In this paper, an adaptive neural network command lter controller is investigated for a class of non-strict feedback stochastic nonlinear systems with full-state constraints. By using the command lter approach and error compensation mechanism, the \\\\explosion of complexity\\\" problem caused by the backstepping method and the ltering errors are eliminated. In order to avoid excessive and burdensome computations and to ensure that the backstepping method works normally for non-strict feedback structures, neural networks are employed to approximate the unknown nonlinear functions that contain all the state variables of the system. Meanwhile, the barrier Lyapunov functions are constructed to ensure the constraints are not transgressed. Finally, based on the Lyapunov stability theorem, an adaptive neural tracking controller is presented to guarantee that all the signals of the closed-loop system are semi-global uniformly ultimately bounded (SGUUB) in probability, and the tracking error converges to a small neighborhood around the origin, besides the full-state constraints are not violated. The simulation results are given to conrm the eectiveness of the proposed control method.

Keywords