ABB Robotics is expanding its simulation environment for industrial robotics and will integrate Nvidia's Omniverse libraries in the future. The goal is to make physical AI easier to use in real production environments. By combining robot simulation with physically accurate digital models, manufacturers will be able to develop robotics applications entirely virtually and then reliably transfer them into practice.
According to ABB Robotics, the technology achieves up to 99 percent consistency between simulation and real-world behavior. The collaboration thus addresses a key challenge in industrial automation: the so-called “sim-to-real” gap between virtual planning and real-world deployment.
ABB Robotics expands simulation environment with AI-based models
The development focuses on integrating Nvidia Omniverse libraries into the RobotStudio programming and simulation platform. Developers can use it to model robots as digital twins and generate synthetic data. This data serves as the basis for training physical AI models that will later be used in real production processes.
“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 Marc Segura, President of ABB Robotics.
The company has been developing automation technologies for industrial applications for more than fifty years. These include fully electric industrial robots, digital twins in simulation, and autonomous mobile robot systems. Through its collaboration with Nvidia, ABB Robotics is now expanding these technologies to include AI-based training methods.
New simulation platform to accelerate industrial development
A central component of the collaboration is the new “RobotStudio HyperReality” platform, which is scheduled to be launched in the second half of 2026. The technology combines simulation, synthetic data, and AI models in a virtual development environment for industrial production processes.
According to ABB Robotics, setup and commissioning times can be reduced by up to 80 percent. At the same time, eliminating the need for physical prototypes can reduce costs by up to forty percent. The time to market for new products is also expected to be significantly reduced.
“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. “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.”
Digital twins improve production planning
An essential component of the technology is ABB Robotics' Virtual Controller. This is an exact copy of the real robot controller within the simulation. This allows virtual processes to be transferred almost identically to real applications.
This approach is complemented by ABB Robotics' Absolute Accuracy technology. It reduces positional deviations from the original eight to fifteen millimeters to around zero point five millimeters. Together with Nvidia's physically accurate simulations, this creates a virtual development environment that is highly realistic. Manufacturers can use it to plan, test, and optimize production lines completely digitally before implementing them in real manufacturing.
First applications of ABB Robotics in electronics manufacturing
The first industrial applications are already being tested. Electronics manufacturer Foxconn is using the technology in a pilot project for the assembly of consumer electronics. Assembly robots are first trained in a virtual environment and then transferred to real production.
“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,” explains Dr. Zhe Shi, Chief Digital Officer at Foxconn. “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.”
AI-based robot systems for small and medium-sized manufacturing companies
The robotics company Workr is also relying on this technology. It develops AI-based robot systems for small and medium-sized manufacturing companies. The systems are trained exclusively with synthetic data and can be operated without programming knowledge. “This collaboration is about making industrial AI deployable today,” explains Ken Macken, CEO and founder of Workr. “Together with ABB and Nvidia, we're proving that advanced automation can work for manufacturers of any size.”
