ABB teams up with Nvidia to improve factory robot training

ABB's robotics business has partnered with Nvidia to narrow the gap between how industrial robots perform in virtual simulations and how they behave on factory floors, the ‌companies said ⁠on Monday.

Swiss-based ⁠ABB will use Nvidia's Omniverse libraries of simulated data to make its training environments more realistic by incorporating details such as lighting, shadows, and textures.

ABB Robotics President Marc Segura said robots often have limited information about the world around them, which can undermine accuracy, repeatability and speed.


Segura cited the example of a factory ​robot working close to a stamping machine, which ⁠created massive ‌vibrations which reduced the robot's performance.

Over time the robot could ​learn or ​be programmed how to deal with the vibration, but ⁠the technology meant it will already be trained virtually and "know ​from day one," Segura told Reuters. "This will save ​companies a lot of time and money."

The development is part of a growing trend where companies run more of their production planning and robot setup in digital simulations to spot problems before equipment starts operating.

ABB said the system, delivered via its robot control software, could cut ‌costs and speed time to market by reducing the need for physical prototypes of products and assembly lines.

The technology, due ​for launch ​in the second ⁠half of 2026, is expected to serve customers in sectors including automotive and consumer electronics.

Electronics contract manufacturer Foxconn is already piloting the technology to install side buttons ​into consumer electronics, a task ABB said was previously difficult because shadows hindered robot vision.

"The industrial sector needs physically accurate simulation to bridge the gap between virtual training and the real-world deployment of AI-driven robotics at scale," said Deepu Talla, vice president of robotics and edge AI at Nvidia.