ABB Robotics and Nvidia on Monday unveiled a new partnership that they say will help bridge the sim-to-real gap in industrial robotics.
under dealThe companies will combine Nvidia’s Omniverse simulation capabilities with ABB’s software design and simulation suite, RobotStudio, to help manufacturers deploy physical AI in real-world robotics applications.
The resulting product, called RobotStudio Hyperreality, will be available in the second half of this year under a subscription model. Vendors claim it can halve engineering time, reduce deployment costs by up to 40%, and accelerate time-to-market by up to 50%. An initial pilot of the platform is currently underway by Foxconn as well as WorkR, a California-based robotic workforce company for consumer electronics assembly.
Closing the Sim-to-Real Gap
The main promise of the platform is a hyper-realistic virtual environment where developers can accurately design and test entire automation processes before deploying them in the real world.
In particular, vendors are touting this tool as offering training data in previously complex situations such as different lighting conditions, textures, and material properties. In this way, it claims to provide an effective means of reducing the gap between simulation accuracy and real-world conditions, also known as Sim-to-Real Gap.
According to the partners, the new platform has achieved 99% correlation between simulations and real-world behavior.
The simulations are continuously refined with real-world data feedback, meaning the underlying AI models improve over time without the need for thousands of physical test runs or expensive physical prototypes.
Speaking at a media briefing, Mark Segura, president of abb Robotics division poised to advance new platform as a key inflection point physical aI.
“For decades, one final barrier has limited the deployment of physical AI at speed and scale,” he said. “Manufacturers have struggled to simulate real-world conditions; lighting, shadows, textures and materials that behave exactly the same as they do on the factory floor. This is known as the sim-to-real gap, and it has limited how quickly businesses can design, test and deploy new automation. Today, we’ve broken that barrier.”
Segura described the benefits of the platform as twofold.
In addition to enhancing simulation capabilities, the platform also enables the training of higher quality AI models which directly translates into better robot autonomy And versatility. “You’ve got the simulation benefit, and you’ve got the benefit of greater autonomy for the robot on a single platform,” he said.
Speaking at the briefing, Dipu Talla, Nvidia’s vice president of robotics and edge AI, said the partnership reflects a broader shift in robotics.
“Physical AI represents the next frontier of intelligence, moving from digital models that process text or images to tangible models that can understand, reason and act within the physical world,” he said, adding that this development is transforming robots from fixed, pre-programmed machines to adaptable, autonomous agents that are able to operate in complex and dynamic environments.
Partners also highlighted uptake among small and medium-sized businesses as a key objective, as these businesses are typically excluded and under-represented in robotics rollouts due to financial and technical barriers.
With RobotStudio Hyperreality, the partners say these companies will now have access to a user-friendly, affordable means of testing and using industrial robots.
“This new product aims to take a big step forward in making robots available to SMBs,” Segura said.
