隨著科技的發展與人力成本的上升，許多自動化生產線皆以機械
手臂完成產線上的應用。不斷改良的感測器技術以及立體視覺的開發，
使機械手臂的應用越來越彈性化，以零件隨機拾取為例，當零件任意
放置於工作面上，利用結構光的技術可以獲得零件所在位置的點雲資
料，透過點雲資料的處理可求取零件的夾取點。然而，當點雲資料不
充足且零件幾何較為複雜時，以殘缺的點雲判斷夾取點，夾爪下爪時
可能產生干涉。為了解決此問題，本研究提出以零件的 3D CAD 模型
自動化求出零件的夾取點，改善因點雲資料不充足，而無法獲得適當
夾取點之情形。
本研究主要是利用 3D CAD 模型的幾何資訊，以射線法進行夾取
資訊的分析，並建立一套干涉檢查系統，以避免夾爪與零件間的干涉。
接著透過特徵匹配將 3D CAD 模型的點雲資料與掃描的點雲資料進
行匹配，以利 3D CAD 模型的夾取資訊轉換為零件實際擺放於工作台
上的夾取資訊，並根據實際的工作環境求得一組離零件重心最近的夾
取點，最終以機械手臂完成零件的拾取與分類。
本論文除了詳述如何以 3D CAD 模型求取夾取資訊，也簡述處理
點雲資料的演算法，最終利用多種不同幾何特質的零件驗證本分析系
統的實用性。
關鍵字：夾取點分析、機械手臂、點雲資料匹配、3D CAD

With the development of science and technology and the rise of labor
costs, many production lines rely on manipulators to complete various
production tasks. The improvement of sensor technology and the
development of computer vision make the application of manipulators
more flexible. Taking the random picking of parts as an example, when a
mechanical part is arbitrarily placed on a working table, a structured-light
scanner can be adopted to obtain the point data of the part, and the data
can then be used to find the grasping points of the part. However, it is
likely that the scanned data points are insufficient for a part with complex
geometry, which results in inappropriate grasping points. To solve this
problem, this study proposes the use of the part’s 3D CAD model to find
grasping points which can ensure free of interference between the gripper
and the part during the grasping operations.
This research uses the ray tracing technique to find grasping points
from the 3D CAD model, and establishes a collision checking algorithm
to avoid the interference between the gripper and the part. After that, a
feature matching method is applied to compare the point cloud data
converted from the 3D CAD model and the point data obtained from the
scanner. The purpose is to transform the grasping information generated
from the 3D CAD model into the real object placed on the working table.
The results are used to find the final set of grasping point which is
interference free and closest to the gravity center of the part. At last, a
manipulator is employed to undertake the part grasping experiment.
Besides expatiating on the algorithm of point cloud processing and
3D CAD analysis, this thesis also demonstrates the capability of the
system via a couple of objects with various types of geometry.
Keyword: 3D CAD, Grasping point, Manipulator, Point cloud processing

[1] Besl, P.J. and McKay, N.D. (1992), “A method for registration of 3-D shapes,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 14, No. 2, pp. 239-256.
[2] Bentley, J.L. (1975), “Multidimensional binary search trees used for associative searching,” Communications of the ACM, Vol. 18, No. 9, pp. 509-517.
[3] Pomerleau, F., Colas, F. and Siegwart, R. (2015), “A review of point cloud registration algorithms for mobile robotics,” Foundations and Trends in Robotics, Vol. 4, No. 1, pp. 1-104.
[4] Meacher, D. (1982), “Geometric modeling using octree encoding,” Computer Graphics and Image Processing, Vol. 19, No 2, pp. 129-147.
[5] Rusu, R.B., Marton, Z.C., Blodow, N. and Beetz, M. (2008), “Persistent point feature histograms for 3D point clouds,” in Proceedings of the 10th International Conference on Intelligent Autonomous Systems, Baden Baden, Germany, July, 2008, pp. 119-128.
[6] Rusu, R.B., Blodow, N., and Beetz, M. (2009), “Fast point feature histograms (FPFH) for 3D registration,” IEEE International Conference on Robotics and Automation, IEEE, Kobe, Japan, May 12-17, 2009, pp. 3212-3217.
