Learning Responsibility-Attributed Adversarial Scenarios for Testing Autonomous Vehicles

TL;DR

This paper introduces CARS, a framework that generates responsibility-attributed adversarial scenarios for autonomous vehicle testing, improving interpretability and regulatory compliance in safety validation.

Contribution

CARS uniquely integrates responsibility attribution into adversarial scenario generation, enabling more meaningful and regulation-aligned safety testing for autonomous driving systems.

Findings

CARS effectively discovers feasible collision scenarios across diverse traffic environments.

High responsibility attribution rates are achieved under multiple driver models.

CARS enhances the interpretability and regulatory relevance of simulation-based safety evidence.

Abstract

Establishing trustworthy safety assurance for autonomous driving systems (ADSs) requires evidence that failures arise from avoidable system deficiencies rather than unavoidable traffic conflicts. Current adversarial simulation methods can efficiently expose collisions, but generally lack mechanisms to distinguish these fundamentally different failure modes. Here we present CARS (Context-Aware, Responsibility-attributed Scenario generation), a framework that integrates responsibility attribution directly into adversarial scenario generation. CARS combines context-aware adversary selection with a generative adversarial policy optimized in closed-loop simulation to construct collision scenarios that are both physically feasible and diagnostically attributable. Across benchmark datasets spanning heterogeneous national traffic environments, CARS consistently discovers feasible collision scenarios with high attribution rates under multiple regulation-prescribed careful and competent driver models. By coupling adversarial generation with normative responsibility assessment, CARS moves simulation testing beyond collision discovery toward the construction of interpretable, regulation-aligned safety evidence for scalable ADS validation.