Development of An Inverse Dynamic Model
In a controller design process, it is interesting to find the inverse model, in which the desired input signal of the system is determined by using a desired output of the system. In many cases, the inverse model problem is very difficult, and sometimes impossible to determine and implement. There are some methods to make an inverse dynamic model, such as computed torque control, which had been studied in the previous Chapters. The capability of the NNs to learn the inverse model of the plant has been investigated for many years; the NN can be used to learn an approximate inverse system. In this approach, the desired output of the dynamic system should be known, and the NN can be trained by the desired output of the dynamic system to obtain the inverse dynamic model. In early studies of adaptive learning control using an NN model, Barto et al. , Jordan , Miller et al.  and Psaltis et al.  addressed the problem of how to obtain the error signal for training the NN controller. Generally, the cost function, consisting of the squared norm of the output reference errors, can not correctly train the NN controller as an inverse dynamic model. Therefore, Jordan  proposed a forward-inverse-modeling, and Albus , Atkeson and Reinkensmeyer , Psaltis et al. , and Kuperstein and Rubinstein  used a direct-inverse-modeling to obtain the command-error for forming the inverse dynamic model as a feedforward controller. Moreover, Watanabe et al.  proposed a linear NN using feedforward NNs with two layers and a linear unit function in the output-layer. Kawato  proposed a learning method to obtain a feedforward controller, which uses the output of a feedback controller as the error for training an NN model. The conventional feedback controller is configured in parallel to the NN controller, in the same manner as reported by Gomi and Kawato , and Miyamoto et al. , but with a different SF and learning algorithm. In another work, Wada and Kawato  used a feedforward NN as an inverse dynamic model.
KeywordsConnection Weight Uniform Random Number Cerebellar Model Articulation Controller Feedforward Controller Momentum Coefficient
Unable to display preview. Download preview PDF.
- A. G. Barto, R. S. Sutton, and C. W. Anderson, “Neuronlike adaptive elements that can solve difficult learning control problems,” IEEE Trans. on System Man and Cybernetics, Vol. SMC-13, pp. 834–846, 1983.Google Scholar
- M. I. Jordan, “Supervised learning and systems with excess degree of freedom, ” (Coins Tech. Rep. No.88–27). University of Massachusetts at Amherst, 1983.Google Scholar
- D. Psaltis, A. Sideris, and A. Yamamura, “A multilayered neural network controller,” IEEE, Control Systems Magazine, pp. 17–20, April 1988.Google Scholar
- C. G. Atkeson and D. J. Reinkensmeyer, “Using associative content-addressable memories to control robots,” Proceeding of IEEE Conference on Decision and Control, pp. 792–797, 1988.Google Scholar
- M. Kawato, “Computational schemes and neural network models for formation and control of multijoint arm trajectory,” in Neural Networks for Control. Cambridge, MA: M.I.T. Press, 1990.Google Scholar
- Y. Wada and M. Kawato, “A neural network model for arm trajectory information using forward and inverse dynamics models,” Neural Networks, Vol. 7, No. 6, pp. 933–946, 1993.Google Scholar
- M. Teshnehlab and K. Watanabe, “A feedback-error-learning by using flexible star network,” Proceedings of First Asian Control Conference, Vol. 3, pp. 475–478, Tokyo, 1994.Google Scholar
- M. Teshnehlab and K. Watanabe, “Control strategy of robotic manipulator based-on flexible neural network structure,” AI in Industrial Decision Making and Control (Klumer Academic Publishers), pp. 385–398, 1994.Google Scholar
- R. T. Newton and Y. Xu, “Neural network control of a space manipulator,” IEEE Control Systems Magazine, Vol. 13, No.6, Decem., pp. 14–22, 1993.Google Scholar