Issues on Stability of ADP Feedback Controllers for Dynamical Systems

Abstract--This paper traces the development of neuralnetwork (NN)-based feedback controllers that are derived from the principle of adaptive/approximate dynamic programming (ADP) and discusses their closed-loop stability. Different versions of NN structures in the literature, which embed mathematical mappings related to solutions of the ADP-formulated problems called "adaptive critics" or "action-critic" networks, are discussed. Distinction between the two classes of ADP applications is pointed out. Furthermore, papers in "model-free" development and model-based neurocontrollers are reviewed in terms of their contributions to stability issues. Recent literature suggests that work in ADP-based feedback controllers with assured stability is growing in diverse forms.

• Type: Journal
• Year: 2008
• Where: TSMC
• Authors: S. N. Balakrishnan, Jie Ding, Frank L. Lewis
• Keywords: -based Feedback Controllers, Closed-loop Stability, Feedback Controllers, TSMC 2008