Human skill. Robot potential. A living collection of interfaces, datasets, and ideas for robot learning.
HKUST · 2026
A scissor-shaped UMI-style interface provides direct mechanical force feedback.
Vision Proprioception
Details ↗ + Compare
Daimon Robotics · 2026
A visuotactile collection interface supporting the TacClaw-Infinity dataset.
Vision Tactile IMU
Details ↗ + Compare
Stanford · 2026
Wearable contact patches and UMI grippers for whole-body contact demonstrations.
Vision Tactile Contact
Details ↗ + Compare
Zhejiang University · 2026
Chest and wrist RGB views provide portable mobile-manipulation demonstrations.
Vision Proprioception
Details ↗ + Compare
Northwestern University · 2026
A wireless collector combining vision, touch, and contact audio in one sensing finger.
Vision Tactile Audio
Details ↗ + Compare
Autel US · 2026
Camera-only bimanual capture, with both hands registered in one metric map.
Vision IMU Audio
Details ↗ + Compare
Zhejiang University · 2026
Native UMI end-effector skills drive humanoid whole-body motion generation.
Vision Proprioception
Details ↗ + Compare
Peking University · 2026
A shared 20-DoF exoskeleton for human demonstration and dexterous robot deployment.
Vision Proprioception
Details ↗ + Compare
NeoteAI · 2026
An infrared-tracked gripper combining RGB vision and two tactile sensors.
Vision Tactile Proprioception
Details ↗ + Compare
Huaweike Intelligent Tech / 华威科 · 2026
A manufacturer UMI solution combining tracked hand motion with tactile acquisition.
Vision Tactile Proprioception
Details ↗ + Compare
Simple AI · 2026
High-fidelity, portable capture with stereo-inertial tracking and a released 2,000-hour dataset.
Vision IMU Proprioception
Details ↗ + Compare
X Square Robot · 2026
A headband and dual-gripper collector with synchronized vision, tactile and audio.
Vision Tactile Audio
Details ↗ + Compare
No matches this time. Try another phrase or use fewer filters.
Clear filters
end The collection could not be loaded.
Try again For the complete collection, read the README . Search, comparison, and continuous loading require JavaScript.
A clearer view of UMI. Awesome UMI connects the hardware, datasets, and research behind robot learning from human demonstrations.
The README is the canonical collection. Specifications and release information are checked against papers and official resources. Images belong to their credited projects.
Paper-reported scale, indexed data, and downloadable releases are kept separate. Missing information stays unverified.
Read the collection ↗