FlowDrive: Energy Flow Field for End-to-End Autonomous Driving
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916955519188992 |
|---|---|
| author | Jiang, Hao Zhang, Zhipeng Gao, Yu Sun, Zhigang Wang, Yiru Heng, Yuwen Wang, Shuo Chai, Jinhao Chen, Zhuo Zhao, Hao Sun, Hao Zhang, Xi Jiang, Anqing Hu, Chuan |
| author_facet | Jiang, Hao Zhang, Zhipeng Gao, Yu Sun, Zhigang Wang, Yiru Heng, Yuwen Wang, Shuo Chai, Jinhao Chen, Zhuo Zhao, Hao Sun, Hao Zhang, Xi Jiang, Anqing Hu, Chuan |
| contents | Recent advances in end-to-end autonomous driving leverage multi-view images to construct BEV representations for motion planning. In motion planning, autonomous vehicles need considering both hard constraints imposed by geometrically occupied obstacles (e.g., vehicles, pedestrians) and soft, rule-based semantics with no explicit geometry (e.g., lane boundaries, traffic priors). However, existing end-to-end frameworks typically rely on BEV features learned in an implicit manner, lacking explicit modeling of risk and guidance priors for safe and interpretable planning. To address this, we propose FlowDrive, a novel framework that introduces physically interpretable energy-based flow fields-including risk potential and lane attraction fields-to encode semantic priors and safety cues into the BEV space. These flow-aware features enable adaptive refinement of anchor trajectories and serve as interpretable guidance for trajectory generation. Moreover, FlowDrive decouples motion intent prediction from trajectory denoising via a conditional diffusion planner with feature-level gating, alleviating task interference and enhancing multimodal diversity. Experiments on the NAVSIM v2 benchmark demonstrate that FlowDrive achieves state-of-the-art performance with an EPDMS of 86.3, surpassing prior baselines in both safety and planning quality. The project is available at https://astrixdrive.github.io/FlowDrive.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_14303 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FlowDrive: Energy Flow Field for End-to-End Autonomous Driving Jiang, Hao Zhang, Zhipeng Gao, Yu Sun, Zhigang Wang, Yiru Heng, Yuwen Wang, Shuo Chai, Jinhao Chen, Zhuo Zhao, Hao Sun, Hao Zhang, Xi Jiang, Anqing Hu, Chuan Robotics Artificial Intelligence Recent advances in end-to-end autonomous driving leverage multi-view images to construct BEV representations for motion planning. In motion planning, autonomous vehicles need considering both hard constraints imposed by geometrically occupied obstacles (e.g., vehicles, pedestrians) and soft, rule-based semantics with no explicit geometry (e.g., lane boundaries, traffic priors). However, existing end-to-end frameworks typically rely on BEV features learned in an implicit manner, lacking explicit modeling of risk and guidance priors for safe and interpretable planning. To address this, we propose FlowDrive, a novel framework that introduces physically interpretable energy-based flow fields-including risk potential and lane attraction fields-to encode semantic priors and safety cues into the BEV space. These flow-aware features enable adaptive refinement of anchor trajectories and serve as interpretable guidance for trajectory generation. Moreover, FlowDrive decouples motion intent prediction from trajectory denoising via a conditional diffusion planner with feature-level gating, alleviating task interference and enhancing multimodal diversity. Experiments on the NAVSIM v2 benchmark demonstrate that FlowDrive achieves state-of-the-art performance with an EPDMS of 86.3, surpassing prior baselines in both safety and planning quality. The project is available at https://astrixdrive.github.io/FlowDrive.github.io/. |
| title | FlowDrive: Energy Flow Field for End-to-End Autonomous Driving |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2509.14303 |