Adaptive Morlet Wavelet Neural Sliding Mode Control of a Ballbot Robotic System

Abstract

Underactuated systems are mechanical systems with more degrees of freedom than actuators. Many benchmark underactuated systems have been developed to the analysis and design of control systems. In this work, we deal with the design of an intelligent controller for a novel underactuated system known as ballbot. Also, we are still exploring the performance of a Morlet wavelet neural network (MWNN) which was proposed in a previous work from our own authorship. So, an adaptive Morlet wavelet neural sliding mode controller (AMWNSMC) is designed to stabilize a ballbot robotic system. The viability of our proposal is validated via simulation through the use of a mathematical model from a ballbot platform based on the LEGO Mindstorms NXT kit. The AMWNSMC here proposed shows a better performance in contrast with an adaptive neural sliding mode controller (ANSMC) whose neural network is based on radial basis functions.