Adaptive NN controller design for an autonomous underwater vehicle

In this paper, we present a nonlinear adaptive neural network controller design for free-pitch-angle diving behavior of an autonomous underwater vehicle (AUV). The dynamics of the AUV is simplified as a non-affine pure-feedback system with only one assumption. By applying adaptive neural network controller design with implicit function theorem, the difficulty in diving control of the AUV is overcome. Advantages of the proposed approach over previous methods include: the simplified dynamics has only one assumption; the output of the system is proven to converge to a small neighborhood of the desired trajectories and the control performance of the closed-loop system is also guaranteed by appropriately choosing the design parameters. Simulation studies are included to illustrate the proposed approach.