本論文主要是完成一個人形機器人自動學習投籃力道的籃球訓練平台。本論文依據FIRA HuroCup競賽中籃球項目為主要需求，競賽場地的架構為一個長120公分、寬120公分的範圍內，有一個籃球的半場環境、一個高30公分的紅色籃框、一顆用來替代籃球的乒乓球以及一台視覺全自主並投乒乓球的人形機器人。本論文首先架設一個120cm(長)*120cm(寬)*160cm(高)的平台，並在平台的上方及側面各裝置一個攝影機。機器人所投出的球是透過兩個攝影機以曲線擬合的方式來定位出球在三維空間中的位置。機器人內架設一個投球距離與力道的一輸入一輸出模糊控制器，以決定機器人的投球力道。為了找出適合的模糊控制器參數，本論文以DNA演算法來做系統的參數最佳化。DNA演算法包含了複製、交配、突變、酶與病毒等幾項過程。在引進最佳化演算法後機器人可以由不斷投球的過程中自動找出適合的模糊控制器。最後，本論文透過實驗的數據模擬以及實際的機器人投球訓練來證明此系統的有效性。

A basketball training platform for the shooting ability of small-sized humanoid robots is presented in the thesis. The basketball scene is based on FIRA HuroCup competition. A vision-based autonomous robot needs to throw a ball into a 30cm high basket. A table tennis ball is substituted for the basketball. In order to setup the platform, A 120cm x 120cm x 160cm platform is built up by aluminum. Two cameras are mounted on the top and side of the platform respectively. These two cameras locate the ball position based on curve fitting. A one input and one output Fuzzy system for determining the strength of the throwing is presented in this thesis. In order to find out the best parameter sets of the proposed Fuzzy system, DNA algorithm is applied in this thesis. DNA is an optimization algorithm including, reproduce, crossover, mutation and enzyme and virus. The proposed system is able to monitor the throwing performance when the small-sized humanoid robot is throwing the ball. According to the real experiment data, the robot is able to adjust the parameter sets of the proposed Fuzzy system. The simulation results and experimental data show the efficiency of the proposed method.

目錄
中文摘要		I
英文摘要		II
目錄		III
圖目錄		V
表目錄		VIII
第1章 緒論	1
1.1	研究背景	1
1.2	研究動機	4
1.3	論文架構	5
第2章 訓練平台之設計與實現	6
2.1	訓練平台開發軟硬體	6
2.2	訓練平台系統架構	8
2.3	訓練平台影像處理與定位	9
2.3.1	影像擷取	9
2.3.2	影像二值化	10
2.3.3	物件標記與分割	13
2.3.4	三維定位	15
2.3.5	曲線擬合	18
2.4	訓練平台機器人介紹	19
第3章 模糊投籃控制器	21
3.1	模糊理論介紹	21
3.2	模糊投籃控制器設計	23
第4章 DNA計算演算法	27
4.1	生物DNA簡介	27
4.2	DNA計算介紹	28
4.3	DNA計算演算法	29
4.3.1	編碼與數值解碼	29
4.3.2	複製	30
4.3.3	交叉	31
4.3.4	突變	33
4.3.5	病毒與酶效應	34
4.3.6	總結	35
4.4	DNA計算演算法測試	37
第5章 模糊投籃控制器之最佳化設計	40
5.1	搜尋範圍與適應涵式	40
第6章 實驗結果	43
6.1	三維定位實驗	43
6.2	曲線擬合測試	46
6.3	小型人形機器人投球訓練	47
第7章 結論與未來展望	51
參考文獻		52

 
圖目錄
圖2.1、平台使用的硬體元件(a) T420s、(b) LifeCam Cinema	7
圖2.2、籃球訓練平台示意圖	7
圖2.3、系統架構方塊圖	8
圖2.4攝影機之擷取畫面	10
圖2.5、影像建模介面(a)色彩模型HSV色彩數值調整結果、(b)擷取的原始影像、(c)經過二值化處理後的結果	12
圖2.6、訓練平台X與Y軸色彩二值化結果(a)右側攝影機原圖、(b)上方攝影機原圖、(c)右側攝影機二值化結果、(d)上方攝影機二值化結果	13
圖2.7、物件標記的遮罩(a)四鄰點遮罩(b)八鄰點遮罩	14
