Neural Network-Based Motion Control of Underactuated Wheeled Inverted Pendulum Models

In this paper, automatic motion control is investigated for wheeled inverted pendulum (WIP) models, which have been widely applied for modeling of a large range of two wheeled modern vehicles. First, the underactuated WIP model is decomposed into a fully actuated second-order subsystem Sigma(a) consisting of planar movement of vehicle forward motion and yaw angular motions, and a passive (nonactuated) first-order subsystem Sigma(b) of pendulum tilt motion. Due to the unknown dynamics of subsystem Sigma(a) and universal approximation ability of neural network (NN), an adaptive NN scheme has been employed for motion control of subsystem Sigma(a). Model reference approach has been used, whereas the reference model is optimized by finite time linear quadratic regulation technique. Inspired by human control strategy of inverted pendulum, the tilt angular motion in the passive subsystem Sigma(b) has been indirectly controlled using the dynamic coupling with planar forward motion of subsystem Sigma(a), such that the satisfactory tracking of set tilt angle can be guaranteed. Rigorous theoretic analysis has been established, and simulation studies have been performed to demonstrate the developed method.