Neural network position tracking control of an inverted pendulum an X-Y table robot

Abstract

In this paper, decentralized neural network control of the reference compensation technique is applied to control a 2-DOF inverted pendulum on an x-y plane. The cart with an inverted pendulum moves on the x-y plane by the x-y plane by the x-y table robot. Decentralized neural network control is applied not only to balance the angle of pendulum, but also to control the position tracking of the cart. In order to estimate velocity of the pendulum correctly, discrete filters are used. Especially, a circular trajectory tracking is tested for position tracking control of the cart while maintaining the angle of the pendulum. Experimental result shows that position control of the inverted pendulum and cart is successful.