除了傳統工業應用之外，機器人已經應用在我們生活之中如醫療保健、保全和家庭生活，因而，透過人形機器人之雙手臂進行協調工作，其控制策略之開發逐漸引起大家的興趣。本論文之目標為提出視覺導引控制策略，用以使人形機器人驅動雙手臂進行物件搬運之應用，而所提出之控制策略是基於倒傳遞神經網路，此神經網路是用來達成目標物之影像特徵及其姿態之映射，並建構一人形機器人，來驗證我們提出方法之理論結果。所建構的半身人形機器人為一固定位置之人形身驅，並擁有一個二自由度的單眼機械頭部，及兩隻各六個自由度的機械手臂。在訓練完成後，機器人即可精確地定位出目標所在。實驗結果顯示所提出之方法，可在不需要事先得知兩方塊之位置資訊下，能使人形機器人協調雙手臂來抱住一個方塊，並將其堆疊置另一方塊上。

In addition to traditional applications in industry, robots now support our lives in such areas as medical care, security and home life. There is growing interest in the development of control strategies for cooperating tasks being done by two robot arms of a humanoid robot. The objective of this thesis is to propose a vision-guided control strategy for a humanoid robot to drive both robot arms in the application of material handling. The proposed control strategy is based on the back-propagation neural network, which is applied to achieve the mapping between image features of a target and the pose of the target. To verify the theoretical results of the proposed method, a humanoid robot is constructed. The constructed partial-body humanoid robot is a humanoid torso in a fixed location, with one 2 degrees of freedom (DOF) robotic monocular head and two 6-DOF robot arms. After the training stage, the robot is capable of locating the target accurately. The experimental results reveal that the proposed approach ensures that two cooperative arms of a humanoid robot can hold and transport a cube from one place to the top of the other cube without beforehand information about the location of the both cubes.

[1] M. A. Aizerman, E. M. Braverman and L. I. Rozonoer, “Theoretical Foundations of the Potential Function Method in Pattern Recognition Learning,” Autom. Remote Control, Vol. 25, 1964.
[2] G. Asuni, G. Teti, C. Laschi, E. Guglielmelli and P. Dario, “Extension to End-effector Position and Orientation Control of a Learning-based Neurocontroller for a Humanoid Arm,” Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 4151-4156, Oct. 2006.
[3] L. Bottou, C. Cortes, J. Denker, H.Drucker, I. Guyon, L.Jackel, Y. LeCun, U.Muller, E. Sackinger, P. Simard, and V. Vapnik, “Comparision of Classifier Methods: A Case Study in Handwriting Digit Recognition,” IEEE Computer Society Press In International Conference on Pattern Recognition, pp. 77-87, 1994.
[4] B. E. Boser, I. Guyon, and V. N. Vapnik, “A Training Algorithm for Optimal Margin Classifiers,” Proceedings of the Fifth Annual Workshop on Computational Learning Theory 5, pp. 144-152, 1992.
[5] C. J. C. Burges, “A Tutorial on Support Vector Machines for Pattern Recognition,” Data Mining and Knowledge Discovery, vol. 2, no. 2, pp. 121-167, 1998.
[6] J. Smola and B. Schölkopf, “A Tutorial on Support Vector Regression,” Tech. Rep.NC2-TR-1998-030, Neural and Computational Learning II, 1998
[7] J. C. Burges and B. Schölkopf, “Improving the Accuracy and Speed of Support Vector Learning Machines,” in Advances in Neural Information Processing Systems 9 (M. Mozer, M. Jordan, and T. Petsche, eds.), pp. 375-381, Cambridge, MA: MIT Press, 1997.
[8] L. J. Cao, K. S. Chua, and L. K. Guan, “C-Ascending Support Vector Machines for Financial Time Series Forecasting,” in 2003 International Conference on Computational Intelligence for Financial Engineering (CIFEr2003), (Hong Kong), pp. 317-323, 2003.
