營造業長期以來面臨勞動力短缺、生產效率低下和工作環境不安全等問題，這些問題在低薪和社會少子化趨勢下尤為嚴重。引入自動化機器人，如噴漆機器人，成為改善這些問題的一種有效途徑。噴漆機器人能夠穩定地執行重複性任務，提高生產品質和效率，並精確控制噴塗量，減少材料浪費，此外，噴漆機器人亦可以減少工人直接接觸有害化學物質的機會，提高工作環境的安全性。由於施工環境的複雜性和多變性，機器人的自適應性尚未足夠先進，導致其在動態環境中的應用受限。建築資訊模型 (BIM) 和點雲技術的結合，為營造業的自動化程度提供了新的可能性。BIM提供了詳細的幾何形狀、空間關係和材料特性等資訊，而點雲技術則提供了虛實整合的優勢，通過創建虛擬環境來幫助機器人進行任務模擬和控制。然而，這些技術在實際應用中仍存在諸多挑戰，需要進一步的技術發展和應用研究。本研究旨在結合虛實整合技術與深度學習，建構一個全自動化噴漆機械手臂模擬系統，以提升噴漆作業的效率和品質，解決營建業面臨的諸多問題。
本研究首先通過文獻回顧和資料蒐集，深入解析全自動化噴漆機器人的作業需求，並確立預測模型的需求。利用Autodesk Revit進行BIM建模，並通過CloudCompare生成點雲數據，再將兩者進行結合以建構虛實整合環境，本研究採用TensorFlow 2.0建構卷積神經網路 (CNN)深度學習模型，以提取和分析噴漆任務的特徵。透過ROS系統和MoveIt!進行機械手臂的規劃與控制，本研究成功地建立了一個能夠自動規劃噴漆任務的預測系統。結果顯示，結合BIM和點雲技術的虛實整合模擬環境，有效提高了機器人的操作精度和穩定性；而深度學習模型則提升了噴漆任務規劃的準確性和效率。這一系統不僅驗證了技術的可行性，還展示了其在實際應用中的巨大潛力，為營造業自動化進程提供了重要的技術支持。

The construction industry has long faced challenges such as labor shortages, low productivity, and unsafe working conditions, further exacerbated by low wages and declining birth rates. Automation, like spray-painting robots, presents an effective solution to these problems. These robots consistently perform repetitive tasks, enhance production quality and efficiency, and precisely control paint application to minimize waste. Additionally, they improve workplace safety by reducing workers' exposure to hazardous chemicals. However, the complexity and variability of construction environments limit the adaptability of current robots, hindering their broader application.

This study addresses this limitation by integrating Building Information Modeling (BIM) and point cloud technology to develop a fully automated spray-painting robotic arm simulation system. BIM provides comprehensive details about geometric shapes, spatial relationships, and material properties, while point cloud technology creates a virtual environment for simulating and controlling tasks. This integration seeks to enhance the efficiency and quality of painting operations, thus tackling persistent issues in the construction industry.

The research involves a detailed analysis of the operational needs for fully automated spray-painting robots, followed by BIM model creation using Autodesk Revit. Point cloud data, generated with CloudCompare, is integrated into a cyber-physical simulation environment. TensorFlow 2.0 is employed to train Convolutional Neural Networks (CNN) for extracting and analyzing features relevant to painting tasks. The system is further optimized using the Robot Operating System (ROS) and MoveIt! for planning and controlling the robotic arm’s movements.

