Call for papers: Special Issue on Learning Issues in Feedback Control of Uncertain Dynamical Systems (SILIFC)

摘要

In the past two decades, there has been a great deal of interest in developing adaptive and learning controllers for uncertain nonlinear systems. Adaptive control using neural networks (NNs) has been one of the main areas of focus. By making use of the general approximation and online learning ability of NNs, adaptive NN controllers have been designed for dynamical systems with uncertain nonlinearities and disturbances. Earlier work on NN-based adaptive control was to employ NNs for system identification and identification-based indirect adaptive control. In the later work, closed-loop system structures and stability issues were studied. Various modifications to back-propagation in feed-forward or recurrent NNs have been presented to guarantee closed-loop stability and weight error boundedness. Recently, NNs have entered the mainstream of control theory as a natural extension of adaptive control to a broad class of nonlinear systems with unknown parameters and nonlinearities. In addition, NN control has been used in conjunction with other control approaches to extend the class of systems that yields to nonparametric control methods.