[9] C. Charalambous, “Conjugate Gradient Algorithm for Efficient Training of Artificial Neural Network,” Proceedings of the IEE International Conference on Circuits, Devices and Systems, Vol. 139, No. 3, pp. 301-310, June 1992.
[10] C. Chevallerean and W. Khalil, “Efficient Method for The Calculation of The Pseudo Inverse Kinematic Problem,” Proceedings of the IEEE Conference on Robotics and Automation, pp. 1842-1848, 1984. [4]
[11] C. Cortes and V. Vapnik, “Support vector networks,”Machine Learning, vol. 20, pp. 273-297,1995.
[12] J. J. Craig, Introduction of Robotics Mechanics & Control, Addision-Wesley, 1986.
[13] K. Crammer and Y. Singer, “On the learnability and design of output codes for multiclass problems,” in Computational Learning Theory, pp. 35-46, 2000
[14] H. Drucker, C. J. C. Burges, L. Kaufman, A. Smola and V. Vapnik, “Support Vector Regression Machines,” in Advances in Neural Information Processing Systems, vol. 9, p. 155, The MIT Press, 1997.
[15] G. Flandin, F. Chaumette and E. Marchand, “Eye-in-hand/Eye-to-hand Cooperation for Visual Servoing,” Proceedings of the IEEE International Conference on Robotics and Automation, Vol. 3, pp. 2741-2746, Apr. 2000.
[16] G. Fung, O. L. Mangasarian, and J. Shavlik, “Knowledge-based support vector machine classifiers,” in Advances in Neural Information Processing, 2002.
[17] M. T. Hagan and M. B. Menhaj, “Training Feedforward Networks with the Marquardt Algorithm,” IEEE Transactions on Neural Networks, Vol. 5, Issue 6, pp. 989-993, Nov. 1994.
[18] C. W. Hsu and C. J. Lin, “A Comparison of Methods for Multi-class Support Vector Machines,” IEEE Transactions on Neural Networks, pp.415-425, 2002. KreBel U., Pairwise Classification and Support Vector Machines. Advances in Kernel Methods－Support Vector Learning, MIT Press , Cambridge, pp. 254-268, 1999.
[19] S. Hutchinson, G. D. Hager and P. I. Corke, “A Tutorial on Visual Servo Control,” IEEE Transactions on Robotics and Automation, Vol. 12, Issue 5, pp. 651-670, Oct. 1996.
[20] T. Joachims, “Text Categorization with Support Vector Machines: Learning with Many Relevant Features,” in Proceedings of ECML-98, 10th European Conference on Machine Learning (C.Nédellec and C. Rouveirol, eds.), (Chemnitz, DE), pp. 137-142, Springer Verlag, Heidelberg, DE,1998.
[21] W. Khalil and J. F. Kleinfinger, “A New Geometric Notation for Open and Closed Loop Robots,” Proceedings of IEEE International Conference on Robotics and Automation, pp.1174-1180, 1986.
[22] C. H. Lai, Design and Control of an Anthropomorphic Robot, Master Thesis, Dept. of Mechanical Eng., Nation Cheng Kung University, 2003.
[23] V. Lippiello, B. Siciliano and L. Villani, “Position-Based Visual Servoing in Industrial Multirobot Cells Using Hybrid Camera Configuration,” IEEE Transactions on Robotics, Vol. 23, Issue 1, pp. 73-86, Feb. 2007.
[24] Q. Meng and M. H. Lee, “Biologically Inspired Automatic Construction of Cross-Modal Mapping in Robotic Eye/Hand systems,” Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 4742-4749, Oct. 2006.
[25] A. Muis and K. Ohnishi, “Eye-to-Hand Approach on Eye-in-Hand Configuration Within Real-Time Visual Servoing,” IEEE/ASME Transactions on Mechatronics, Vol. 10, Issue 4, pp. 404-410, Aug. 2005.
