一篇题为“迷失在雾中”的新研究论文，调查了自动驾驶领域中视觉-语言-动作（VLA）模型的推理脆弱性。该研究在近2000个场景中，对Alpamayo R1模型进行了包括噪声、极端光照和雾等多种传感器扰动测试。研究人员发现，模型因果链（CoC）解释的变化与轨迹偏差的显著增加直接相关，这凸显了推理一致性作为VLA部署的关键安全指标的重要性。 AI
影响 揭示了自动驾驶AI中关键的安全漏洞，促使为VLA系统开发新的运行时监控技术。
排序理由 该集群包含一篇详细介绍AI模型鲁棒性研究的论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.21446v1 Announce Type: cross Abstract: Interpretable autonomous driving planners depend not only on generating explanations, but also on those explanations remaining reliable under real-world sensor degradation. In this paper we present a controlled perturbation study …
Interpretable autonomous driving planners depend not only on generating explanations, but also on those explanations remaining reliable under real-world sensor degradation. In this paper we present a controlled perturbation study of Vision-Language-Action (VLA) robustness in auto…