Abstract
This paper develops an observer-based direct adaptive output feedback control for a class of multi-input-multi-out nonaffine nonlinear discrete-time systems with unknown bounded disturbances. A neural network (NN) observer is designed to estimate unavailable system states. Then, under the framework of reinforcement learning, two other NNs are used to generate the optimal control signal and estimate the cost function, respectively. Based on Lyapunov’s direct method, the stability of the closed-loop system is verified. Moreover, all signals involved are guaranteed to be uniformly ultimately bounded. Finally, an example is provided to demonstrate the effectiveness of the present approach.
Chapter PDF
Similar content being viewed by others
Keywords
References
Chen, F.C., Khalil, H.K.: Adaptive control of a class of nonlinear discrete-time systems using neural networks. IEEE Transactions on Automatic Control 40(5), 791–801 (1995)
Leu, Y.G., Wang, W.Y., Lee, T.T.: Observer-based direct adaptive fuzzy-neural control for nonaffine nonlinear systems. IEEE Transactions on Neural Networks 16(4), 853–861 (2005)
Li, T., Li, R., Wang, D.: Adaptive neural control of nonlinear MIMO systems with unknown time delays. Neurocomputing 78(1), 83–88 (2012)
Sutton, R.S., Barto, A.G.: Reinforcement Learning–An Introduction. MIT Press, Cambridge (1998)
Lewis, F.L., Vrabie, D.: Reinforcement learning and adaptive dynamic programming for feedback control. IEEE Circuits and Systems Magazine 9(3), 32–50 (2009)
Liu, D., Yang, X., Li, H.: Adaptive optimal control for a class of continuous-time affine nonlinear systems with unknown internal dynamics. Neural Computing and Applications, doi: 0.1007/s00521-012-1249-y
Lewis, F.L., Liu, D.: Reinforcement Learning and Approximate Dynamic Programming for Feedback Control. Wiley-IEEE Press, New Jersey (2013)
Werbos, P.J.: Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences. Ph.D thesis, Harvard University (1974)
He, P., Jagannathan, S.: Reinforcement learning-based output feedback control of nonlinear systems with input constraints. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics 35(1), 150–154 (2005)
Yang, L., Si, J., Tsakalis, K.S., Rodriguez, A.A.: Direct heuristic dynamic programming for nonlinear tracking control with filtered tracking error. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics 19(6), 1617–1622 (2009)
Yang, Q., Jagannathan, S.: Reinforcement learning controller design for affine nonlinear discrete-time systems using approximators. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics 42(2), 377–390 (2012)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yang, X., Liu, D., Wang, D. (2013). Observer-Based Adaptive Output Feedback Control for Nonaffine Nonlinear Discrete-Time Systems Using Reinforcement Learning. In: Lee, M., Hirose, A., Hou, ZG., Kil, R.M. (eds) Neural Information Processing. ICONIP 2013. Lecture Notes in Computer Science, vol 8226. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-42054-2_79
Download citation
DOI: https://doi.org/10.1007/978-3-642-42054-2_79
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-42053-5
Online ISBN: 978-3-642-42054-2
eBook Packages: Computer ScienceComputer Science (R0)