Fu, Y. (2024). Detecting sun glint in UAV RGB images at different times using a deep learning algorithm. Ecological Informatics, 81, 102660. https://doi.org/10.1016/J.ECOINF.2024.102660
6.Chen, Z., Chen, K., Song, C., Zhang, X., Cheng, J. C. P., & Li, D. (2022). Global path planning based on BIM and physics engine for UGVs in indoor environments. Automation in Construction, 139, 104263. https://doi.org/10.1016/J.AUTCON.2022.104263
7.Coupry, C., Noblecourt, S., Richard, P., Baudry, D., & Bigaud, D. (2021). BIM-Based digital twin and XR devices to improve maintenance procedures in smart buildings: A literature review. Applied Sciences (Switzerland), 11(15). https://doi.org/10.3390/APP11156810
8.Djehaiche, R., Aidel, S., Sawalmeh, A., Saeed, N., & Alenezi, A. H. (2023). Adaptive Control of IoT/M2M Devices in Smart Buildings Using Heterogeneous Wireless Networks. IEEE Sensors Journal, 23(7), 7836–7849. https://doi.org/10.1109/JSEN.2023.3247007
9.Dreher, M., Blum, H., Siegwart, R., & Gawel, A. (2021). Global Localization in Meshes. Proceedings of the International Symposium on Automation and Robotics in Construction, 2021-November, 747–754. https://doi.org/10.22260/ISARC2021/0101
10.Fei Fei Li. (2025, November 9). From words to worlds: Spatial intelligence is AI’s next frontier. . Https://Drfeifei.Substack.Com/p/from-Words-to-Worlds-Spatial-Intelligence.
11.Follini, C., Magnago, V., Freitag, K., Terzer, M., Marcher, C., Riedl, M., Giusti, A., & Matt, D. T. (2020). BIM-Integrated Collaborative Robotics for Application in Building Construction and Maintenance. Robotics 2021, Vol. 10, Page 2, 10(1), 2. https://doi.org/10.3390/ROBOTICS10010002
12.Global Energy Review 2025. (2025). www.iea.org
13.Grieves, M. (2022). Intelligent digital twins and the development and management of complex systems. Digital Twin, 2, 8. https://doi.org/10.12688/DIGITALTWIN.17574.1
14.IJFM, Sarel Lavy, & Nishaant Saxena. (2022, January 1). Quantifying the Effect of BIM and COBie for FM. https://knowledgelibrary.ifma.org/quantifying-the-effect-of-bim-and-cobie-for-fm/
15.Kelly, J., & Sukhatme, G. S. (2009). Visual-inertial simultaneous localization, mapping and sensor-to-sensor self-calibration. Proceedings of IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA, 360–368. https://doi.org/10.1109/CIRA.2009.5423178
16.Khanam, R., & Hussain, M. (2024). YOLOv11: An Overview of the Key Architectural Enhancements. https://arxiv.org/pdf/2410.17725
17.Kim, K., & Peavy, M. (2022). BIM-based semantic building world modeling for robot task planning and execution in built environments. Automation in Construction, 138, 104247. https://doi.org/10.1016/J.AUTCON.2022.104247
18.Kim, S., Peavy, M., Huang, P. C., & Kim, K. (2021). Development of BIM-integrated construction robot task planning and simulation system. Automation in Construction, 127, 103720. https://doi.org/10.1016/J.AUTCON.2021.103720
19.Kramberger, A., Kunic, A., Iturrate, I., Sloth, C., Naboni, R., & Schlette, C. (2022). Robotic Assembly of Timber Structures in a Human-Robot Collaboration Setup. Frontiers in Robotics and AI, 8, 768038. https://doi.org/10.3389/FROBT.2021.768038/BIBTEX
20.Laxmikant Deshmukh, S., Wilchek, M., Batarseh, F. A., & Member, S. (2025). HydroVision: Predicting Optically Active Parameters in Surface Water Using Computer Vision. https://arxiv.org/pdf/2509.01882v1
21.Lecun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. https://doi.org/10.1038/NATURE14539;SUBJMETA
22.Lin, F., Wang, B., Chen, Z., Zhang, X., Song, C., Yang, L., & Cheng, J. C. P. (2025). Efficient visual inspection of fire safety equipment in buildings. Automation in Construction, 171, 105970. https://doi.org/10.1016/J.AUTCON.2025.105970
23.Marocco, M., & Garofolo, I. (2021). Integrating disruptive technologies with facilities management: A literature review and future research directions. Automation in Construction, 131, 103917. https://doi.org/10.1016/J.AUTCON.2021.103917
24.Maruyama, Y., Kato, S., & Azumi, T. (2016a). Exploring the performance of ROS2. Proceedings of the 13th International Conference on Embedded Software, EMSOFT 2016. https://doi.org/10.1145/2968478.2968502
25.Maruyama, Y., Kato, S., & Azumi, T. (2016b). Exploring the performance of ROS2. Proceedings of the 13th International Conference on Embedded Software, EMSOFT 2016. https://doi.org/10.1145/2968478.2968502
26.Messbah, H., Emharraf, M., & Saber, M. (2024). Robot indoor navigation: comparative analysis of LiDAR 2D and visual SLAM. IAES International Journal of Robotics and Automation, 13(1), 41–49. https://doi.org/10.11591/IJRA.V13I1.PP41-49
