Open X-AV: Unifying End-to-End Autonomous Driving Datasets

Long Nguyen, Micha Fauth, Bernhard Jaeger, Daniel Dauner, Maximilian Igl, Andreas Geiger, Kashyap Chitta

CVPR 2025 Workshops (Waymo Vision-based End-to-End Driving Challenge)

2nd Place — 2025 Waymo Vision-based End-to-End Driving Challenge

Paper (PDF) NVIDIA Project Page Challenge
Open X-AV overview

Abstract

The fragmentation of existing autonomous vehicle (AV) datasets hinders the development of generalizable driving policies that can handle complex and infrequent events. To overcome this, we introduce the Open-X AV (OXAV) repository, an initiative designed to aggregate a wide variety of AV datasets and enable models to learn from these diverse sources. We propose a two-stage training workflow using OXAV: a pre-training phase using perception-focused data, followed by post-training on challenging planning-centric scenarios. Our method DiffusionLTF, a simple end-to-end policy trained on OXAV, ranked second in the 2025 Waymo vision-based end-to-end driving challenge, demonstrating the benefits of diverse, aggregated data.

BibTeX

@inproceedings{nguyen2025openxav,
  title     = {Open X-AV: Unifying End-to-End Autonomous Driving Datasets},
  author    = {Nguyen, Long and Fauth, Micha and Jaeger, Bernhard and Dauner, Daniel and Igl, Maximilian and Geiger, Andreas and Chitta, Kashyap},
  booktitle = {CVPR 2025 Workshops (Waymo Vision-based End-to-End Driving Challenge)},
  year      = {2025},
  note      = {2nd Place, Waymo Vision-based End-to-End Driving Challenge}
}