Teradyne Robotics, Sereact Join Forces on Industrial Physical AI

Teradyne Robotics, the company behind Universal Robots and Mobile Industrial Robots, and physical AI company Sereact announced an official partnership on October 21, 2026, aimed at accelerating industrial AI deployments across retail, logistics and manufacturing.

Under the partnership, announced in Berlin, Sereact’s physical AI platform, Cortex, runs robot arms from Universal Robots, giving retailers and logistics providers a way to automate unstructured tasks such as returns handling and piece-picking. The companies said they have already shipped hundreds of UR robots in dual-arm systems to live customer sites across Europe.

Commercial Scope and Application Range

“Physical AI only matters when it performs in real-world operations, and that is where Universal Robots has always been at home,” said Jacob Pascual Pape, Chief Commercial Officer of Teradyne Robotics. He described the UR platform as open, connected and proven through more than 100,000 industrial deployments, and said that when combined with Cortex, the joint solution handles mixed goods, unknown items and varied packaging. Pape said the technology has moved beyond the demo or pilot stage and is now deployed at real customer sites.

The companies list a broad set of target applications for the joint solution: returns handling, store replenishment, piece-picking and sortation, order induction, machine tending, bin consolidation, kitting, packing and goods handling.

“Returns, replenishment, kitting: with Cortex, every one of these applications runs on the same production model. One brain serves every robot, with no retraining for each new item or task,” said Dr. Ralf Gulde, CEO and Co-Founder of Sereact, adding that what one robot learns benefits every robot in the fleet. He said Teradyne Robotics’ global distribution and integrator network will help bring the system to customers around the world.

To serve growing demand, Sereact opened a US headquarters in Boston, Massachusetts, this summer to bring the joint solution to North America.

Joint Demonstration at NVIDIA GTC Berlin

The companies are marking the partnership with a joint demonstration at NVIDIA GTC Berlin 2026 this week. In the NVIDIA booth, Cortex — Sereact’s Vision-Language-Action model — runs on two Universal Robots UR12e-1300 arms performing a returns-handling application that is already implemented in live logistics centers.

Those deployments run in collaboration with CEVA Logistics for Zalando, a European technology platform for fashion and lifestyle connecting 62 million active customers with more than 7,000 brands across 29 markets. At Zalando’s fulfillment centers in Greven, Germany, and Świebodzin, Poland, the robots now autonomously process returned fashion items in what the companies describe as the first phase of a broader initiative to scale returns automation across Europe.

Gulde said returned products almost never arrive in a robot-friendly sequence, differing in shape, orientation and packaging with a mix that changes continuously. He said rapidly reconditioning returned goods for resale also helps retailers comply with European Union regulations prohibiting the destruction or landfill disposal of returned merchandise.

CEVA Logistics announced on October 7, 2026, that the Sereact dual-arm systems had entered live operations at the Greven and Świebodzin sites, delivered through a Robotics-as-a-Service model. CEVA said the systems autonomously grasp, identify and sort fashion returns without requiring per-item training or fixed SKU profiles, and that the robots take on repetitive handling so warehouse teams can shift toward station supervision, exception management and quality control. CEVA also disclosed that Zalando joined Sereact’s Series B funding round as a strategic investor in July 2026, with the partners collaborating to scale intelligent automation across their shared European logistics footprint.

NVIDIA Technology Foundation

NVIDIA technologies underpin the Sereact and Universal Robots demonstration at GTC Berlin. Cortex is trained in NVIDIA Isaac Sim, an open simulation framework, using NVIDIA Cosmos open world models. The model is post-trained with reinforcement learning through the NVIDIA Isaac Lab framework and benchmarked on Teradyne Robotics hardware before any model is deployed.

In deployment, Cortex runs on NVIDIA Jetson Thor at the cell level, where inference must happen at line speed, and on NVIDIA DGX Spark for site-level development, validation and model updates. Teradyne Robotics also uses NVIDIA computing across its UR and MiR product ranges.

Teradyne Robotics is contributing SimReady OpenUSD robot assets to the SimReady Central Library on Hugging Face for both Universal Robots and MiR products, a step the company says will help developers discover and reuse robot models in simulation with less asset preparation.