Neural network-based adaptive asymptotic tracking of nonstrict feedback nonlinear systems with state constraints

This paper devotes to develop an adaptive neural network (ANN) asymptotic tracking control strategy for nonstrict feedback nonlinear systems subject to state constraints. With the aid of barrier Lyapunov function, the state constraints are ingeniously addressed. By combining a bound estimation scheme with adaptive backstepping technique, an ANN asymptotic controller is recursively constructed. In addition, by selecting the appropriate Lyapunov function, the asymptotic convergence feature is achieved and the predefined state constraints are not transgressed. Finally, the validity of the presented control scheme is elucidated by numerical as well as practical examples.