Search

This paper proposes a hybrid robust-adaptive learning-based control scheme based on Approximate Dynamic Programming (ADP) for the tracking control of autonomous ship maneuvering. We adopt a Time-Delay Control (TDC) approach, which is known as a simple, practical, model free and roughly robust strategy, combined with an Actor-Critic Approximate Dynamic Programming (ACADP) algorithm as an adaptive part in the proposed hybrid control algorithm. Based on this integration, Actor-Critic Time-Delay Control (AC-TDC) is proposed. It offers a high-performance robust-adaptive control approach for path following of autonomous ships under deterministic and stochastic disturbances induced by the winds, waves, and ocean currents. Computer simulations have been conducted under two different conditions in terms of the deterministic and stochastic disturbances and all simulation results indicate an acceptable performance in tracking of paths for the proposed control algorithm in comparison with the conventional TDC approach. [ABSTRACT FROM AUTHOR]

This paper presents a new robust Model Predictive Control (MPC) algorithm for trajectory tracking of an Autonomous Surface Vehicle (ASV) in presence of the time-varying external disturbances including winds, waves and ocean currents as well as dynamical uncertainties. For fulfilling the robustness property, a sliding mode control-based procedure for designing of MPC and a super-twisting term are adopted. The MPC algorithm has been known as an effective approach for the implementation simplicity and its fast dynamic response. The proposed hybrid controller has been implemented in MATLAB / Simulink environment. The results for the combined Model Predictive Super-Twisting Sliding Mode Control (MP-STSMC) algorithm have shown that it significantly outperforms conventional MPC algorithm in terms of the transient response, robustness and steady state response and presents an effective chattering attenuation in comparison with the Super-Twisting Sliding Mode Control (STSMC) algorithm. [ABSTRACT FROM AUTHOR]

This research addresses two kinds of problems related to optimal trajectory tracking of a Maritime Autonomous Surface Ship (MASS): those caused by the time-varying external disturbances including winds, waves and ocean currents as well as those resulting from inherent dynamical uncertainties. As the paper shows, an accurate and robust optimal controller can successfully deal with both issues. An improved Optimal Adaptive Super-Twisting Sliding Mode Control (OAST-SMC) algorithm is proposed here as a robust optimal adaptive strategy. In this strategy, in order to improve performance of the standard super-twisting approach, we apply an Approximate Dynamic Programming (ADP)-based optimal tuning of gains and an underlying concept based on Time Delay Estimation (TDE). An ADP algorithm is implemented using an actor-critic neural network to deal with the curse of dimensionality in Hamilton–Jacobi–Bellman (HJB) equation. The critical role of TDE part in this algorithm is estimating the impact of disturbances and uncertainties on the MASS model. The results have shown that OAST-TDE significantly outperforms the ST-TDE and AST-TDE algorithm in terms of the optimal control efforts. Also, compared with a Nonlinear Model Predictive Control (NMPC), proposed controller meets the optimal control efforts and accurate tracking concurrently. • Robust optimal control approach is addressed for control of a maritime autonomous surface ship. • An improved super-twisting SMC in terms of the robustness and optimal control is proposed. • An approximate dynamic programming-based optimal parameter tuning is adopted. • A near-optimal performance similar to the NMPC algorithm is achieved. • The proposed optimal parameter tuning algorithm can be adopted for kinds of tunable controllers. [ABSTRACT FROM AUTHOR]