AI 中文总结
本研究针对自动驾驶车辆道路评估中环境干扰与数据特性导致的公平性问题，提出感知分布的评估框架，通过潜在表示与两阶段双样本测试方法提升评估可靠性，经实验验证有效。
AI 中文摘要
随着自动驾驶车辆（AV）系统的快速发展，通过道路测试进行快速可靠的迭代变得愈发关键。然而，测试环境的变化使得难以区分不同AV版本间的真实性能差异与无关环境变化，破坏了评估的公平性与可靠性。大规模道路测试数据具有高维、非结构化的特性，有效的分析与比较方法仍较为有限，进一步加剧了这一挑战。本研究提出了一种感知分布的AV评估原则性框架以应对这些挑战：首先学习结构化潜在表示，将高维、非结构化的道路测试数据映射至紧凑的潜在空间，实现对场景分布的有效表征；基于该表示，提出两阶段双样本测试框架，该框架可（i）检测并定位测试数据集间的分布偏移，（ii）通过重要性采样校准这些偏移，以降低评估偏差与指标估计误差。在合成数据与真实道路测试数据上的实验验证了所提方法的有效性。
英文摘要
With the rapid advancement of autonomous vehicle (AV) systems, fast and reliable iteration through road testing has become increasingly critical. However, changes in testing environments make it difficult to disentangle true performance differences between AV versions from extraneous environmental variations, undermining fair and reliable evaluation. This challenge is further compounded by the high-dimensional and unstructured nature of large-scale road testing data, for which effective analysis and comparison methods remain limited. In this work, we address these challenges by introducing a principled framework for distribution-aware AV evaluation. We first learn structured latent representations that map high-dimensional, unstructured road testing data into a compact latent space, enabling effective characterization of scenario distributions. Building on this representation, we propose a two-stage two-sample testing framework that (i) detects and localizes distributional shifts between testing datasets and (ii) calibrates these shifts via importance sampling to reduce evaluation bias and metric estimation error. Experiments on synthetic and real-world road testing data demonstrate the effectiveness of the proposed method.
