A Humanoid Visual-Tactile-Action Dataset for Contact-Rich Manipulation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917079975723008 |
|---|---|
| author | Kwon, Eunju Oh, Seungwon Baek, In-Chang Park, Yucheon Kim, Gyungbo Moon, JaeYoung Choi, Yunho Kim, Kyung-Joong |
| author_facet | Kwon, Eunju Oh, Seungwon Baek, In-Chang Park, Yucheon Kim, Gyungbo Moon, JaeYoung Choi, Yunho Kim, Kyung-Joong |
| contents | Contact-rich manipulation has become increasingly important in robot learning. However, previous studies on robot learning datasets have focused on rigid objects and underrepresented the diversity of pressure conditions for real-world manipulation. To address this gap, we present a humanoid visual-tactile-action dataset designed for manipulating deformable soft objects. The dataset was collected via teleoperation using a humanoid robot equipped with dexterous hands, capturing multi-modal interactions under varying pressure conditions. This work also motivates future research on models with advanced optimization strategies capable of effectively leveraging the complexity and diversity of tactile signals. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_25725 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Humanoid Visual-Tactile-Action Dataset for Contact-Rich Manipulation Kwon, Eunju Oh, Seungwon Baek, In-Chang Park, Yucheon Kim, Gyungbo Moon, JaeYoung Choi, Yunho Kim, Kyung-Joong Robotics Contact-rich manipulation has become increasingly important in robot learning. However, previous studies on robot learning datasets have focused on rigid objects and underrepresented the diversity of pressure conditions for real-world manipulation. To address this gap, we present a humanoid visual-tactile-action dataset designed for manipulating deformable soft objects. The dataset was collected via teleoperation using a humanoid robot equipped with dexterous hands, capturing multi-modal interactions under varying pressure conditions. This work also motivates future research on models with advanced optimization strategies capable of effectively leveraging the complexity and diversity of tactile signals. |
| title | A Humanoid Visual-Tactile-Action Dataset for Contact-Rich Manipulation |
| topic | Robotics |
| url | https://arxiv.org/abs/2510.25725 |