English

A Humanoid Visual-Tactile-Action Dataset for Contact-Rich Manipulation

Robotics 2025-11-17 v2

Abstract

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.

Keywords

Cite

@article{arxiv.2510.25725,
  title  = {A Humanoid Visual-Tactile-Action Dataset for Contact-Rich Manipulation},
  author = {Eunju Kwon and Seungwon Oh and In-Chang Baek and Yucheon Park and Gyungbo Kim and JaeYoung Moon and Yunho Choi and Kyung-Joong Kim},
  journal= {arXiv preprint arXiv:2510.25725},
  year   = {2025}
}
R2 v1 2026-07-01T07:12:25.191Z