Scenario Generation in Roundabouts with Adjustable Interaction Intensity

TL;DR

This paper introduces a novel scenario generator for roundabouts that allows continuous adjustment of interaction intensity, improving safety testing and analysis of autonomous driving functions.

Contribution

It presents a new method combining autoencoders and Wasserstein GANs to generate controllable, realistic roundabout scenarios with adjustable interaction criticality.

Findings

Enhanced fidelity of generated scenarios compared to baseline.

Scaling the yield code modulates interaction criticality effectively.

Increasing interaction intensity expands safety margins in generated scenarios.

Abstract

Roundabouts, characterized by frequent merging and yielding interactions, remain a safety-critical corner case for the development and testing of intelligent driving functions. However, extracting sufficient near-critical scenarios from naturalistic data is inefficient. Most existing scenario generation methods provide limited controllability over interaction intensity and criticality, making systematic safety testing and detailed analysis difficult. This paper presents an interaction-aware roundabout scenario generator with continuously adjustable interaction intensity. Geometric routes and temporal progress profiles are first decoupled and mapped to latent codes using pretrained autoencoders. Conditional latent generation is then performed with Wasserstein Generative Adversarial Networks (WGAN) to generate scenarios. Yielding is modeled as a controllable timing intervention via a compact yield code during the approach-to-entry segment, where interaction intensity is modulated by scaling the code with a factor $\lambda$. Results demonstrate enhanced timing-latent fidelity and plausible interaction responses compared to a baseline model. Under criticality-calibrated scaling, increasing $\lambda$ expands the safety margin, providing a scalable and controlled testing mechanism.