Latent Two-Sample Testing for Fair Autonomous Vehicle Road Evaluation
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.