Delta Intelligence shows single generalist policy driving 69-DoF humanoid at near-human speed
chris_j_paxton · x · 2026-11-09
Delta Intelligence unveiled Δ₀, a humanoid full-body foundation model: a single generalist policy controls a 69-DoF humanoid for long-horizon, contact-rich whole-body loco-manipulation at roughly human speed in human environments.
Key details from the RoboPapers podcast with founders Siyuan Huang and jeasinema: large-scale pretraining on whole-body human data, joint policy-controller design, and a delta action space that lets a human operator seamlessly correct the robot mid-task without interrupting the whole-body controller.
More from Embodied
- Stanford team teaches an AI agent a pool table's physics by letting it take real shots (CoRL) — drmapavone · 2026-11-09
- Furong Huang Lab brings six human-video-to-robot works to CoRL 2026 — furongh · 2026-11-09
- Three CMU robot papers spotlighted at CoRL 2026: memory, vision-touch steering, world models — pabbeel · 2026-11-09
- CoRL 2026 balloons to 5,000+ attendees; Princeton PRISM brings 6 robotics papers including oral MolmoB0T — shahdhruv_ · 2026-11-09
- UW RAIVN Lab brings GAM, MolmoAct2 and Reflex to CoRL: 3D grounding beats VLA baselines — LINJIEFUN · 2026-11-09
- BitRobot Ecosystem Lightning Talks Day 1: MolmoAct2, RoboEval, RoboTTS Lineup — DJiafei · 2026-11-09