ABB-Nvidia robotic simulation tie-up will cut costs by up to 40%
9 March 2026 
ABB Robotics has announced that it is integrating Nvidia’s Omniverse libraries into its RobotStudio programming and simulation software, helping manufacturers to deploy physical AI in real-world robotics applications. It says the development will deliver physical AI for industry, closing the gap between virtual training and real-world deployment, with accuracies of up to 99%. ABB predicts that the development will change fundamentally how quickly and reliably manufacturers can scale production, slashing costs by up to 40% and halving time-to-market.
“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,” says ABB Robotics’ president, Marc Segura. “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.”
The collaboration combines RobotStudio with the physically accurate simulation capabilities of Nvidia’s Omniverse libraries, helping to close the long-standing “sim-to-real” gap – the difference between simulation accuracy, and real-world materials and environments. For decades, ABB says, this gap has limited the ability of manufacturers to design and develop advanced manufacturing processes in the virtual world.
With the new software, called RobotStudio HyperReality, developers will be able to simulate robots in digital twins and generate synthetic data to train their physical AI models, thus allowing businesses to deploy AI-driven robotics for various industrial workflows.
The software optimises physically accurate simulations and foundation models, using real-world data feedback to improve systems continuously. The models can be used to train any number of ABB robots, anywhere in the world, reliably and accurately.
“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,” says Nvidia’s vice-president of robotics and edge AI, Deepu Talla. “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.”
By integrating Nvidia’s libraries into RobotStudio, ABB Robotics says it will be able to deliver “unprecedented” robotics simulation and synthetic data generation capabilities that will allow intelligent robots to bridge the sim-to-real gap with an accuracy of up to 99%. The company claims that it is the only robot manufacturer with a virtual controller running the same firmware as the hardware, ensuring near-perfect correlation between simulation and real-world performance.
Combined with ABB Robotics’ Absolute Accuracy technology – which reduces positioning errors from 8–15mm to around 0.5mm – ABB says it can deliver high precision in both virtual and physical environments.
It states that the innovation will enable manufacturers to design, test and optimise production lines virtually, cutting set-up and commissioning times by up to 80%, and reducing costs by up to 40% by eliminating the need for physical prototypes. Time-to-market for complex products such as consumer electronics could be halved.
The world’s largest electronics contract manufacturer, Foxconn, is piloting the first use of RobotStudio HyperReality in electronics assembly. Automating the assembly of a tiny consumer electronics items is challenging because multiple device variants need different production methods and the delicate metal structures require precise pick-and-place and assembly control, as well as fine-tuned set-up, often demanding additional debugging time and engineering resources.
Using the new software, Foxconn, is training assembly robots virtually, using synthetic data to perfect multiple real-world production processes in various scenarios, before moving them to the production line with a claimed accuracy of 99%. By optimising production lines virtually, Foxconn says it will cut set-up times and costs by eliminating physical training and tests, and cut time-to-market for consumer electronics.
“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,” says Foxconn’s chief digital officer, Dr Zhe Shi. “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.”
After a period of testing with select customers, ABB is planning to full release the software in the second half of 2026. It is also assessing the potential to integrate Nvidia’s Jetson edge computing platform into its Omnicore controller to achieve real-time AI inference at the edge.
ABB is in the process of selling ABB Robotics to the Japanese investor SoftBank Group (SBG) for $5.375bn. The transaction is expected to close in mid-to-late 2026.
