NVIDIA Expands Isaac Platform With Agile ONE SN Humanoid, Isaac Lab 3.0 for General-Purpose Robotics

NVIDIA Unveils Major Isaac Platform Expansion for General-Purpose Robotics

NVIDIA announced a significant expansion of the NVIDIA Isaac platform at GTC Berlin, introducing new tools designed to accelerate the development of general-purpose robotics1

1

. The robotics development platform now includes a reference humanoid robot, updated frameworks, simulation pipelines, and datasets that provide developers an integrated path from data to deployment2

2

. Jensen Huang, NVIDIA's founder and CEO, stated that "the ChatGPT moment for robotics is fast approaching," positioning the Isaac platform as a full-stack solution for bringing physical AI to major industries1

1

.

Agile ONE SN Humanoid Robot Built on Isaac GR00T and Jetson Thor

Agile Robots unveiled the Agile ONE SN humanoid, a full-stack reference platform preconfigured with NVIDIA Isaac GR00T and powered by the NVIDIA Jetson Thor edge AI platform3

3

. The humanoid robot stands 1.40 meters tall, weighs 40 kilograms, and features 31 degrees of freedom with a 3-kilogram payload capacity per arm2

2

. Equipped with dual WUJI Hand 2 five-finger hands, each hand offers 20 degrees of freedom, 1kHz force control, and tactile sensing for dexterous manipulation1

1

. The platform unifies simulation, training, and deployment tools on a single system, cutting setup time from weeks to days3

3

.

NVIDIA Jetson Thor delivers 2,070 FP4 teraflops of compute and 128GB of unified memory for onboard reasoning and real-time control2

2

. Multimodal sensing capabilities include head and wrist cameras, lidar sensors, and inertial measurement units to help the robot perceive and interact with its surroundings1

1

. Zhaopeng Chen, founder and CEO of Agile Robots, emphasized that "the breakthrough for humanoids is usefulness at scale: one adaptable machine that learns many skills and works across environments built for people"1

1

. Scheduled for availability in early 2027, the Agile ONE SN humanoid has attracted interest from leading institutions including Stanford University and ETH Zurich1

1

.

Isaac Lab 3.0 and New Tools Accelerate Robot Learning

NVIDIA released Isaac Lab 3.0, now generally available as an open source learning framework for training and refining robot policies from desktop to data center using multi-GPU workflows and physics engines including Newton and NVIDIA PhysX3

3

. The platform introduces NVIDIA Isaac OS, an open source runtime framework built on NVIDIA Holoscan that connects AI, sensors, controls, and robot hardware for deterministic, real-time performance from simulation to physical robots2

2

.

The SimReady Central Library, available on Hugging Face, offers more than 2,000 simulation-ready robotics and factory assets2

2

. NVIDIA also released the Human 1M Dataset, which includes diverse human activities, synchronized three-view video, and 3D hand tracking, accessible to Cosmos Coalition partners1

1

. Three open source reference workflows for NVIDIA DGX Station help developers refine GR00T 1.7 models with reinforcement learning, train dexterous manipulation skills in Isaac Lab, and post-train NVIDIA Cosmos world models for synthetic data generation using ChatGPT Astra3

3

.

European Robotics Ecosystem Adopts NVIDIA Platform

Europe's robotics ecosystem is integrating the NVIDIA Isaac platform into their systems. ABB Robotics is incorporating NVIDIA Omniverse libraries with its RobotStudio HyperReality for robotic system simulation2

2

. KUKA Group is using Omniverse libraries in its Visual Components FactoryLens for factory simulation workflows2

2

. Other European leaders including Flexion, Hexagon Robotics, Humanoid, NEURA Robotics, Sereact, and Universal Robots are building on the open robotics platform to advance autonomous robotic systems1

1

.

NVIDIA also introduced NVIDIA Halos, a full-stack safety platform built on NVIDIA IGX Thor designed to help move autonomous vehicles and robots from development to safer real-world deployment at scale3

3

. Partners including Agile Robots, Agility, Dexory, FORT Robotics, and KION are integrating Halos within their safety architectures2

2

. The Agile ONE SN features planned integration of on-robot safety protocols with the NVIDIA Halos system1

1

.