Nature Will launches Natura-1, a physical-world foundation model trained on 1M hours of egocentric video
testingcatalog · x · 2026-10-13
Robotics startup Nature Will has launched Natura-1, billed as the first general foundation model for the physical world.
- Trained on 1 million hours of egocentric video of humans handling diverse scenarios and objects, capturing hand movements and interaction spaces;
- Generalizes to objects and tasks it has never seen, with instructions specific down to an object's final position and orientation;
- Tested on real robots including tasks deliberately held out of the final training round;
- Demos include notoriously hard robot skills like putting glasses into a case and unfolding a towel.
Related event: Nature Will Unveils Natura-1, a Foundation Model for the Physical World(9 posts)→
More from Embodied
- UNITAS: a 1.7B 3D-native world action model hits 99.8% on LIBERO and 85% on real tasks — CUHKSZ · 2026-10-14
- Frontier LLM scores on real robot benchmark double every 6 weeks, 15% to 48% in 3 months — ycombinator · 2026-10-14
- Raven Prism AI glasses launch set for October 28 in San Francisco — smtabatabaie · 2026-10-14
- DeLorean joins Airspeeder International Series, first American team debuting in November — evilrabbit_ · 2026-10-14
- Gemini 4 Argon taught Apptronik's Apollo humanoid cornhole from video, sinking 7 straight throws — GoogleDeepMind · 2026-10-14
- Box2D dev unveils contact recycling, making contact generation almost free in physics sims — EricLengyel · 2026-10-14