UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations
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_ | 1866916958634508288 |
|---|---|
| author | Kim, Hanjung Kang, Jaehyun Kang, Hyolim Cho, Meedeum Kim, Seon Joo Lee, Youngwoon |
| author_facet | Kim, Hanjung Kang, Jaehyun Kang, Hyolim Cho, Meedeum Kim, Seon Joo Lee, Youngwoon |
| contents | Mimicry is a fundamental learning mechanism in humans, enabling individuals to learn new tasks by observing and imitating experts. However, applying this ability to robots presents significant challenges due to the inherent differences between human and robot embodiments in both their visual appearance and physical capabilities. While previous methods bridge this gap using cross-embodiment datasets with shared scenes and tasks, collecting such aligned data between humans and robots at scale is not trivial. In this paper, we propose UniSkill, a novel framework that learns embodiment-agnostic skill representations from large-scale cross-embodiment video data without any labels, enabling skills extracted from human video prompts to effectively transfer to robot policies trained only on robot data. Our experiments in both simulation and real-world environments show that our cross-embodiment skills successfully guide robots in selecting appropriate actions, even with unseen video prompts. The project website can be found at: https://kimhanjung.github.io/UniSkill. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_08787 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations Kim, Hanjung Kang, Jaehyun Kang, Hyolim Cho, Meedeum Kim, Seon Joo Lee, Youngwoon Robotics Computer Vision and Pattern Recognition Mimicry is a fundamental learning mechanism in humans, enabling individuals to learn new tasks by observing and imitating experts. However, applying this ability to robots presents significant challenges due to the inherent differences between human and robot embodiments in both their visual appearance and physical capabilities. While previous methods bridge this gap using cross-embodiment datasets with shared scenes and tasks, collecting such aligned data between humans and robots at scale is not trivial. In this paper, we propose UniSkill, a novel framework that learns embodiment-agnostic skill representations from large-scale cross-embodiment video data without any labels, enabling skills extracted from human video prompts to effectively transfer to robot policies trained only on robot data. Our experiments in both simulation and real-world environments show that our cross-embodiment skills successfully guide robots in selecting appropriate actions, even with unseen video prompts. The project website can be found at: https://kimhanjung.github.io/UniSkill. |
| title | UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.08787 |