ProgressVLA: Progress-Guided Diffusion Policy for Vision-Language Robotic Manipulation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915897521733632 |
|---|---|
| author | Yan, Hongyu Li, Qiwei Yang, Jiaolong Mu, Yadong |
| author_facet | Yan, Hongyu Li, Qiwei Yang, Jiaolong Mu, Yadong |
| contents | Most existing vision-language-action (VLA) models for robotic manipulation lack progress awareness, typically relying on hand-crafted heuristics for task termination. This limitation is particularly severe in long-horizon tasks involving cascaded sub-goals. In this work, we investigate the estimation and integration of task progress, proposing a novel model named {\textbf \vla}. Our technical contributions are twofold: (1) \emph{robust progress estimation}: We pre-train a progress estimator on large-scale, unsupervised video-text robotic datasets. This estimator achieves a low prediction residual (0.07 on a scale of $[0, 1]$) in simulation and demonstrates zero-shot generalization to unseen real-world samples, and (2) \emph{differentiable progress guidance}: We introduce an inverse dynamics world model that maps predicted action tokens into future latent visual states. These latents are then processed by the progress estimator; by applying a maximal progress regularization, we establish a differentiable pipeline that provides progress-piloted guidance to refine action tokens. Extensive experiments on the CALVIN and LIBERO benchmarks, alongside real-world robot deployment, consistently demonstrate substantial improvements in success rates and generalization over strong baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_27670 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ProgressVLA: Progress-Guided Diffusion Policy for Vision-Language Robotic Manipulation Yan, Hongyu Li, Qiwei Yang, Jiaolong Mu, Yadong Robotics Artificial Intelligence Most existing vision-language-action (VLA) models for robotic manipulation lack progress awareness, typically relying on hand-crafted heuristics for task termination. This limitation is particularly severe in long-horizon tasks involving cascaded sub-goals. In this work, we investigate the estimation and integration of task progress, proposing a novel model named {\textbf \vla}. Our technical contributions are twofold: (1) \emph{robust progress estimation}: We pre-train a progress estimator on large-scale, unsupervised video-text robotic datasets. This estimator achieves a low prediction residual (0.07 on a scale of $[0, 1]$) in simulation and demonstrates zero-shot generalization to unseen real-world samples, and (2) \emph{differentiable progress guidance}: We introduce an inverse dynamics world model that maps predicted action tokens into future latent visual states. These latents are then processed by the progress estimator; by applying a maximal progress regularization, we establish a differentiable pipeline that provides progress-piloted guidance to refine action tokens. Extensive experiments on the CALVIN and LIBERO benchmarks, alongside real-world robot deployment, consistently demonstrate substantial improvements in success rates and generalization over strong baselines. |
| title | ProgressVLA: Progress-Guided Diffusion Policy for Vision-Language Robotic Manipulation |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2603.27670 |