本論文旨在承接先前的研究論文〈球彈跳之智慧型手眼協調控制〉與〈手眼協調控制之適應性拍球系統〉的擊球系統，對其作改良與修正。此一連串的研究目的乃在發展類似人類的靈巧操作技巧，以奠立智慧型機械臂控制之基礎。
本文利用Xtion PRO LIVE體感攝影機同時擷取影像與深度資訊，採用乒乓球為追蹤目標，並以機械臂顛球動作行為，實現類似人類的靈活操作能力。為了提升影像目標物位置精確度，選擇受照明影響較小的HSV色彩空間。先經由背景分離得到影像的二維資訊，再搭配深度資料，以獲得乒乓球在三維空間的座標位置。接著運用力學方程式預測球體運動軌跡，提供電腦下達命令至控制板的時機，以使得機械臂順利完成拍擊動作。
經由擊球實驗影片分析，主要針對完成連續拍擊的兩個關鍵因素：球的三維座標位置和擊球機構反應時間進行修正，使系統能準確地掌握乒乓球軌跡的預測和機構拍擊動作反應所需的時間。透過兩者的搭配，使得拍擊機構在拍擊乒乓球後，乒乓球仍在拍擊範圍內以完成連續拍擊的目標。
透過實驗與修正，能即時準確抓取乒乓球的三維座標，藉由剩餘落下時間與馬達作動反應時間的預測，在較佳的時間點拍擊乒乓球。實驗結果顯示最後連續拍擊之乒乓球可到達至拍擊板上方25公分處，且平均連續拍擊次數可達4次。

The main objective of this thesis is to focus on improvement and modification of the bouncing system developed in previous researches including “Intelligent Hand-Eye Coordination Control on Ball Bouncing” and “Hand-Eye Coordination Control on an Adaptive Ball Bouncing System”. A series of researches aims to develop human-like dexterous manipulation techniques to lay foundation for control of future intelligent robots.
An Xtion PRO LIVE camera is applied to capture images with depth information at the same time to track a ping-pong ball as a target. The task of paddle juggling by bouncing the pong-pong ball is achieved by a robotic manipulator for realization of dexterous operational capability of humans. In order to enhance the position accuracy on the image plane, the HSV color space less affected by illumination is selected. Firstly, two-dimensional image information is obtained by the background separation technique. Incorporating with the depth information, the ball’s position in three-dimensional space can be determined. Then the ball’s trajectory is predicted based on dynamic equations of the ball. Therefore, the timing for the computer to give control command to the control board for the purpose of achieving the mission of paddle juggling can be calculated.
By analyzing videos of bouncing ball experiments, the emphasis is on improvement on two key factors: the ball’s position in three-dimensional space and the reaction time of the bouncing mechanism. As a result, the bouncing mechanism is able to play the ball upwards and the ball will stay in a region to allow for another play to accomplish the goal of continuous bouncing.
Through experiments and modification, accurate three-dimensional spatial information of the ping-pong ball can be acquired in real-time. According to prediction of the remaining fall time and the motor reaction time, the better instant to hit the ball can be computed. Experimental results demonstrate that the ping-pong ball reaches at twenty-five centimeters height in continuous bouncing condition and the average bouncing time is about four times.

論文審定書 i
誌謝 ii
摘要 iii
Abstract iv
目 錄 vi
圖次 viii
表次 xii
第一章緒論 1
1.1研究動機與目的 1
1.2文獻回顧 2
1.3論文架構 7
第二章問題分析與系統流程架構 8
2.1拍擊機構問題分析 8
2.2系統流程圖 14
2.3訊號流程圖 15
2.4硬體設備 16
2.4.1 Xtion PRO LIVE硬體與原理介紹 16
2.4.2伺服控制板與伺服馬達 18
2.4.3拍擊板 21
2.4.4乒乓球 21
第三章影像處理 22
3.1攝影機與拍擊機構架設 22
3.2影像處理流程 25
3.3RGB轉HSV 26
3.3.1RGB色彩空間 26
3.3.2HSV色彩空間 26
3.3.3色彩空間轉換公式與閥值設定 28
3.4二維座標轉三維座標 32
第四章馬達接收命令的時間點預測 35
4.1 預測球體飛行軌跡 35
4.1.1飛行球體受力情形 35
4.1.2影像中的球體軌跡預測 38
4.2拍擊機構 42
4.3拍擊動作 44
4.4命令時間點估測 45
第五章實驗結果 47
5.1HSV閥值設定修正前後比較 47
5.2紅外線攝影機初始深度實驗 52
5.3深度對照實驗 55
5.4高度對照實驗 57
5.5動態模糊修正 60
5.6拍擊動作反應時間實驗 63
5.7拍擊實驗 66
第六章結論與未來展望 74
6.1結論 74
6.2未來展望 75
參考文獻 77

