PlannerRFT: Reinforcing Diffusion Planners through Closed-Loop and Sample-Efficient Fine-Tuning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912832105218048 |
|---|---|
| author | Li, Hongchen Li, Tianyu Yang, Jiazhi Tian, Haochen Wang, Caojun Shi, Lei Shang, Mingyang Lin, Zengrong Wu, Gaoqiang Hao, Zhihui Lang, Xianpeng Hu, Jia Li, Hongyang |
| author_facet | Li, Hongchen Li, Tianyu Yang, Jiazhi Tian, Haochen Wang, Caojun Shi, Lei Shang, Mingyang Lin, Zengrong Wu, Gaoqiang Hao, Zhihui Lang, Xianpeng Hu, Jia Li, Hongyang |
| contents | Diffusion-based planners have emerged as a promising approach for human-like trajectory generation in autonomous driving. Recent works incorporate reinforcement fine-tuning to enhance the robustness of diffusion planners through reward-oriented optimization in a generation-evaluation loop. However, they struggle to generate multi-modal, scenario-adaptive trajectories, hindering the exploitation efficiency of informative rewards during fine-tuning. To resolve this, we propose PlannerRFT, a sample-efficient reinforcement fine-tuning framework for diffusion-based planners. PlannerRFT adopts a dual-branch optimization that simultaneously refines the trajectory distribution and adaptively guides the denoising process toward more promising exploration, without altering the original inference pipeline. To support parallel learning at scale, we develop nuMax, an optimized simulator that achieves 10 times faster rollout compared to native nuPlan. Extensive experiments shows that PlannerRFT yields state-of-the-art performance with distinct behaviors emerging during the learning process. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_12901 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PlannerRFT: Reinforcing Diffusion Planners through Closed-Loop and Sample-Efficient Fine-Tuning Li, Hongchen Li, Tianyu Yang, Jiazhi Tian, Haochen Wang, Caojun Shi, Lei Shang, Mingyang Lin, Zengrong Wu, Gaoqiang Hao, Zhihui Lang, Xianpeng Hu, Jia Li, Hongyang Robotics Diffusion-based planners have emerged as a promising approach for human-like trajectory generation in autonomous driving. Recent works incorporate reinforcement fine-tuning to enhance the robustness of diffusion planners through reward-oriented optimization in a generation-evaluation loop. However, they struggle to generate multi-modal, scenario-adaptive trajectories, hindering the exploitation efficiency of informative rewards during fine-tuning. To resolve this, we propose PlannerRFT, a sample-efficient reinforcement fine-tuning framework for diffusion-based planners. PlannerRFT adopts a dual-branch optimization that simultaneously refines the trajectory distribution and adaptively guides the denoising process toward more promising exploration, without altering the original inference pipeline. To support parallel learning at scale, we develop nuMax, an optimized simulator that achieves 10 times faster rollout compared to native nuPlan. Extensive experiments shows that PlannerRFT yields state-of-the-art performance with distinct behaviors emerging during the learning process. |
| title | PlannerRFT: Reinforcing Diffusion Planners through Closed-Loop and Sample-Efficient Fine-Tuning |
| topic | Robotics |
| url | https://arxiv.org/abs/2601.12901 |