圖2.8、連通物件標記法的示意圖	15
圖2.9、影像分割示意圖	16
圖2.10、Y軸夾角計算示意圖	16
圖2.11、X軸夾角計算示意圖	17
圖2.12、OpenGL空間圖	18
圖2.13、曲線擬合示意圖	19
圖2.14、訓練平台之機器人(a)小型人形機器人、(b)測試平台	20
圖3.1、模糊控制器的基本結構	21
圖3.2、一輸入一輸出模糊控制器	23
圖3.3、小型人形機器人手部馬達示意圖	23
圖3.4、距離與速度關係圖	24
圖3.5、模糊控制器輸入的歸屬函數	25
圖3.6、模糊控制器輸出的歸屬函數	25
圖4.1、DNA雙股螺旋	27
圖4.2、DNA序列	28
圖4.3、DNA編碼示意圖	30
圖4.4、編碼數值轉換	30
圖4.5、輪盤法示意圖	31
圖4.6、交叉示意圖(a)交叉前、(b)交叉後	32
圖4.7、突變示意圖	33
圖4.8、病毒效應示意圖	34
圖4.9、酶效應示意圖	35
圖4.10、DNA計算演算法流程圖	37
圖4.11、二維適應函式圖	38
圖4.12、遺傳演算法測試結果	39
圖4.13、DNA計算演算法沒有病毒與酶效測試結果	39
圖4.14、DNA計算演算法加入病毒與酶效應測試結果	39
圖5.1、模糊控制器輸出的歸屬函數	41
圖5.2、DNA計算演算法調整模糊控制器示意圖	42
圖5.3、架構圖	42
圖6.1、測試平台高30公分測試結果(a)上視圖、(b)正視圖	44
圖6.2、測試平台高45公分測試結果(a)上視圖、(b)正視圖	45
圖6.3、測試平台高60公分測試結果(a)上視圖、(b)正視圖	45
圖6.4、測試平台高70公分測試結果(a)上視圖、(b)正視圖	46
圖6.5、曲線擬合測試(a)上視圖、側視圖	47
圖6.6、測試環境圖	48
圖6.7、每一個粒子之模糊控制器輸出	48
圖6.8、第一個模糊輸出歸屬函數	49
圖6.9、第一代最佳模糊輸出歸屬函數	49
圖6.10、最佳模糊輸出歸屬函數	50
 
表目錄
表2.1、顏色模型之色彩代碼表	11
表2.2、EV3規格表	20
表3.1、模糊控制器輸出的規則庫	26
表4.1、DNA計算最佳化參數表	36
表 6.1、投球測試命中率	50

[1]	URL：http://zh.wikipedia.org/wiki/%E6%A9%9F%E5%99%A8%E4%BA%BA
[2]	K. Hirai, "Current and future perspective of Honda humanoid robot," IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 500-508, 1997.
[3]	K. Hirai, "The development of Honda humanoid robot," IEEE InternationalConferenceon Robotics and Automation, pp. 1321-1326, 1998.
[4]	T. Takenaka, T. Matsumoto, and T. Yoshiike, “Real time motion generation and con¬trol for biped robot -1st report: walking gait pattern generation-,” IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp.1084–1091, 2009.
[5]	T. Takenaka, T. Matsumoto, T. Yoshiike, and S. Shirokura, “Real time motion genera¬tion and control for biped robot -2nd report: Running gait pattern generation-,” IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1092–1099, 2009.
[6]	T. Takenaka, T. Matsumoto, and T. Yoshiike, “Real time motion generation and con¬trol for bipedrobot -3rd report: Dynamics error compensation-,” IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1594–1600, 2009.
[7]	T. Takenaka, T. Matsumoto, and T. Yoshiike, T. Hasegawa, S. Shirokura, H. Kaneko, A. Orita, “Real time motion generation and control for biped robot -4th report: Integrated balance control-,” IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1601–1608, 2009.
[8]	J. I. Yamaguchi, A. Takanishi, and I. Kato, "Development of a biped walking robot compensating for three-axis moment by trunk motion," IEEE/RSJ International Conference on Intelligent Robots and Systems, pp.561-566, 1993.
