ART-Glove: Articulated Tactile Glove for Contact-Grounded Dexterous Interaction Capture
Provides a new hardware platform for capturing high-fidelity contact-rich manipulation data, addressing the need for contact-grounded demonstrations in dexterous robot learning.
ART-Glove captures contact-grounded dexterous demonstrations with 22-DoF joint and 2048-taxel tactile measurements at 120 Hz, preserving human dexterity for downstream robot learning.
We present ART-Glove, an articulated tactile glove designed to capture contact-grounded dexterous demonstrations while preserving human dexterity. ART-Glove makes hand-side contact geometry explicit with 16 rigid functional surfaces covering the fingers, thumb, and palm. Twenty-two anatomically aligned joints connect these surfaces and allow them to follow human hand motion during dexterous manipulation. Encoder-based sensing tracks surface motion, while dense piezoresistive tactile sensing records contact over the same surfaces. The complete system captures synchronized 22-DoF joint measurements and 2048-taxel tactile measurements at 120 Hz. We evaluate ART-Glove across experiments on motion freedom, joint sensing, tactile sensing, and contact-rich interaction capture, demonstrating its ability to preserve human dexterity while recording contact-grounded information that can support downstream dexterous robot learning.