Risk-Aware Imitation Learning with Environmental Context for AIS

Imitation-learning anomaly detection for AIS is improved by adding environmental data (wind, waves), so the model can tell apart risky vessel behavior from safe weather-driven detours.

2025.08 –
Human Centered – Carbon Neutral Global Supply Chain Research CenterTime-Series Representation Learning
Imitation LearningAnomaly DetectionRisk-AwareEnvironmental Data

Motivation

  • Most imitation-learning approaches to anomaly detection rely only on vessel trajectories.
  • Without environmental context, hazard-avoidance maneuvers are often misclassified as anomalies.
  • By enhancing imitation-learning–based anomaly detection with environmental context (e.g., wind, waves), the model can better distinguish unsafe vessel actions from safe, weather-driven detours.
Representative image of OIL-AD, which serves as the reference for this preliminary research.

Methodology

  • Redefine the imitation-learning state space to include ERA5 environmental variables.
  • Train policies on normal trajectories under environmental context.
  • Evaluate with hazard-injection scenarios to test decision robustness.

Contribution (Expected)

  • Hazard-injection evaluation pipeline for imitation learning under weather impact.
  • Framework showing how enriched state representations improve risk-sensitive imitation learning for anomaly detection