Neural inverse modeling and control of a base-excited inverted pendulum

Abstract

In this paper multilayer neural networks are used to control the balancing of a base-excited inverted pendulum. The pendulum has two degrees of rotational freedom and the base-point moves freely in the 3D space. The goal is to apply control torques to keep the pendulum in a prescribed orientation in spite of disturbing base-point movement. The inclusion of the base-point motion leads to a nonautonomous dynamic system with time-varying parametric excitation. The controlling neural networks are updated online. Furthermore, since the pendulum's base-point movement is considered unmeasurable, a novel neural inverse model is employed to estimate it from measurable variables. The performance of the proposed neural controller has been compared with the performance of the recently developed control law on the same problem. It is shown that the proposed neural controller produces fast, yet well maintained damped responses with reasonable control torques and without a knowledge of the model or model parameters. Additionally, the developed controller does not require measurement of the base-point accelerations, which are difficult to obtain in practice.