Neural network H-infinity robust adaptive control for autonomous underwater vehicle in 3-dimensional path following
自主式水下航行器三维路径跟踪的神经网络H∞鲁棒自适应控制方法

The 3-dimensional path following control of autonomous underwater vehicle (AUV) with uncertain model and unknown disturbance is investigated. First, the time singular perturbation method and the orthogonal projection reference frame are used to model the position motion, and the attitude dynamic model of the AUV is described by an affine nonlinear system. Next, a neural network robust adaptive control algorithm is employed in the controller design to overcome the uncertainties of the model and the influence of external disturbances. Meanwhile, the dominant input idea is adopted to reduce the complexity of the closed-loop. The stability performance of the system is proved by using Lyaponov stability theory. Simulation indicates that the path following controller keeps the motion of AUV along the prescribed path with desirable performances.