NTU's Facet-0 robot model lifts precision assembly success from 16% to 82%

jiqizhixin · x · 2026-09-11

NTU's PINE Lab unveiled Facet-0, a robot foundation model for contact-rich precision assembly. Existing models struggle badly: π0.5 averages 10% success and GR00T N1.7 just 4% on insertions with 0.10–0.30mm clearances. Facet-0 judges whether it's performing correctly from real contact feedback and improves from failure experience, with the training pipeline lifting success from 16% (pretraining) to 38% (RL post-training) to 82% (lightweight adaptation), handling 23 sub-goals per task across alignment, insertion, pressing, and locking.

Original post →

More from Embodied

Embodied channel →