NVIDIA Unveils Omniverse NuRec, Cosmos Models for Robotics Solutions Acceleration

NVIDIA has announced new Omniverse libraries and Cosmos models that accelerate robotics solution development. The libraries and models enable large-scale world reconstruction, world generation, and spatial reasoning. They can be run on RTX PRO Servers and DGX Cloud, allowing developers to create physically accurate digital twins, capture and reconstruct the real world, generate synthetic data, and build AI agents that understand the physical world. Amazon, Boston Dynamics, Figure AI, and Hexagon are embracing simulation and synthetic data generation.

NVIDIA has made significant strides in the realm of robotics with the introduction of new Omniverse libraries and Cosmos models. These advancements are set to revolutionize the development and deployment of robotics solutions by enabling large-scale world reconstruction, world generation, and spatial reasoning.

The new NVIDIA Omniverse™ libraries and NVIDIA Cosmos™ world foundation models (WFMs) are designed to accelerate the development of physically accurate digital twins. These tools allow developers to capture and reconstruct the real world in simulation, generate synthetic data for training physical AI models, and build AI agents that understand the physical world. The libraries and models are powered by NVIDIA RTX PRO™ Servers and NVIDIA DGX™ Cloud, providing a robust infrastructure for running the most demanding simulations anywhere [1].

NVIDIA's new Omniverse SDKs and libraries introduce data interoperability between MuJoCo (MJCF) and Universal Scene Description (OpenUSD), enabling over 250,000 MJCF robot learning developers to seamlessly simulate robots across platforms. The Omniverse NuRec libraries and AI models introduce Omniverse RTX ray-traced 3D Gaussian splatting, a rendering technique that allows developers to capture, reconstruct, and simulate the real world in 3D using sensor data [1].

NVIDIA Isaac Sim™ 5.0 and NVIDIA Isaac Lab 2.2 open-source robot simulation and learning frameworks are now available on GitHub, featuring NuRec neural rendering and new OpenUSD-based robot and sensor schemas. These tools help robot developers close the simulation-to-reality gap. The integration of Omniverse NuRec rendering in CARLA, a leading open-source simulator used by over 150,000 developers, further underscores the practical applications of these advancements [1].

Cosmos WFMs, downloaded over 2 million times, enable developers to generate diverse data for training robots at scale using text, image, and video prompts. New Cosmos models announced at SIGGRAPH deliver major advances in synthetic data generation speed, accuracy, language support, and control. Cosmos Transfer-2, coming soon, simplifies prompting and accelerates photorealistic synthetic data generation from ground-truth 3D simulation scenes or spatial control inputs like depth, segmentation, edges, and high-definition maps [1].

NVIDIA Cosmos Reason, a new open, customizable, 7-billion-parameter reasoning VLM for physical AI and robotics, lets robots and vision AI agents reason like humans. It uses prior knowledge, physics understanding, and common sense to understand and act in the real world. Cosmos Reason can be used for data curation and annotation, robot planning and reasoning, and video analytics AI agents that extract valuable insights and perform root-cause analysis on massive volumes of video data [1].

To support these advanced technologies and software libraries, NVIDIA announced AI infrastructure designed for the most demanding workloads. NVIDIA RTX PRO Blackwell Servers and NVIDIA DGX Cloud offer a single architecture for every robot development workload across training, synthetic data generation, robot learning, and simulation. NVIDIA DGX Cloud, available on Microsoft Azure Marketplace, provides a fully managed platform to simplify streaming OpenUSD- and NVIDIA RTX™-based applications at scale from the cloud, minimizing infrastructure orchestration and management [1].

Major players in the industry, including Amazon Devices & Services, Boston Dynamics, Figure AI, and Hexagon, are embracing these advancements to power new manufacturing solutions, accelerate AI robotics development, and enhance their AI capabilities. The adoption of these tools is expected to transform industries worth trillions of dollars, as NVIDIA continues to lead the convergence of computer graphics and AI in robotics [1].

References:

[1] https://www.globenewswire.com/news-release/2025/08/11/3131074/0/en/NVIDIA-Opens-Portals-to-World-of-Robotics-With-New-Omniverse-Libraries-Cosmos-Physical-AI-Models-and-AI-Computing-Infrastructure.html