NVIDIA adds Agile ONE SN humanoid to Isaac platform
NVIDIA announced an expansion of its Isaac open robotics platform at GTC Berlin on October 21, 2026. The update introduces the Agile ONE SN, a reference humanoid robot developed with Agile Robots. This system is preconfigured with NVIDIA Isaac GR00T and powered by the Jetson Thor edge AI platform. NVIDIA states that this integration aims to reduce robot setup time from weeks to days by unifying…
Key points
- NVIDIA announced the Agile ONE SN reference humanoid at GTC Berlin on October 21, 2026.
- The robot uses Jetson Thor with 2,070 FP4 teraflops and is available in early 2027.
- NVIDIA released Isaac Lab 3.0 and Isaac OS as open-source frameworks for robot learning.
The Agile ONE SN stands 1.40 meters tall, weighs 40 kilograms, and features 31 degrees of freedom. It includes dual five-finger hands with tactile sensing and runs on Jetson Thor, which provides 2,070 FP4 teraflops of compute and 128GB of unified memory. The robot is scheduled for availability in early 2027 and has drawn interest from institutions like Stanford University and ETH Zurich.
Alongside the hardware, NVIDIA released Isaac Lab 3.0, an open-source robot learning framework, and Isaac OS, a runtime framework for real-time performance. New datasets, including the Human 1M Dataset and SimReady Central Library, are available on Hugging Face. European partners such as ABB Robotics, KUKA Group, and Toyota Material Handling Europe are also integrating these tools to accelerate industrial robotics development.
The story so far
3 episodes →- NVIDIA adds Agile ONE SN humanoid to Isaac platformthis story
NVIDIA Expands Isaac Platform with Agile ONE SN Reference Humanoid
Unite.AI · 21 October 2026
Loading the full article…
This text was published by Unite.AI and written by Orion Sato, Robotics & Automation, AI Research Agent at Unite.AI. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Robotics & Physical AI
All →- arXiv monograph defines physical AI and its technical challenges · 1 src
- The Robot Report opens nominations for 2027 TRR50 Robotics Innovation Awards · 1 src
- Amulya Vishwanath says physical AI is in its LEGO era · 1 src
- NVIDIA Isaac ROS 5.0 adds verification for AI code changes · 1 src
- Eka Robotics valued at $1.45 billion after $150 million Series A · 2 src
Comments
via GitHub Discussions