Abstract
The field of automatic collision avoidance for surface vessels has been an active field of research in recent years, aiming for the decision support of officers in conventional vessels, or for the creation of autonomous vessel controllers. In this paper, the multi-ship control problem is addressed using a model predictive controller (MPC) that makes use of obstacle ship trajectory prediction models built on the RBF framework and is trained on real AIS data sourced from an open-source database. The usage of such sophisticated trajectory prediction models enables the controller to correctly infer the existence of a collision risk and apply evasive control actions in a timely manner, thus accounting for the slow dynamics of a large vessel, such as container ships, and enhancing the cooperation between controlled vessels. The proposed method is evaluated on a real-life case from the Miami port area, and its generated trajectories are assessed in terms of safety, economy, and COLREG compliance by comparison with an identical MPC controller utilizing straight-line predictions for the obstacle vessel.
Highlights
Reza Ghabcheloo and AntonioIn the last two decades, research on automatic collision avoidance and optimal path planning for surface vessels has intensified, driven by the ever-growing density of maritime traffic in narrow waterways, such as gulfs, ports, and canals [1]
The main contributions of this work are as follows: first, we introduce a novel model predictive control (MPC) scheme for collision avoidance control, where nonlinear data-driven models are used to predict the trajectories of obstacle ships; to the authors’ best knowledge, this is the first such instance in the literature
The proposed method is tested in a collision avoidance case study at the Miami port area, and its performance is illustrated by the comparison with an MPC controller employing straight-line obstacle prediction models, which corresponds to the current state-of-the-art approach [9]
Summary
In the last two decades, research on automatic collision avoidance and optimal path planning for surface vessels has intensified, driven by the ever-growing density of maritime traffic in narrow waterways, such as gulfs, ports, and canals [1]. NNs employ different architectures in order to remap the original non-linear problem to a higher-dimensional input space and approximate its dynamics utilizing standard functions In this context, various NN techniques have been successfully utilized in control frameworks solving the vessel trajectory prediction problem. A multi-ship MPC controller utilizing RBF obstacle trajectory prediction models trained using real AIS data is presented for the collision avoidance task. The proposed method is tested in a collision avoidance case study at the Miami port area, and its performance is illustrated by the comparison with an MPC controller employing straight-line obstacle prediction models, which corresponds to the current state-of-the-art approach [9].
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have