[9]	H. O. Lim, Y. Kaneshimat and A. Takanishi, "Online walking pattern generation for biped humanoid robot with trunk," IEEE International Conference on Robotics and Automation, pp.3111-3116, 2002.
[10]	G. Endo, J. Morimoto, J. Nakanishi, and G. Cheng, “An empirical  exploration of a neural oscillator for biped locomotion control,” International Conference on Robotics and Automation (ICRA), pp. 3036–3042, 2004.
[11]	J. Nakanishi, J. Morimoto, G. Endo, G. Cheng, S. Schall, and M. Kawato, “Learning from demonstration and adaptation of biped locomotion,” Robotics and Autonomous Systems, vol. 47, pp. 79–91, 2004.
[12]	G. Endo, J Nakanishi, J. Morimoto, and G. Cheng, “Experimental studies of a neural oscilla¬tor for biped  locomotion with QRIO,” International Conference on Robotics and Automation (ICRA), pp. 598–603, 2005.
[13]	J. Morimoto, G. Endo, J. Nakanishi, and G. Cheng, “A biologically inspired biped locomotion strategy for humanoid robots: modulation of sinusoidal patterns by a coupled oscillator model,” IEEE Transactions on Robotics, vol. 24, no. 1, pp. 185–191, 2008.
[14]	W. Park, J. Y. Kim, J. Lee, and J. H. Oh, "Online free walking trajectory generation for biped humanoid robot KHR-3(HUBO)," IEEE International Conference on Robotics and Automation, pp. 1231-1236, 2006.
[15]	W. Park, J. Y. Kim, and J. H. Oh, "Online biped walking pattern generation for humanoid robot KHR-3(KAIST humanoid robot - 3: HUBO)," International Conference on Humanoid Robots, pp. 398-403, 2006.
[16]	URL：http://www.bostondynamics.com/robot_petman.html
[17]	H. Frank, N. Wellerdick-Wojtasik, N. B. Hagebeuker, G. Novak, and S. Mahlknecht, “Throwing objects – a Bioinspired approach for the transportation of parts,” IEEE International Conference on Robotics and Biomimetics (ROBIO), pp. 91–96, 2006.
[18]	H. Frank, D. Barteit, and F. Kupzog, “Throwing or shooting – a new Technology for logistic chains within production systems,” IEEE International Conference on Technologies for Practical Robot Applications, pp. 62–67, 2008.
[19]	H. Frank, A. Mittnacht, T. Moschinsky, and F. Kupzog, “1-DOF-robot for fast and accurate throwing of objects,” IEEE Conference on Emerging Technologies & Factory Automation (ETFA), pp. 1–7, 2009.
[20]	Y. Sameshima and R. Oguro, “Developing a new carrier system with throwing and catching robot,” International Conference on Control, Automation and Systems (ICCAS), pp. 152–155, 2008.
[21]	W. Mori, J. Ueda, and T. Ogasawara, “1-DOF dynamic pitching robot that independently controls velocity, angular velocity, and direction of a ball: contact models and motion planning,” International Conference on Robotics and Automation (ICRA), pp. 1655–1661, 2009.
[22]	Justin ，URL：http://www.robotic.dlr.de/bcatch
[23]	C.Y. Cheng, Y.J. Chen, and S.Y. Lin, “Design and implementation of a vision-based basketball shooting robot,” IEEE International Conference on Mechatronics, pp. 113–117, 2005.
[24]	C.Y. Cheng, H.Y. Liu, and C.C. Lo, “Toward a robot basketball game,” IEEE Industrial Electronics Society (IECON), pp. 3013–3017, 2007.
[25]	C.Y. Cheng, C.H. Ke, L.W. Huang, C.C. Lin, and J.D. Wang, “Design and implementation of a ball-shooting robot with IR-based embedded vision,” Asian Control Conference, pp. 441–446, 2011.
[26]	J.S. Hu, M.C. Chien, Y.J. Chang, S.H. Su and C.Y. Kai, “A ball-throwing robot with visual feedback,” IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2511–2512, 2010.
[27]	C.H. Kuo, T.S. Chen, H.C. Chou, and G.Z. Chen, “PN-WSNA-Based Eye-Hand-Leg Coordination with a FIRA HuroCup Basketball Game,” IEEE/ASME Transactions on Mechatronics, vol. PP, pp. 1–13, 2012.
