臺灣博碩士論文加值系統

本研究主要在探討如何將Microsoft Kinect感測器之骨架追蹤系統與兩隻機械手臂整合，以快速又穩健之方式打造出一組雙機械手臂之自然體感控制平台。這個構想主要源自於救災與危險物品之處理，以及像深海探勘等這類危險的工作，如果能以自然體感直覺的操作方式遠端遙控機械手臂，而非傳統按鍵、觸控面板和類比搖桿這類操作複雜度較高的方式來控制機械手臂，不僅可以降低操作學習門檻，而且一次操作兩隻手臂工作效能更高。
自然體感主要強調人就是控制器這個概念，其優勢主要來自於使用者不需穿戴任何控制器，只需使用自己的身體及聲音等作為虛擬控制器，即可操縱受控體。為實現此一構想並驗證其可行性，本研究使用Kinect深度感測器之骨架追蹤系統，結合ROBOTIS 4-DOF機械手臂，建立一組以自然體感控制之雙機械手臂控制平台。本研究測試由Kinect深度感測器抓到之手部資料傳送至手臂作動之響應效能與對應比例效能，同時探討雙機械手臂之自然體感控制平台夾筆畫圖形之效能，經由此一連串的測試展示此平台之工作效能。

The main purpose of the research is to build a prototype platform of robot arms with Natural Interaction (NI). In a quick and robust way, a Microsoft Kinect sensor was used to integrate with two 4-axis robot arms. The idea was from the handling of hazardous materials, disaster relief management, deep-sea mining, and other dangerous tasks. Instead of using the analog stick or keypad to control the robot arm, if the operators can use their bodies as a controller to remote control the robot arm in a natural way, then the learning curve for the operation can be reduced dramatically. And, operators can control two robot arms in the same time.
NI emphasizes that human is the controller. The main benefit is that operators use their own bodies or voice and need not to carry any extra facility to manipulate the system. To achieve this concept and validate its feasibility, a Kinect depth sensor combined with two ROBOTIS 4-DOF robot arms was used to set up a NI platform. This research tested the efficiency between the Kinect and two ROBOTIS 4-DOF robot arms. Through a series of experiments, the NI’s concepts and its merits have been verified in this research.

摘要 I
Abstract II
誌謝 IV
目錄 V
圖目錄 VII
表目錄 IX
第一章 緒論 1
1.1 研究動機與目的 1
1.2 文獻回顧 1
1.3 論文架構 7
第二章 自然體感(Natural Interaction) 8
2.1 前言 8
2.2 何謂自然體感 8
2.3 Kinect感測器於自然體感之相關應用 10
第三章 軟體技術與硬體設備之介紹 13
3.1 Ruby Programming Language 13
3.1.1 Ruby的特色 14
3.2 Microsoft Kinect Sensor 14
3.2.1 Kinect感測器之硬體規格 14
3.2.2 Kinect感測器之運作原理 16
3.2.3 Kinect軟體開發工具介紹 21
3.3 機械手臂 26
第四章 雙機械手臂之自然體感控制平台之設計與實作 28
4.1 系統架構 28
4.2 機械手臂操作方式 32
4.3 系統之運作流程 33
4.4 機械手臂之設計與實作 35
4.4.1 逆向運動學 36
4.4.2 機械手臂抽象層API設計 38
4.5 Kinect感測器之骨架追蹤於手部時之雜訊抑制 39
第五章 雙機械手臂之自然體感控制平台之測試與分析 41
5.1 KINECT感測器與機械手臂之對應效能測試 41
5.1.1 KINECT感測器與機械手臂之對應比例效能測試 45
5.2 雙機械手臂之自然體感控制平台之夾筆畫圖形測試 52
5.3 雙機械手臂之自然體感控制平台之操作測試 55
第六章 結論 57
6.1 結果與討論 57
6.2 未來展望 58
參考文獻 60
附錄 64
附錄一 : ROBOTIS AX-12+ Control Table 64
附錄二 : ROBOTIS AX-12+ Dimension 65
附錄三 : ROBOTIS USB2Dynamixel Connector Pin Layout 65
附錄四 : AX-12+ Robot Arm Controller Source Code (Ruby) 66
附錄五 : AX-12+ Robot Arm Abstraction Layer Source Code (Ruby) 68
附錄六 : Kinect Sensor Server Source Code (C/C++) 75

