NVIDIA announced today at COMPUTEX that major Taiwanese electronics manufacturers are adopting its technology to enhance the autonomy of their factories. The new reference workflow integrates NVIDIA Metropolis vision AI, NVIDIA Omniverse™ for rendering and simulation, and NVIDIA Isaac™ for AI robot development and deployment.

This workflow allows manufacturers to create digital twins for real-time simulation of various factory layouts, optimizing space, processes, and efficiency without the need for physical modifications.

“AI for manufacturing is here. Every factory is becoming more and more autonomous due to the transformational impact of generative AI and digital twin technologies,” said Deepu Talla, vice president of robotics and edge computing at NVIDIA. “With NVIDIA Omniverse, Metropolis, and Isaac, the industrial ecosystem can accelerate its adoption of autonomous technologies, helping advance operational efficiencies and lower costs.”

Several prominent electronics manufacturers—Delta Electronics, Foxconn, Pegatron, and Wistron—are utilizing this reference workflow to develop robotic facilities.

During a keynote demonstration at COMPUTEX, NVIDIA founder and CEO Jensen Huang showcased how Foxconn uses NVIDIA Omniverse to create digital twins of its factories. This platform virtually integrates 3D data from industry tools such as Teamcenter from Siemens Xcelerator. Foxconn leverages these digital twins to optimize equipment layout for operational flow and monitor worker safety using AI cameras powered by NVIDIA Metropolis. Additionally, these virtual environments serve as training grounds for testing autonomous mobile robots (AMRs) built on NVIDIA Isaac Perceptor acceleration libraries.

“AI and robotics are poised to revolutionize manufacturing, enhancing safety on factory floors and driving significant operational efficiencies,” said Young Liu, CEO and chairman of Foxconn. “By integrating NVIDIA Omniverse, Metropolis, and Isaac into our operations, we can create sophisticated digital twins of our factories to train robots, optimizing workflows with unprecedented precision and reducing costs.”

Delta Electronics employs NVIDIA Isaac Sim™, an extensible robotics simulation platform developed on Omniverse and OpenUSD. This platform helps integrate demo production lines virtually while generating photorealistic synthetic data for training computer vision models used in automatic optical inspection solutions powered by NVIDIA Metropolis.

Pegatron has implemented an NVIDIA Metropolis multi-camera workflow along with a suite of services connecting its factory digital twin workflow in Omniverse with NVIDIA NeMo™ and NIM™. These advancements aim to improve worker safety and productivity across Pegatron’s extensive factory network.

Wistron has utilized digital twins created with Omniverse to expedite the production process of servers like the NVIDIA DGX™and HGX™ systems. By simulating facility layouts first through Omniverse before going live in actual production environments, Wistron was able to bring a new factory online in half the usual time while increasing worker efficiency significantly.

“The combination of NVIDIA Omniverse and Metropolis allows us to test new layouts virtually to identify new processes," said Alec Lai, president of global manufacturing at Wistron. "Digitalizing our factory planning process has reduced end-to-end cycle times by 50%.”

Kenmec is another early adopter using both Omniverse-optimized workflows for major clients such as Giant Group.

These digital twin workflows are now available as part of a reference architecture series aimed at aiding developers across various industries.