Conditional Flow-VAE for Safety-Critical Traffic Scenario Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gong, Zimu, Zhang, Brian Zhaoning, Zhang, Chris, Wong, Kelvin, Urtasun, Raquel
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918485833023488
author Gong, Zimu
Zhang, Brian Zhaoning
Zhang, Chris
Wong, Kelvin
Urtasun, Raquel
author_facet Gong, Zimu
Zhang, Brian Zhaoning
Zhang, Chris
Wong, Kelvin
Urtasun, Raquel
contents Safety-critical scenarios are essential for the development of autonomous vehicles (AVs) but are rare in real-world driving data. While simulation offers a way to generate such scenarios, manually designed test cases lack scalability, and adversarial optimization often produces unrealistic behaviors. In this work, we introduce a conditional latent flow matching approach for scalable and realistic safety-critical scenario generation. Our method uses distribution matching to transform nominal scenes into safety-critical rollouts. Furthermore, we demonstrate that incorporating both simulation and real-world data enables our framework to efficiently generate diverse, data-driven scenarios. Experimental results highlight that our approach is able to more consistently and realistically generate novel safety-critical scenarios, making it a valuable tool for training and benchmarking AV systems.
format Preprint
id arxiv_https___arxiv_org_abs_2605_04366
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Conditional Flow-VAE for Safety-Critical Traffic Scenario Generation
Gong, Zimu
Zhang, Brian Zhaoning
Zhang, Chris
Wong, Kelvin
Urtasun, Raquel
Robotics
Machine Learning
Safety-critical scenarios are essential for the development of autonomous vehicles (AVs) but are rare in real-world driving data. While simulation offers a way to generate such scenarios, manually designed test cases lack scalability, and adversarial optimization often produces unrealistic behaviors. In this work, we introduce a conditional latent flow matching approach for scalable and realistic safety-critical scenario generation. Our method uses distribution matching to transform nominal scenes into safety-critical rollouts. Furthermore, we demonstrate that incorporating both simulation and real-world data enables our framework to efficiently generate diverse, data-driven scenarios. Experimental results highlight that our approach is able to more consistently and realistically generate novel safety-critical scenarios, making it a valuable tool for training and benchmarking AV systems.
title Conditional Flow-VAE for Safety-Critical Traffic Scenario Generation
topic Robotics
Machine Learning
url https://arxiv.org/abs/2605.04366