本論文的主要研究目的在於以形狀記憶合金做為人造手之致動器，並利用影像伺服達成人造手的姿態控制。
本文中人造手的姿態是由手指指尖之空間位置所決定；而在指尖位置的描述上，先利用雙攝影機先將手指可活動範圍的空間座標系建立出來後，再運用機器人學中的D-H齊次轉換矩陣並結合正向運動學得到。
從指尖位置的數學表示式中，可以發現其位置是由各關節的角度變量所決定，而驅動指節使關節角度產生變化的大小，是由形狀記憶合金的形變量所控制，因此控制形狀記憶合金的形變量即可控制人造手的姿態。
由於形狀記憶合金存在著遲滯現象，使得在其形變量的控制上會產生誤差，因此本文採用Preisach 模型去近似遲滯現象，並利用Preisach 模型去計算出逆Preisach 模型以補償遲滯現象，再使用參考模型的適應控制器，使形狀記憶合金的模型之響應趨近於參考模型之響應。
在本文中，利用雙攝影機做為人造手指尖位置的感測器，並利用逆向運動學得到手指各關節所對應的形狀記憶合金之形變量，藉由控制形變量去控制人造手的姿態。
最後，指尖定位控制的實驗結果顯示，經由逆Preisach 模型的補償、正逆運動學的轉換、空間座標系的建立、雙攝影機的影像伺服與適應控制確實能實現人造手的姿態控制。

The purpose of this thesis is to accomplish the gesture control of an artificial hand that is actuated by shape memory alloy with visual servo. In this thesis, the gesture of an artificial hand is determined by the position of fingertips in space. At first, two cameras are utilized to establish the spatial coordinates of the active area of fingertips, then, we combine the D-H homogeneous transformation matrix in the robotics and the forward kinematics to get the position of fingertips. From the mathematical expression of the position of fingertips, we can find the position of the fingertip is determined by the angle of each joint, and the angle of each joint is determined by the deformation of shape memory alloy that actuates the finger. Therefore, controlling the deformation of shape memory alloy can control the gesture of an artificial hand. However, because of hysteresis phenomenon in shape memory alloys, the performance of controlling the deformation of shape memory alloys will degrade. In order to confront this problem, Preisach model is used to approximate the hysteresis phenomenon, and then the inverse Preisach model is utilized to compensate for the hysteresis phenomenon. Besides, by using the Model-Reference-based of adaptive control, the response of shape memory alloy can be improved to approach the response of the reference model. In this thesis, two cameras are used as the sensors to detect the position of fingertips, and the inverse kinematics is employed to obtain the corresponding deformation of shape memory alloys of each joint on the finger. Experimental results show that, by using the inverse Preisach model, the transformation of forward and inverse kinematics, the established spatial coordinate, the binocular visual servo, and the adaptive control can indeed execute the gesture control of an artificial hand.

[1] N. G. Hockstein, C. G. Gourin, R. A. Faust, and D. J. Terris. A history of robots:
from science fiction to surgical robotics. Journal of robotic surgery, 1(2):113–118,
2007.
[2] V. Bundhoo. Design and evaluation of a shape memory alloy-based tendon-driven
actuation system for biomimetic artificial fingers. Master’s thesis, University of
Mauritius, 1999.
[3] G.S. Sorock, D. A. Lombard, T. K. Courtney, J. P. Cotnam, and M. A. Mittleman.
Epidemiology of occupational acute traumatic hand injuries: a literature review.
Safety Science, 38(3):241–256, 2001.
[4] S. C. Jacobsen, J. E. Wood, D. F. Knutti, and K. B. Biggers. The utah/mit
dextrous hand: Work in progress. The International Journal of Robotics Research,
3(4):21–50, 1984.
[5] S. Jacobsen, E. Iversen, D. Knutti, R. Johnson, and K. Bigger. Design of the
utah/mit dextrous hand. In Robotics and Automation. Proceedings. 1986 IEEE
International Conference on, volume 3, pages 1520–1532. IEEE, 1986.
[6] L. R. Lin and H. P. Huang. Mechanism design of a new multifingered robot hand. In
Robotics and Automation, 1996. Proceedings., 1996 IEEE International Conference
on, volume 2, pages 1471–1476. IEEE, 1996.
[7] G. Hirzinger, J. Butterfass, S. Knoch, and H. Liu. Dlr’s multisensory articulated
hand. i. hard-and software architecture. In Robotics and Automation, 1998. Proceedings.
1998 IEEE International Conference on, volume 3, pages 2081–2086. IEEE,
1998.
101
[8] C. Connolly. Prosthetic hands from touch bionics. Industrial Robot: An International
Journal, 35(4):290–293, 2008.
[9] P.K. Levangie and C.C. Norkin. Joint Structure and Function: A comprehensive
Analysis. Philadelphia, PA, USA: F.A Davis Company, 4th edition, 2005.
[10] K.H. Kao. Desing and visual servo control of a sma actuated biomimetic hand.
Master’s thesis, National Cheng Kung University, 2012.
[11] L.W. Tsai. Robot analysis: the mechanics of serial and parallel manipulators. Wiley-
Interscience, 1st edition, 1999.
[12] R. W. Webster and Y. Wei. Arinep-a robot golfing system using binocular stereo
vision and a heuristic feedback mechanism. In Proceedings of the IEEE international
conference on intelligent robots and system, pages 2027–34, 1992.
[13] R. C. Gonzalez and R. E. Woods. Digital image processing (International ed.).
Upper Saddle River, NJ: Prentice Hall, 3rd edition, 2008.
[14] N. J. Naccache and R. Shinghal. Spta: A proposed algorithm for thinning binary
patterns. Systems, Man and Cybernetics, IEEE Transactions on, (3):409–418, 1984.
[15] S. M. Dutta, F. H. Ghorbel, and J. B. Dabney. Modeling and control of a shape
memory alloy actuator. In Intelligent Control, 2005. Proceedings of the 2005 IEEE
International Symposium on, Mediterrean Conference on Control and Automation,
pages 1007–1012. IEEE, 2005.
[16] K.J. Astrom and B. Wittenmark. Adaptive Control. Pearson Education Taiwan
Ltd, 2nd edition, 2006.
[17] K.H. Liang. Positioning and tracking control of sma based actuator. Master’s thesis,
National Cheng Kung University, 2011.
[18] J. Chestnutt, M. Lau, G. Cheung, J. Kuffner, J. H, and T. Kanade. Footstep
planning for the honda asimo humanoid. In Robotics and Automation, 2005. ICRA
2005. Proceedings of the 2005 IEEE International Conference on, pages 629–634.
IEEE, 2005.
102
[19] G. H. Ballantyne. Robotic surgery, telerobotic surgery, telepresence, and telementoring.
Surgical Endoscopy and Other Interventional Techniques, 16(10):1389–1402,
2002.
[20] N. Dechev, W.L. Cleghorn, and S. Naumann. Multiple finger, passive adaptive
grasp prosthetic hand. Mechanism and machine theory, 36(10):1157–1173, 2001.
[21] K. Ikuta. Micro/miniature shape memory alloy actuator. IEEE Int. Conf. On
Robotics and Automation, 3:2156–2161, 1990.