Teradyne Robotics partners with Sereact to scale physical AI in retail and logistics

At Zalando's fulfillment centers in Germany and Poland, Sereact and Universal Robots now autonomously process returned fashion items, in this case the robot is picking a black women's shoe.

At Zalando’s fulfillment centers in Germany and Poland, Sereact and Universal Robots now autonomously processes returned fashion items. | Source: Teradyne Robotics

Teradyne Robotics, the company behind Universal Robots and Mobile Industrial Robots, last week partnered with Sereact. The companies aim to accelerate industrial AI solutions in retail, logistics and manufacturing.

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

“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, the chief commercial officer of Teradyne Robotics. “Our robots are built for the AI era: open, connected, and proven through more than 100,000 industrial deployments. That is why Sereact has chosen our platform.”

“When combined with Sereact’s Cortex, the joint solution handles mixed goods, unknown items, and varied packaging,” he added. “This has moved well beyond the demo or pilot stage with the technology now usefully deployed at real customer sites. Our technologies are a natural fit and through our partnership we will scale these AI-powered solutions fast across applications, industries and markets.”

To serve the rapidly growing demand and bring the joint solution to North America, Sereact this summer opened U.S. headquarters in Charlestown, Mass. The company develops physical AI software that enables robots to grasp, identify, and handle objects they have never seen before. The companies made the announcement at NVIDIA GTC Berlin 2026.

Teradyne and Sereact already have deployments running

Teradyne Robotics and Sereact said their joint offering can help a variety of critical logistics and manufacturing use cases. These include 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. And what one robot learns, every robot benefits from,” said Dr. Ralf Gulde, co-founder and CEO of Sereact. “Partnering with Teradyne Robotics and its global distribution and integrator network helps us bring that one brain to their customers around the world, accelerating the abilities of retailers and logistics providers to adopt AI-powered automation across their operations.”

The company is already deploying the system with CEVA Logistics for Zalando, a European technology platform for fashion and lifestyle. At Zalando’s fulfillment centers in Greven, Germany, and Świebodzin, Poland, the robots now autonomously process returned fashion items. This is the first phase of a broader initiative to scale returns automation across Europe.

“Returns are one of the hardest jobs in logistics,” said Gulde. “Returned products almost never arrive in a robot-friendly sequence. Items differ in shape, orientation and packaging, and the mix changes continuously.”

“That is exactly what Cortex is built to handle on the Universal Robots platform,” he said. ”By rapidly reconditioning returned goods for resale, the solution also helps retailers comply with European Union regulations prohibiting the destruction or landfill disposal of returned merchandise.”

NVIDIA plays a role in the collaboration

NVIDIA’s technologies are a key part of 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.

It is post-trained with reinforcement learning using 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 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 in its Universal Robots cobots and Mobile Industrial Robot platforms. The company said it is contributing SimReady OpenUSD robot assets to SimReady Central Library on Hugging Face for both UR and MiR products, helping developers discover and reuse robot models in simulation with less asset preparation.