project page

VAD: Vectorized Scene Representation for Efficient Autonomous Driving

Bo Jiang ¹*, Shaoyu Chen ¹*, Qing Xu², Bencheng Liao ¹, Jiajie Chen², Helong Zhou ², Qian Zhang ², Wenyu Liu ¹, Chang Huang ², Xinggang Wang ^1,†

¹ Huazhong University of Science and Technology, ² Horizon Robotics

*: equal contribution, ^†: corresponding author.

arXiv Paper, ICCV 2023

• 31 Jan, 2026: VADv2 is accepted by ICLR 2026 🎉 !
• 28 Sep, 2025: RAD is accepted by NeurIPS 2025. Core code for RL training is released at RAD.
• 27 Feb, 2025: Check out our latest work, DiffusionDrive, accepted by CVPR 2025! This study explores multi-modal end-to-end driving using diffusion models for real-time and real-world applications.
• 19 Feb, 2025: Checkout our new work RAD 🥰, end-to-end autonomous driving with large-scale 3DGS-based Reinforcement Learning post-training.
• 30 Oct, 2024: Checkout our new work Senna 🥰, which combines VAD/VADv2 with large vision-language models to achieve more accurate, robust, and generalizable autonomous driving planning.
• 20 Sep, 2024: Core code of VADv2 (config and model) is available in the VADv2 folder. Easy to integrade it into the VADv1 framework for training and inference.
• 17 June, 2024: CARLA implementation of VADv1 is available on Bench2Drive.
• 20 Feb, 2024: VADv2 is available on arXiv paper project page.
• 1 Aug, 2023: Code & models are released!
• 14 July, 2023: VAD is accepted by ICCV 2023🎉! Code and models will be open source soon!
• 21 Mar, 2023: We release the VAD paper on arXiv. Code/Models are coming soon. Please stay tuned! ☕️

VAD is a vectorized paradigm for end-to-end autonomous driving.

• We propose VAD, an end-to-end unified vectorized paradigm for autonomous driving. VAD models the driving scene as a fully vectorized representation, getting rid of computationally intensive dense rasterized representation and hand-designed post-processing steps.
• VAD implicitly and explicitly utilizes the vectorized scene information to improve planning safety, via query interaction and vectorized planning constraints.
• VAD achieves SOTA end-to-end planning performance, outperforming previous methods by a large margin. Not only that, because of the vectorized scene representation and our concise model design, VAD greatly improves the inference speed, which is critical for the real-world deployment of an autonomous driving system.

• Open-loop planning results on nuScenes. See the paper for more details.

• Closed-loop simulation results on CARLA.

*: LiDAR-based method.

• Installation
• Prepare Dataset
• Train and Eval
• Visualization

• Code & Checkpoints Release
• Initialization

If you have any questions or suggestions about this repo, please feel free to contact us (bjiang@hust.edu.cn, outsidercsy@gmail.com).

If you find VAD useful in your research or applications, please consider giving us a star 🌟 and citing it by the following BibTeX entry.

@article{jiang2023vad,
 title={VAD: Vectorized Scene Representation for Efficient Autonomous Driving},
 author={Jiang, Bo and Chen, Shaoyu and Xu, Qing and Liao, Bencheng and Chen, Jiajie and Zhou, Helong and Zhang, Qian and Liu, Wenyu and Huang, Chang and Wang, Xinggang},
 journal={ICCV},
 year={2023}
}
@article{chen2024vadv2,
 title={Vadv2: End-to-end vectorized autonomous driving via probabilistic planning},
 author={Chen, Shaoyu and Jiang, Bo and Gao, Hao and Liao, Bencheng and Xu, Qing and Zhang, Qian and Huang, Chang and Liu, Wenyu and Wang, Xinggang},
 journal={arXiv preprint arXiv:2402.13243},
 year={2024}
}

All code in this repository is under the Apache License 2.0.

VAD is based on the following projects: mmdet3d, detr3d, BEVFormer and MapTR. Many thanks for their excellent contributions to the community.