Figure's humanoid completes 56% of zero-shot household trials, up from 9%
VraserX · x · 2026-09-19
Figure's humanoid robot completed 56% of its zero-shot household trials — far from a product level you'd trust at home.
The interesting part: that's up from 9% before broad human-behavior pretraining, a roughly 6× improvement that suggests large-scale pretraining on human behavior significantly boosts task generalization for general-purpose humanoids.
Related event: Human-Behavior Pretraining Boosts Robot Task Success from 9% to 56%(3 posts)→
More from Embodied
- Physical AI's real story: a 4-layer map of 15 companies behind humanoid robots — pdamodaran · 2026-11-02
- Autonomous's Harness Pro uses an ESP32-P4, not a mini PC, to monitor AI coding agents — dee_hw · 2026-11-02
- KAIST's QCP lets robot policies control execution quality in real time — kaist-ai · 2026-11-02
- ANYbotics begins customer deliveries of ANYmal X, first legged robot certified for explosive atmospheres — lukas_m_ziegler · 2026-11-02
- InSpatio opens China's first embodied simulation data center targeting 1M hours/month — 智东西 · 2026-11-02
- GR-BC mines better trajectories from imperfect demos, hitting ~91% success on precise manipulation — 机器之心 · 2026-11-02