Manufacturing
Transforming Production With Digital Twins and Physical AI
Objective
Schaeffler Group, a global leader in motion technology, is adopting the latest AI, simulation, and digital twin technologies to address labor shortages, increased production complexity, supply chain volatility, and more. Through collaboration with ecosystem partners such as NVIDIA and Wandelbots, the company has developed a comprehensive digital twin platform that enables it to accelerate the development of physical AI, enhance operational excellence, increase flexibility, and reduce time to market across its global manufacturing operations.
Customer
Schaeffler
Partners
Wandelbots
Use Case
Simulation / Modeling / Design
Robotics
Products
Key Takeaways
- Reduced commissioning times and accelerated facility layout planning through advanced simulation and virtual commissioning, leading to more efficient production concepts and faster ramp-up.
- Enhanced decision-making with AI-enabled dashboards and KPI tracking, improving operational transparency and responsiveness.
- Accelerated robotic task development, reducing time from hundreds of hours to half a day, through AI-driven simulation and training, enabling more agile operational workflows.
- Optimized robot fleet performance, including autonomous mobile robots (AMRs) and humanoid robots, via AI-driven training and simulation, driving high throughput and resource utilization.
- By 2030, Schaeffler plans to integrate digital twins into more than half of its global manufacturing sites, enabling real-time simulation and optimization of production processes.
- Streamlined planning processes resulting in stronger production concepts, greater planning accuracy, and reduced time-to-market, positioning facilities for long-term success.
Scaling Digitalization From Planning to Operations
Rising labor costs and workforce shortages are increasingly straining manufacturing operations. Product complexity, particularly in the automotive and industrial sector, demands more sophisticated assembly and quality control. Beyond the increased demand for accelerated simultaneous development cycles, pressures related to sustainability and regulatory compliance have also intensified.
For Schaeffler, these industry dynamics presented an opportunity to reimagine its processes with new approaches to production concept planning, physics-based process simulation, and advanced robot training to enable humanlike robots and humanoid robots in the future.
As part of a forward looking and transformative digitalization strategy, Schaeffler aims to leverage investments in AI, digital twins, and simulation to innovate, enhance operational efficiency, accelerate time to market, and deliver advanced automation at scale. These investments, alongside its collaborations with Wandelbots, are enabling Schaeffler to establish advanced tools, processes, and automation across its global manufacturing operations.
Schaeffler’s Digital Twin Platform for Manufacturing
To achieve its ambitious goals for manufacturing excellence and to effectively test and deploy advanced automation across its global network, Schaeffler built a virtual collaboration platform with NVIDIA Omniverse™ technologies and libraries. The platform leverages OpenUSD to integrate critical planning and production data from the company’s industrial expert software to enable Schaeffler teams to create physics-based digital twins for planning, simulating, and optimizing plants, machines, and workflows.
The Schaeffler platform has enabled their internal teams to drive significant speed and quality improvements in areas such as new production concepts and the training, testing, and validation of complex robotic tasks like the gripping and assembly of rare, high-value prototype parts.
Schaeffler’s engineers use these digital twin solutions to virtually design and optimize facility layouts for both new and existing sites. They allow teams to simulate and identify optimal factory and warehouse configurations, including the arrangement of production lines and kitting stations. By planning within a digital twin environment teams can test and optimize material flows, human-robot collaboration, and identify the optimal degree of automation for each facility. This innovative approach has dramatically increased planning efficiency and significantly reduced commissioning times for new production lines.
“Schaeffler is consistently and persistently driving the digitalization of its plants. To be able to shape the production of the future, you need strong partners like NVIDIA. Together, we will create a digital ecosystem for our more than 100 plants that will sustainably revolutionize production processes.” |
Andreas Schick
Chief Operating Officer, Schaeffler AG
From Pilot to Global Rollout
The development of Schaeffler’s platform was established through initial pilot phases, involving a core team of 15–20 specialists over a 12-month period. The AI computing infrastructure powering the development and deployment of the platform is currently based on a mixed architecture of local virtual machines and NVIDIA L40S GPUs.
