Adaptive friction identification and compensation based on RBF neural network for the linear inverted pendulum

Generally, researches on inverted pendulum system only considered the viscous friction, the system with controllers designed based on this model was stable in simulations. However, when the controller was implemented in experimental system, small oscillation resulted. To eliminate the small oscillation, friction identification along with compensation scheme based on radial basis function neural network (RBF network) is proposed in this paper. The LQR controller is employed to stabilize the inverted pendulum in the upright position. Finally, simulation results are given to prove the validity of the proposed strategy.