Seeking Safety From Uncertainty: Probabilistic Vessel Trajectory Prediction With a Flow-Based Generative Model

Abstract

Vessel trajectory prediction remains a critical focus in maritime safety, serving as a pivotal component in vessel traffic service and maritime autonomous surface ship. However, unmeasurable factors, such as human intentions and vessel failure, pose challenges to the reliability of predictions, particularly in multivessel encounters. In response to this, we propose the sequence generative flow (SGlow), a flow-based deep generative model that describes future motions of the vessels with a multimodal probability distribution. It mitigates navigation uncertainty by multiple probabilistic inferences, mapping a single observation to multiple possible predictions. By combining sequential modeling with flow-based distribution learning, SGlow provides more reliable and comprehensive trajectory forecasts for maritime risk warning and navigation decision-making. Compared to existing deep generative models, SGlow excels in multimodal prediction of vessel trajectory with two distinct advantages: first, precise modeling of trajectory distributions through exact log-likelihood optimization, and second, a mathematically traceable learning process that aligns with trajectory evolution dynamics. Experimental results show that SGlow achieves favorable performance compared with 11 benchmark deep learning models in both prediction accuracy and plausibility, enhancing maritime operations safety.