Decoupled Neural Network Reference Compensation Technique for a PD Controlled Two Degrees-of-Freedom Inverted Pendulum

In this paper, the decoupled neural network reference compensation technique (DRCT) is applied to the control of a two degrees-of-freedom inverted pendulum mounted on an x-y table. Neural networks are used as auxiliary controllers for both the x axis and y axis of the PD controlled inverted pendulum. The DRCT method known to compensate for uncertainties at the trajectory level is used to control both the angle of a pendulum and the position of a cart si- multaneously. Implementation of an on-line neural network learning algorithm has been imple- mented on the DSP board of the dSpace DSP system. Experimental studies have shown success- ful balancing of a pendulum on an x-y plane and good position control under external distur- bances as well.

[1]  Seul Jung,et al.  On an effective design approach of cartesian space neural network control for robot manipulators , 1997, Robotica.

[2]  Mark W. Spong,et al.  Swing up control of the acrobot using partial feedback linearization , 1994 .

[3]  T. Lahdhiri,et al.  Cart-pendulum balancing problem using fuzzy logic control , 1994, Proceedings of SOUTHEASTCON '94.

[4]  Laura Menini.  Non-linear control for underactuated mechanical systems: Isabelle Fantoni and Rogelio Lozano; Springer, London, 2002, ISBN 1-85233-423-1 , 2002, Autom..

[5]  June Ho Park,et al.  Active Contour Model Based Object Contour Detection Using Genetic Algorithm with Wavelet Based Image Preprocessing , 2004 .

[6]  Lothar Wenzel,et al.  Computer vision based inverted pendulum , 2000, Proceedings of the 17th IEEE Instrumentation and Measurement Technology Conference [Cat. No. 00CH37066].

[7]  Seul Jung,et al.  Neural network inverse control techniques for PD controlled robot manipulator , 2000, Robotica.

[8]  Ihn Namgung,et al.  Application of Quadratic Algebraic Curve for 2D Collision-Free Path Planning and Path Space Construction , 2004 .

[9]  Mario E. Magaña,et al.  Fuzzy-logic control of an inverted pendulum with vision feedback , 1998 .

[10]  Rogelio Lozano,et al.  Non-linear Control for Underactuated Mechanical Systems , 2001 .

[11]  Michifumi Yoshioka,et al.  Neuro-PID control for inverted single and double pendulums , 2000, Smc 2000 conference proceedings. 2000 ieee international conference on systems, man and cybernetics. 'cybernetics evolving to systems, humans, organizations, and their complex interactions' (cat. no.0.

[12]  Michifumi Yoshioka,et al.  Neuro-control for single-input multi-output systems , 1998, 1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111).

[13]  Ming-Feng Yeh,et al.  A PI-like fuzzy controller implementation for the inverted pendulum system , 1997, 1997 IEEE International Conference on Intelligent Processing Systems (Cat. No.97TH8335).