Abstract: This paper proposes an intelligent constrained control method to address the challenges of external disturbances and uncertain dynamic parameters faced by underwater vehicles operating in complex underwater environments. First, the dynamic system of the underwater vehicle is modeled and analyzed. Then, a Radial Basis Function (RBF) neural network is introduced to leverage its powerful nonlinear approximation capability for online fitting of the system's nonlinear dynamics, thereby effectively reducing system uncertainties. Furthermore, to ensure trajectory tracking accuracy, a Barrier Lyapunov Function (BLF) is incorporated to design a constrained controller, which strictly confines the trajectory tracking error within predefined bounds. Finally, validation experiments conducted on the BlueROV simulation platform demonstrate that the proposed control method guarantees trajectory tracking accuracy and system stability for the underwater vehicle under various operating conditions in complex environments, confirming its effectiveness.