UMI-FT
real-stanford
A handheld interface and learning workflow for recording forceful manipulation without using a robot during capture.
What you can explore
Explore hardware instructions, iPhone capture and force-aware demonstration processing.
Before you use it
The interface is gripper-based, not a full articulated robot hand. Robot deployment still needs compatible force sensing, calibration and action mapping.
Original contributors
Stanford REAL / UMI-FT contributors
License / access: Code: MIT · check external data, models and hardware terms separately
Keep exploring
TacThru
Combined tactile and visual perception for learning contact-rich manipulation.
DexUMI
A wearable interface that records dexterous demonstrations and adapts their visual appearance for robot learning.
YUBI interface software
Operator-side software for a two-handed manipulation-data collection interface.
Editorial reference · checked 2026-09-22