Affiliation:
1. Ming Chuan University
2. Ming Chuan University,
3. China University of Science and Technology
4. National Taiwan Normal University
Abstract
In this paper, an adaptive Fuzzy Cerebellar Model Articulation Controller (FCMAC) is proposed to control two-wheeled robot at upright position. The dynamical model of the robot, LEGO Mindstorms NXT, is derived from Lagrange of kinetic and potential energies. Based on the developed model, an adaptive FCMAC is then designed. Adaptation laws are derived from the Lyapunov stability analysis. According to the stability analysis, the developed FCMAC guarantees that the system tracking performance and the error convergence can be assured in the closed-loop system. Finally, to compare the system performances we apply the proposed FCMAC and the PID (Proportional Integral Derivative) controller to balance the two-wheeled robot.
Publisher
Trans Tech Publications, Ltd.
Reference31 articles.
1. J. S. Albus, A new approach to manipulator control: the Cerebellar Model Articulation Controller (CMAC), Journal of Dynamic Systems, Measurement and Control, Transactions of the ASME, 97 (1975) 220-227.
2. J. S. Albus, Data storage in the Cerebellar Model Articulation Controller (CMAC), Journal of Dynamic Systems, Measurement and Control, Transactions of the ASME, 97(1975) 228-233.
3. J. Cai and X. Ruan, Self-organization stochastic fuzzy control based on OCPFA and applied on self-balanced robot, 8th World Congress on Intelligent Control and Automation, (2010) 4775-4780.
4. J. Y. Chen, C. H. Liu, C. W. Fan, H. Y. Shin, and M. H. Yen, An adaptive PID controller, International Conference on Machine Learning and Cybernetics, pp.884-889, (2010).
5. C. M. Chen, H. M. Lee, and Y. R. Hsieh, A new learning model of hierarchical CMAC neural networks, Proceeding of Fourth Nation Conference on Artificial Intelligence and Application, pp.17-22, (1999).