HiP-AD: Hierarchical and Multi-Granularity Planning with Deformable Attention for Autonomous Driving in a Single Decoder
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915191805968384 |
|---|---|
| author | Tang, Yingqi Xu, Zhuoran Meng, Zhaotie Cheng, Erkang |
| author_facet | Tang, Yingqi Xu, Zhuoran Meng, Zhaotie Cheng, Erkang |
| contents | Although end-to-end autonomous driving (E2E-AD) technologies have made significant progress in recent years, there remains an unsatisfactory performance on closed-loop evaluation. The potential of leveraging planning in query design and interaction has not yet been fully explored. In this paper, we introduce a multi-granularity planning query representation that integrates heterogeneous waypoints, including spatial, temporal, and driving-style waypoints across various sampling patterns. It provides additional supervision for trajectory prediction, enhancing precise closed-loop control for the ego vehicle. Additionally, we explicitly utilize the geometric properties of planning trajectories to effectively retrieve relevant image features based on physical locations using deformable attention. By combining these strategies, we propose a novel end-to-end autonomous driving framework, termed HiP-AD, which simultaneously performs perception, prediction, and planning within a unified decoder. HiP-AD enables comprehensive interaction by allowing planning queries to iteratively interact with perception queries in the BEV space while dynamically extracting image features from perspective views. Experiments demonstrate that HiP-AD outperforms all existing end-to-end autonomous driving methods on the closed-loop benchmark Bench2Drive and achieves competitive performance on the real-world dataset nuScenes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_08612 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HiP-AD: Hierarchical and Multi-Granularity Planning with Deformable Attention for Autonomous Driving in a Single Decoder Tang, Yingqi Xu, Zhuoran Meng, Zhaotie Cheng, Erkang Robotics Computer Vision and Pattern Recognition Although end-to-end autonomous driving (E2E-AD) technologies have made significant progress in recent years, there remains an unsatisfactory performance on closed-loop evaluation. The potential of leveraging planning in query design and interaction has not yet been fully explored. In this paper, we introduce a multi-granularity planning query representation that integrates heterogeneous waypoints, including spatial, temporal, and driving-style waypoints across various sampling patterns. It provides additional supervision for trajectory prediction, enhancing precise closed-loop control for the ego vehicle. Additionally, we explicitly utilize the geometric properties of planning trajectories to effectively retrieve relevant image features based on physical locations using deformable attention. By combining these strategies, we propose a novel end-to-end autonomous driving framework, termed HiP-AD, which simultaneously performs perception, prediction, and planning within a unified decoder. HiP-AD enables comprehensive interaction by allowing planning queries to iteratively interact with perception queries in the BEV space while dynamically extracting image features from perspective views. Experiments demonstrate that HiP-AD outperforms all existing end-to-end autonomous driving methods on the closed-loop benchmark Bench2Drive and achieves competitive performance on the real-world dataset nuScenes. |
| title | HiP-AD: Hierarchical and Multi-Granularity Planning with Deformable Attention for Autonomous Driving in a Single Decoder |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.08612 |