Tactile Glove Captures Dexterous Manipulation Data
lukas_m_ziegler · x · 2026-07-13
ART-Glove is a tactile glove designed to record human dexterous manipulation, targeting not just hand movements but simultaneously capturing "how it moves" and "what it touches."
It features 16 rigid surfaces, 22 joints, and dense tactile sensors covering 2048 taxels, with encoders tracking surface motion to record joint angles, contact locations, and contact forces. The author emphasizes that this data is better suited for robot learning than plain video or standard demonstrations, as robots need to know actual contact points and forces rather than just observing visual actions.
The collected data can be directly used for robot learning, allowing systems to learn grasping and manipulation tasks without relying solely on vision to guess where to touch or how much force to apply.
Related event: ART-Glove Captures Tactile Data for Robotic Dexterity(2 posts)→
More from Embodied
- Tesla expands Robotaxi rides to seven areas, including new Orlando and Tampa zones — elonmusk · 2026-07-22
- Hands-on robotics workshop on Saturday may be the last in-person session before August — StewartalsopIII · 2026-07-22
- NVIDIA pitches World Foundation Models as a way to scale physical AI data generation — MonaJalal_ · 2026-07-22
- RoboMME Podcast Preview: Benchmarking Memory for Robotic Policies — chris_j_paxton · 2026-07-21
- Gritt says an 8-person crew now installs 3,000 to 4,000 solar panels a day — HaktanSuren · 2026-07-21
- A helium-powered flying robot whale aims to be a quiet companion pet — chris_j_paxton · 2026-07-21