SEOUL, South Korea — September 29, 2025 — Leads & Copy — NVIDIA has announced the availability of the open-source Newton Physics Engine in NVIDIA Isaac™ Lab, alongside the open NVIDIA Isaac GR00T N1.6 reasoning vision language action model for robot skills and new AI infrastructure. These technologies provide developers and researchers with an open, accelerated robotics platform that speeds iteration, standardizes testing, unifies training with on‑robot inference, and helps robots transfer skills safely and reliably from simulation to the real world.
According to Rev Lebaredian, vice president of Omniverse and simulation technology at NVIDIA, humanoids are the next frontier of physical AI, requiring the ability to reason, adapt, and act safely in an unpredictable world. He added that these updates equip developers with the tools to bring robots from research into everyday life, with Isaac GR00T serving as the robot’s brains, Newton simulating their body, and NVIDIA Omniverse as their training ground.
Newton, managed by the Linux Foundation, is a GPU-accelerated physics engine built on the NVIDIA Warp and OpenUSD frameworks, and codeveloped by Google DeepMind, Disney Research, and NVIDIA. The latest adopters include ETH Zurich Robotic Systems Lab, Technical University of Munich, Peking University, Lightwheel, and Style3D.
The Isaac GR00T N1.6 robot foundation model integrates NVIDIA Cosmos™ Reason, a customizable reasoning vision language model built for physical AI. Cosmos Reason, downloaded over 1 million times, can curate and annotate large sets of real and synthetic data for model training and is available as an NVIDIA NIM™ microservice for AI model deployment. Leading robot makers such as AeiROBOT, Franka Robotics, LG Electronics, Lightwheel, Mentee Robotics, Neura Robotics, Solomon, Techman Robot, and UCR are evaluating Isaac GR00T N models.
NVIDIA also announced updates to its open Cosmos WFMs, and a new dexterous grasping workflow in the developer preview of Isaac Lab 2.3 is available. NVIDIA and Lightwheel are codeveloping Isaac Lab – Arena, an open-source policy evaluation framework for experimentation and standardized testing.
NVIDIA announced AI infrastructure designed for demanding workloads, including NVIDIA GB200 NVL72, NVIDIA RTX PRO™ Servers, and NVIDIA Jetson Thor™.
NVIDIA technologies were referenced in nearly half of CoRL’s accepted papers. Also highlighted at CoRL is BEHAVIOR and Taccel.
Paris Fox, Corporate Communications, NVIDIA Corporation, 408-242-0035, pfox@nvidia.com
Source: NVIDIA
