Discrete-time neuro-fuzzy adaptive control based on dynamic inversion for robotic manipulators

A discrete-time neuro-fuzzy (NF) adaptive control approach is developed in this paper for the trajectory tracking of a robotic manipulator with unknown dynamics nonlinearities. Two novel design techniques - dynamic inversion constructed by the dynamic NF system and the NF variable structure control (NF-VSC), are introduced for the controller design, and the system stability and the convergence of tracking errors are guaranteed by Lyapunov stability theory, and the learning algorithm is obtained thereby. Finally, simulation studies are carried out to show the viability and effectiveness of the proposed control approach.