Probabilistic Ship Trajectory Forecasting using Transformer Models on AIS Data

Key points

• Anticipation of vessel trajectories is an essential task when navigating at sea.1
• Historical information on how other vessels have moved in the local area surrounding each agent is conveyed using positional heat maps.1
• The heat maps are generated using Kernel Density Estimation (KDE) and encoded with a Convolutional Neural Network (CNN) before entering the Transformer models.1
• 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.1

Sources (1)

• [1]Probabilistic Ship Trajectory Forecasting using Transformer Models on AIS Data
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 9, 01:13 PM

  This paper investigates Transformer and Performer models for trajectory prediction of surface vessels in confined waters.

  Anticipation of vessel trajectories is an essential task when navigating at sea.

Extractive summary: sentences quoted from the sources.