[1] E. W. Aboaf , S. M. Drucker and C. G. Atkeson, “Task-Level Robot Learning: Juggling a Tennis Ball More Accurately,” Proceedings of IEEE International Conference on Robotics and Automation, Vol. 3, pp. 1290-1295, May 1989
[2] 劉安陞，球彈跳之智慧型手眼協調控制，國立中山大學機械與機電工程學系研究所碩士論文，民國一百年七月
[3] T. Kizaki and A. Namiki, “Two Ball Juggling with High-speed Hand-Arm and High-speed Vision System,” Proceedings of IEEE International Conference on Robotics and Automation, pp. 1372-1377, May 2012
[4] J. Kober, M. Glisson, and M. Mistry, “Playing Catch and Juggling with a Humanoid Robot,” Proceedings of IEEE International Conference on Humanoid Robots, pp. 875-881, Dec. 2012
[5] 邱奕鳴，手眼協調控制之適應性拍球系統，國立中山大學機械與機電工程學系研究所碩士論文，民國一百零二年八月
[6] H. Liu, “ Table Tennis Robot with Stereo Vision and Humanoid Manipulator II:
Visual Measurement of Motion-Blurred Ball,” Proceeding of the IEEE
International Conference on Robotics and Biomimetics, pp. 2430-2435, Dec. 2013
[7] M. Deswal and N. Sharma, “A Fast HSV Image Color and Texture Detection and Image Conversion Algorithm,” International Journal of Science and Research, Vol. 3, No. 6, pp. 1279-1284, June 2014
[8] 羅至中，單視域之遞迴式深度估測補償，國立交通大學電信工程研究所碩士論文，民國一百零一年九月
[9] 周景荃，球板系統之影像伺服控制及路徑規劃，國立中山大學機械與機電工程學系研究所碩士論文，民國九十八年七月
[10] O. Birbach, U. Frese and B. Bauml, “ Realtime Perception for Catching a Flying Ball with a Mobile Humanoid,” Proceedings of IEEE International Conference on Robotics and Automation, pp. 5955-5962, May 2011
[11] 周建佑，基於L-K演算法及Kinect的動態目標追蹤系統之研究，國立中央大學電機工程學系研究所碩士論文，民國一百零一年六月
[12] 樊景超，周國民，kinect深度數據随機跳變誤差分析及修正算法研究，期刊電腦知識與技術，第10卷，第22期，5328頁到5349頁，八月，民國一百零三年
[13] H. Yadav, S. Srivastavat, P. Mukherjeet and B. Lall, “ A Real-time Ball Trajectory Follower using Robot Operating System,” Proceedings of IEEE International Conference on Image Information Processing, pp. 511-515, Dec. 2015
[14] W. Dong, G. Gu, Y. Ding, X. Zhu, and H. Ding, “ Ball Juggling with an Under-Actuated Flying Robot,” Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 68-73, Oct. 2015
[15] P. Cigliano, and V. Lippiello, “ Robotic Ball Catching with an Eye-in-Hand
Single-Camera System,” Proceedings of IEEE Transactions on Control Systems Technology, Vol. 23, pp. 1657-1671, Jan. 2015
[16] H. Myint, P. Wong, and L. Dooley, “ Tracking a Table Tennis Ball for Umpiring Purposes,” Proceedings of IAPR International Conference on Machine Vision Applications, pp. 170-173, May 2015
[17] M. Buehler, D. E. Koditschek, and P. J. Kindlmann, “Planning and Control of Robotic Juggling and Catching Tasks,” International
Journal of Robotics Research, Vol. 13, pp. 101-118, April 1994

[18] F. Maleki, and Z. Farhoud “Making Humanoid Robots More Acceptable Based on the Study of Robot Characters in Animation,” International Journal of Robotics and Automation, Vol. 4, No. 1, pp. 63~72, March 2015
[19] Intervalzero RTX64 Help, https://www.intervalzero.com/library/RTX64/HTML5/RTX64_Help.htm#Welcome.htm?TocPath=_____1
[20] Intervalzero RTOS Platform,
https://www.intervalzero.com/taiwanese/