FastUMI-100K: Advancing Data-driven Robotic Manipulation with a Large-scale UMI-style Dataset
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_ | 1866916998524436480 |
|---|---|
| author | Liu, Kehui Jia, Zhongjie Li, Yang Zhaxizhuoma Chen, Pengan Liu, Song Liu, Xin Zhang, Pingrui Song, Haoming Ye, Xinyi Cao, Nieqing Wang, Zhigang Zeng, Jia Wang, Dong Ding, Yan Zhao, Bin Li, Xuelong |
| author_facet | Liu, Kehui Jia, Zhongjie Li, Yang Zhaxizhuoma Chen, Pengan Liu, Song Liu, Xin Zhang, Pingrui Song, Haoming Ye, Xinyi Cao, Nieqing Wang, Zhigang Zeng, Jia Wang, Dong Ding, Yan Zhao, Bin Li, Xuelong |
| contents | Data-driven robotic manipulation learning depends on large-scale, high-quality expert demonstration datasets. However, existing datasets, which primarily rely on human teleoperated robot collection, are limited in terms of scalability, trajectory smoothness, and applicability across different robotic embodiments in real-world environments. In this paper, we present FastUMI-100K, a large-scale UMI-style multimodal demonstration dataset, designed to overcome these limitations and meet the growing complexity of real-world manipulation tasks. Collected by FastUMI, a novel robotic system featuring a modular, hardware-decoupled mechanical design and an integrated lightweight tracking system, FastUMI-100K offers a more scalable, flexible, and adaptable solution to fulfill the diverse requirements of real-world robot demonstration data. Specifically, FastUMI-100K contains over 100K+ demonstration trajectories collected across representative household environments, covering 54 tasks and hundreds of object types. Our dataset integrates multimodal streams, including end-effector states, multi-view wrist-mounted fisheye images and textual annotations. Each trajectory has a length ranging from 120 to 500 frames. Experimental results demonstrate that FastUMI-100K enables high policy success rates across various baseline algorithms, confirming its robustness, adaptability, and real-world applicability for solving complex, dynamic manipulation challenges. The source code and dataset will be released in this link https://github.com/MrKeee/FastUMI-100K. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_08022 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FastUMI-100K: Advancing Data-driven Robotic Manipulation with a Large-scale UMI-style Dataset Liu, Kehui Jia, Zhongjie Li, Yang Zhaxizhuoma Chen, Pengan Liu, Song Liu, Xin Zhang, Pingrui Song, Haoming Ye, Xinyi Cao, Nieqing Wang, Zhigang Zeng, Jia Wang, Dong Ding, Yan Zhao, Bin Li, Xuelong Robotics Artificial Intelligence Data-driven robotic manipulation learning depends on large-scale, high-quality expert demonstration datasets. However, existing datasets, which primarily rely on human teleoperated robot collection, are limited in terms of scalability, trajectory smoothness, and applicability across different robotic embodiments in real-world environments. In this paper, we present FastUMI-100K, a large-scale UMI-style multimodal demonstration dataset, designed to overcome these limitations and meet the growing complexity of real-world manipulation tasks. Collected by FastUMI, a novel robotic system featuring a modular, hardware-decoupled mechanical design and an integrated lightweight tracking system, FastUMI-100K offers a more scalable, flexible, and adaptable solution to fulfill the diverse requirements of real-world robot demonstration data. Specifically, FastUMI-100K contains over 100K+ demonstration trajectories collected across representative household environments, covering 54 tasks and hundreds of object types. Our dataset integrates multimodal streams, including end-effector states, multi-view wrist-mounted fisheye images and textual annotations. Each trajectory has a length ranging from 120 to 500 frames. Experimental results demonstrate that FastUMI-100K enables high policy success rates across various baseline algorithms, confirming its robustness, adaptability, and real-world applicability for solving complex, dynamic manipulation challenges. The source code and dataset will be released in this link https://github.com/MrKeee/FastUMI-100K. |
| title | FastUMI-100K: Advancing Data-driven Robotic Manipulation with a Large-scale UMI-style Dataset |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2510.08022 |