Through integration and deployment support from its partners, including Wandelbots, the platform is being rolled out across multiple sites and use cases globally, with successful brownfield and greenfield projects already underway in China and Germany. As a result of its success to date, Schaeffler plans to integrate the platform into more than half of its global manufacturing sites by 2030.
The platform’s capabilities are demonstrated through three selected pilot projects: the assembly of electric motors, an inverter assembly line, and a Vehicle Lifetime Solutions (VLS) warehouse in Europe.
E-Motor Assembly
In its existing e-motor assembly plant in China, Schaeffler leveraged the platform for several key applications:
Physics-Optimized Simulation
Schaeffler conducts 3D-based simulations of automated guided vehicles (AGVs) within a factory digital twin. These 3D simulations replicate real-world physics, enabling teams to model AGV movements, test navigation, and assess sensor feedback under varying conditions—all before any hardware is deployed. This minimizes risk and streamlines the rollout of automation.
Live Process Data Integration
Real-time and historical operations and machine data, such as energy consumption of different machines and single stations, can be streamed to the Schaeffler platform, enabling teams to monitor equipment and quickly pinpoint areas for improvement.
Schaeffler
Schaeffler’s live-process data integration allows for real-time energy consumption tracking, visually represented by green, yellow, and red diamonds above single stations inside the digital twin.
Inverter Assembly Line
Virtual Robot Training
At its new small series inverter assembly line in Germany, Schaeffler is focusing on delivering advanced automation to optimize operations during the facility’s ramp-up:
- Simulation-First Robotics Development: The Schaeffler platform supports the simulation, training, and optimization of robot fleets, from manipulators, to autonomous mobile robots (AMRs), and humanoid robots —such as Agility Robotics’ Digit and Sanctuary AI’s Phoenix. Leveraging physics-based digital twins, engineers can generate synthetic data to train AI models, simulate and validate robot performance, and significantly reduce the simulation-to-real gap. This approach is enabling the company to optimize robotic gripping and assembly strategies for specialized parts. As a result of these new approaches, development time is being cut from hundreds of hours to just half a day, unlocking new levels of performance and optimization with minimal risk. This is establishing crucial groundwork for widespread adoption of general-purpose humanoid robots in industrial settings.
- Closing the Sim-to-Real Gap: Schaeffler leveraged simulation to develop a highly reliable robotics platform, achieving consistent performance after just 24 hours of training. To transition this capability to 24/7 real-world production, the company partnered with Wandelbots to deploy trained models onto its physical robots. Wandelbots utilized a virtual controller to ensure precise sim-to-real alignment, and reinforcement learning was used to refine robotic movements to within 5–6 centimeters for gearbox assembly tasks. These approaches are accelerating deployment, reducing trial and error, and delivering scalable, production-ready automation.
Vehicle Lifetime Solutions Warehouses
Within its Vehicle Lifetime Solutions (VLS) warehouses, where parts are repackaged and labeled for aftermarket distribution, Schaeffler is developing and scaling new solutions:
- Warehouse Configurator: To industrialize new warehouses, Schaeffler is developing a warehouse configurator, utilizing existing planning data to quickly develop and optimize warehouse use cases.
- Automation and Humanoid Robot Development: Physically accurate models of production stations enable teams to determine how viable processes are for automation. Once automation decisions are made, teams use the models for training and optimizing the systems. These new workflows are helping teams quickly test system requirements and enabling external customers—such as robot OEMs, industrial automation companies, and technology integration partners—to develop and optimize their own automation solutions.
- Robot Fleet Testing: Schaeffler’s adoption of the NVIDIA Mega Blueprint is enabling teams to test entire robot fleets—including autonomous mobile robots (AMRs), manipulators, and general-purpose humanoid robots.
Redefining the Factory of the Future
Schaeffler is pioneering the future of industrial automation through its investments in digital twins and physical AI. Its innovative strategy and close collaboration with its ecosystem partners is driving significant optimization across operations and serves as a blueprint for the next generation of intelligent factories.
To learn more about Schaeffler’s journey with digital twins and physical AI, check out its GTC session.
Contact our team to learn more about Omniverse digital twins for industrial settings.