A multilayer neural network (NN) controller in discrete-time is designed to deliver a desired tracking performance for a class of nonlinear systems with input deadzones. This multilayer NN controller has an adaptive critic NN architecture with two NNs for compensating the deadzone nonlinearity and a third NN for approximating the dynamics of the nonlinear system. A reinforcement learning scheme in discrete-time is proposed for the adaptive critic NN deadzone compensator, where the learning is performed based on a certain performance measure, which is supplied from a critic. The adaptive generating NN rejects the errors induced by the deadzone whereas a second NN based critic generates a signal, which is used to tune the weights of the action generating NN so that the deadzone compensation scheme becomes adaptive whereas a third multilayer NN simultaneously approximate the nonlinear dynamics of the system. Using the Lyapunov approach, the uniform ultimately boundedness (UUB) of the closed-loop tracking error and weight estimates of action generating NN, critic NN and the third NN are shown by using a novel weight update.

Meeting Name

41st IEEE Conference on Decision and Control, 2002


Electrical and Computer Engineering

Second Department

Computer Science

Third Department

Mechanical and Aerospace Engineering

Keywords and Phrases

Lyapunov Approach; Adaptive Control; Adaptive Critic-Based Neural Network Controller; Closed Loop Systems; Closed-Loop Tracking Error; Control Nonlinearities; Control System Synthesis; Deadzone Compensation Scheme; Deadzone Nonlinearity; Discrete Time Systems; Dynamics Approximation; Learning (Artificial Intelligence); Multilayer Neural Network Controller; Multilayer Perceptrons; Neurocontrollers; Nonlinear Control Systems; Reinforcement Learning Scheme; Tracking Performance; Uncertain Nonlinear Systems; Uncertain Systems; Uniform Ultimately Boundedness; Unknown Deadzones; Weight Estimates

International Standard Serial Number (ISSN)


Document Type

Article - Conference proceedings

Document Version

Final Version

File Type





© 2002 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.

Publication Date

01 Jan 2002