Deep reinforcement learning based active disturbance rejection control for ship course control

Ship Steering Adaptive CGS Control Based on EKF Identification Method

In recent years, marine autonomous surface vessels (MASS) have grown into a ship research issue to increase the level of autonomy of ship behavior decision-making and control while sailing at sea. This paper focuses on the MASS motion control module design that aims to improve the accuracy and reliability of ship steering control systems. Nevertheless, the stochastic sea and wind environment have led to the extensive use of filters and state observers for estimating the ship-motion-related parameters, which are important for ship steering control systems. In particular, the ship maneuverability Nomoto index, which primarily determines the designed ship steering controller’s performance, cannot be observed directly due to the model errors and the external environment disturbance in the process of sailing. Hence, an adaptive robust ship steering controller based on a closed-loop gain shaping (CGS) scheme and an extended Kalman filter (EKF) on-line identification method is explored in this paper. To verify the effectiveness of the proposed steering controller design scheme, the motor vessel YUKUN was taken as the control plant and a series of simulation experiments were carried out. The results show the advantages of the dynamic response performance of the proposed steering controller compared with the classical PD and traditional CGS controllers. Therefore, the proposed adaptive CGS steering controller would be a good solution for MASS motion control module design.