Teradyne Robotics partners with Sereact to scale physical AI in retail and logistics
In Zalando’s logistics centers in Germany and Poland, Sereact and Universal Robots now process returned fashion items independently. | Source: Teradyne Robotics
Teradyne Robotics, the company behind Universal Robots and Mobile Industrial Robots, partnered with Sereact last week. Companies aim to accelerate industrial AI solutions in the retail, logistics and manufacturing sectors.
Through this partnership, Sereact’s Cortex AI physics platform powers Universal Robots’ robotic arms to offer retailers and logistics providers a proven way to automate unstructured tasks such as returns management and parts picking. Together, the companies have already shipped hundreds of UR robots in dual-arm systems to customer sites across Europe.
“Physical AI only matters when executed in real-world operations, and that’s where Universal Robots has always been at home,” said Jacob Pascual Pape, chief commercial officer of Teradyne Robotics. “Our robots are built for the age of artificial intelligence: open, connected and proven in over 100,000 industrial deployments. That’s why Sereact chose our platform.”
“When combined with Sereact’s Cortex, the joint solution handles mixed goods, unknown items and miscellaneous packaging,” he added. “This has moved well beyond the demonstration or pilot phase with the technology now usefully deployed at real customer sites. Our technologies are a natural fit and through our partnership we will rapidly scale these AI-based solutions across all applications, industries and markets.”
To meet rapidly growing demand and bring the joint solution to North America, Sereact opened U.S. headquarters in Charlestown, Massachusetts this summer. The company develops physical AI software that allows 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 implementations running
Teradyne Robotics and Sereact said their joint offering can help a variety of critical use cases in logistics and manufacturing. These include picking and sorting parts, placing orders, tending machinery, consolidating containers, kitting, packing and moving goods.
“Returns, replenishment, kitting – with Cortex, each of these applications runs on the same production model. One brain serves each robot, without retraining for each new item or task. And what a robot learns, each robot benefits,” said Dr. Ralf Gulde, co-founder and CEO of Sereact. “Partnering with Teradyne Robotics and its global distribution and integration network helps us bring that brain to their customers around the world, accelerating the capabilities of retailers and logistics providers to adopt AI-driven automation across their operations.”
The company is already implementing the system with CEVA Logistics for Zalando, a European fashion and lifestyle technology platform. In the Zalando logistics centers in Greven, Germany, and Świebodzin, Poland, robots now autonomously process returned fashion items. This is the first phase of a larger initiative to extend returns automation across Europe.
“Returns are one of the most difficult jobs in logistics,” Gulde said. “Returned products almost never arrive in a robotic sequence. The items differ in shape, orientation and packaging, and the mix changes constantly.”
“This is exactly what Cortex was designed to handle the Universal Robots platform,” he said. “By quickly refurbishing returned goods for resale, the solution also helps retailers comply with European Union regulations that prohibit the destruction or landfilling of returned goods.”
NVIDIA plays a role in the collaboration
NVIDIA 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 the NVIDIA Isaac Lab framework and benchmarked on Teradyne Robotics hardware before any models are deployed. During deployment, Cortex runs on NVIDIA Jetson Thor in the cell where inference needs to occur at line speed, and on NVIDIA DGX Spark for development, validation, and site-level model updates.
Teradyne Robotics also uses NVIDIA computing in its Universal Robots cobot and mobile industrial robot platforms. The company said it is contributing SimReady OpenUSD robotic assets to the 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.
Register now and help us celebrate 20 years of RoboBusiness!



Post Comment