Track trials, findings, and clinical evidence as it lands.
Search papers, labs, and topics across Lattice.
This paper investigates Transformer and Performer architectures for probabilistic ship trajectory forecasting using Automatic Identification System (AIS) data, incorporating local vessel movement context via Kernel Density Estimation (KDE) generated heatmaps encoded by Convolutional Neural Networks (CNNs). By training with quantile loss, the models generate model-aware prediction intervals crucial for collision avoidance in confined waters, significantly outperforming prior methods. The inclusion of contextual heatmaps allows for the prediction of movements not discernible from an agent's own historical trajectory alone.
Local vessel movement context, encoded as CNN-processed heatmaps, unlocks Transformer-based trajectory forecasting that anticipates non-obvious future ship positions.
Anticipation of vessel trajectories is an essential task when navigating at sea. This applies to both human navigators and autonomous surface vessels. Trajectory forecasting enables sub-routines such as collision avoidance to assess the situation and react accordingly in time. This paper investigates Transformer and Performer models for trajectory prediction of surface vessels in confined waters. Using widely available position data from the Automatic Identification System (AIS), candidate models are trained and evaluated. Historical information on how other vessels have moved in the local area surrounding each agent is conveyed using positional heat maps. The heat maps are generated using Kernel Density Estimation (KDE) and encoded with a Convolutional Neural Network (CNN) before entering the Transformer models. The models are trained with quantile loss to efficiently obtain a model-aware prediction interval, as this is crucial for timely collision avoidance. The proposed model architectures are shown to greatly outperform previous work while the inclusion of local heat maps enables the prediction of vessel movement that is not otherwise indicated from the previous positions.