From Vessel Trajectories to Safety-Critical Encounter Scenarios: A Generative AI Framework for Autonomous Ship Digital Testing

2026-03-30

AI Summary

This study addresses the scarcity of realistic and diverse safety-critical ship encounter scenarios, which hinders the digital testing and validation of autonomous navigation systems. To overcome this limitation, the authors propose a data-driven framework that leverages large-scale AIS trajectory data and employs a multi-scale temporal variational autoencoder to enhance trajectory realism and robustness under noise. By integrating generative modeling, automated encounter pairing, and temporal parameterization, the framework systematically constructs high-fidelity, scalable encounter scenarios. The approach preserves statistical consistency and smoothness of original trajectories while successfully generating high-risk encounter configurations rarely observed in historical data, thereby substantially expanding scenario diversity and providing strong support for the validation of autonomous ship navigation systems.

Abstract

Digital testing has emerged as a key paradigm for the development and verification of autonomous maritime navigation systems, yet the availability of realistic and diverse safety-critical encounter scenarios remains limited. Existing approaches either rely on handcrafted templates, which lack realism, or extract cases directly from historical data, which cannot systematically expand rare high-risk situations. This paper proposes a data-driven framework that converts large-scale Automatic Identification System (AIS) trajectories into structured safety-critical encounter scenarios. The framework combines generative trajectory modeling with automated encounter pairing and temporal parameterization to enable scalable scenario construction while preserving real traffic characteristics. To enhance trajectory realism and robustness under noisy AIS observations, a multi-scale temporal variational autoencoder is introduced to capture vessel motion dynamics across different temporal resolutions. Experiments on real-world maritime traffic flows demonstrate that the proposed method improves trajectory fidelity and smoothness, maintains statistical consistency with observed data, and enables the generation of diverse safety-critical encounter scenarios beyond those directly recorded. The resulting framework provides a practical pathway for building scenario libraries to support digital testing, benchmarking, and safety assessment of autonomous navigation and intelligent maritime traffic management systems. Code is available at https://anonymous.4open.science/r/traj-gen-anonymous-review.

Problem

• safety-critical encounter scenarios
• autonomous ship
• digital testing
• AIS trajectories
• scenario generation

Innovation

• generative AI
• safety-critical scenarios
• multi-scale temporal VAE
• autonomous ships
• AIS trajectory modeling