用强化学习与扩散模型发现自动驾驶卡车罕见故障，再通过主成分分析定位问题根源。
Importance Sampling and PCA for Finding Failures in Commercial Autonomous Vehicles
- 结合强化学习与扩散模型，自动搜索高风险驾驶场景中的罕见碰撞。
- 在变道和切入场景中发现传统蒙特卡洛方法无法检测到的碰撞，成功率提升3倍以上。
- 用主成分分析分解失败模式，可复现并诊断感知系统的根本缺陷，适合系统安全团队使用。
现有罕见故障发现方法主要基于简单仿真环境和学术级驾驶系统，难以推广至商业级自动驾驶系统。本文将两种罕见事件发现算法应用于商用自动驾驶卡车系统：自适应压力测试（AST）利用强化学习搜索最可能引发碰撞的噪声轨迹；基于扩散的故障采样（DiFS）训练去噪扩散模型以生成多样化故障样本。实验表明，两者均能在变道与切入场景中发现传统蒙特卡洛模拟未捕捉到的碰撞。为使故障可操作，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。通过聚类主成分并反向变换，恢复出可复现故障的通用噪声轨迹，验证其在相似场景中仍能重现失败。该方法实现了从故障发现到感知层面缺陷系统性诊断的闭环。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。