Unleashing the Potential of Diffusion Models for End-to-End Autonomous Driving
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916019494191104 |
|---|---|
| author | Zheng, Yinan Tan, Tianyi Huang, Bin Liu, Enguang Liang, Ruiming Zhang, Jianlin Cui, Jianwei Chen, Guang Ma, Kun Ye, Hangjun Chen, Long Zhang, Ya-Qin Zhan, Xianyuan Liu, Jingjing |
| author_facet | Zheng, Yinan Tan, Tianyi Huang, Bin Liu, Enguang Liang, Ruiming Zhang, Jianlin Cui, Jianwei Chen, Guang Ma, Kun Ye, Hangjun Chen, Long Zhang, Ya-Qin Zhan, Xianyuan Liu, Jingjing |
| contents | Diffusion models have become a popular choice for decision-making tasks in robotics, and more recently, are also being considered for solving autonomous driving tasks. However, their applications and evaluations in autonomous driving remain limited to simulation-based or laboratory settings. The full strength of diffusion models for large-scale, complex real-world settings, such as End-to-End Autonomous Driving (E2E AD), remains underexplored. In this study, we conducted a systematic and large-scale investigation to unleash the potential of the diffusion models as planners for E2E AD, based on a tremendous amount of real-vehicle data and road testing. Through comprehensive and carefully controlled studies, we identify key insights into the diffusion loss space, trajectory representation, and data scaling that significantly impact E2E planning performance. Moreover, we also provide an effective reinforcement learning post-training strategy to further enhance the safety and robustness of the learned planner. The resulting diffusion-based learning framework, Hyper Diffusion Planner (HDP), is deployed on a real-vehicle platform and evaluated across 6 urban driving scenarios and 200 km of real-world testing, achieving a notable 10x performance improvement over the base model. Our work demonstrates that diffusion models, when properly designed and trained, can serve as effective and scalable E2E AD planners for complex, real-world autonomous driving tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_22801 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Unleashing the Potential of Diffusion Models for End-to-End Autonomous Driving Zheng, Yinan Tan, Tianyi Huang, Bin Liu, Enguang Liang, Ruiming Zhang, Jianlin Cui, Jianwei Chen, Guang Ma, Kun Ye, Hangjun Chen, Long Zhang, Ya-Qin Zhan, Xianyuan Liu, Jingjing Robotics Artificial Intelligence Machine Learning Diffusion models have become a popular choice for decision-making tasks in robotics, and more recently, are also being considered for solving autonomous driving tasks. However, their applications and evaluations in autonomous driving remain limited to simulation-based or laboratory settings. The full strength of diffusion models for large-scale, complex real-world settings, such as End-to-End Autonomous Driving (E2E AD), remains underexplored. In this study, we conducted a systematic and large-scale investigation to unleash the potential of the diffusion models as planners for E2E AD, based on a tremendous amount of real-vehicle data and road testing. Through comprehensive and carefully controlled studies, we identify key insights into the diffusion loss space, trajectory representation, and data scaling that significantly impact E2E planning performance. Moreover, we also provide an effective reinforcement learning post-training strategy to further enhance the safety and robustness of the learned planner. The resulting diffusion-based learning framework, Hyper Diffusion Planner (HDP), is deployed on a real-vehicle platform and evaluated across 6 urban driving scenarios and 200 km of real-world testing, achieving a notable 10x performance improvement over the base model. Our work demonstrates that diffusion models, when properly designed and trained, can serve as effective and scalable E2E AD planners for complex, real-world autonomous driving tasks. |
| title | Unleashing the Potential of Diffusion Models for End-to-End Autonomous Driving |
| topic | Robotics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2602.22801 |