Abstract A review presents the state-of-the-art path-following control systems for maritime autonomous surface ships, where special focus is placed on guidance subsystem and subsystem. The path following system one of basic requirements ships since it guarantees that ship can track predefined with small cross-track errors. problem firstly defined, error dynamics are derived from kinematic equat...

This paper revisits system identification and shows how new paradigms from machine learning can be used to improve it in the case of non-linear systems modeling noisy unbalanced dataset. We show that using importance sampling schemes provide a significant performance boost modeling, which is helpful predictive controller. The approach first evaluated on simulated data Unmanned Surface Vehicle (...

Abstract A deep reinforcement learning approach for solving the quadrotor path following and obstacle avoidance problem is proposed in this paper. The solved with two agents: one task another task. novel structure proposed, where action computed by agent becomes state of agent. Compared to traditional approaches, method allows interpret training process outcomes, faster can be safely trained on...

This article presents a novel path-following algorithm for fixed-wing unmanned aerial vehicles by virtue of nonlinear optimal control approach and wind disturbance observers. Different from some exiting algorithms, the proposed formulates problem into introducing auxiliary dynamics path parameter. The controller is designed in an systematic manner where action generated according to well-define...