英文文獻
[1] Abioye, S. O., Oyedele, L. O., Akanbi, L., …Ahmed, A. (2021). Artificial intelligence in the construction industry: A review of present status, opportunities and future challenges. Journal of Building Engineering, Volume 44, 2021, 103299, ISSN 2352-7102
[2] Akanmu, A., Anumba, C., & Chin, C. (2014). Scenarios for Cyber-Physical Systems Integration in Construction. Proceedings of the 2014 ASCE International Conference on Computing in Civil and Building Engineering (ICCCBE), 131-138. https://doi.org/10.1061/9780784413616.017
[3] Akinosho, T. D., Oyedele, L. O., Bilal, M., Ajayi, S. O., Akinade, O. O., Davies, O., & Ogunsemi, D. R. (2020). Deep learning in the construction industry: A review of present status and future innovations. Journal of Building Engineering, 32, 101827. https://doi.org/10.1016/j.jobe.2020.101827
[4] Anumba, C., Chen, X., & Li, H. (2017). Cyber-Physical Systems Development for Construction. Journal of Construction Engineering and Management, 143(3), 04016106. https://doi.org/10.1061/(ASCE)CO.1943-7862.0001245
[5] Ayodele, O. A., Chang-Richards, Alice. & González, Vicente. (2019). Factors Affecting Workforce Turnover in the Construction Sector: A Systematic Review. American Society of Civil Engineers. https://doi.org/10.1061/(ASCE)CO.1943-7862.0001725
[6] Asadi, E., Li, B. & Chen, I. M. Pictobot: A Cooperative Painting Robot for Interior Finishing of Industrial Developments. IEEE Robotics and Automation Magazine, 25(2), 82–94. 2018. https://doi.org/10.1109/MRA.2018.2816972
[7] Azhar, S. (2011). Building Information Modeling (BIM): Trends, Benefits, Risks, and Challenges for the AEC Industry. Leadership and Management in Engineering, Volume 11, Issue 3. https://doi.org/10.1061/(ASCE)LM.1943-5630.0000127
[8] Beer, J. M., Fong, T., Sheridan, T., Kaber, D. B., & Chen, J. Y. C. (2014). Toward a framework for levels of robot autonomy in human-robot interaction. Journal of Human-Robot Interaction, 3(2), 74-99. https://doi.org/10.5898/JHRI.3.2.Beer
[9] Burden, A.G., Caldwell, G.A. & Guertler, M.R. (2022). Towards human–robot collaboration in construction: current cobot trends and forecasts. Construction Robotics, 6(209–220). https://doi.org/10.1007/s41693-022-00085-0
[10] Chen, H. P., & Ying, K. (2022). Artificial Intelligence in the Construction Industry: Main Development Trajectories and Future Outlook. Appl. Sci. 2022,12, 5832. https://doi.org/10.3390/app12125832
[11] Deng, Z., Liang, X., Cheng, H., Guo, J., & Fan, J. (2021). Compressive strength prediction of recycled concrete based on deep learning. Construction and Building Materials, 277, 122352. https://doi.org/10.1016/j.conbuildmat.2021.122352
[12] Dimiduk, D. M., Holm, E. A., & Niezgoda, S. R. (2018). Perspectives on the impact of machine learning, deep learning, and artificial intelligence on materials, processes, and structures engineering. Integrating Materials and Manufacturing Innovation, 7, 157-172. https://doi.org/10.1007/s40192-018-00120-8
[13] Endlskey, S., McNeese, N., & Goldberg, L. (2020). Level of automation effects on performance, situation awareness, and workload in a dynamic control task. Cognitive Technology, 25(3), 241-255. https://doi.org/10.1080/00140139.2020.1770931
[14] Gharbia, M., Chang-Richards, A., Lu, Y., Zhong, R. Y., & Li, H. (2020). Robotic technologies for on-site building construction: A systematic review. Journal of Building Engineering, 32, 101584. https://doi.org/10.1016/j.jobe.2020.101584
[15] Hasan, M., Esmaeili, B., & Goodrum, P. (2020). Augmented Reality and Digital Twin System for Integrated and Automated Construction Progress Monitoring and Project Controls. Automation in Construction, 114, 103137. https://doi.org/10.1016/j.autcon.2020.103137
[16] Janiesch, C., Zschech, P., & Heinrich, K. (2021). Machine learning and deep learning. Electronic Markets, 31, 685-695. https://doi.org/10.1007/s12525-021-00475-2
[17] LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444. https://doi.org/10.1038/nature14539
[18] Liang, X., Zhong, R. Y., Xu, G., Qin, J., & Xu, X. (2021). Human–robot collaboration in construction: Classification and research trends. Automation in Construction, 122, 103465. https://doi.org/10.1016/j.autcon.2021.103465
[19] Melenbrink, N. R., Keller, A. D., & Willmann, J. (2020). On-site autonomous construction robots: Towards unsupervised building. Automation in Construction, 119, 103312. https://doi.org/10.1016/j.autcon.2020.103312
[20] Moein, S., Salman, A., Milani, A. S., Banihashem, S., & Bagherzadeh, R. (2020). Predictive models for concrete properties using machine learning and deep learning approaches: A review. Construction and Building Materials, 261, 119658. https://doi.org/10.1016/j.conbuildmat.2020.119658
[21] Nguyen, T. (2024). The Framework of Developing the Cyber-Physical Environment for Construction Operations.
