Safety Analysis of Autonomous Driving Systems Based on Model Learning

TL;DR

This paper introduces a verification method for autonomous driving systems that uses surrogate models to analyze safety properties with probabilistic guarantees across different traffic scenarios.

Contribution

It proposes a practical approach to safety verification of ADS by building surrogate models that capture system behavior and exploring safe and unsafe parameter spaces.

Findings

Safety properties verified with probabilistic guarantees

Effective evaluation on state-of-the-art ADS

Analysis across diverse traffic scenarios

Abstract

We present a practical verification method for safety analysis of the autonomous driving system (ADS). The main idea is to build a surrogate model that quantitatively depicts the behaviour of an ADS in the specified traffic scenario. The safety properties proved in the resulting surrogate model apply to the original ADS with a probabilistic guarantee. Furthermore, we explore the safe and the unsafe parameter space of the traffic scenario for driving hazards. We demonstrate the utility of the proposed approach by evaluating safety properties on the state-of-the-art ADS in literature, with a variety of simulated traffic scenarios.