臺灣博碩士論文加值系統

本論文提出一個採用眼在手視覺伺服技術的自動化組裝系統，運用視覺伺服進行三維資訊的測量，並控制機械手臂完成組裝任務，以運用於3C產業生產線上的機殼組裝工作。然而配備立體視覺之機械手臂系統若欲展現手眼協調之任務操作能力，必須執行離線或線上手眼校準，以確立機械手臂末端致動器與攝影機間之座標轉換關係。因此本文針對眼在手之架構提出一種可於離線施行之校準方法並應用於以雙眼視覺為基礎之機械手臂控制系統。由於需完成精密之任務，因此本論文採用眼在手架構，並分別針對於六軸機械手臂上架設結構光與無架設結構光兩種方式執行組裝任務。首先透過攝影機擷取工件之特徵，經由影像處理，運用立體視覺辨識出工件之位置與姿態。藉適當定義之任務編碼，設計一閉迴路視覺伺服控制器以進一步精確完成定位與組裝之任務。

An automatic assembly system with eye-in-hand visual servoing is proposed in the thesis. Real-time vision is employed to assist a robotic manipulator to perform assembly tasks for 3C products. In order to accomplish hand-eye coordination tasks using a robotic manipulator with stereo vision, either an offline or online hand-eye calibration procedure should be performed to determine the coordinate transformation between the robotic manipulator and the vision system. In this thesis, offline hand-eye calibration approaches are employed for eye-in-hand configurations. Since precision control task is required, an eye-in-hand configuration is employed. The system is implemented in two ways, with and without structured lighting mounted on the end-effector of a 6-DOF robotic manipulator. Firstly, object features are extracted with the stereo vision system. Then, positions and orientations of objects are reconstructed by performing image processing techniques. Finally, the assembly task is encoded to hold the back shell and precisely position it onto the cellular phone to accomplish the automatic assembly task with precision.

中文摘要 i
英文摘要 ii
誌謝 iii
目錄 iv
圖目錄 vii
表目錄 xi
第一章 緒論 1
1.1 研究動機及目的 1
1.2 文獻回顧 2
1.3 論文具體成果 3
1.4 論文章節瀏覽 4
第二章 系統簡介 5
2.1 系統架構 5
2.2 系統流程 5
第三章 手眼協調關係參數校準 9
3.1 攝影機校準 9
3.2 徑向失真之校準與量測 15
3.3 立體視覺 16
3.4 順向運動學 18
3.5 攝影機與TOOL端校準 21
第四章 影像處理 27
4.1 顏色濾波 27
4.2 無結構光下之特徵點擷取 28
4.3 有結構光下之特徵點擷取 30
4.4 極線幾何 31
第五章 控制器設計 35
5.1 快速定位控制器設計 35
5.2 近端定位控制器設計 39
5.2.1 無結構光之第一階段控制器設計 45
5.2.2 無結構光之第二階段控制器設計 47
5.2.3 有結構光之第一階段控制器設計 49
5.2.4 有結構光之第二階段控制器設計 51
第六章 實驗結果 54
6.1 實驗設備 54
6.2 雙眼視覺校準 55
6.3 攝影機對Tool端校準 59
6.4 無結構光之快速定位 63
6.5 無結構光之近端定位 64
6.6 無結構光之數據 64
6.7 有結構光之快速定位 71
6.8 有結構光之近端定位 72
6.9 有結構光之數據 73
第七章 結論 81
7.1 結論 81
7.2 未來展望 82
REFERENCES 83
第八章 作者簡介 86

[1] S. Hutchinson, G. D. Hager, and P. I. Corke, “A tutorial on visual servo control,” IEEE Transactions on Robotics and Automation, vol. 12, no. 5, pp. 651–670, Oct. 1996.
[2] P. I. Corke and M. C. Good, “Dynamic effects in visual closed-loop systems,” IEEE Transactions on Robotics and Automation, vol. 12, no. 5, pp. 671–683, Oct. 1996.
[3] B. Espiau, F. Chaumette, and P. Rives, “A new approach to visual servoing in robotics,” IEEE Transactions on Robotics and Automation, vol. 8, no. 3, pp. 313–326, Jun. 1992.
[4] W.-C. Chang, “Binocular vision-based 3-d trajectory following for autonomous robotic manipulation,” Robotica, vol. 25, pp. 615–626, Sep 2007.
[5] N. H. Quach and M. Liu, “Visual based tracking of planar robot arms: a scheme using projection matrix,” in Robotics, Intelligent Systems and Signal Processing, 2003, pp. 588–593.
[6] G. C. Buttazzo, B. Allotta, and F. Fanizza, “Mousebuster: a robot for real-time catching,” IEEE Transactions on Control System Magazine, vol. 14, no. 1, pp. 49–56, 1994.
[7] V. Lippiello, F. Ruggiero, and L. Villani, “Floating visual grasp of unknown objects,” in Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems, Oct. 2009, pp. 1290 –1295.
[8] R. C. Luo, M. H. Li, H. L. Jhu, and J. W. Chen, “Multi-sensor based object grasping with eye-in-hand laser ranger,” in Proc. of the 2009 IECON 35th Annual Conference on Industrial Electronics, 2009.
[9] W.-F. Xie, Z. Li, X.-W. Tu, and C. Perron, “Switching control of image-based visual servoing with laser pointer in robotic manufacturing systems,” IEEE Transactions on Industrial Electronics, vol. 56, no. 2, pp. 520–529, Feb 2009.
[10] H. Cui, N. Dai, W. Liao, and X. Cheng, “An accurate reconstruction model using structured light of 3-d computer vision,” in Intelligent Control and Automation, 2008. WCICA 2008. 7th World Congress on, Jun. 2008, pp. 5100–5104.
[11] R. Furukawa and H. Kawasaki, “Uncalibrated multiple image stereo system with arbitrarily movable camera and projector for wide range scanning,” in Proceedings of the Fifth International Conference on 3-D Digital Imaging and Modeling, jun. 2005, pp. 302– 309.
[12] X. Lin, C. Maoyong, W. Haixia, and C. Michael, “A method to locate initial welding position of container reinforcing plates using structured-light,” in Control Conference, 2008. CCC 2008. 27th Chinese, Jul. 2008, pp. 310–314.
[13] M. Takeda and K. Mutoh, “Fourier transform profilometry for the automatic measurement of 3-d object shapes,” Appl. Opt., vol. 22, pp. 3977–3982, 1983.
[14] Z. Zhang, “A flexible new technique for camera calibration,” IEEE transactions on pattern analysis and machine intelligence, vol. 22, no. 11, pp. 1330–1334, Nov 2000.
[15] D. C. Brown, “Close-range camera calibration,” PHOTOGRAMMETRIC ENGINEERING, vol. 37, pp. 855–866, 1971.
[16] O. Faugeras and Q.-T. Luong, The Geometry of Multiple Images. Cambridge, MA: MIT Press, 2001.