[26] S. Mukherjee, E. Osuna and F. Girosi, “Nonlinear Prediction of Chaotic Time Series Using Support Vector Machines,” in 1997 IEEE Workshop on Neural Networks for Signal Processing, pp.511-519, 1997.
[27] K.-R. Müller, A. Smola, G. Rätsch, B. Schölkopf, J. Kohlmorgen and V. Vapnik, “Predicting time series with support vector machines,” in Articial Neural Networks - ICANN'97 (W. Gerstner, A. Germond, M. Hasler, and J.-D. Nicoud, eds.), pp. 999-1004, 1997.
[28] E. D. Orin and W. W. Schrader, “Efficient Computation of the Jacobian for Robot Manipulator,” The International Journal of Robotics Research, Vol.3, No.4, pp.66-75, 1984.
[29] M. Pontil and A. Verri, Support Vector Machines for 3D Object Recognition. IEEE Trans. on Pattern Analysis and Machine Intelligence, pp. 637–646, 1998.
[30] Platt J. C., N. Cristianini and J. Shawe-Taylor. Large Margin DAGs for Multiclass Classification. In Advances in Neural Information Processing Systems, MIT Press, Vol. 12, pp. 547-553, 2000.
[31] H. Ritter, T. Martinetz and K. Schulten, Neural Computation and Self-Organizing Maps: an Introduction, Addison-Wesley, pp. 64-72, 127-130, 1992.
[32] A. C. Sanderson and L. E. Weiss, “Image-Based Visual Servo Control using Relational Graph Error Signals,” Proceedings of the IEEE International Conference on Cybernetics and Society, pp. 1074-1077, 1980.
[33] L. Sciavicco and B. Siciliano, ”Modeling and Control of Robot Manipulators,” New York: McGraw-Hill Company, Inc. 1996.
[34] W. Sepp, S. Fuchs and G. Hirzinger, “Hierarchical Featureless Tracking for Position-Based 6-DoF Visual Servoing,” Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 4310-4315, Oct. 2006.
[35] I. H. Suh and T. W. Kim, “Fuzzy Membership Function Based Neural Networks with Applications to the Visual Servoing of robot Manipulators,” IEEE Transactions on Fuzzy Systems, Vol. 2, Issue 3, pp. 203-220, Aug. 1994.
[36] J. Su, Y. Xi, U. D. Hanebeck and G. Schmidt, “Nonlinear Visual Mapping Model for 3-D Visual Tracking With Uncalibrated Eye-in-Hand Robotic System,” IEEE Transactions on Part B of System, Man, and Cybernetics, Vol. 34, Issue 1, pp. 652-659, Feb. 2004.
[37] F. E. H. Tay and L. Cao, “Application of Support Vector Machines in Financial Time Series Forecasting,” Omega, vol. 29, pp. 309-317, 2001.
[38] V. Vapnik, Estimation of Dependences Based on Empirical Data. Springer-Verlag, 1982
[39] T. P. Vogl, J. K. Mangis, A. K. Zigler, W. T. Zink and D. L.Alkon, “Accelerating the Convergence of the Backpropagation Method,” Biological Cybernetics, Vol. 59, No. 4-5, pp. 256-264, Sep. 1998.
[40] J. K. Waldron, W. S. Liang and S. J. Bolin, “A Study of The Jacobian Matrix of Serial manipulator,” Tran. Of ASME Journal Of Mechanisms, Transmissions and Automation in Design, Vol. 107, pp.230-238, June 1985.
[41] J. A. Walter and K. J. Schulten, “Implementation of Self-Organizing Neural Networks for Visuo-Motor Control of an Industrial Robot,” IEEE Transactions on Neural Networks, Vol. 4, Issue 1, pp. 86-96, Jan. 1993.
[42] Robotis 網站http://www.robotis.com/html/main.php, AX-12 Manual (English) 說明書