Neural network-based asymptotic tracking control design for stochastic nonlinear systems

Abstract

ABSTRACT This article is focused on the adaptive neural network (ANN) asymptotic tracking control design for stochastic nonlinear systems with state constraints. The neural networks are utilised to deal with unknown uncertainties. The existence of state constraints and unknown virtual control coefficients (UVCC) bring many difficulties for control synthesis and analysis. With the aid of barrier Lyapunov function, the predefined state constraints are guaranteed. By fusing the lower bounds of UVCC into Lyapunov function construction, a novel ANN asymptotic tracking control method is devised by employing the bound estimation approach and backstepping technique. The presented asymptotic tracking controller can guarantee that the tracking error converges to zero in probability and the state constraints are not violated. The validity of the developed scheme is elucidated by simulation example.