ABB and Nvidia partner to transform factory robot training with physically accurate simulation

ABB and Nvidia Close the Sim-to-Real Gap in Industrial Robotics

ABB Robotics has announced a partnership with Nvidia that promises to transform how industrial robots are trained and deployed across manufacturing facilities worldwide. By integrating NVIDIA Omniverse libraries directly into its RobotStudio programming suite, ABB aims to bridge the long-standing sim-to-real gap that has plagued factory robot training for decades1

1

. The collaboration brings physically accurate simulation capabilities that achieve 99% correlation between virtual training environments and actual factory floor performance2

2

.

The new product, called RobotStudio HyperReality, will be available in the second half of 2026 and is already drawing significant interest from global manufacturers2

2

. Marc Segura, president of ABB Robotics, emphasized that robots often have limited information about the world around them, which can undermine robot accuracy, repeatability, and speed. He cited an example of a factory robot working near a stamping machine where massive vibrations reduced performance. With this technology, robots will be trained virtually to handle such lighting and vibrations scenarios and "know from day one," saving companies substantial time and money1

1

.

Dramatic Cost Reductions and Faster Time to Market

The partnership delivers measurable benefits for manufacturers struggling with the costs and complexities of automation. ABB projects that RobotStudio HyperReality will reduce deployment costs by up to 40% and accelerate time to market by as much as 50%2

2

. The system can cut setup and commissioning times by up to 80% by eliminating the need for physical prototypes of products and assembly lines2

2

.

The breakthrough lies in how Omniverse libraries enable synthetic data generation with photorealistic detail. RobotStudio HyperReality exports fully parameterized robot stations—including robots, sensors, lighting, kinematics, and parts—as USD files into NVIDIA Omniverse. ABB's virtual controller runs the same firmware as physical robots, enabling unprecedented precision2

2

. Combined with ABB's Absolute Accuracy technology, which reduces positioning errors from 8-15 mm to around 0.5 mm, the system delivers industrial-grade precision for demanding applications2

2

.

Foxconn Pilots Technology for Consumer Electronics Assembly

Foxconn, the world's largest electronics manufacturer, is already piloting RobotStudio HyperReality ahead of its launch in 20262

2

. The company is testing the technology for consumer electronics assembly tasks, specifically installing side buttons into devices—a process previously hindered by shadows that affected robot vision3

3

. Using HyperReality, Foxconn trains AI-driven robotics virtually with synthetic data, achieving precision when deployed on production lines while expecting to eliminate costly physical testing2

2

.

Workr, a California-based robotic workforce company, is also integrating its WorkrCore platform with ABB industrial robots trained using synthetic data generated through NVIDIA Omniverse. The company aims to bring advanced automation to small and medium-size manufacturers, with plans to demonstrate AI-powered systems at NVIDIA GTC 2026 that can onboard new parts in minutes without programming expertise2

2

.

What This Means for Manufacturing's Future

Deep Talla, vice president of robotics and edge AI at Nvidia, noted that the industrial sector needs physically accurate simulation to bridge the gap between virtual training and real-world deployment of AI-driven robotics at scale1

1

. The development reflects a growing trend where companies run more production planning and robot setup in digital simulations to identify problems before equipment starts operating3

3

.

The technology targets sectors including automotive and consumer electronics, where precision and speed determine competitive advantage1

1

. With RobotStudio already used by more than 60,000 robotics engineers worldwide, the integration of Omniverse libraries positions ABB to deliver physical AI capabilities at unprecedented scale2

2

. ABB is also exploring integration of the NVIDIA Jetson edge AI platform into its Omnicore controller to enable real-time inference across its robot portfolio2

2

. As manufacturers face pressure to reduce costs while increasing flexibility, this partnership offers a pathway to deploy sophisticated automation without the traditional barriers of extensive programming and testing.