Teradyne Robotics announces collaboration with NVIDIA

Teradyne Robotics recently announced a collaboration with NVIDIA to bring new AI capabilities to automation applications. Teradyne is the parent company of collaborative robot arm provider Universal Robots (UR) and autonomous mobile robot (AMR) provider Mobile Industrial Robots (MiR).

Last week, UR demonstrated an autonomous inspection system powered by NVIDIA Isaac cuMotion path planning at the GTC global AI conference in San Jose, California.

MiR recently launched its new MiR1200 autonomous pallet jack, which harnesses AI pallet detection powered by the NVIDIA Jetson AGX Orin module.

The MiR1200 Pallet Jack and UR’s cuMotion demo are Teradyne’s two most recent examples of “physical AI” systems, with others already available through Teradyne Robotics’ ecosystem partners, OEMs, and end users, the company said.

Ujjwal Kumar, group president of Teradyne Robotics, said the recent examples are the first of a series of planned AI offerings. “By adding high-performance compute hardware to our control systems, as well as investing in targeted upgrades to our software stacks, we are investing to establish UR and MiR as the preferred robotics platforms for developing and deploying AI applications.

“We are working to shape the future of robotics by combining NVIDIA’s state-of-the-art AI platform with Teradyne Robotics’ real-world domain expertise in industrial automation,” said Kumar. “We’re creating the platform for new solutions to previously unsolvable problems.”

Universal Robots cobot follows NVIDIA cuMotion path planner

Teradyne said combining NVIDIA’s cuMotion path planning software with Universal Robots’ cobot arms can help simplify the setup of common industrial applications. Source: Teradyne Robotics

Through their collaboration and for the GTC showcase, UR integrated NVIDIA accelerated computing into its cobot for faster path planning. Teradyne said NVIDIA’s computing made UR’s path planning 50 to 80 times faster than current solutions.

The demonstration combined the NVIDIA Jetson AGX Orin - a complete system-on-module designed for edge AI applications - the cuMotion path planner for robot arms from the NVIDIA Isaac Manipulator platform, UR’s new PolyScope X software, and its UR5e cobot arm.

“NVIDIA’s Isaac platform is enabling increased autonomy in robotics with rapid advancements in simulation, generative AI, foundation models and optimized edge compute,” said Deepu Talla, vice president of robotics and edge computing for NVIDIA. “This collaboration with Teradyne Robotics will bring the power of AI and accelerated computing to rapidly growing cobot and AMR markets.”

Teradyne said using cuMotion in combination with the UR cobot and PolyScope X makes possible a range of applications that were previously not feasible to automate fully, as well as improving existing programming concepts. Benefits include ease of programming and lower computation time for planning, optimizing, and executing robot arm trajectories.

For customers, this technology can help simplify the setup of common industrial applications, increasing automation potential in high-mix, low-volume scenarios. CuMotion not only allows automatic calculation of path planning for collision-free trajectories but also enables path optimization for other criteria such as speed, minimum wear, or energy efficiency.

Teradyne said it expects to increase application potential and efficiency for automation customers through the combination of UR and NVIDIA technologies.

MiR1200 detects pallets with NVIDIA Jetson AGX Orin

Through NVIDIA Jetson AGX Orin, the MiR1200 autonomous pallet jack combines data from four RGBD cameras and 3D LiDAR to detect obstacles and navigate autonomously. Source: Mobile Industrial Robots (MiR)

The MiR1200 Pallet Jack uses 3D machine vision from NVIDIA to identify, pick up, and deliver pallets with precision, even in dynamic and complex environments. Teradyne said with the addition of this Pallet Jack to the portfolio, MiR has become a one-stop shop for autonomous material handling at factories and warehouses.

The MiR1200 Pallet Jack was designed to deal with complex warehouse requirements and dynamic environments that make traditional automation challenging. Trained on more than 1.2 million real and synthetic images, the MiR1200 Pallet Jack combines data from four RGBD cameras to enable fast and precise pallet handling.

Concurrently, the NVIDIA Jetson platform fuses feedback from the RGBD cameras, as well as 3D LiDAR, to detect obstacles in 3D space for fully autonomous navigation. Jetson provides the computing needed to handle data in real time. As a result, the MiR1200 Pallet Jack can dynamically modify its route to avoid obstacles, such as loose objects on the floor, raised forks in the drive path, or overhead obstacles.

MiR said the MiR1200’s ability to navigate in tight spaces with minimal changes to the existing infrastructure makes it well-suited to optimizing logistics efficiency and ensuring timely delivery of pallets.

In addition to Teradyne, MiR also recently publicized details and specifications of its new MiR1200 autonomous pallet jack.