[22] Nyugen, T., Nguyen, T. K., Dinh, T., Nguyen, T. T., & Nguyen, T. D. (2021). Deep neural network with high-order neuron for the prediction of foamed concrete strength. Journal of Building Engineering, 42, 102746. https://doi.org/10.1016/j.jobe.2021.102746
[23] O'Shea, K., & Nash, R. (2015). An Introduction to Convolutional Neural Networks. arXiv preprint arXiv:1511.08458. https://doi.org/10.48550/arXiv.1511.08458
[24] Pradhananga, P., ElZomor, M. & Kasabdji, G. S. (2021). Identifying the Challenges to Adopting Robotics in the US Construction Industry. Journal of Construction Engineering and Management Volume 147, Issue 5. https://doi.org/10.1061/(ASCE)CO.1943-7862.0002007
[25] Qi, C. R., Su, H., Mo, K., & Guibas, L. J. (2017). PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 652-660. https://doi.org/10.1109/CVPR.2017.75
[26] Ragaglia, M., Argiolas, A., & Niccolini, M. (2017). Cartesian-space motion planning for autonomous construction machines. 34th International Symposium on Automation and Robotics in Construction (ISARC 2017), 78-85. https://doi.org/10.22260/isarc2017/0096
[27] Rane, N. (2023). Integrating Building Information Modelling (BIM) and Artificial Intelligence (AI) for Smart Construction Schedule, Cost, Quality, and Safety Management: Challenges and Opportunities. SSRN Electronic Journal.
[28] Regona, M., Yigitcanlar, T., Xia, B., & Li, R.Y.M. (2022). Opportunities and Adoption Challenges of AI in the Construction Industry: A PRISMA Review. Journal of Open Innovation: Technology, Market, and Complexity, 8(45). https://doi.org/10.3390/joitmc8010045
[29] Sheridan, T. B. (1992). Human and computer control of undersea teleoperators. MIT Press.
[30] Tan, T., Liu, Y., Zhao, H., Wu, Y., & Gong, J. (2021). Modeling, Planning, and Scheduling of Shop-Floor Assembly Process with Dynamic Cyber-Physical Interactions: A Case Study for CPS-Based Smart Industrial Robot Production. Robotics and Computer-Integrated Manufacturing, 67, 101983. https://doi.org/10.1016/j.rcim.2020.101983
[31] Tantawy, A., Abdelwahed, S., & Chen, Q. (2019). Continuous Stirred Tank Reactors: Modeling and Simulation for CPS Security Assessment. Proceedings of the 2019 11th International Conference on Computational Intelligence and Communication Networks (CICN), 5-10. https://doi.org/10.1109/CICN.2019.8902372
[32] Tsai, Y. C., Chen, J. H., & Wang, J. J. (2018). Predict Forex Trend via Convolutional Neural Networks. arXiv preprint arXiv:1801.03018. https://doi.org/10.48550/arXiv.1801.03018
[33] Turner, C. J., Oyekan, J., Stergioulas, L., & Griffin, D. (2021). Utilizing Industry 4.0 on the Construction Site: Challenges and Opportunities. IEEE Transactions on Industrial Informatics, 17(2), February 2021. https://doi.org/10.1109/TII.2020.3002197
[34] Usmanov, B., Karimov, S., & Mamedov, E. (2021). Modelling of industrial robotic brick system. Journal of Industrial Information Integration, 24, 100218. https://doi.org/10.1016/j.jii.2021.100218
[35] Wang, Y., Xie, L., Wang, H., ...Hu, J. (2022). Intelligent spraying robot for building walls with mobility and perception. Human–robot collaboration for on-site construction, Automation in Construction, Volume 150. https://doi.org/10.1016/j.autcon.2023.104812.
[36] Wu, Y., Li, W., Zhang, H., & He, J. (2020). Deep convolutional neural network model based chemical process. Journal of Process Control, 92, 87-98. https://doi.org/10.1016/j.jprocont.2020.05.001
[37] Yamada, M., Fujino, K., Kajita, H., & Hashimoto, T. (2017). Survey of the line of sight characteristics of construction machine operators to improve the efficiency of unmanned construction. 34th International Symposium on Automation and Robotics in Construction (ISARC 2017), 45-52. https://doi.org/10.22260/isarc2017/0057
[38] Zedin, B., Wang, X., & Lin, H. (2020). A method based on C-K theory for fast STCR development. Journal of Engineering Design, 31(8), 365-382. https://doi.org/10.1080/09544828.2020.1784251
[39] Zhang, M., Xu, R., Wu, H., Pan, J., & Luo, X. (2023). Human–robot collaboration for on-site construction. Automation in Construction, 150, 104812. https://doi.org/10.1016/j.autcon.2023.104812
[40] Zhou, Q., Liu, C., Wu, P., Gao, W., & Jiang, Y. (2021). Building information modeling-based 3D reconstruction and coverage planning enabled automatic painting of interior walls using a novel painting robot in construction. Automation in Construction, 125, 103573. https://doi.org/10.1016/j.autcon.2021.103573
 
中文文獻
[1] 林煒埕, “建築資訊模型及混合實境建構輔助機電工程施工之協同系統”, 碩士論文, 國立成功大學土木工程學研究所, 台南市, 2021.
[2] 王勝榮, “應用卷積神經網路於預測台灣鋼筋價格漲幅之研究”,碩士論文, 國立成功大學土木工程學研究所, 台南市, 2019.
[3] 江怡萱, “結合深度學習及關鍵字搜尋熱度趨勢於臺灣鋼筋價格漲跌幅之預測” , 碩士論文, 國立成功大學土木工程學研究所, 台南市, 2020.
[4] 李宜蓁, “以虛實整合為基礎建構營建工程之人機協作系統—以噴漆作業為例” ,碩士論文, 國立成功大學土木工程學研究所, 台南市, 2023.
[5] 黃柏瑜, “利用虛實整合及人機協作建構全自動化營建機器人之雛型系統—以噴漆施工作業之移動行為為例”，碩士論文, 國立成功大學土木工程學研究所, 台南市, 2023.
[6] 蕭苡烜, “結合建築資訊模型及混合實境建構室內油漆工程之人機協作系統”，碩士論文, 國立成功大學土木工程學研究所, 台南市, 2022.