[28]	L. M. Adeleman, “Molecular computing of solutions to combinational problems,” Science, vol. 266, no. 5187, pp. 1021–1024, Nov. 1994.
[29]	X. Liu and Y. Li, “Efficient DNA algorithms for chromatic number of graph problems,” IEEE International Confernence on Automation and Logistics, pp. 450–454, 2007.
[30]	Narayan and S. Zorbalas, “DNA algorithms for computing shortest paths,” Proceedings of Genetic Programming, 1998.
[31]	林稚融，動態平台之最佳運動路徑規畫，逢甲大學自動控制工程所碩士論文(指導教授:林南州)，2004。 
[32]	C.L. Lin, H.Y. Jan, and T.H. Huang, “Self-organizing PID control design based on DNA computing method,” IEEE International Conference on Control Applications, pp. 568–573, 2004.
[33]	H.Y. Jan and T.S. Hwang, “Structure Variable PID Control Design Based on DNA Coding Method,” IEEE International Symposium on Industrial Electronics, vol. 1, pp. 423–428, 2004.
[34]	C.T. Wu, J.T. Tien, T.S. Li, “Integration of DNA and Real Coded GA for the design of PID-like fuzzy controllers,” IEEE International Conference on Systems, Man, and Cybernetics, pp.2809-2814, 2012.
[35]	吳俊德，應用DNA-RNA計算演算法於類PID模糊控制器之設計，國立成功大學電機工程學系所碩士論文(指導教授:李祖聖)，2010。
[36]	L. A. Zadeh, “Fuzzy set,” Information and Computation/information and Control - IANDC , vol. 8, no. 3, pp. 338-353, 1965
[37]	R. C. Luo and T. M. Chen, "Target tracking by grey prediction theory and look-ahead fuzzy logic control," IEEE International Conference on Robotics and Automation, pp. 1176-1181, 1999.
[38]	T. H. S. Li, S. J. Chang, and W. Tong, "Fuzzy target tracking control of autonomous mobile robots by using infrared sensors," IEEE Transactions on Fuzzy Systems, vol. 12, no. 4, pp. 491-501, 2004.
[39]	W. Tong and T. H. S. Li, "Realization of two-dimensional target tracking problem via autonomous mobile robots using fuzzy sliding mode control," Annual Conference of the IEEE Industrial Electronics Society, pp. 1158-1163, 1998.
[40]	R. J. Wai and Y. W. Lin, "Adaptive moving-target tracking control of vision-based mobile robot via dynamic petri recurrent-fuzzy-neural-network," IEEE Transactions on Fuzzy Systems, vol. 21, no. 4, pp. 688-701, 2012.
[41]	URL：http://www.fira.net/?mid=HuroSot
[42]	鐘皓家，小型人形機器人行走訓練平台之設計與實現，淡江大學電機工程學系機器人工程所碩士論文(指導教授：翁慶昌)，2013。
[43]	URL：http://blog.csdn.net/czyt1988/article/details/21743595
[44]	URL：http://en.wikipedia.org/wiki/Least_squares
[45]	C. T. Ching, C. C. Wong, Y. Y. Hu, I. H. Tseng, Y. F. Chung, M. W. Chou, “Fuzzy Basketball Throwing Strength Control System for Vision-Based Humanoid Robot,” 16th FIRA RoboWorld Congress, FIRA 2013, Kuala Lumpur, Malaysia, August 24-29, 2013. Proceedings, pp. 275-285, 2013.
[46]	URL：http://en.wikipedia.org/wiki/DNA
[47]	李家同，與DNA 有關的演算法問題，數學傳播，24卷，4期，29-35頁，2000。
[48]	URL：http://en.wikipedia.org/wiki/DNA_computing
[49]	DNA計算：一種新的計算模式，北京清華大學出版社，2004。
[50]	URL：
http://www.dotblogs.com.tw/dragon229/archive/2013/01/03/86692.aspx
[51]	URL：http://zh.wikipedia.org/wiki/%E4%BA%A4%E985%8D
[52]	URL：http://zh.wikipedia.org/wiki/%E7%AA%81%E5%8F%98
[53]	URL：http://zh.wikipedia.org/wiki/%E7%97%85%E6%AF%92
[54]	URL：http://zh.wikipedia.org/wiki/%E9%85%B6