Localized advanced ship predictor for maritime situation awareness with ship close encounter

Abstract

The marine navigation environment can become further complex when ships with different autonomy levels are introduced. To ensure navigation safety in such a mixed environment, advanced ship predictor type technologies are essential in aiding ship navigators to attain the highest levels of situation awareness (SA). Consequently, precise ship trajectory prediction, specifically within a short prediction horizon, should be included in such predictors as an indispensable component. This study introduces two methods for ship trajectory prediction on a local scale: the kinematic-based method and the Gate Recurrent Unit (GRU)-Pivot Point (PP)-based method. The first method utilizes kinematic motion models to predict a ship trajectory. In the second method, the GRU is trained to generate the predictions of related ship navigation states. The ship's PP is then extracted from these predicted states, subsequently providing the predicted ship trajectory. Both methods are validated using simulated maneuvering exercises to assess their effectiveness, with a prediction horizon of 90 s. The results show that the kinematic-based method excels in the predictions during ship's stable stages, i.e., steady-state conditions. Meanwhile, the GRU-PP-based method exhibits robust performances in cases when new rudder orders are executed, i.e., transient conditions. It is considered that these applications can provide significant benefits in maritime SA in present and future ship navigation.