[7] Fischler, M.A. and Bolles, R.C. (1981), “Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography,” Communications of the ACM, Vol. 24, No. 11, pp. 381-395.
[8] 黃良正，「利用三維特徵點資訊以實現機器人即時定位」（2013），碩士論文，國立雲林科技大學資訊工程系研究所，雲林縣。
[9] Rusu, R.B., Bradski, G., Thibaux, R. and Hsu, J. (2010), “Fast 3d recognition and pose using the viewpoint feature histogram,” Intelligent Robots and Systems, IEEE/RSJ International Conference, October 18-22, 2010, Taipei, Taiwan.
[10] Aldoma, A., Vincze, M., Blodow, N., Gossow, D., Gedikli, S., Rusu, R.B. Rusu (2011), “CAD-model recognition and 6DOF pose estimation using 3D cues,” Computer Vision Workshops, IEEE International Conference, November 06-13, 2011, Barcelona, Spain.
[11] Sipiran, I. and Bustos, B.(2011), “Harris 3D: A robust extension of the Harris operator for interest point detection on 3D meshes,” Visual Computer, Vol. 27, Issue 11, pp. 963-976.
[12] 陳柏均，「基於3D物件辨識與對位之機械手臂夾取系統」（2016），碩士論文，台北科技大學自動化科技研究所，台北市。
[13] Vidal, J., Lin, C.Y, Lladó, X., Martí, R. (2018), “A method for 6D pose estimation of free-form rigid objects using point pair features on range data,” Sensors, Vol. 18, No. 8, https://doi.org/10.3390/ s18082678.
[14] 郭皓淵，「利用單張深度影像的三維物體定位與姿態估測」（2014），碩士論文，國立清華大學資訊系統與應用研究所，新竹市。
[15] 蔡碩倫，「應用深度學習及雙目立體視覺於機械手臂夾取物體作業」（2019），碩士論文，國立台北科技大學工業工程與管理研究所，台北市。
[16] Romero, J. (2011), From human to robot grasping, Doctoral Thesis, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
[17] Wong, L.L.S. (2008), Robotic grasping on the stanford artificial intelligence robot, Master's Thesis, Department of Computer Science, Stanford Univeristy, CA, USA.
[18] Choi, C., Taguchi, Y., Tuzel, O., Liu, M. and Ramalingam, S., "Voting-based pose estimation for robotic assembly using a 3D sensor," Proceedings of IEEE International Conference on Robotics and Automation, St. Paul, MN, USA, May 14, 2012, pp. 1724-1731.
[19] 吳政輝，「基於CAD模型之物體姿態辨識及其於機械臂隨機堆疊抓取之應用」（2019），碩士論文，國立交通大學電控工程研究所，新竹市。
[20] 顏鳳婷，「以機械手臂搭配Creo Toolkit程式及3D點資料處理技術進行簡易零件組裝」（2014），碩士論文，國立台灣科技大學機械工程系研究所，台北市。
[21] 王柏富，「以3D CAD模型及3D點資料處理技術進行自動化機械手臂物件夾取」（2019），碩士論文，國立台灣科技大學機械工程系研究所，台北市。
[22] Point Cloud Library (PCL), Retrieved from http://pointclouds.org/documentation/
[23] MeshLab Retrieved from https://www.meshlab.net/
[24] M. C. Lee (2016), “几何特征系列：Point feature histogram（点特征直方图）,” Retrieved from http://lemonc.me/point-feature-histogram.html
[25] M. C. Lee (2016), “几何特征系列：Fast point feature histogram（快速点特征直方图）,” Retrieved from http://lemonc.me/fast-point-feature-histogram.html
[26] EPSON Prosix S5-A701S (S5), Retrieved from https://neon.epson-europe.com/robots/products/product.php?id=10884&content=547
[27] SCHUNK GmbH & Co. KG., Retrieved from https://wettmeister.schunk.com/tr_en/gripping-systems/product/2764-0360140-rh-918/
[28] HP 3D Structured Light Scanner Pro S3, Retrieved from https://www8.hp.com/us/en/campaign/3Dscanner/overview.html