TL;DR研究实施了一种模拟测试框架来评估自动驾驶汽车系统的性能,并采用自适应重要性抽样方法加速稀有事件概率评估,评估了 Comma AI 的 OpenPilot,对自主车辆技术的测试和验证提出了新的方法。
Abstract
While autonomous vehicle (AV) technology has shown substantial progress, we
still lack tools for rigorous and scalable testing. Real-world testing, the
$\textit{de-facto}$ evaluation method, is dangerous to the public. Moreover,
due to the rare nature of failures, billions of miles of driving are needed to
statistically validate performance claims. Thus, the