A Formal Safety Characterization of Advanced Driver Assist Systems in the Car-Following Regime with Scenario-Sampling

TL;DR

This paper introduces a formal, unbiased, and sampling-efficient scenario-based framework for evaluating the safety of advanced driver assist systems in car-following situations, addressing limitations of previous methods.

Contribution

It presents a novel safety characterization method inspired by $psilon\u03b4$-almost safe set theory, enabling comprehensive safety performance assessment in the car-following regime.

Findings

The framework provides unbiased safety evaluation results.

It effectively assesses various decision-making modules and commercial systems.

Demonstrated in challenging real-world scenarios.

Abstract

The capability to follow a lead-vehicle and avoid rear-end collisions is one of the most important functionalities for human drivers and various Advanced Driver Assist Systems (ADAS). Existing safety performance justification of the car-following systems either relies on simple concrete scenarios with biased surrogate metrics or requires a significantly long driving distance for risk observation and inference. In this paper, we propose a guaranteed unbiased and sampling efficient scenario-based safety evaluation framework inspired by the previous work on $\epsilon\delta$-almost safe set quantification. The proposal characterizes the complete safety performance of the test subject in the car-following regime. The performance of the proposed method is also demonstrated in challenging cases including some widely adopted car-following decision-making modules and the commercially available Openpilot driving stack by CommaAI.