Neural network-based nonlinear sliding-mode control for an AUV without velocity measurements

Abstract

For an autonomous underwater vehicle (AUV), a nonlinear sliding-mode control based on linear-in-parameter neural network (NSMC-NN) is proposed to deal with the unknown dynamics and the external environmental disturbances and a first-order robust exact differentiator is introduced considering unknown velocities of an AUV. The sliding-mode surfaces of NSMC-NN can enter into the boundary layers after a period that depends on the design parameters. To demonstrate the feasibility of the proposed controller, simulation studies applying Omni-Directional Intelligent Navigator (ODIN) are carried out, compared with proportional–integral–derivative (PID) and the modified sliding-mode control (MSMC). The simulation results show that the presented control method can achieve the effective control performance.