On control of a base-excited inverted pendulum using neural networks

In this paper a neural-network-based control technique is proposed for stabilizing a base-excited inverted pendulum. The pendulum has two degrees of rotational freedom and the base-point moves freely in the three-dimensional space. The goal is to apply control torques to keep the pendulum in a prescribed position in spite of disturbing base-point movements. First, the problem of modeling such a highly nonlinear, non-autonomous system with neural networks is investigated. The model is then applied within a feedback control loop to keep the pendulum about the upright position. The stability of the control system in the presence of the approximation errors of neural networks is also analyzed. The examination of the proposed controller, through simulations, demonstrates the promise of the methodology and exhibits positive aspects, which cannot be achieved by the previously developed techniques, based on Lyapunov stability analysis. These aspects include fast, yet well-maintained damped responses with smooth control torques. The work presented here, can benefit practical problems such as the study of stable locomotion of human upper body and bipedal robots.