Delta Intelligence's Δ₀: single generalist policy drives 69-DoF humanoid at near-human speed
chris_j_paxton · x · 2026-11-07
Delta Intelligence's Δ₀ is a humanoid full-body foundation model: a single generalist policy controls a 69-DoF humanoid through long-horizon loco-manipulation at near-human speed, pretrained on large-scale whole-body human data. Key design choices include jointly designing policy and controller and using a delta action space, letting human operators seamlessly intervene without interrupting the whole-body controller. Details on RoboPapers episode 115.
More from Embodied
- MIT and Stanford release free robotics textbook merging classical engineering with AI — GioeleZardini · 2026-11-07
- RoboColosseum offers academic researchers 10,000 free real-world robot eval hours — DJiafei · 2026-11-07
- Hugging Face nears 100K robotics datasets, Reachy mini sells 50K+ units — DJiafei · 2026-11-07
- Infinite Factory: endless robot factory generated live in-browser with WFC and OpenUSD — mishig25 · 2026-11-07
- Playing rock-paper-scissors with a robot next to a flying car: 'We live in the future we were promised' — beffjezos · 2026-11-07
- Darwin Robotics Raises $3.6M Pre-Seed to Build Robot Technicians for Data Centers — ycombinator · 2026-11-07