Teredyne is a conglomerate that has been snarfing up collaborative robotic assets. Many are based on Universal Robotics technology. This news expands AI-powered applications. Of course, AI is the entry point phrase for any new technology currently. That’s OK, it is an advancement in usability. And that’s a good thing.
Teradyne Robotics and its partners are set to unveil a suite of advanced, AI-driven robotics solutions at NVIDIA GTC 2025 March 17-21. The unveiling represents the first public demonstration of the AI Accelerator in commercially viable applications.
“Physical AI equips robots with the capacity to perceive and respond to the real world providing the versatility and problem-solving capabilities that are often required by complex use cases that have been out of scope until now,” says James Davidson, Chief AI Officer, Teradyne Robotics. “Instead of merely executing pre-programmed instructions, robots empowered by AI gain the ability to learn, adapt, and make informed decisions grounded in their sensory input,” he says.
Davidson adds, “Think of a logistics operation where robots navigate through a warehouse with constantly changing layouts and obstacles. Or a construction site where robots assist in assembly tasks within unpredictable and changing environments. The AI Accelerator helps our cobots better understand their surroundings, plan optimal paths, and execute tasks safely and efficiently in previously unmanageable spaces.”
The AI Accelerator is a toolkit designed by Teradyne Robotics company Universal Robots (UR) in collaboration with NVIDIA to enable the development of AI-powered applications by bringing AI acceleration to UR’s next-generation software platform, PolyScope X. The toolkit is powered by NVIDIA Isaac accelerated libraries and AI models, running on the NVIDIA Jetson AGX Orin system-on-module.
Partner displays:
- 3D Infotech – Dynamic Metrology: Showcasing a UR3e cobot that scans workpieces, compares them with CAD models, and highlights dimensional inaccuracies by projecting them onto the workpiece surface. The AI Accelerator enhances the perception capabilities of the cobot, allowing it to more accurately locate the workpiece for inspection.
- T-Robotics – GenAI Driven Programming: Demonstrating a UR5e cobot with LLM-driven CNC machine tending. With T-Robotics ActGPT, users can describe an application setup in natural language and have it translated into a robot program with the help of the AI Accelerator.
- AICA – Reinforcement Learning Assembly: Featuring a UR5e cobot executing single-arm gear assembly using reinforcement learning. The cobot locates a part using AI Accelerator-based perception and then uses a reinforcement learning skill to complete a contact-rich assembly process.
- Acumino – Bimanual Assembly: The AI Accelerator facilitates a bimanual UR5e cobot’s ability to learn complex manipulation tasks from human demonstrations. The system completes an electrical cable handling task and attendees can collaborate with the robot to solve the task.
- Groundlight – Workpiece Detection for Streamlined Picking: The AI Accelerator trains a model to detect a workpiece and generate a robot program for picking, then verifies that the robot workspace is ready, ensuring a robust and easily deployed solution.
While the AI Accelerator is primarily focused on UR cobots, the underlying AI and accelerated computing technology also benefit Mobile Industrial Robots (MiR), another Teradyne company featured at GTC. The MiR1200 Pallet Jack uses 3D vision and the NVIDIA Jetson AGX Orin module for pallet detection, allowing the pallet jack to identify, pick up, and deliver pallets with precision in complex environments.
