Adaptive neural tracking control of nonlinear systems with output constraint and input delay

This paper proposes an adaptive neural-network control design for output-constrained nonlinear systems with input delay and unmodeled dynamics. A coordinate transformation with input integral term and Nussbaum functions are combined to deal with the input delay and the unknown state gains. The unmodeled dynamics is restricted by dynamic signal, and the unknown functions are approximated by radial basis function neural networks (RBFNNs). The output constraint is not violated by introducing barrier Lyapunov function (BLF). Based on Lyapunov stability theory, an adaptive tracking control scheme is developed to guarantee all the signals of the closed-loop systems are semi-globally uniformly ultimately bounded (SGUUB).