簡易檢索 / 詳目顯示

研究生: 陳振中
Zhen-Zhong Chen
論文名稱: 基於影像伺服之移動鞋子追蹤自動塗膠
Image-based autonomous moving shoe gluing
指導教授: 林其禹
Chyi-Yeu Lin
口試委員: 林紀穎
Chi-Ying Lin
劉孟昆
Meng-Kun Liu
學位類別: 碩士
Master
系所名稱: 工程學院 - 機械工程系
Department of Mechanical Engineering
論文出版年: 2014
畢業學年度: 102
語文別: 中文
論文頁數: 48
中文關鍵詞: 工業型機械手臂Kinect感測器運動學鞋底黏著物件追蹤STL分析
外文關鍵詞: Manipulator, Kinect, Kinematic, Sole gluing, Object tracking, STL analysis
相關次數: 點閱:190下載:10
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報
  • 本研究旨在開發出一套應用工業型六軸機械手臂進行塗膠動作的鞋底自動黏著系統,其技術包含三大區塊;分析鞋子模型並定義塗膠軌跡、利用影像辨識系統判定物件位於工作空間中位置和推導反向運動學使機械手臂能根據以上資料自動進行塗膠,讓未來的鞋底塗膠動作可得以在此先進系統下加工。
    此系統的使用策略為,第一、分析鞋子模型方面,利用STL檔案結構提供一序列的面資料,每面以一個單位法向量及三個頂點座標來表示,參考以上資料定義出鞋子輪廓的位置;第二、影像辨識系統採用Kinect感測器,先利用感測器所擷取的場景深度資訊濾除鞋子可能位於工作空間中的所有影像以節省分析時間,接著搜索鞋子輪廓並取得其角度及中心位置;第三、結合以上所得的資訊經過反向運動學計算得到機械手臂之角度控制命令,使得機械手臂得以循著鞋底邊緣進行模擬塗膠的動作。
    經過實驗證實,快速鞋底黏著系統能夠成功導引機械手臂對鞋子完成指定路徑塗抹。


    This study aims to develop an automatic adhesive system of six-axis industrial manipulator to glue shoe soles. The technology includes three sections: analyzing the models of the sole and defining the tracks of gluing, using the image-based recognition system to determine the position of the sole in the working space, and deriving the inverse kinematics allowing the manipulator to moving along the gluing trajectory automatically.
    The system is implemented with three strategies. The first is that the model analysis of the soles, the STL file structure, offers a number of surface information, each with a unit normal vector and three vertex coordinates. All above information defines the profile of soles. The second strategy is to use Kinect sensor on the image recognition system in order to reduce analysis time. The sensor captures scene depth information to filter all out but the image for sole, and then searches the profiles of the sole to determine the orientation and the center location. The third strategy is to feed all information so as to find robot coordinates. Finally, based on the inverse kinematics calculates the joint angles of the manipulator and the manipulator can track the edge of the moving sole and implement the gluing action.
    The experiments verify that the sole tracking and gluing system can be successfully operated for gluing applications.

    中文摘要 I ABSTRACT II 誌謝 III 目錄 IV 圖目錄 VI 表目錄 VIII 第一章 緒論 1 1.1 研究背景、動機與目的 1 1.2 文獻回顧 2 1.3 本文架構 5 第二章 3D模型結構分析 6 2.1 STL檔案資料結構 6 2.2 定義塗膠軌跡 8 2.2.1 投影方式及投影轉換 9 2.2.2 STL檔案之化簡並定義塗膠軌跡 12 第三章 影像擷取及處理 16 3.1 深度資訊的運用 16 3.1.1 Kinect感測器之數據擷取 16 3.1.2 影像背景濾除 17 3.2 基礎形態學運算 18 3.2.1 二值化 19 3.2.2 膨脹運算 19 3.2.3 侵蝕運算 20 3.3 連通物件法 20 第四章 機械手臂之運動學分析 25 4.1 連桿參數與座標 25 4.2 機械手臂運動學 27 4.2.1 正向運動學 28 4.2.2 反向運動學 29 4.3 座標系之轉換矩陣 32 4.3.1 尤拉角 33 4.3.2 視覺校正作法 34 第五章 實驗結果與討論 38 5.1 系統架構與硬體介紹 38 5.2 驗證與結果 41 第六章 結論與未來展望 45 6.1 結論 45 6.2 未來展望 46 參考文獻 47 附錄一 Denso VS-6556G 詳細規格 49 附錄二 數學推導 51 附錄三 手臂控制器I/O配置 53 附錄四 OMRON E6C2-CWZ1X詳細規格 54

    [1] Hollingum, Jack. "Quick-change automation for shoe manufacture." Assembly Automation 16.3 (1996): 34-39.
    [2] Jin, Yuzhen, et al. "Detection of 3D curve for shoe sole spraying based on laser triangulation measurement." Automation and Logistics, 2009. ICAL'09. IEEE International Conference on. IEEE, 2009.
    [3] Wu, Chuanyu, et al. "Methods of Generating Robot Spraying Trajectory Based on Shoe Sole Information." Intelligent Systems and Applications, 2009. ISA 2009. International Workshop on. IEEE, 2009.
    [4] Sepulveda, Joao, Carlos Couto, and J. Monteiro. "Developing an automated system for shoe sole halogenation." Industrial Electronics, 1997. ISIE'97., Proceedings of the IEEE International Symposium on. IEEE, 1997.
    [5] Vilaca, Joao L., and Jaime Fonseca. "A new software application for footwear industry." Intelligent Signal Processing, 2007. WISP 2007. IEEE International Symposium on. IEEE, 2007.
    [6] Wu, Chuanyu, et al. "Implementation of 5-DOF apparatus used for adhesive spray and roughing of shoe upper." Automation and Logistics, 2008. ICAL 2008. IEEE International Conference on. IEEE, 2008.
    [7] Senior, A., Hampapur, A., Tian, Y. L., Brown, L., Pankanti, S., & Bolle, R. (2006). Appearance models for occlusion handling. Image and Vision Computing, 24(11), 1233-1243.
    [8] J. Hill and W.T. Park, “Real Time Control of a Robot with a Mobile Camera,” Proc. 9th ISIR, Washington, D.C., pp.233- 246, 1979.
    [9] S. Hutchinson, G.D. Hager and P.I. Corke, “A Tutorial on Visual Servo Control,” IEEE Trans. on Robotics and Automation, Vol. 12, No.5, pp.651-670, 1996.
    [10] B. Yoshimi and P. Allen, “Visual Control of Grasping and Manipultion Tasks,” Proceedings of the IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI 94’, pp. 575–582, 1994.
    [11] R. Kelly, “Robust Asymptotically Stable Visual Servoing of Planar Robots,” IEEE Transactions on Robotics and Automation, Vol. 12, No. 5, October 1996.
    [12] K. Hashimoto and T. Noritsugu, “Performance and Sensitivity in Visual Servoing,” Proceedings of the IEEE International Conference on Robotics and Automation, ICRA’98’, Vol. 2, pp. 2321–2326, 1998.
    [13] Horn, Berthold KP. "Closed-form solution of absolute orientation using unit quaternions." JOSA A 4.4 (1987): 629-642.
    [14] B. Roth, “Performance Evaluation of Manipulators from a Kinematic Viewpoint,” Peformance Evaluation of Manipulators, National Bureau of Standards, special publication, 1975.
    [15] L. Tsai,”ROBOT ANALYSIS-The Mechanics of Serial and Parallel Manipulators”,pp.184-185
    [16] W. Clifford. Preliminary sketch of bi-quaternions. Proc. London Math. Soc, 1873

    QR CODE