本研究主要目的為設計使用工業型機械手臂的自動射擊系統並且以射擊裝置對立體空間中氣球進行追蹤與射擊的動作。本論文使用基於位置視覺伺服控制(Position-based visual servoing)作為射擊系統的基本理論；藉由固定在空間中之視覺裝置感測目標物，利用Camshift追蹤過濾目標與立體視覺計算目標座標；經過卡爾曼濾波器作狀態預估，並加入對目標物之速度評估與系統時間補償，可以得到應給予手臂座標。最後再經正向運動學、賈氏矩陣與虛擬機械臂計算得到機械手臂之角度控制命令，使得機械手臂得以瞄準、射擊目標。經過實驗證實，自動射擊系統能夠成功導引機械手臂對目標物完成追蹤與射擊動作。

The objective of this research is to design an autonomous shooting system by using an industrial robot arm with a shooting device. It can track and shoot a balloon in the 3D space. The shooting system is based on the position-based visual servoing technique. A target and its coordinate in the space can be detected by a stereo vision system which is fixed beside the robot arm. The camshift algorithm is used to track and filter the target and stereo vision to calculate the position in the space. The Kalman filter is used to predict the position of the target, estimate the target velocity and the compensating time, and define the position which the robot arm should move to. Finally, with forward kinematic, Jacobian matrix and virtual arm calculation, we get the angular command of the robot arm, capable of tracking and shooting target, can be obtained. In experiments, the results show the shooting system can guide the robot arm to track and shoot the target successfully.

參考文獻
1. 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.
2. 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.
3. 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.
4. R. Kelly, “Robust Asymptotically Stable Visual Servoing of Planar Robots,” IEEE Transactions on Robotics and Automation, Vol. 12, No. 5, October 1996.
5. 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.
6. J.G. Allen, R.Y.D. Xu and J.S. Jin, “Object Tracking Using CamShift Algorithm and Multiple Quantized Feature Spaces,” Proceedings of the Pan-Sydney Area Workshop on Visual Information Processing, Australian Computer Society, pp. 3-7, 2004.
7. Intel, “Open Source Computer Vision Library”, 1999.
8. D. Murray and C. Jennings. “Stereo Vision Based Mapping for a Mobile Robot,” In Proc. IEEE Conf. on Robotics and Automation, 1997.
9. R.E. Kalman,” A New Approach to Linear Filtering and Prediction Problems,” Trans-actions of the ASME - Journal of Basic Engineering Vol. 82: pp. 35-45, 1960.
10. G. Welch and G. Bishop,”An Introduction to the Kalman Filter,” University of North Carolina at Chapel Hill, available at http://www.cs.unc.edu/~welch/kalman/, 2006.
11. 張進億，基於影像伺服之移動物體追蹤與夾取，國立台灣科技大學機械工程研究所碩士論文，台北，2009。
12. 蔡育維，基於視覺伺服之機械手臂射擊系統，國立台灣科技大學機械工程研究所碩士論文，台北，2010。
13. Y. Wand and B. Yuan, “A Novel Approach for Human Face Detection from Color Images under Complex Background,” Pattern Recognition, Vol. 34, pp.1983-1992, 2001.
14. 鍾國亮，影像處理與電腦視覺，台北市：東華書局，2006。
15. N. Funk, “A Study of the Kalman Filter applied to Visual Tracking,” Project for CMPUT 652, 2003
16. 陳韋戎、盧福明、林達德，立體視覺系統於距離量測上之應用，國立台灣大學生物產業機電工程學研究所，2006。
17. Intel, “Blob Tracking Modules”, 1999.
18. Wiki, “Blob detection” http://en.wikipedia.org/wiki/Blob_detection
19. 英特爾新一代處理器架構可達百萬兆級效能，2010.7.13 http://www.ithome.com.tw/itadm/article.php?c=68524
20. 張俊彥、姜順馨、張彥中，基於FPGA之嵌入式高速視覺伺服平台，工研院機械所，2010。
21. 蔡高岳，機械系統設計之第五章：機器人及機構之速度與靜力分析，新北市：高立圖書，2004。
22. High-Speed Robot Hand Demonstrates Dexterity and Skillful Manipulation http://www.hizook.com/blog/2009/08/03/high-speed-robot-hand-demonstrates-dexterity-and-skillful-manipulation