发表机构
Department of Aeronautics and Astronautics, Stanford University; Torc Robotics（斯坦福大学航空航天系; Torc机器人公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究商用自动驾驶车辆故障发现问题，应用自适应压力测试和基于扩散的故障采样算法找到模拟碰撞，引入基于主成分分析的统计分析将故障分类并恢复噪声轨迹，为故障发现到系统诊断提供路径。
AI 中文摘要
目前，用于发现自主系统中罕见故障的方法几乎仅在具有简单学术驾驶堆栈的模拟中得到验证，尚不清楚它们是否能推广到商用系统中更强大的规划器。我们通过将两种罕见事件发现算法应用于商用自动驾驶卡车堆栈来填补这一空白。自适应压力测试（AST）使用强化学习搜索最可能导致模拟碰撞的噪声轨迹，而基于扩散的故障采样（DiFS）训练去噪扩散模型以采样各种故障。我们表明这两种算法都能发现传统蒙特卡罗模拟无法发现的合并和切入操作中的模拟碰撞。为使这些故障具有可操作性，我们引入基于主成分分析（PCA）的统计分析，将故障分类为常见模式并识别对结果影响最大的时间步长。我们对主成分进行聚类并反转PCA变换以恢复广义噪声轨迹，并表明这些轨迹在相同和相似场景中重现故障。这提供了一条从故障发现到感知级缺陷系统诊断的路径。
英文摘要
Methods for discovering rare failures in autonomous systems have so far been demonstrated almost exclusively in simulations with simple, academic driving stacks, leaving open whether they generalize to the more robust planners used in commercial systems. We address this gap by applying two rare-event discovery algorithms to a commercial autonomous trucking stack. Adaptive stress testing (AST) uses reinforcement learning to search for the most likely noise trajectories leading to a simulated collision, while diffusion-based failure sampling (DiFS) trains a denoising diffusion model to sample a diverse set of failures. We show that both algorithms find simulated collisions during merge and cut-in maneuvers where traditional Monte Carlo simulation does not. To make these failures actionable, we introduce a statistical analysis based on principal component analysis (PCA) that classifies failures into common modes and identifies the timesteps that most influence the outcome. We cluster the principal components and invert the PCA transform to recover generalized noise trajectories, and show that these trajectories reproduce failures in identical and similar scenarios. This provides a path from failure discovery to systematic diagnosis of perception-level flaws.
CommentsIEEE ICVES 2026 (Submitted)
