我們將固定式攝影機手臂(Eye-to-hand)系統分為兩個子系統，包括視覺子系統(攝影機)以及控制子系統(機械手臂)，兩個子系統一開始沒有關聯，需進行校正來計算攝影機與機械手臂基底的轉換式，用來轉換兩者間的座標關係，傳統校正方法程序費時且對非專業人員來說較為困難。本論文提出一自動校正演算法，讓機械手臂夾取棋盤格，並在攝影機前擺動七組特定姿態，藉此達到校正目的，整個過程只需約30秒，且校正結果的標準差在0.3mm以下，與傳統方法相比較為穩定、快速及安全。我們可以將此校正結果，應用在動態目標抓取實驗中，利用視覺定位出目標在空間中的姿態，引導機械手臂抓取移動中的目標物。此系統設計將攝影機以斜拍之方式取像，提升影像精度並解決遮蔽(Occlusion)問題，並利用影像輪廓矩(Contour Moment)定位追蹤動態目標，預測目標三維姿態控制手臂抓取目標，在運輸帶速度不高於120mm/s的情況下，抓取成功率為97%。

There are two subsystems in the eye-to-hand system, including the visual subsystem (camera) and the control subsystem (robotic arm). The two subsystems are not associated at the beginning and need to be calibrated. The transformation between the camera and the robot base is used to transform the coordinate relationship between the two subsystems, and the traditional calibration method is time consuming and difficult for non-professionals. In this paper, an automatic calibration algorithm is proposed to allow the robot arm to catch the checkerboard and swing the seven groups of specific postures in front of the camera to achieve the calibration purpose. The whole process takes only about 30 seconds and the standard deviation of the calibration results is 0.3 mm. Comparing with the traditional method, our method is more stable, fast and safe. We use this calibration results, applied to the motion target pick and place experiment. Using visual technology to locate the target and guide the robot arm to pick the target. This system is designed to take the camera in an oblique way to improve the image accuracy and solve the occlusion problem. Using contour moment to locate the dynamic target information. Then, we predict the target three-dimensional attitude and control robot arm to grab the target. In the case of a conveyor speed less than 120 mm / s, the success rate is 97%.

[1] G. Bradski, "Computer Vision Face Tracking for Use in a Perceptual User Interface," IEEE Workshop Applications of Computer Vision, pp. 790-799, 1998.
[2] S. Belongie, "Rodrigues’ Rotation Formula," MathWorld–A Wolfram Web, 1999.
[3] G. Bradsky and A. Kaehler, "Learning OpenCV: Computer Vision with the OpenCV Library," O’Reilly Media, 2008.
[4] A. De La Escalera and J. Armingol, "Automatic Chessboard Detection for Intrinsic and Extrinsic Camera Parameter Calibration," Sensors, 10, pp. 2027–2044, 2010.
[5] G.L. Du and P. Zhang, "Online Robot Calibration Based on Vision Measurement," Robotics and Computer-Integrated Manufacturing, 29 (6), pp. 484-492, 2013.
[6] C. Finn, and S. Levine. "Deep Visual Foresight for Planning Robot Motion," arXiv preprint arXiv: 1610.00696, 2016.
[7] S. Huang, K. Murakami, Y. Yamakawa, T. Senoo and M. Ishikawa, "Fast Peg-and-Hole Alignment Using Visual Compliance," IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) November 3-7, 2013.
[8] R. Hartley and A. Zisserman, "Multiple View Geometry in Computer Vision," Cambridge University Press, pp. 588-596, 2003.
[9] P. Joubert, "Dense Object Reconstruction from Uncontrolled Motion Using the Microsoft Kinect Sensor," Applied Mathematics Honours Project, 2011.
[10] Y. Meng and H. Zhuang, "Autonomous Robot Calibration Using Vision Technology," Robotics and Computer-Integrated Manufacturing, vol. 23, pp. 436-446, 2007.
[11] J. Miseikis, K. Glette, O. J. Elle, and J. Torresen, "Automatic Calibration of a Robot Manipulator and Multi 3D Camera System," CoRR, vol. abs/1601.01566, 2016.
[12] D. Pagliari and L. Pinto, "Calibration of Kinect for Xbox One and Comparison between the Two Generations of Microsoft Sensors, " Sensors, 15, pp. 27569–27589, 2015.
[13] L. Pinto and A. Gupta, "Supersizing Self-Supervision: Learning to Grasp from 50k Tries and 700 Robot Hours," IEEE International Conference on Robotics and Automation, pp. 3406-3413, 2015.
[14] A.R. Smith, "Color Gamut Transform Pairs," SIGGRAPH 78, pp. 12-19, 1978.
[15] S. Suzuki and K. Abe, "Topological Structural Analysis of Digitized Binary Images by Border Following," Computer Vision Graphics and Image Processing, vol. 30, no. l, pp. 32-46, 1985.
[16] H. Sung, S. Lee and D. Kim, "A Robot-Camera Hand/Eye Self-Calibration System Using a Planar Target," 44th International Symposium on Robotics, pp. 1-4, 2013.
[17] A. Watanabe, S. Sakakibara, K. Ban, M. Yamada, G. Shen and T. Arai, "A Kinematic Calibration Method for Industrial Robots Using Autonomous Visual Measurement," Annals of the CIRP, vol.55, pp. 1-6, 2006.
[18] YASKAWA, "FS100 Instructions," pp. 8.21-8.42, 2012.
[19] YASKAWA, "Motoman MH5LF Robot," 2013.
[20] YASKAWA, "FS100 Operator’s Manual," pp. 2.5-2.15, 2014.
[21] YASKAWA, "FS100 Options Instructions Programmer Manul for New Language Environment MotoPlus," pp. 4.1-4.6, 2014.
[22] Z. Zhang, "Flexible Camera Calibration by Viewing a Plane from Unknown Orientations," International Conference on Computer Vision, pp.666-673, 1999.
[23] Z. Zhang, "A Flexible New Technique for Camera Calibration," IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol.22, no.11, pp.1330-1334, 2000.