NVIDIA Expands Isaac Open-Source Robotics Platform, Unveils Humanoid Robot Reference Design Agile ONE SN and Isaac Lab 3.0

Related topics top start Related topics top end Futures promotion begin Futures promotion end Miaopai begin Miaopai end Video player start Video player end Market chart begin Market chart end

NVIDIA today announced a major expansion of its open-source robot development platform NVIDIA Isaac™, adding a humanoid robot reference prototype, accompanying datasets and runtime, and upgrading its robot learning framework.

With this technology stack, developers gain an end-to-end solution from data collection to deployment, bringing general-purpose robots to real-world scenarios faster.

"General-purpose robots are advancing rapidly, and the 'ChatGPT moment' for robotics is nearly here," said Jensen Huang, founder and CEO of NVIDIA. "With the full-stack open-source robot platform NVIDIA Isaac, we give developers models, data, simulation tools and computing systems to bring physical AI into major core industries worldwide."

Agile ONE SN — a cutting-edge humanoid robot reference platform for research

Agile Robots has released Agile ONE SN, a full-stack humanoid robot reference prototype preloaded with NVIDIA Isaac GR00T and powered by the NVIDIA Jetson Thor™ edge AI platform.

Robot developers often face a major pain point: simulation, training and deployment tools are fragmented, making it hard to transfer robot skills from the development environment to physical robots. Agile ONE SN integrates all tools and workflows into a single platform, cutting deployment preparation time from weeks to days.

Agile ONE SN key specifications:

- Agile ONE S humanoid body: 1.4 meters tall, 40 kilograms, 31 degrees of freedom, 3 kilograms maximum payload per arm

- A pair of WUJI Hand 2 five-fingered dexterous hands: 20 degrees of freedom per hand, 1kHz force control, tactile sensing for fine manipulation

- Multimodal perception: head and wrist cameras, LiDAR, inertial measurement unit to perceive and interact with the environment

- NVIDIA Isaac GR00T platform: includes the GR00T foundation model, a complete workflow from data collection to deployment, and whole-body coordinated motion control

- Safety capabilities: plans to integrate robot-side safety protocols and connect to NVIDIA Halos, NVIDIA's full-stack safety system for robots

"The breakthrough for humanoid robots lies in practical use at scale: an adaptive machine that learns multiple skills and works in various environments designed for humans," said Chen Zhaopeng, founder and CEO of Agile Robots. "Today Agile Robots introduces Agile ONE SN, a full-stack open-source humanoid reference prototype based on NVIDIA Isaac GR00T and powered by Jetson Thor, giving developers a ready-made system to develop, train and validate the capabilities needed for humanoid robots to be deployed."

Agile ONE SN is expected to launch in early 2027, targeting cutting-edge humanoid robot research; top institutions such as Stanford University and ETH Zurich have already expressed interest in collaboration.

NVIDIA's new technologies accelerate robot learning: from data to deployment

NVIDIA's new toolchain helps developers generate training data, scale robot learning, build simulation environments and deploy robot applications, shortening development cycles.

- SimReady central asset library: provides more than 2,000 robot and industrial assets ready for simulation; the Human 1M dataset contains rich human motion, synchronized multi-view video and 3D hand tracking data. Both are now available on Hugging Face; the full Human 1M dataset is available only to Cosmos coalition partners.

- NVIDIA Isaac Lab 3.0 officially launched: an open-source agent learning framework supporting workflows from local workstations to data centers and multi-GPU parallelism, training and iterating robot policies on the Newton and NVIDIA PhysX™ physics engines.

- NVIDIA Isaac OS: an open-source runtime framework built on NVIDIA Holoscan that connects AI, sensors, control units and robot hardware to achieve deterministic real-time scheduling from simulation to physical robots.

- NVIDIA released three open-source reference workflows for DGX Station™: iterating the GR00T 1.7 model with reinforcement learning, training dexterous manipulation skills in Isaac Lab, and fine-tuning the NVIDIA Cosmos™ world model combined with ChatGPT Astra to generate synthetic data.

- NVIDIA Halos: a full-stack safety platform based on NVIDIA IGX Thor™ that helps autonomous vehicles and robots move from prototypes to safe, large-scale deployment.

The SimReady asset library assets on Hugging Face come from: Comau, FANUC, ForgeCAD, Franka Robotics, LG Electronics, Palatial, Robotiq, Standard Bots, Universal Robots and Vertiv.

NVIDIA's open-source robot learning reference workflows running on DGX Station are supported by vendors including 1X, Agile Robots, Humanoid, Maven Robotics, Mentee, MicroAGI, Rhoda, Sereact and Skild AI.

Multiple robot partners are integrating Halos into their safety architectures: Agile Robots, Agility, Dexory, FORT Robotics and KION for warehouse robot safety solutions; SICK is evaluating Halos to build dynamic safety capabilities for industrial robots, breaking free from fixed safety zones to handle dynamically changing scenarios.

Advantech and NexCOBOT are developing industrial computing platforms based on NVIDIA IGX; Reynolds & Moore, Accenture and TÜV SÜD are accelerating certification processes for safe deployment of industrial physical AI.

European robot makers conduct R&D on NVIDIA open-source technologies

ABB Robotics is integrating NVIDIA Omniverse™ libraries into RobotStudio HyperReality to complete robot system simulation and virtual commissioning before production across multiple industries. KUKA Group is integrating Omniverse components into Visual Components FactoryLens to add real-time rendering to factory simulation. Sereact is using Isaac GR00T + Cosmos Transfer to train and fine-tune its Cortex platform for goods sorting, deployed on Universal Robots industrial robotic arms.

Humanoid is using Jetson Thor, Holoscan Sensor Bridge, Halos and Isaac OS to develop and validate robot behaviors before industrial pilots; Hexagon Robotics is developing AEON's perception capabilities, including teleoperation video, localization, mapping and object pose detection; Bear Robotics is accelerating KR1's perception and model execution, fine-tuning Isaac GR00T with Kino-2 for warehouse, returns and industrial scenarios.

Toyota Material Handling Europe and SoftServe are using Omniverse + NVIDIA Isaac Sim™ to develop autonomous material handling solutions, cutting deployment cycles by up to 50%. Idealworks is using NVIDIA open-source models and Jetson to develop memory capabilities for autonomous mobile robots in factories. ADI>Analog Devices (ADI) is using Jetson AGX Orin™ and the cuVSLAM library to develop autonomous mobile robots.

Hugging Face and Pollen Robotics built Microduck on Isaac Lab, Isaac Sim and Newton, a small open-source robot for developers and students to train, modify and share new embodied behaviors. Franka Robotics integrated NVIDIA NIM™ microservices + Isaac Sim to translate natural language commands into Franka FR3 Duo robotic arm motions. Bellboy is using Jetson and GR00T to power its robot Billie, its first physical AI robot companion, already deployed at hotels under Marriott, Hilton, IHG and OYO.

Flexion is using Isaac Lab and Newton to scale training of Reflect, a unified robot intelligence model; Reflect combines reasoning and whole-body motion to complete complex operations across robot types. Schaeffler is exclusively providing actuator technology to Newton, working with Isaac Lab and Isaac Sim to accelerate humanoid robot development.

NEURA Robotics is using Isaac Sim and Isaac Lab to generate synthetic training data, training robot skills for its multimodal foundation model Neuron AI in simulated environments. news_keyword_pub,usstock,ACN&ADI&ADI Account opening QR code start

Account opening QR code end iframe below body iframe below body General statement General statement QR code at end of article start QR code at end of article start

QR code at end of article start QR code at end of article start Editor name and work code

Editor name and work code