End-to-End Autonomous Driving through V2X Cooperation
January 25, 2025 ยท View on GitHub
arXiv | Demo | Code

Table of Contents:
Highlights
- UniV2X is the first cooperative autonomous driving framework that seamlessly integrates all key driving modules across diverse driving views into a unified network.
News
2025/01/26Code & model initial releasev1.0.2024/12/10UniV2X is accepted by AAAI 2025.2024/04/02UniV2X paper is available on arXiv.
Getting Started
TODO List
- Base-model code release (on DAIR-V2X)
- Base-model configs & checkpoints (on DAIR-V2X)
- Benchmark code release (on DAIR-V2X)
- Benchmark configs & checkpoints (on DAIR-V2X)
- Support more datasets
License
All assets and code are under the Apache 2.0 license unless specified otherwise.
Citation
Please consider citing our paper if the project helps your research with the following BibTex:
@inproceedings{yu2024_univ2x,
title={End-to-End Autonomous Driving through V2X Cooperation},
author={Haibao Yu and Wenxian Yang and Jiaru Zhong and Zhenwei Yang and Siqi Fan and Ping Luo and Zaiqing Nie},
booktitle={The 39th Annual AAAI Conference on Artificial Intelligence},
year={2025}
}