CronusVLA: Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling
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_ | 1866911240018722816 |
|---|---|
| author | Li, Hao Yang, Shuai Chen, Yilun Chen, Xinyi Yang, Xiaoda Tian, Yang Wang, Hanqing Wang, Tai Lin, Dahua Zhao, Feng Pang, Jiangmiao |
| author_facet | Li, Hao Yang, Shuai Chen, Yilun Chen, Xinyi Yang, Xiaoda Tian, Yang Wang, Hanqing Wang, Tai Lin, Dahua Zhao, Feng Pang, Jiangmiao |
| contents | Recent vision-language-action (VLA) models built on pretrained vision-language models (VLMs) have demonstrated strong performance in robotic manipulation. However, these models remain constrained by the single-frame image paradigm and fail to fully leverage the temporal information offered by multi-frame histories, as directly feeding multiple frames into VLM backbones incurs substantial computational overhead and inference latency. We propose CronusVLA, a unified framework that extends single-frame VLA models to the multi-frame paradigm. CronusVLA follows a two-stage process: (1) Single-frame pretraining on large-scale embodied datasets with autoregressive prediction of action tokens, establishing an effective embodied vision-language foundation; (2) Multi-frame post-training, which adapts the prediction of the vision-language backbone from discrete tokens to learnable features, and aggregates historical information via feature chunking. CronusVLA effectively addresses the existing challenges of multi-frame modeling while enhancing performance and observational robustness. To evaluate the robustness under temporal and spatial disturbances, we introduce SimplerEnv-OR, a novel benchmark featuring 24 types of observational disturbances and 120 severity levels. Experiments across three embodiments in simulated and real-world environments demonstrate that CronusVLA achieves leading performance and superior robustness, with a 70.9% success rate on SimplerEnv, a 26.8% improvement over OpenVLA on LIBERO, and the highest robustness score on SimplerEnv-OR. These results highlight the potential of efficient multi-frame adaptation in VLA models for more powerful and robust real-world deployment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_19816 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CronusVLA: Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling Li, Hao Yang, Shuai Chen, Yilun Chen, Xinyi Yang, Xiaoda Tian, Yang Wang, Hanqing Wang, Tai Lin, Dahua Zhao, Feng Pang, Jiangmiao Robotics Computer Vision and Pattern Recognition Recent vision-language-action (VLA) models built on pretrained vision-language models (VLMs) have demonstrated strong performance in robotic manipulation. However, these models remain constrained by the single-frame image paradigm and fail to fully leverage the temporal information offered by multi-frame histories, as directly feeding multiple frames into VLM backbones incurs substantial computational overhead and inference latency. We propose CronusVLA, a unified framework that extends single-frame VLA models to the multi-frame paradigm. CronusVLA follows a two-stage process: (1) Single-frame pretraining on large-scale embodied datasets with autoregressive prediction of action tokens, establishing an effective embodied vision-language foundation; (2) Multi-frame post-training, which adapts the prediction of the vision-language backbone from discrete tokens to learnable features, and aggregates historical information via feature chunking. CronusVLA effectively addresses the existing challenges of multi-frame modeling while enhancing performance and observational robustness. To evaluate the robustness under temporal and spatial disturbances, we introduce SimplerEnv-OR, a novel benchmark featuring 24 types of observational disturbances and 120 severity levels. Experiments across three embodiments in simulated and real-world environments demonstrate that CronusVLA achieves leading performance and superior robustness, with a 70.9% success rate on SimplerEnv, a 26.8% improvement over OpenVLA on LIBERO, and the highest robustness score on SimplerEnv-OR. These results highlight the potential of efficient multi-frame adaptation in VLA models for more powerful and robust real-world deployment. |
| title | CronusVLA: Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.19816 |