臺灣博碩士論文加值系統

隨著生產操作自動化的比例增加，使用機器手臂執行工作的需求也大幅增加。無論機器手臂的類型及工作情境為何，過去多是使用可提供擬真影像及精緻動作控制的軟體來規劃手臂動作。儘管軟體可以靈巧地操作3D環視來觀看擬真影像，但該影像僅是幾何上相仿而未與實境畫面重合，無法傳遞完整的實境視覺感，於是不可避免地須來回於軟體與實境間調校至完成。本研究中以延展實境(XR)技術為核心設計人機介面，令工作人員穿戴Microsoft Hololens 2，視覺化地以直覺手勢透過介面設計牽動實體機器手臂，即時互動地完成動作規劃。實作上則是將實體空間工作物件之關鍵點方位及虛擬版機器手臂一併建立於虛擬空間中，由操作者透過Microsoft Hololens 2依工作需求直覺地指派關鍵點給具備逆向運動能力之虛擬手臂，並即時演算確認路徑之可行性，再將關節值傳給實體手臂來做運動。結果顯示介面的操作簡易平順且便利，而空間定位之精度尚可以透過離線式深度學習達到虛實高度吻合之程度。

As the percentage of automation in production operations increases, so does the need to use robotic arms to perform work. Regardless of the type of robotic arm and the context in which it works, arm motions were commonly planned using software that mimics the physical scene with photorealistic imagery and realistic motion control gadget. Although the software tries to provide an immersive feeling, the image is only a geometric replica and cannot convey any visual sense of the reality. Therefore, it is inevitable to go back and forth between the software and the real world for adjustments until complete. In this research, a human-machine interface is designed with XR (eXtended Reality) techniques as the core, by wearing Microsoft Hololens 2, a user may visually use intuitive gestures to move the physical robot arm and complete the action plan interactively in real time. In practice, some key points of the physical working environment and a virtual robot are preliminarily defined in the virtual space, then the operator may intuitively assign the key point’s positions and orientations to the end-effector of the virtual robot that has inverse kinematics capability through Microsoft Hololens 2 to meet the work requirements. Immediately followed by a real-time calculation will confirms the feasibility of the path properties, and then pass the virtual joint movements to the physical arm for physical transports. Any adjustment may still apply through a similar interactive process. The results show that the operation of the interface is simple, smooth and convenient, and the accuracy of the physical matching can be achieved through an off-line deep learning procedure.

摘要..i
Abstract..ii
誌謝..iii
目錄...iv
表目錄...vi
圖目錄...vii
第一章 緒論...1
1.1 研究背景...1
1.2 研究動機...1
1.3 研究目的...2
1.4 研究限制...3
1.5 章節說明...3
第二章文獻探討...4
2.1 延展實境定義...4
2.1.1 人機介面...6
2.2 機器手臂運動學...10
2.2.1 正向運動(Forward Kinematic, IK)...10
2.2.2 逆向運動(Inverse Kinematic, IK)...11
2.2.3 奇異點...12
2.3 XR相關應用...14
2.4 文獻總結...15
第三章 研究方法...17
3.1 研究方法介紹...17
3.2 模型建構...19
3.3 虛擬機器手臂控制-逆向運動(INVERSE KINEMATIC, IK)...21
3.4 人機介面-XR技術應用...28
3.5 Unity與實際機器手臂串接...32
3.5.1 Unity設定傳輸格式...33
3.5.2 即時狀態反應...34
第四章 研究實作...35
4.1 研究設備...35
4.2 實作介紹...36
4.3 虛擬環境投射...37
4.3.1 互動區域牽引虛擬目標...39
4.4 結果分析並調整...43
第五章 研究結論...44
5.1 研究貢獻...44
5.2 未來研究...45
參考文獻...46
EXTENDED ABSTRACT...48

Aristidou, A., and Lasenby, J., FABRIK: A fast, iterative solver for the Inverse Kinematics problem, Vol. 73, Issue5. pp. 243-260,2011.

Azuma, R., Baillot, Y., Behringer, R., Feiner, S., Julier, S. and MacIntyre, B., Recent Advances in Augmented Reality, IEEE Computer Graphics and Applications, Vol. 21, pp. 34-47, 2001.

Denavit, J., and Hartenberg, R. S., A Kinematic Notation for Lower-Pair Mechanisms Based on Matrices. Vol.0 22, pp.215-221,1955.

Gorecky, D., Schmitt, M., Loskyll, M., and Zühlke, D., Human-machine-interaction in the industry 4.0 era,IEEE International Conference on Industrial Informatics (INDIN), pp. 289-294,2014.

Hayes, M. J. D., Husty, M. L., and Zsombor-Murray, P. J., Singular Configurations of Wrist-Partitioned 6R Serial Robots: a Geometric Perspective for Users ,Transactions of the Canadian Society for Mechanical Engineering, 26(1), pp. 41-45,2002.

Milgram, P., and Kishino, F., A Taxonomy of Mixed Reality Visual Displays, IEICE Trans. Information Systems, Vol. E77-D, No. 12, pp. 1321-1329,1994.

Namjoshi, J., and Rawat, M., Role of smart manufacturing in industry 4.0, Materials Today: Proceedings, Vol. 63, pp. 475-478,2022.

Nikolakis, N., Maratos, V., and Makris, S., A cyber physical system (CPS) approach for safe human-robot collaboration in a shared workplace,Robotics and Computer-Integrated Manufacturing, Vol. 56, pp. 233-243,2019.

Park, K. B., Choi, S. H., Kim, M., and Lee, J. Y., Deep learning-based mobile augmented reality for task assistance using 3D spatial mapping and snapshot-based RGB-D data,Computers & Industrial Engineering, Vol. 146, 106585,2020.

Rauschnabel, P. A., Felix, R., Hinsch, C., Shahab, H., and Alt, F., What is XR? Towards a Framework for Augmented and Virtual Reality, Computers in Human Behavior, Vol. 133, 107289,2022.

Wang, B., Zheng, L., Wang, Y., Fang, W., and Wang, L., Towards the industry 5.0 frontier: Review and prospect of XR in product assembly, Journal of Manufacturing Systems, Vol. 74, pp 777-811,2024.

Wang, L. C. T., and Chen, C. C., A Combined Optimization Method for Solving The Inverse Kinematics Problem of Mechanical Manipulators,Vol. 7, No. 4,pp. 489-499,1991.

Xie, J., Liu, Y., Wang, X., Fang, S., and Liu, S., A new XR-based human‐robot collaboration assembly system based on industrial metaverse, Journal of Manufacturing Systems,Vol. 74,pp. 949-964,2024.

Yun, H., and Jun, M. B. G. (2022). "Immersive and interactive cyber-physical system (I2CPS) and virtual reality interface for human involved robotic manufacturing." Journal of Manufacturing Systems,Vol. 62,pp. 234-248,2022.