Ship Track Adaptive Control Using Error Estimator

Abstract

The error estimator control scheme for ship track with unknown dynamics is proposed in this paper. The control scheme is based on a multilayer perceptrons neural network (MLPNN) of the ship. The MLPNN is adapted by an extended Kalman filter (EKF) to learn ship's dynamics changes. Therefore, the autopilot output is guaranteed to converge to the desired trajectory asymptotically, and the ship also tracks the desired trajectory due to error estimator. The proposed scheme is evaluated by applying it to a simulated continuous ship's movement process.