Design and validation of an intention-aware probabilistic framework for trajectory prediction: Integrating COLREGS, grounding hazards, and planned routes

Collision avoidance capability is an essential component in an autonomous vessel navigation system. To this end, an accurate prediction of dynamic obstacle trajectories is vital. Traditional approaches to trajectory prediction face limitations in generalization and often fail to account for the intentions of other vessels. The current state-of-the-art in this area is a Dynamic Bayesian Network (DBN) model, which infers target vessel intentions by considering multiple underlying causes and allowing for different interpretations of the situation by different vessels. However, since its inception, there have not been any significant structural improvements to this model. In this paper, we propose improving the performance of the DBN model by incorporating considerations for grounding hazards and vessel waypoint information. The proposed model is validated using real vessel encounters extracted from historical Automatic Identification System (AIS) data.