Further Investigations on Noise-Tolerant Zeroing Neural Network for Time-Varying Quadratic Programming with Robotic Applications

Abstract

Recently, a modified zeroing neural network (MZNN) model has been presented for solving quadratic programming problems, which is of noise-tolerant ability. In this paper, we conduct further investigations on such a model and then present a nonlinear function activated model. Finally, the presented nonlinear function activated model is applied to the motion control of robots.