In this paper a neural-network-based control technique is proposed for stab
ilizing a base-excited inverted pendulum. The pendulum has two degrees of r
otational 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 presc
ribed position in spite of disturbing base-point movements. First, the prob
lem of modeling such a highly nonlinear, non-autonomous system with neural
networks is investigated. The model is then applied within a feedback contr
ol loop to keep the pendulum about the upright position. The stability of t
he control system in the presence of the approximation errors of neural net
works is also analyzed. The examination of the proposed controller, through
simulations, demonstrates the promise of the methodology and exhibits posi
tive aspects, which cannot be achieved by the previously developed techniqu
es, based on Lyapunov stability analysis. These aspects include fast, yet w
ell-maintained damped responses with smooth control torques. The work prese
nted here, can benefit practical problems such as the study of stable locom
otion of human upper body and bipedal robots. (C) 2000 The Franklin Institu
te. Published by Elsevier Science Ltd. All rights reserved.