This paper addresses short-term Collision-Risk-Aware ship route planning while utilizing a deep learning-based Vessel Collision Risk Assessment and Forecasting (VCRA/F) framework to quantify risks. Lacking a clear boundary between risky and viable routes, we propose a Pareto-optimal search for alternative routes, balancing collision risk and voyage time. Our main contribution is a novel framework that integrates VCRA/F for Pareto-optimal route queries in dynamic environments. We model maritime routes using a hexagon-based graph network on the sea. Our experiments on real-world AIS data validate the effectiveness of Skyline-VCRA/F while highlighting areas for further improvement.
Read the full publication here