恒定的眼睛：自动驾驶中外观鲁棒性的基准测试与弥合
The Constant Eye: Benchmarking and Bridging Appearance Robustness in Autonomous Driving
AI总结：
本文提出navdream基准测试，通过生成像素对齐的风格迁移，评估自动驾驶算法在极端天气等外观变化下的鲁棒性，并提出通用感知接口实现零样本泛化。
摘要：
尽管取得了快速进展，自动驾驶算法在分布外（OOD）条件下仍表现出异常脆弱性。我们识别出当前研究中一个关键的解耦失败：缺乏对基于外观的位移（如天气和光照）与结构场景变化之间的区分。这留下了一个根本性问题未被回答：规划器失败是因为复杂的道路几何，还是仅仅因为下雨了？为了解决这一问题，我们建立了navdream，一个高保真的鲁棒性基准测试，利用生成像素对齐的风格迁移。通过创建一个具有极小几何偏差的视觉压力测试，我们隔离了外观对驾驶性能的影响。我们的评估揭示了现有规划算法在OOD外观条件下往往表现出显著的退化，即使底层场景结构保持一致。为弥合这一差距，我们提出了一种通用的感知接口，利用冻结的视觉基础模型（DINOv3）。通过提取对外观不变的特征作为规划器的稳定接口，我们实现了在多种规划范式中（包括回归式、扩散式和评分式模型）的卓越零样本泛化能力。我们的即插即用解决方案在极端外观位移下保持一致的性能，而无需进一步微调。基准测试和代码将被公开。
英文摘要：
Despite rapid progress, autonomous driving algorithms remain notoriously fragile under Out-of-Distribution (OOD) conditions. We identify a critical decoupling failure in current research: the lack of distinction between appearance-based shifts, such as weather and lighting, and structural scene changes. This leaves a fundamental question unanswered: Is the planner failing because of complex road geometry, or simply because it is raining? To resolve this, we establish navdream, a high-fidelity robustness benchmark leveraging generative pixel-aligned style transfer. By creating a visual stress test with negligible geometric deviation, we isolate the impact of appearance on driving performance. Our evaluation reveals that existing planning algorithms often show significant degradation under OOD appearance conditions, even when the underlying scene structure remains consistent. To bridge this gap, we propose a universal perception interface leveraging a frozen visual foundation model (DINOv3). By extracting appearance-invariant features as a stable interface for the planner, we achieve exceptional zero-shot generalization across diverse planning paradigms, including regression-based, diffusion-based, and scoring-based models. Our plug-and-play solution maintains consistent performance across extreme appearance shifts without requiring further fine-tuning. The benchmark and code will be made available.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
