×

An adaptive critic neural network for motion control of a wheeled mobile robot. (English) Zbl 1170.70316

Summary: We propose a new application of the adaptive critic methodology for the feedback control of wheeled mobile robots, based on a critic signal provided by a neural network (NN). The adaptive critic architecture uses a high-level supervisory NN adaptive critic element (ACE), to generate the reinforcement signal to optimise the associative search element (ASE), which is applied to approximate the non-linear functions of the mobile robot. The proposed tracking controller is derived from Lyapunov stability theory and can guarantee tracking performance and stability. A series of computer simulations have been used to emulate the performance of the proposed solution for a wheeled mobile robot.

MSC:

70E60 Robot dynamics and control of rigid bodies
70Q05 Control of mechanical systems
93C85 Automated systems (robots, etc.) in control theory
92B20 Neural networks for/in biological studies, artificial life and related topics
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Barto, A.G., Sutton, R.S., Anderson, W.: Neuron-like adaptive elements can solve difficult learning control problems. IEEE Trans. Syst. Man Cybern. 13(5), 834–846 (1983)
[2] Giergiel, J., Zylski, W.: Description of motion of a mobile robot by Maggie’s equations. J. Theor. Appl. Mech. 43(3), 511–521 (2005)
[3] Hendzel, Z.: Fuzzy combiner of behaviours for reactive control of a wheeled mobile robot. In: Artificial Intelligence and Soft Computing. Rutkowski, L. et al. (eds.), Springer-Verlag, Berlin Heidelberg New York, pp. 774–779 (2004) · Zbl 1058.68669
[4] Hendzel, Z.: Collision free path planning and control of wheeled mobile robot using a Kohopnen self-organising map. Bull. Polish Acad. Sci. Tech. Sci. 53(1), 39–47 (2005) · Zbl 1112.42002 · doi:10.4064/ba53-1-5
[5] Hunt, K.J., Sbarbaro, D., Zbikowski, R., Gawthrop, P.J.: Neural networks for control systems – A survey. Automatica 28(6), 1083–1112 (1992) · Zbl 0763.93004 · doi:10.1016/0005-1098(92)90053-I
[6] Kim, Y.H., Lewis, F.L., Abdallah, C.T.: A dynamic recurrent neural-network based adaptive observer for a class of non-linear systems. Automatica 33(8), 1539–1543 (1997) · Zbl 1047.93504 · doi:10.1016/S0005-1098(97)00065-4
[7] Lewis, F.L., Liu, K., Yesildirek, A.: Neural net robot controller with guaranteed tracking performance. IEEE Trans. Neural Netw. 6(3), 703–715 (1995) · doi:10.1109/72.377975
[8] Lewis, F.L., Jagannathan, S., Yesildirek, A.: Neural Network Control for Robot Manipulators and Nonlinear Systems. Taylor & Francis, London (1999)
[9] Lin, C.-K.: A reinforcement learning adaptive fuzzy controller for robots. Fuzzy Sets Syst. 137, 339–352 (2003) · Zbl 1037.93055 · doi:10.1016/S0165-0114(02)00299-3
[10] Narendra, K.S.: Adaptive control using neural networks. In: Neural Networks for Control. Miller, W.T, Sutton, R.S, Werbos, P.W. (eds.), MIT Press, Cambridge, MA, pp. 115–142 (1991)
[11] Prokhorov, D.V., Wunch, D.C.: Adaptive critic designs. IEEE Trans. Neural Netw. 8(5), 997–1007 (1997) · doi:10.1109/72.623201
[12] Sutton R.S., Barto A.G.: Reinforcement Learning, An Introduction. MIT Press, Cambridge, MA, (1999).
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.