SKETCH: Semantic Key-Point Conditioning for Long-Horizon Vessel Trajectory Prediction

TL;DR

This paper introduces a semantic-key-point-conditioned framework for long-horizon vessel trajectory prediction, improving accuracy and consistency by modeling navigational intent through high-level key points.

Contribution

It proposes a novel approach that decomposes trajectory prediction into semantic decision-making and local motion modeling, enhancing long-term prediction accuracy.

Findings

Outperforms state-of-the-art methods on real-world AIS data

Improves long-duration trajectory accuracy and directional consistency

Effectively captures navigational intent through high-level key points

Abstract

Accurate long-horizon vessel trajectory prediction remains challenging due to compounded uncertainty from complex navigation behaviors and environmental factors. Existing methods often struggle to maintain global directional consistency, leading to drifting or implausible trajectories when extrapolated over long time horizons. To address this issue, we propose a semantic-key-point-conditioned trajectory modeling framework, in which future trajectories are predicted by conditioning on a high-level Next Key Point (NKP) that captures navigational intent. This formulation decomposes long-horizon prediction into global semantic decision-making and local motion modeling, effectively restricting the support of future trajectories to semantically feasible subsets. To efficiently estimate the NKP prior from historical observations, we adopt a pretrain-finetune strategy. Extensive experiments on real-world AIS data demonstrate that the proposed method consistently outperforms state-of-the-art approaches, particularly for long travel durations, directional accuracy, and fine-grained trajectory prediction.