[1]"Blog", By Heresy,"http://viml.nchc.org.tw/blog/paper_info.php?CLASS_ID=1 &;SUB_ID=6&;PAPER_ID=419"
[2]J.Tong, J.Zhou, L.Liu, Z.Pan, H.Yan, "Scanning 3D Full Human Bodies Using Kinects", IEEE Visualization and Computer Graphics Magazine, VOL.18, NO.4, April 2012, Pages 643-650
[3]Xiaolong Tong,Pin Xu, Xing Yan, "Research on skeleton animation motion data based on Kinect", IEEE Computational Intelligence and Design (ISCID), 2012
[4]Y.Manabe,R.Saito ,K.Sugawara, "Biometric Gait Verification by Horizontal Swings in Frontal Manner towards Human-Aware Environment", IEEE Cognitive Informatics &; Cognitive Computing (ICCI*CC), 2012
[5]L.Gallo, A.P.Placitelli,M.Ciampi, "Controller-free exploration of medical image data: Experiencing the Kinect", IEEE Computer-Based Medical Systems(CBMS) International Conference, 2011
[6]"FAAST Project Website", "http://projects.ict.usc.edu/mxr/faast/"
[7]E.A.Suma, B.Lange, A.Rizzo, D.M.Krum, M.Bolas, "FAAST : The Flexible Action and Articulated Skeleton Toolkit", IEEE Virtual Reality Conferences, 2011
[8]"Ultimate Battlefield 3 Simulator (Build &; Test) – The Gadget Show", "http://www.youtube.com/watch?v=eg8Bh5iI2WY"
[9]"Programming Ruby : The Pragmatic Programmers' Guide", by Dave Thomas, with Chad Fowler and Andy Hunt
[10]"松本行弘的程式世界 : 成為一流程式設計師的14種思考術", 作者：松本行弘, 譯者：鄧瑋敦
[11]"Ruby 的名字由來", "http://www.43911.com/peixun/jsjpx/rubypx/ruby0/ 1341356372.shtml"
[12]"Ruby Programming Language Official Website", "http://www.ruby-lang.org/"
[13]"The Mythical Man-Month : Essays on Software Engineering", by Frederick P. Brooks, Jr.
[14]"The Teardown_Teardown Kinect", IET Journals &; Magazines, 2011
[15]"PrimeSense Reference Design 1.08", PrimeSense Inc., 2010
[16]"Programming Guide : Getting Started with the Kinect for Windows SDK Beta", Microsoft Research, 2011
[17]"Blog", By Eric Gregori, "http://buildsmartrobots.ning.com/profiles/blogs/ one-year-anniversary-for-the-kinect-over-10-million-units-shipped"
[18]Mohd Sidik, M.K., Sunar, M.S., Ismail, I., Mokhtar, M.K., Jusoh, N.B.M., “A Study on Natural Interaction for Human Body Motion using Depth Image Data", IEEE Digital Media and Digital Content Management (DMDCM), 2011
[19]Zhengyou Zhang,"Microsoft Kinect Sensor and Its Effect” , IEEE MultiMedia, 2012
[20]"OpenNI Organization Official Website", "http://www.openni.org/"
[21]"OpenNI User Guide", OpenNI, 2010
[22]"NITE Controls User Guide", PrimeSense Inc., 2011
[23]"NITE Algorithms 1.3 Note", PrimeSense Inc., 2010
[24]Jwu-Sheng Hu, Ming-Chih Chien, Yung-Jung Chang, Shyh-Haur Su, and Chen-Yu Kai, "A Ball-Throwing Robot with Visual Feedback", IEEE Intelligent Robots and Systems Conferences, 2010
[25]"ROBOTIS User’s Manual_Dynamixel:AX-12", ROBOTIS, 2006
[26]"ROBOTIS User’s Manual_USB2Dynamixel", ROBOTIS, 2006
[27]莊修一, "AX-12 機械手臂路徑軌跡規劃與影像辨識之研究", 國立勤益科技大學機械工程系碩士論文, 2010
[28]林明毅, "自然體感機械手臂展示平台之設計與測試", 國立勤益科技大學機械工程系碩士論文, 2012
[29]J.Smisek, M.Jancosek, T.Pajdla, "3D with Kinect", IEEE Computer Vision Workshops International Conference(ICCV Workshops), 2011
[30]C.S.Park, S.W.Kim, D.Kim, S.R.Oh, "Comparison of plane extraction performance using laser scanner and Kinect", IEEE Ubiquitous Robots and Ambient Intelligence(URAI) International Conference, 2011
[31]M.A.Livingston, J.Sebastian, Z.Ai, J.W.Decker, "Performance measurements for the Microsoft Kinect skeleton", IEEE Virtual Reality(VR) Conference, 2012
[32]T.Dutta, "Evaluation of the Kinect™ sensor for 3-D kinematic measurement in the workplace", Applied Ergonomics, Volume 43, Issue 4, July 2012, Pages 645-649
[33]The Computer Language Benchmarks Game, "http://shootout.alioth.debian.org/"