27.Muhammad, I., Ying, K., Nithish, M., Xin, J., Xinge, Z., & Cheah, C. C. (2021). Robot-Assisted Object Detection for Construction Automation: Data and Information-Driven Approach. IEEE/ASME Transactions on Mechatronics, 26(6), 2845–2856. https://doi.org/10.1109/TMECH.2021.3100306
28.Mur-Artal, R., Montiel, J. M. M., & Tardos, J. D. (2015). ORB-SLAM: A Versatile and Accurate Monocular SLAM System. IEEE Transactions on Robotics, 31(5), 1147–1163. https://doi.org/10.1109/TRO.2015.2463671
29.Mur-Artal, R., & Tardos, J. D. (2017). ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras. IEEE Transactions on Robotics, 33(5), 1255–1262. https://doi.org/10.1109/TRO.2017.2705103
30.Naqvi, S. A. A. (1996). Critical Human Factor Issues in Quality Inspection Tasks. Journal of King Saud University - Engineering Sciences, 8(1), 133–140. https://doi.org/10.1016/S1018-3639(18)30644-5
31.Patacas, J., Dawood, N., & Kassem, M. (2020). BIM for facilities management: A framework and a common data environment using open standards. Automation in Construction, 120, 103366. https://doi.org/10.1016/J.AUTCON.2020.103366
32.Peng, Y., Zhang, M., Yu, F., Xu, J., & Gao, S. (2020). Digital Twin Hospital Buildings: An Exemplary Case Study through Continuous Lifecycle Integration. Advances in Civil Engineering, 2020. https://doi.org/10.1155/2020/8846667
33.Pishdad-Bozorgi, P., Gao, X., Eastman, C., & Self, A. P. (2018). Planning and developing facility management-enabled building information model (FM-enabled BIM). Automation in Construction, 87, 22–38. https://doi.org/10.1016/J.AUTCON.2017.12.004
34.Revolti, A., Gualtieri, L., Pauwels, P., & Dallasega, P. (2024). From building information modeling to construction digital twin: a conceptual framework. Production & Manufacturing Research, 12(1). https://doi.org/10.1080/21693277.2024.2387679
35.Satyanarayanan, M. (2017). The emergence of edge computing. Computer, 50(1), 30–39. https://doi.org/10.1109/MC.2017.9
36.Shirowzhan, S., Sepasgozar, S. M. E., Edwards, D. J., Li, H., & Wang, C. (2020). BIM compatibility and its differentiation with interoperability challenges as an innovation factor. Automation in Construction, 112, 103086. https://doi.org/10.1016/J.AUTCON.2020.103086
37.Spatial Intelligence and Large World Models: Bridging Perception and Action in 3D Environments. [Technical Report/White Paper]. (2025). World Lab.
38.Torres, M. A. V., Braun, A., & Borrmann, A. (2024). BIM-SLAM: Integrating BIM Models in Multi-session SLAM for Lifelong Mapping using 3D LiDAR. Proceedings of the International Symposium on Automation and Robotics in Construction, 521–528. https://doi.org/10.22260/ISARC2023/0070
39.van der Wal, C. N., Robinson, M. A., Bruine de Bruin, W., & Gwynne, S. (2021). Evacuation behaviors and emergency communications: An analysis of real-world incident videos. Safety Science, 136, 105121. https://doi.org/10.1016/J.SSCI.2020.105121
40.Wang, Z., Li, H., & Zhang, X. (2019). Construction waste recycling robot for nails and screws: Computer vision technology and neural network approach. Automation in Construction, 97, 220–228. https://doi.org/10.1016/J.AUTCON.2018.11.009
41.Wistron Advances Energy Efficiency in Manufacturing with AI and NVIDIA Omniverse. (2024, January 24). https://developer.nvidia.com/blog/wistron-advances-energy-efficiency-in-manufacturing-with-ai-and-nvidia-omniverse/?utm_source=chatgpt.com
42.Yin, H., Lin, Z., & Yeoh, J. K. W. (2023). Semantic localization on BIM-generated maps using a 3D LiDAR sensor. Automation in Construction, 146, 104641. https://doi.org/10.1016/J.AUTCON.2022.104641
43.Yoon, S., Song, J., & Li, J. (2025). Ontology-enabled AI agent-driven intelligent digital twins for building operations and maintenance. Journal of Building Engineering, 108, 112802. https://doi.org/10.1016/J.JOBE.2025.112802
44.Zager, M., Sieber, C., & Fay, A. (2024). Towards Semantic Interoperability: An Information Model for Autonomous Mobile Robots. J. Intell. Robotic Syst., 110(3). https://doi.org/10.1007/S10846-024-02159-3
45.Zhang, Z., Zhang, Z., Li, G., & Xia, C. (2025). ZZ-YOLOv11: A Lightweight Vehicle Detection Model Based on Improved YOLOv11. Sensors 2025, Vol. 25, Page 3399, 25(11), 3399. https://doi.org/10.3390/S25113399
46.Zhao, X., & Cheah, C. C. (2023). BIM-based indoor mobile robot initialization for construction automation using object detection. Automation in Construction, 146, 104647. https://doi.org/10.1016/J.AUTCON.2022.104647
47.Zheng, Y., & Hsiehm Yi Hsieh. (2025, September). alianlbj23/ros2_yolo_integration. https://github.com/alianlbj23/ros2_yolo_integration
48.Zhu, A., Pauwels, P., Torta, E., Zhang, H., & De Vries, B. (2024). Data linking and interaction between BIM and robotic operating system (ROS) for flexible construction planning. Automation in Construction, 163, 105426. https://doi.org/10.1016/J.AUTCON.2024.105426