Adaptive Neural Network Fixed-Time Control for Robotic Manipulators with Input Quantization

Abstract

An adaptive neural network fixed-time control method is proposed for an uncertain robotic manipulator in this paper. To deal with input quantization and improve the stability, fixed-time control is added to the controller design. In addition, adaptive neural network is applied to approximate the uncertainties of the model. Compared with existing results, fixedtime convergence is used to enhance the learning rate for neural networks and to improve the system accuracy. The validity and stability of the proposed control is proved by the simulation.