How NVIDIA Is Advancing AI-Powered Factories, Engineering and Robotics in Europe

European industry leaders are using NVIDIA CUDA-X, the NVIDIA Omniverse libraries, NVIDIA Cosmos and NVIDIA Nemotron to improve productivity, accelerate innovation and create new opportunities for economic growth.

At the center of these efforts is the NVIDIA Factory Operations Blueprint (FOX), now available through early access on GitHub. FOX gives developers a path to build and deploy always-on factory management agents that coordinate work across machines.

The blueprint also supports specialized agents for visual inspection, root-cause analysis, report generation and fleet management. These industrial AI agents can connect frontier models such as NVIDIA Cosmos and Nemotron with engineering and operational data, including computer-aided design, product lifecycle management, simulation software and IT and operational technology systems.

Using FOX, industrial agents can monitor factory operations in real time, correlate visual observations with machine logs, investigate issues and coordinate responses. NVIDIA Cosmos in-context learning allows agents to adapt from examples and documentation without additional fine-tuning.

Siemens integrates agents built with FOX into its Intelligence Center X enterprise agent system. The system helps identify root causes and adjust factory operations, delivering an estimated 20% cost savings.

Siemens also uses NVIDIA Cosmos Data Factory tools and skills in its Process Preparation X agent to generate defect images for circuit board inspection. At Siemens’ electronics factory in Erlangen, this approach reduced inspection-process calibration time by 40%, according to the company.

Accelerating engineering from the first design

NVIDIA CUDA-X libraries help speed up simulations, giving engineers faster feedback as they evaluate design alternatives before committing to physical prototypes. At GTC Berlin, NVIDIA announced the general availability of cuDSS, which accelerates demanding calculations for simulations involving structural stresses, fluid flow, electromagnetic fields and semiconductor device behavior.

Siemens uses Simcenter STAR-CCM+ on NVIDIA GPUs to compare vehicle designs through faster aerodynamic simulations. In its factories, the company applies NVIDIA Cosmos 3 and the Metropolis VSS Blueprint to build agents for vehicle inspection and windshield assembly verification.

Cadence benchmarks automotive fluid-dynamics workloads on NVIDIA GPUs to evaluate opportunities for faster design iterations. Autodesk is also bringing NVIDIA Physics NeMo and NVIDIA Warp into NavPack and Autodesk Alias to help designers use simulation-trained AI to predict vehicle performance and accelerate iterations.

Imec and Infineon are using NVIDIA accelerated computing to advance semiconductor simulation. Benchmarking of Imec’s S-Litho model shows up to a 40x speedup, while Infineon uses Sentaurus Device and the NVIDIA CUDA library to achieve 12x acceleration in 3D breakdown simulations for next-generation power devices.

Leonardo is working with Neural Concept on AI-driven aircraft design. The companies use the NVIDIA Omniverse libraries to integrate aircraft geometry with aerodynamic simulation results.

Dassault Systèmes uses LEO and AURA Virtual Companions, powered by NVIDIA Nemotron, together with SIMULIA solvers accelerated by NVIDIA CUDA-X libraries. These tools help tune CATIA AI agents and SIMULIA AI agents to design and virtually test vehicle doors before physical prototypes are built.

Universal AGI is working with Saab to assess thousands of wave conditions and headings in real time. Its latent interaction field transformer physical AI foundation model uses high-speed processing with NVIDIA Warp to help ships predict dangerous movements and autonomously select safer routes. The NVIDIA Omniverse libraries help visualize ship behavior at sea.

PhysicsX, working with GB1, Britain’s America’s Cup team, uses the NVIDIA Omniverse libraries to visualize yacht hull shapes and pressure fields. FermionIQ’s Sophia agent can translate natural-language requests into simulation solvers. Deltares and Dutch ministries use a similar approach to model river flow with a solver built on NVIDIA Warp.

Mistral plans to use CUDA-X, Warp and Omniverse libraries to accelerate physics simulations and generate training data for engineering AI models.

Testing factories and robots virtually

Powered by NVIDIA Omniverse and Isaac libraries, digital twins and robot simulation help manufacturers evaluate production systems and robot behavior before making changes on the factory floor.

Audi uses a battery-production digital twin built with NVIDIA Omniverse libraries to test production concepts before physical equipment is available. Audi is also working with Dassault Systèmes and Agile Robots to simulate and validate mobile humanoid robots and logistics processes using a DELMIA virtual twin built with the Omniverse libraries.

Schaeffler integrates digital twins of humanoid actuators—components that move robot joints—with the NVIDIA Isaac simulation framework. This enables robotics partners to evaluate component behavior in simulation and reduce physical testing.

Wandelbots uses NOVA with Isaac Sim, built on Omniverse and OpenUSD, to digitally validate assembly workflows and prepare applications for physical robots.

Falkor, a KONGSBERG company, integrates agents and the NVIDIA Omniverse libraries into its platform. Using an Microsoft Azure NCv6 virtual machine with an NVIDIA RTX PRO 6000 Blackwell Server Edition GPU, its agents combine engineering data, behavioral information and 3D equipment geometry to see, simulate and reason about industrial facilities. The technology supports inspection and maintenance use cases across the process and energy industries.

The same simulation approach extends to AI infrastructure. Schneider Electric and AVEVA are developing an AI factory digital twin for N-scale environments. The NVIDIA Omniverse libraries allow engineers to compare power, cooling and equipment configurations before making physical changes.

Explore NVIDIA technology for industrial AI.