Normalizing Flows are Capable Models for Bi-manual Visuomotor Policy
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_ | 1866908851521978368 |
|---|---|
| author | Li, Jialong Lind, Simon Kristoffersson Xie, Wenrui Stenmark, Maj Krüger, Volker |
| author_facet | Li, Jialong Lind, Simon Kristoffersson Xie, Wenrui Stenmark, Maj Krüger, Volker |
| contents | The field of general-purpose robotics has recently embraced powerful probabilistic diffusion-based models to learn the complex embodiment behaviours. However, existing models often come with significant trade-offs, namely high computational costs for inference and a fundamental inability to quantify output uncertainty. We introduce Normalizing Flows Policy (NF-P), a conditional normalizing flow-based visuomotor policy for bi-manual manipulation. NF-P learns a conditional density over action sequences and enables single-pass generative sampling with tractable likelihood computation. Using this property, we propose two inference-time optimization strategies: Stochastic Batch Selection, which selects the highest-likelihood trajectory among sampled candidates, and Gradient Refinement, which directly ascends the log-likelihood to improve action quality. In both simulation and real robot experiments, NF-P achieves promising success rates compared to the baseline. In addition to improved task performance, NF-P demonstrates faster training and lower inference latency. These results establish normalizing flows as a competitive and computationally efficient visuomotor policy, particularly for real-time, uncertainty-aware robotic control. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_21073 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Normalizing Flows are Capable Models for Bi-manual Visuomotor Policy Li, Jialong Lind, Simon Kristoffersson Xie, Wenrui Stenmark, Maj Krüger, Volker Robotics The field of general-purpose robotics has recently embraced powerful probabilistic diffusion-based models to learn the complex embodiment behaviours. However, existing models often come with significant trade-offs, namely high computational costs for inference and a fundamental inability to quantify output uncertainty. We introduce Normalizing Flows Policy (NF-P), a conditional normalizing flow-based visuomotor policy for bi-manual manipulation. NF-P learns a conditional density over action sequences and enables single-pass generative sampling with tractable likelihood computation. Using this property, we propose two inference-time optimization strategies: Stochastic Batch Selection, which selects the highest-likelihood trajectory among sampled candidates, and Gradient Refinement, which directly ascends the log-likelihood to improve action quality. In both simulation and real robot experiments, NF-P achieves promising success rates compared to the baseline. In addition to improved task performance, NF-P demonstrates faster training and lower inference latency. These results establish normalizing flows as a competitive and computationally efficient visuomotor policy, particularly for real-time, uncertainty-aware robotic control. |
| title | Normalizing Flows are Capable Models for Bi-manual Visuomotor Policy |
| topic | Robotics |
| url | https://arxiv.org/abs/2509.21073 |