隨著科技迅速發展，現今自動化生產線皆以多部機械搭配各式機構及夾治具進行零件組裝，雖已是自動化生產線，但仍有許多前置作業需以人工方式事先安排，如零件定位、移載及組裝路徑規劃等，且各站生產線之機台皆以同一路徑重複進行零件組裝的動作，此方法雖可減少零件組裝的人力成本，但卻需要有專業技術人員來進行組裝路徑規劃組裝及開發各式夾治具，因此前置作業仍需耗費不少人力、物力及時間。本研究開發「簡易零件之機械手臂自動化組裝系統」，以單一機械手臂取代人力、以3D結構光掃描器取代人眼視覺、以裝配圖取代路徑規劃，以達成減少自動化組裝之前置作業及夾治具開發的目標。
本論文主要可分為兩大部分：「組裝路徑規劃」及「裝配零件辨識與定位」，其中「組裝路徑規劃」是以Creo Toolkit二次開發工具取得裝配圖中的組裝順序及路徑，而「裝配零件辨識與定位」則是使用3D點資料演算法分析工作台所有零件之點雲資料，進行零件辨識與定位，並使用Epson機械手臂依序組裝零件。最後本論文以螺母拆裝組合積木作為實例，驗證所開發系統之實用性。
關鍵字：機械手臂、3D點資料處理、零件組裝、CAD

As technology develops rapidly, the automated production lines are using multiple machines and various types of mechanisms and fixtures at assembly operations. Although the automated production lines are common, there is plenty of preparation for initializing the project of assembling operations, such as locate, move and assemble parts. And the machine at each station in the production line repeats the assembly operation in the same path. This method can reduce the labor cost, but it requires professional technicians to carry out assembly routing and the development of various types of fixtures. Therefore it also resulted in high demand for manpower, material resources, time and costs.
In order to reduce the time of pre-processing assembly operations and design the fixtures, this thesis studies the issue of developing a robot-based assembly system for simple parts. The system aims to replace manpower with a single robotic arm, the human vision with a 3D scanner, and assembly path planning with an assembly drawing.
This study consists of the following two research issues: planning of assembled path and identification and location of parts. The first issue "planning of assembled path" is to acquire the assembly path and the sequence via Creo Toolkit programs. The second issue "identification and location of parts" uses several algorithms developed based on 3D data points to identify the location of parts by scanning the parts placed on the working table. Afterward, an Epson robot arm is utilized to assemble all of the parts in sequence. Finally, this study will illustrate the practicability of this system via building blocks with nuts and bolts.

Keywords: Robot arm, 3D points processing, Assembly, CAD

[1]http://blog.udn.com/ansercomtw/112281934
[2]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.
[3]Zhang, Z.Y.(1994),“Iterative point matching for registration of free-form curves and surfaces,” International Journal of Computer Vision. Springer, Vol. 13, No. 12, pp. 119-152
[4]Rusinkiewicz, S. and Marc L. (2001), “Efficient Variants of the ICP Algorithm,” Proceedings Third International Conference on 3-D Digital Imaging and Modeling, May28-June1,Quebec, Canada.
[5]Meacher, D. (1982), “Geometric modeling using octree encoding,” Computer Graphics and Image Processing, Vol. 19,No 2, pp. 129-147.
[6]Friedman, J.H., Bentley, J.H., and Finkel, R.A. (1977), “An algorithm for finding best matches in logarithmic expected time,” ACM Transactions on Mathematical Software, Vol. 3, No. 3 pp. 209-226
[7]Nene, SA. and Nayar, SK. (1997) “A simple algorithm for nearest neighbor search in high dimensions,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 19, No. 9, pp.989-1003.
[8]Nüchter, A., Lingemann, K. and Hertzberg, J. (2007) “Cached k-d tree search for ICP algorithms,” Sixth International Conference on 3-D Digital Imaging and Modeling, August 21-23, Montreal, Canada.
[9]Sample, N., Haines, M., Arnold, M. and Purcell, T. (2001) “Optimizing search strategies in k-d trees,” 5th WSES/IEEE World Multiconference on Circuits, July 8-15, Crete, Greece.
[10]Rusu, R.B., Blodow, N., and Beetz, M. (2008), “Towards 3D point cloud based object maps for the household environment,” Robotics and Autonomous Systems Journal, Vol. 56, No. 11, pp. 927-941.
[11]Low, K.L. (2004), “Linear Least-Squares Optimization for Point-to Plane ICP Surface Registration,’’ Technical Report, TR04-04
Department of Computer Science, University of North Carolina,
Chapel Hill, NC, USA.
[12]Rusu, R.B., Blodow, N., and Beetz, M.(2009), “Fast point feature histograms(FPFH)for 3D registration,” IEEE International Conference on Robotics and Automation, May 12-17, Kobe, Japan.
[13]Rusu, R.B., Bradski, G., Thibaux, R and Hsu, J. (2010), “Fast 3d recognition and pose using the viewpoint feature histogram,” IEEE/RSJ International Conference on Intelligent Robots and Systems, October 18-22, Taipei, Taiwan.
[14]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.
[15]陳柏均，「基於3D物件辨識與對位之機械手臂夾取系統」（2015），碩士論文，台北科技大學自動化科技研究所，台北市。
[16]唐培文，「基於結構光之自動隨機物件夾取系統」（2015），碩士論文，台灣科技大學機械工程系研究所，台北市。
[17]韓致偉，「3D視覺伺服系統整合機械手臂於物體追蹤取放之研究」（2006），碩士論文，華梵大學機電工程學系，新北市。
[18]https://www8.hp.com/us/en/campaign/3Dscanner/overview.html
[19]https://www.epson.com.tw/RobotArm
[20]https://schunk.com/de_en/gripping-systems/series/rh/
[21]http://pointclouds.org/documentation/
[22]https://neon.epson-europe.com/robots?content=687
[23]http://pointclouds.org/documentation/tutorials/fpfh_estimation.php
[24]http://pointclouds.org/documentation/tutorials/pfh_estimation.php
[25]http://pointclouds.org/documentation/tutorials/kdtree_search.php
[26]https://en.wikipedia.org/wiki/Random_sample_consensus
[27]劉彥峰，「以機械手臂輔助零件隨機拾取與表面瑕疵檢測之系統開發與應用」（2018），碩士論文，台灣科技大學機械工程系研究所，台北市。
[28]黃薇耘，「使用機械手臂搭配影像處理技術進行簡單零件組裝」（2018），碩士論文，台灣科技大學機械工程系研究所，台北市。
[29]林亮均，「結構光結合機械手臂重建工件三維模型之研究」（2018），碩士論文，中正大學機械工程系研究所，嘉義縣。