科技引領著產業轉型，尤其工業4.0下，製造工廠紛紛引入機械手臂作為智慧自動化的應用。機械手臂的引進為了替代人類執行高度重複性且潛在危險的工作。然而，在機械加工產業中，去毛邊加工仍然依賴人力，這種人力密集、耗時耗力的工作也面臨著缺工的挑戰。
去毛邊加工在製造業中扮演決定產品質量的重要角色。人類去毛邊的過程中，需經歷兩個步驟：首先，透過眼睛檢查毛邊位置；其次，手持工具進行去除毛邊，根據毛邊大小不同，進而改變加工速度和施力等。本研究的主要目標是透過觀察人類的加工策略，開發一套毛邊辨識流程和系統，進而將辨識毛邊以應用於機器人去毛邊中。
本研究論文主要為毛邊辨識研究。在研究中，透過自製掃描平台搭配機械手臂進行多角度的掃瞄。將雷射輪廓儀的掃描資料轉成點雲，而後與工件CAD模型進行比較，並利用開發的毛邊辨識演算法判斷出毛邊位置以及大小。藉此，從獲得的毛邊資訊將提供後續機械手臂去毛邊加工參數的參考依據，並驗證了毛邊辨識技術應用於機械手臂去毛邊加工的可行性與應用性。

Technological advancements, particularly under Industry 4.0, have led many manufacturing facilities to adopt robotic arms for intelligent automation, aiming to replace human labor in repetitive and hazardous tasks. However, in the machining industry, deburring—a process vital to product quality—still heavily relies on manual labor, posing challenges due to labor shortages.
Deburring is essential for ensuring product quality and is an indispensable process in manufacturing. When humans perform deburring, they typically follow two key steps: first, they visually inspect the location of burrs, and second, they use handheld tools to remove the burrs, adjusting their approach based on the size of the burrs, often requiring variations in speed and force. The objective of this research is to observe and understand the strategies and thought processes employed by humans in deburring, and to develop a systematic approach and system for applying these strategies to robotic arm-based deburring.
In this study, a custom-made scanning platform is utilized in conjunction with a robotic arm to perform multi-angle scans of the workpieces. Laser profiler scan data is converted into point clouds and compared with the workpieces' CAD model to identify discrepancies. An in-house-developed burr identification algorithm is used to determine the location and size of the burrs. The information obtained from this identification process serves as a reference for subsequent robotic arm deburring operations. Additionally, the research findings are validated through extensive experiments.

[1] S. Y. Jin, A. Pramanik, A. Basak, C. Prakash, S. Shankar, and S. Debnath, "Burr formation and its treatments—a review," The International Journal of Advanced Manufacturing Technology, vol. 107, pp. 2189-2210, 2020.
[2] D. Dornfeld, "Strategies for preventing and minimizing burr formation," 2004.
[3] N. Ramachandran, S. Pande, and N. Ramakrishnan, "The role of deburring in manufacturing: A state-of-the-art survey," Journal of materials processing technology, vol. 44, no. 1-2, pp. 1-13, 1994.
[4] J. C. Aurich, D. Dornfeld, P. Arrazola, V. Franke, L. Leitz, and S. Min, "Burrs—Analysis, control and removal," CIRP annals, vol. 58, no. 2, pp. 519-542, 2009.
[5] S.-L. Ko and D. A. Dornfeld, "A study on burr formation mechanism," 1991.
[6] V. Franke, L. Leitz, and J. Aurich, "Burr measurement: a round robin test comparing different methods," in Burrs-Analysis, Control and Removal: Proceedings of the CIRP International Conference on Burrs, 2nd-3rd April, 2009, University of Kaiserslautern, Germany, 2010: Springer, pp. 167-178.
[7] O. Olvera and G. Barrow, "An experimental study of burr formation in square shoulder face milling," International Journal of Machine Tools and Manufacture, vol. 36, no. 9, pp. 1005-1020, 1996.
[8] H.-D. Lin, "Automated defect inspection of light-emitting diode chips using neural network and statistical approaches," Expert Systems with Applications, vol. 36, no. 1, pp. 219-226, 2009.
[9] C.-F. J. Kuo, C.-T. M. Hsu, Z.-X. Liu, and H.-C. Wu, "Automatic inspection system of LED chip using two-stages back-propagation neural network," Journal of Intelligent Manufacturing, vol. 25, pp. 1235-1243, 2014.
