An Intelligent Position-Tracking Controller for Constrained Robotic Manipulators Using Advanced Neural Networks

Abstract

Nowadays, robots have become a key labor force in industrial manufacturing, exploring missions as well as high-tech service activities. Possessing intelligent robots for such the work is an understandable reason. Adoptions of neural networks for excellent control accuracies of robotic control systems that are restricted in physical constraints are practical challenges. This chapter presents an intelligent control method for position tracking control problems of robotic manipulators with output constraints. The constrained control objectives are transformed to be free variables. A simple yet effective driving control rule is then designed to force the new control objective to a vicinity around zeros. To suppress unexpected systematic dynamics for outstanding control performances, a new neural network is employed with a fast-learning law. A nonlinear disturbance observer is then used to estimate the neural estimation error to result in an asymptotic control outcome. Robustness of the closed loop system is guaranteed by the Lyapunov theory. Effectiveness and feasibility of the advanced control method are validated by comparative simulation.