ABB Robotics announced a partnership with NVIDIA to bring industrial-grade physical AI to manufacturing by integrating NVIDIA Omniverse libraries into ABB’s RobotStudio platform. The collaboration aims to close the long-standing gap between simulation and real-world robotics deployment, enabling manufacturers to design, test and optimize production lines virtually before deploying robots on factory floors.
The companies are combining ABB Robotics’ programming, design and simulation software with NVIDIA’s physically accurate simulation and accelerated computing capabilities. By integrating Omniverse libraries into RobotStudio, developers can simulate robotic systems in digital twin environments and generate synthetic data to train AI models for real-world robotics applications.
The new system, called RobotStudio HyperReality, is expected to launch in the second half of 2026. ABB said the technology will allow robots to be trained in virtual environments with up to 99 percent correlation between simulated and real-world performance. The system continuously improves by using real-world data feedback to refine foundation models that can then be deployed across ABB’s global fleet of industrial robots.
The innovation addresses what the robotics industry calls the “sim-to-real” gap, a longstanding challenge caused by differences between simulated environments and real-world conditions such as lighting, materials and surface textures. By improving simulation accuracy and generating synthetic training data, the technology enables robots to learn complex tasks before deployment, reducing the need for extensive physical testing.
ABB said the technology could significantly accelerate manufacturing operations. Companies will be able to design and test production lines virtually, cutting setup and commissioning times by up to 80 percent while reducing costs by up to 40 percent by eliminating physical prototypes. The approach could also shorten time-to-market for complex products, including consumer electronics, by as much as 50 percent.
The collaboration also includes potential integration of NVIDIA’s Jetson edge computing platform into ABB’s Omnicore controller, enabling real-time AI inference at the edge across ABB’s robot portfolio. The companies previously collaborated on integrating NVIDIA Jetson technology into ABB’s autonomous mobile robots using visual simultaneous localization and mapping technology.
Early industrial applications are already underway. Foxconn, the world’s largest electronics contract manufacturer, is piloting the technology to automate delicate consumer electronics assembly tasks. By training robots virtually using synthetic data, Foxconn aims to optimize production processes across multiple product variants before deploying robots on the production line.
California-based robotic workforce company WORKR is also using the technology to expand automation capabilities for small and medium manufacturers across the United States. The company’s WorkrCore AI platform combines with ABB robotics systems trained through Omniverse-powered simulations to deploy robots capable of learning new manufacturing tasks quickly.
ABB Robotics said the technology will ultimately be made available to its more than 60,000 RobotStudio customers worldwide, helping manufacturers of all sizes scale AI-driven automation across industrial workflows.
KEY QUOTES
“Today, using NVIDIA accelerated computing and simulation technologies, we have removed the last barriers to making industrial and physical AI a reality at a global scale by closing the sim-to-real gap. For more than 50 years, ABB Robotics has led the evolution of intelligent industrial automation, from pioneering the first generation of fully electric industrial robots to advancing digital twin simulation through RobotStudio® and shaping a new area of autonomous and versatile mobile robots. Today’s announcement with NVIDIA brings physical AI to industry at scale.”
Marc Segura, President Of ABB Robotics
“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. Integrating NVIDIA Omniverse libraries into RobotStudio brings advanced simulation and accelerated computing to ABB Robotics’ unique virtual controller technology, accelerating how manufacturers of all sizes bring complex products to market.”
Deepu Talla, Vice President Of Robotics And Edge AI At NVIDIA
“Precision is everything in consumer electronics manufacturing and until now, this level of accuracy and fidelity just wasn’t possible in simulation and digital twins. We’re incredibly excited by the potential of ABB Robotics and NVIDIA’s collaboration, which enables parallel engineering for better designs, faster production ramp-up and greater product evolution through advanced AI inference and understanding.”
Dr. Zhe Shi, Chief Digital Officer Of Foxconn
“This collaboration is about making industrial AI deployable today. Together with ABB and NVIDIA, we’re proving that advanced automation can work for manufacturers of any size.”
Ken Macken, CEO And Founder Of WORKR
