Balancing and position tracking control of an inverted pendulum on a x-y plane using decentralized neural networks

In this paper, neural network control of an inverted pendulum on an x-y plane is proposed. The inverted pendulum has two degrees-of-freedom to move freely on the x-y plane. Decentralized neural networks are used not only to balance the angle of pendulum, but also to control the position tracking of the cart. Specially, circular trajectory position tracking control of the cart while balancing the pendulum is presented. Experimental works show that position tracking of the cart was successful as well as it maintains balance of the pendulum.