SparseAD: Sparse Query-Centric Paradigm for Efficient End-to-End Autonomous Driving
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929308889513984 |
|---|---|
| author | Zhang, Diankun Wang, Guoan Zhu, Runwen Zhao, Jianbo Chen, Xiwu Zhang, Siyu Gong, Jiahao Zhou, Qibin Zhang, Wenyuan Wang, Ningzi Tan, Feiyang Zhou, Hangning Xu, Ziyao Yao, Haotian Zhang, Chi Liu, Xiaojun Di, Xiaoguang Li, Bin |
| author_facet | Zhang, Diankun Wang, Guoan Zhu, Runwen Zhao, Jianbo Chen, Xiwu Zhang, Siyu Gong, Jiahao Zhou, Qibin Zhang, Wenyuan Wang, Ningzi Tan, Feiyang Zhou, Hangning Xu, Ziyao Yao, Haotian Zhang, Chi Liu, Xiaojun Di, Xiaoguang Li, Bin |
| contents | End-to-End paradigms use a unified framework to implement multi-tasks in an autonomous driving system. Despite simplicity and clarity, the performance of end-to-end autonomous driving methods on sub-tasks is still far behind the single-task methods. Meanwhile, the widely used dense BEV features in previous end-to-end methods make it costly to extend to more modalities or tasks. In this paper, we propose a Sparse query-centric paradigm for end-to-end Autonomous Driving (SparseAD), where the sparse queries completely represent the whole driving scenario across space, time and tasks without any dense BEV representation. Concretely, we design a unified sparse architecture for perception tasks including detection, tracking, and online mapping. Moreover, we revisit motion prediction and planning, and devise a more justifiable motion planner framework. On the challenging nuScenes dataset, SparseAD achieves SOTA full-task performance among end-to-end methods and significantly narrows the performance gap between end-to-end paradigms and single-task methods. Codes will be released soon. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_06892 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SparseAD: Sparse Query-Centric Paradigm for Efficient End-to-End Autonomous Driving Zhang, Diankun Wang, Guoan Zhu, Runwen Zhao, Jianbo Chen, Xiwu Zhang, Siyu Gong, Jiahao Zhou, Qibin Zhang, Wenyuan Wang, Ningzi Tan, Feiyang Zhou, Hangning Xu, Ziyao Yao, Haotian Zhang, Chi Liu, Xiaojun Di, Xiaoguang Li, Bin Computer Vision and Pattern Recognition End-to-End paradigms use a unified framework to implement multi-tasks in an autonomous driving system. Despite simplicity and clarity, the performance of end-to-end autonomous driving methods on sub-tasks is still far behind the single-task methods. Meanwhile, the widely used dense BEV features in previous end-to-end methods make it costly to extend to more modalities or tasks. In this paper, we propose a Sparse query-centric paradigm for end-to-end Autonomous Driving (SparseAD), where the sparse queries completely represent the whole driving scenario across space, time and tasks without any dense BEV representation. Concretely, we design a unified sparse architecture for perception tasks including detection, tracking, and online mapping. Moreover, we revisit motion prediction and planning, and devise a more justifiable motion planner framework. On the challenging nuScenes dataset, SparseAD achieves SOTA full-task performance among end-to-end methods and significantly narrows the performance gap between end-to-end paradigms and single-task methods. Codes will be released soon. |
| title | SparseAD: Sparse Query-Centric Paradigm for Efficient End-to-End Autonomous Driving |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.06892 |