Work

From Particles to Perils: SVGD-Based Hazardous Scenario Generation for Autonomous Driving Systems Testing

Year: 2026

Type: article

Abstract: Simulation-based testing of autonomous driving systems (ADS) must uncover realistic and diverse failures in dense, heterogeneous traffic. However, existing search-based seeding methods (e.g., genetic algorithms) struggle in high-dimensional spaces, often collapsing to limited modes and missing many failure scenarios. We present PtoP, a framework that combines adaptive random seed generation with Stein Variational Gradient Descent (SVGD) to produce diverse, failure-inducing initial conditions. SVGD balances attraction toward high-risk regions and repulsion among particles, yielding risk-seeking yet well-distributed seeds across multiple failure modes. PtoP is plug-and-play and enhances existing online testing methods (e.g., reinforcement learning--based testers) by providing principled seeds. Evaluation in CARLA on two industry-grade ADS (Apollo, Autoware) and a native end-to-end system shows that PtoP improves safety violation rate (up to 27.68%), scenario diversity (9.6%), and map coverage (16.78%) over baselines.

Source: Proceedings of the ACM on software engineering.

DOI: 10.1145/3808153

Authors: Linfeng Liang, Xiao Cheng, Tsong Yueh Chen, Xi Zheng

Institutions: Macquarie University, Swinburne University of Technology

Language: English

Topic: Software Testing and Debugging Techniques

Subfield: Software

Field: Computer Science

Domain: Physical Sciences

SDG: Industry, innovation and infrastructure

Open Access status: hybrid

Funder: Australian Research Council