No π0 weights changed: Motoniq layer lifts real-robot precision fitting from 0/10 to 9/10
hbouammar · x · 2026-10-27
Motoniq reports early results: adding its layer on top of Physical Intelligence's π0 — with zero weight changes — lifted real-robot precision fitting success from 0/10 to 9/10. Across six tasks on π0 and π0.5, gains ranged from +4 to +90 percentage points (10 physical trials, 50 sim episodes per condition). Part 1 of 3, with more capability-from-existing-models results promised.
More from Embodied
- π0.5 study: raising demos from 10 to 438 lifts Place Ball in Bowl success from 7% to 83% — stingning · 2026-10-27
- GPT-6 Astra controls dexterous hands zero-shot at just 5.2% success in 500 trials — stingning · 2026-10-27
- HandsOn benchmark: 66 verified tasks and 18,000 human demos for dexterous manipulation — stingning · 2026-10-27
- DexPort: a handheld interface with a real robot hand for dexterous-hand data collection — pabbeel · 2026-10-27
- ROS names Alejandro Hernández Cordero new project lead, eyes 2027 release — ___Mufasaa · 2026-10-27
- ROS Meetup coming to Google's NYC office Oct 29 with speakers from Tangent, Cohesive Robotics, Intrinsic — kscottz · 2026-10-27