Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Sijin Sun, Liangbin Zhao, Ming Deng, Xiuju Fu

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.

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

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.

Paper Structure

This paper contains 28 sections, 8 equations, 6 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Safety-Critical Vessel Encounter Scenario Generation
  4. Vessel Trajectory Generation
  5. Methodology
  6. Overall Framework
  7. Data-Driven Trajectory Generation from Historical AIS
  8. Data Preprocessing
  9. Conflux EMA for Sequence Modeling
  10. ConfluxVAE for Trajectory Generation
  11. Data Postprocessing
  12. Evaluation Index
  13. Encounter Pairing and Safety-Critical Scenario Construction
  14. Problem Formulation
  15. Region-Constrained Encounter Pairing
  16. ...and 13 more sections

Figures (6)

  • Figure 1: Overview of the trajectory generation and scenario construction pipeline including Data Preprocessing, Conflux VAE Structure, and Encounter Pairing and Safety-Critical Scenario Construction: synthetic trajectories are paired and filtered to form realistic vessel encounters for safety analysis.
  • Figure 2: Conflux EMA block (CEConv): three parallel multi-headed EMA branches at different scales (small, medium, large) are combined via a learnable softmax gate and added to the input as a residual.
  • Figure 3: Visualization of trajectory datasets for (a) Route 1 and (b) Route 2.
  • Figure 4: Vessel trajectories generated by ConfluxVAE
  • Figure 5: Traffic Flow and Encounter Context
  • ...and 1 more figures