FOMO-DEX from Amazon FAR, CMU and Berkeley uses force feedback to fix only contact commands
HaozhiQ · x · 2026-10-19
FOMO-DEX, from Amazon FAR, CMU and Berkeley, takes a third route beyond stiff hands (which crush or drop objects) and fully compliant hands (floppy and imprecise): force feedback modifies only the contact-relevant portion of the operator's command and leaves everything else untouched.
The result is smoother contact, fewer failed grasps, and demos good enough to train policies on—addressing a real pain point in teleoperation data collection for robot learning.
More from Embodied
- Compliant gears update: single-flank compliance with preload yields zero backlash — yacineMTB · 2026-10-19
- Scoble: 'What if robots never touch anything?' talk helped store lift sales 258% — Scobleizer · 2026-10-19
- ASUS Ascent GX10 (GB10) drops to ~$4,300 used on Amazon, 3 units left — AIFlow_ML · 2026-10-19
- Researchers demo 0-click RCE on Tesla Model 3 via Bluetooth TPMS sensors — matthew_d_green · 2026-10-19
- Sim-ready humanoid character revealed, RL experiments coming next — _Stocko_ · 2026-10-19
- Open-source ROS 2 LiDAR localization runs 390 m outdoors on handheld Livox MID-360 — rsasaki0109 · 2026-10-19