[10] A. Pillai, S. Chiddarwar, M. Rahul, and M. Dalvi, "Burr registration using image processing," in Advances in Industrial Machines and Mechanisms: Select Proceedings of IPROMM 2020, 2021: Springer, pp. 321-330.
[11] A. Mohammed, J. Kvam, I. F. Onstein, M. Bakken, and H. Schulerud, "Automated 3D burr detection in cast manufacturing using sparse convolutional neural networks," Journal of Intelligent Manufacturing, vol. 34, no. 1, pp. 303-314, 2023.
[12] A. Tellaeche and R. Arana, "Robust 3d object model reconstruction and matching for complex automated deburring operations," Journal of Imaging, vol. 2, no. 1, p. 8, 2016.
[13] S.-L. Ko, J.-E. Chang, and G.-E. Yang, "Burr minimizing scheme in drilling," Journal of Materials Processing Technology, vol. 140, no. 1-3, pp. 237-242, 2003.
[14] K.-i. Shimokura and S. Liu, "Programming deburring robots based on human demonstration with direct burr size measurement," in Proceedings of the 1994 IEEE International Conference on Robotics and Automation, 1994: IEEE, pp. 572-577.
[15] H.-Y. J.-Y. C., "3d surface scanning based on stereo vision for burr detection," Master, Power Mechanical Engineering, National Tsing Hua University, 2020.
[16] J.-Y. J. C. Yi-An Chen, "Burr Position Detection With Laser Profiler to Guide 6-axis Manipulator for Deburring Processing," presented at the JSME-IIP/ASME-ISPS Micromechatronics for Information and Precision Equipment, 2022.
[17] Y.-A. C. J.-Y. C, "Identification of 3d burrs on irregular-shaped workpieces with novel computational intelligence based on laser profiler data," Master, Power Mechanical Engineering, National Tsing Hua University, 2022.
[18] S. Liu and H. Asada, "Task-level robot adaptive control based on human teaching data and its application to deburring," in 1993 American Control Conference, 1993: IEEE, pp. 1414-1417.
[19] J. Wang, G. Zhang, H. Zhang, and T. Fuhlbrigge, "Force control technologies for new robotic applications," in 2008 IEEE International Conference on Technologies for Practical Robot Applications, 2008: IEEE, pp. 143-149.
[20] S. A. Bello, S. Yu, C. Wang, J. M. Adam, and J. Li, "Deep learning on 3D point clouds," Remote Sensing, vol. 12, no. 11, p. 1729, 2020.
[21] R. Sreenivasulu and C. S. Rao, "Overview on Burr Formation, Simulation and Experimental Investigation of Burr size—based on Taguchi Design of Experiments during Drilling of Alluminium 7075 Alloy," Esnaola A, 2015.
[22] F. Schäfer, "Gratbildung und Entgraten beim Umfangsstirnfräsen," VDI-Zeitschrift, vol. 120, no. 1-2, pp. 47-55, 1978.
[23] L. Gillespie, "The battle of the burr: new strategies and new tricks," Manufacturing Engineering(USA), vol. 116, no. 2, pp. 69-70, 1996.
[24] ISO13715:2000(en) technical drawings —edges of undefined shape —vocabulary and indications, t. I. O. f. Standardization.
[25] L. K. Gillespie, "The formation and properties of machining burrs," 1973.
[26] U. Heisel, M. Luik, R. Eisseler, and M. Schaal, "Prediction of parameters for the burr dimensions in short-hole drilling," CIRP annals, vol. 54, no. 1, pp. 79-82, 2005.
[27] T. Wang, "Poisson-Disk Sampling: Theory and Applications," in Encyclopedia of Computer Graphics and Games, N. Lee Ed. Cham: Springer International Publishing, 2020, pp. 1-8.
[28] S. D. Roth, "Ray casting for modeling solids," Computer graphics and image processing, vol. 18, no. 2, pp. 109-144, 1982.
[29] P. J. Besl and N. D. McKay, "Method for registration of 3-D shapes," in Sensor fusion IV: control paradigms and data structures, 1992, vol. 1611: Spie, pp. 586-606.
[30] J. L. Bentley, "Multidimensional binary search trees used for associative searching," Communications of the ACM, vol. 18, no. 9, pp. 509-517, 1975.
[31] M. Muja and D. G. Lowe, "Scalable nearest neighbor algorithms for high dimensional data," IEEE transactions on pattern analysis and machine intelligence, vol. 36, no. 11, pp. 2227-2240, 2014.
[32] M. Her and H. Kazerooni, "Automated robotic deburring of parts using compliance control," 1991.