Teradyne Robotics, the company that owns Universal Robots and Mobile Industrial Robots, will demonstrate how physical AI is transforming industrial automation at Automate 2026 in Chicago, June 22-25 at booth #1250.
“Physical AI is on full display across our robotic solutions at Automate,” said Jean-Pierre Hathout, President of the Teradyne Robotics Group.
“The demos we are presenting are real and deployable. Manufacturers can purchase the physical AI‑enabled applications we have on display, including our first physical AI-product the MiR1200 Pallet Jack, today – delivered through our global ecosystem of system integrators and partners – to automate tasks that have traditionally been difficult or impractical for robots, including those in dynamic and unstructured environments.”
PolyScope X introduces PLC style logic for multiple work cell control
The foundational layer for physical AI advancements is PolyScope X, UR’s next-generation software platform: PolyScope X still relies on the powerful motion-control foundation that has defined UR for decades, while modernizing the operator experience on a state-of-the-art technology stack.
This includes modern web technologies, containerized applications and native ROS 2 support, which allow developers and engineers to program automation applications the way they are most comfortable.
PolyScope X also introduces Logic Programs, continuously running, multi-threaded programs that execute in parallel with the main robot program.
This native, PLC-style background logic lets programmers coordinate and control multiple work cell components, exchange data, and, in many deployments, reduce or replace external PLCs, running independently of safeguard stops, program pauses, and robot power state.
Teradyne Robotics’ Automate booth will host a demonstration stage showcasing hourly live demos of how PolyScope X serves as the tech stack for future-proof, cyber-secure, and AI-ready robotics.
“Automation today requires more than just a robot – it demands a platform that can adapt, integrate, and evolve with the needs of modern manufacturing,” said Hathout.
A new era of data centers and AI training
Teradyne Robotics’ booth highlights the company’s strategic focus on the infrastructure of the future, specifically addressing the needs of electronics manufacturers and AI data centers:
- The UR AI Trainer: Developed with Scale AI, UR’s imitation learning platform allows users to physically guide a UR robot through tasks like smartphone packaging, capturing high-fidelity, force-aware data to train sophisticated Vision-Language-Action (VLA) models for direct factory deployment. The AI Trainer also supports integration with cloud services, with examples of how users can take data from the Trainer to train the Nvidia GR00T open VLA model or use the Nvidia Isaac Sim open simulation framework to validate and test robot behavior.
- Generalist: Two UR12e robots running autonomously on Generalist’s GEN-1 model, showcasing complex dexterous manipulation capabilities. Shown here leveraging the high-quality motion and reliability of the Universal Robots platform, GEN-1 is a class of general-purpose robotic foundation models delivering general intelligence from the physical world at levels of speed and reliability that demonstrate traction toward the practical thresholds required for real deployments.
- Cambrian: Directly supporting the global build-out of AI infrastructure, this demo uses dual-arm UR7e robots and Cambrian’s AI vision system to identify and insert copper cables into high-density server racks, a process traditionally plagued by manual errors and labor shortages.
On-the-fly learning: Physical AI in action
The booth features a diverse range of demos from ecosystem partners leveraging UR robots and MiR AMRs to perceive and react to the “messy reality” of the industrial world:
- AICA: Showcases how a UR7e robot executes learned trajectories from human demonstrations that are both adaptive and force-sensing. The robot picks up a metal part and buffs it against a polishing wheel, matching the speed and applied force of an operator with only a single demonstration.
- beRobox (PALTZ) + MiR Mobility: The PALTZ palletizer utilizes AI vision to redirect a UR20 robot on the fly, picking up boxes even if they have shifted orientation. In the demo, the AI-enabled Pallet Jack and the MiR600 operate directly alongside the beRobox palletizer, retrieving pallets, exchanging positions, and returning them to their original locations to clearly showcase coordinated material flow. Together, this creates a flexible, mobile system that moves between tasks and locations without fixed infrastructure, providing a practical, end-to-end alternative to humanoid robots.
- Mobile cobot + ROEQ: A similar alternative to humanoids is showcased next to the beRobox demo where a MiR250 equipped with an ROEQ conveyor topper transfers a box to a conveyor. The conveyor then moves the box to the end of the line, where the MC250 mobile cobot picks it up, transports it back to the MiR250, and places it for the process to repeat.
- Maple Advanced Robotics Inc.: An Autonomous Spot Sanding Solution that requires no CAD models or manual teaching; an operator simply marks defects, and the system, powered by a UR8L robot, automatically scans and applies the correct finishing recipe.
- Trener Robotics: Acteris is an AI-native platform with a conversational interface that allows operators to deploy robotic machine tending jobs via simple chat input in any language, setting up new tasks handled by a UR7e robot in just 1-2 minutes.
- Vention: The Rapid Operator AI is a bin picking solution achieving a 99% first-pick success rate, configured in minutes with zero programming. The system uses a UR12e robot and 3D vision to handle unstructured parts for real-time identification.
“With physical AI deployed with UR and MiR robots, we are providing solutions enabling automation to work with the world as it is, not as we wish it to be,” said Hathout.
