NVIDIA previews the GR00T N2 world action model and announces Cosmos 3 at GTC 2026
Confirmed
Status
- Claim
Confirmed
- Our reporting
- High confidence
- Importance
- 3 of 5
- Last verified
- 29 September 2026
Your AI and this story
- GPT-6 AstraIn its training data
- Claude Opus 5.5In its training data
- Gemini 4 HydrogenIn its training data
- Grok 4.7In its training data
It happened before the cutoffs of all four assistants, so it can be in their training data.
Key facts
- GR00T N2: DreamZero-based world action model; predicts future world states before acting; >2x success on new tasks/environments vs leading VLAs; No. 1 on MolmoSpaces and RoboArena (NVIDIA); availability end of 2026
- GR00T N1.7: 3B open reasoning VLA, early access with commercial licensing at GTC; open weights on Hugging Face with blog 2026-04-17
- GR00T N1.7 pretrained on 20,854 hours of human egocentric video; NVIDIA claims the first scaling law for robot dexterity
- Cosmos 3: ‘first world foundation model unifying synthetic world generation, vision reasoning and action simulation’ (weights released ~2026-06-01)
- Isaac Lab 3.0 early access with Newton physics engine 1.0
- Isaac Lab 3.0 timeline (GitHub): beta 2026-03-17 (on Isaac Sim 6.0), beta 2 2026-06-17, Early Access 2026-09-16; GA targeted for end of October 2026
- Newton: open-source GPU physics engine on NVIDIA Warp/OpenUSD, co-developed by NVIDIA, Google DeepMind and Disney Research under the Linux Foundation; v1.0.0 tagged on GitHub 2026-04-13; solvers include MuJoCo Warp and Kamino plus VBD for deformables
- Healthcare robotics: Open-H-Embodiment (first large open medical-robotics dataset, ~778 h real+synthetic from 35 organizations), GR00T-H (GR00T VLA with a Cosmos-Reason 2 2B backbone post-trained for surgery on ~600 h; called ‘the first policy model for surgical robotics tasks’; completes an end-to-end suture on the SutureBot benchmark) and Cosmos-H surgical simulator; a GR00T-H-N1.7 variant followed on HF 2026-05-30
Show 2 more
- Same-day open-model release also covered Nemotron 3 Ultra/Omni/VoiceChat, Alpamayo 1.5 (reasoning VLA for autonomous vehicles), Proteina-Complexa (protein binder design) and nvQSP
- Partners: FANUC, ABB, YASKAWA, KUKA (2M+ installed robots), plus Boston Dynamics, Figure, Agility, 1X
What happened
The robotics part of Jensen Huang’s GTC 2026 keynote. GR00T N2 moves NVIDIA’s humanoid model from a VLA to a world model that “imagines” outcomes before acting. GR00T N1.7 swaps in a Cosmos-Reason2-2B backbone and adds human-video pretraining.
Why it matters
NVIDIA is pitching world-model-based policies and human video as a way to trade scarce robot teleoperation data for compute. The N1.7 weights are one of the main open alternatives to closed models from Physical Intelligence, Google and Figure. As of 2026-09-29, N2 had not been released.
Sources
10 sources from 5 sites. Numbers match the chips in the text.
10 sources: 8 primary, 2 press
Primary
- NVIDIA Newsroom: NVIDIA and Global Robotics Leaders Take Physical AI to the Real Worldnvidianews.nvidia.com, official
- NVIDIA Newsroom: NVIDIA Expands Open Model Families (agentic, physical, healthcare AI)nvidianews.nvidia.com, official
- Hugging Face blog: The first healthcare robotics dataset and foundational physical AI models (Open-H, GR00T-H, Cosmos-H)huggingface.co, official
- Hugging Face: nvidia/GR00T-H-N1.7huggingface.co, code
- Isaac Lab releases (GitHub)github.com, code
- Newton physics engine (GitHub)github.com, code
- Hugging Face blog: Isaac GR00T N1.7huggingface.co, official
- Isaac-GR00T GitHubgithub.com, code
Press
- The Decoder: Nvidia wants to swap robotics’ data problem for a compute problemthe-decoder.com, press
- TrendForce: NVIDIA expands robotics ecosystem at GTCtrendforce.com, press
Changes
- Added healthcare robotics (Open-H, GR00T-H, GR00T-H-N1.7) and the companion ‘Expands Open Model Families’ release; added Isaac Lab 3.0 / Newton 1.0 release timeline
- Filed