|
Listen to this text  |
SAN JOSE, Calif. — Artificial intelligence is already making robots smarter. Teradyne Robotics introduced at GTC 2024 a collaboration with NVIDIA so as to add new AI capabilities to collaborative and cell robots.
North Reading, Mass.-based Teradyne owns collaborative robotic maker Universal Robots A/S (UR) and autonomous cell robotic (AMR) firm Mobile Industrial Robots A/S (MiR), each of that are in Odense, Denmark.
“This is the first of a series of planned AI offerings by Teradyne Robotics,” acknowledged Ujjwal Kumar, group president of Teradyne Robotics. “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,” he added. “We’re creating the platform for new solutions to previously unsolvable problems.”
Kumar will ship a keynote on the Robotics Summit & Expo in Boston in May.
Universal Robots integrates accelerated computing
Universal Robots is demonstrating at this week’s GPU Technology Conference (GTC) an autonomous inspection system utilizing its cobot arms and AI. The firm has built-in NVIDIA accelerated computing into its cobots for path planning 50 to 80 occasions sooner than as we speak’s functions.
“NVIDIA has been working with Universal Robots for three years,” Kumar defined to Collaborative Robotics Trends. “Its researchers were used to the UR cobots, which are inherently safe and thus good for testing AI.”
“While the Microsofts and Googles of the world may own digital AI, NVIDIA wants to be the market leader in physical AI, as CEO Jensen Huang mentioned in his keynote,” he stated. “In digital AI, 90% might be OK for an image or text generated with AI, but that’s not sufficient in the real world. Teradyne has experience with quality and reliability.”
The companions stated the applying combines the next to extend effectivity for automation prospects:
The mixture of cuMotion, PolyScope X, and the UR cobot makes potential a spread of functions that had been beforehand not possible to automate totally, in keeping with the companions. It may enhance current programming ideas.
Teradyne and NVIDIA cited advantages together with ease of programming and decrease computation time for planning, optimizing, and executing trajectories. For prospects, this know-how can simplify the setup of frequent industrial functions, facilitating robotic adoption for high-mix, low-volume situations.
Not solely can cuMotion enable computerized calculation of path planning for collision-free trajectories, however it additionally allows path optimization for different standards reminiscent of pace, minimal put on, or power effectivity, in keeping with Universal Robots.
At the GTC demonstration, The Robot Report watched the cobot-mounted digicam transfer to examine a workpiece that was randomly reoriented. It did so mechanically, and a digital twin mirrored its maneuvers.
For the inspection software, customers can load CAD recordsdata for as much as 20 elements with related check procedures. NVIDIA’s know-how allows the robotic to determine every half and process and conduct path planning accordingly, defined Andrew Pether, principal innovation analysis engineer at Universal Robots. He stated the mix of cuMotion on AGX Orin for dynamic positioning, Isaac Sim for digital twins of the present state and trajectories can enhance inspections for automotive, massive electronics, and “white goods”/home equipment producers.
Teradyne, NVIDIA anticipate AI robotics apps to develop
Mobile Industrial Robots additionally introduced the MiR1200 Pallet Jack, which makes use of the NVIDIA Jetson AGX Orin module for AI-powered pallet detection. This allows it to determine and exactly transfer objects, navigate autonomously, and function in advanced manufacturing facility and warehouse environments.
“There are two kinds of workers in factories or warehouses — those in static cells or who are moving,” stated Kumar. “We have robots to help both sorts of tasks. Mobile robots and cobots could jointly meet needs in welding, semiconductors, and more.”
Teradyne famous that autonomous inspection and the autonomous pallet dealing with are two use circumstances with vital potential for scalability. The MiR1200 Pallet Jack and UR’s cuMotion demo are the 2 most up-to-date examples of “physical AI” options, with others already out there via Teradyne Robotics’ ecosystem companions, OEMs, and finish customers.
“NVIDIA’s Isaac platform is enabling increased autonomy in robotics with rapid advancements in simulation, generative AI, foundation models and optimized edge compute,” stated Deepu Talla, vp of robotics and edge computing at NVIDIA. “This collaboration with Teradyne Robotics will bring the power of AI and accelerated computing to rapidly growing cobot and AMR markets.”
