AI Toolkit Promises Faster Robot Development
Accelerator provides researchers, developers with an extensible out-of-the-box platform to build applications
Denmark-based Universal Robots has launched a new ready-to-use hardware and software toolkit that aims to ease the development of AI-powered collaborative robot applications.
The company manufactures small, flexible robot arms for industrial purposes and its new offering, the UR AI accelerator toolkit, provides researchers and developers with an extensible out-of-the-box platform to build applications, accelerate research and reduce the time to market of AI products.
Through built-in demo programs, the AI accelerator leverages Universal Robots’ Polyscope X platform to enable features such as pose estimation, tracking, object detection, path planning, image classification, quality inspection and state detection, among other things.
Polyscope X is globally available and can be used for all collaborative robots – also known as cobots – and automation applications across industries. It allows developers to choose what toolsets, programming languages and libraries they want to use to create their own programs.
The new toolkit is powered by Nvidia Isaac accelerated libraries and AI models, running on the Nvidia Jetson AGX Orin system-on-module. Specifically, Nvidia Isaac Manipulator gives developers the ability to bring accelerated performance and state-of-the-art AI technologies to their robotics products, the company said. It also includes the newly developed Orbbec Gemini 335Lg 3D camera.
This offers everything needed to develop and deploy new, innovative AI solutions, according to Kim Povlsen, CEO and president of Universal Robots.
“We are already a leading platform for taking AI cobot applications to market and now we are pushing the boundaries even further. The most exciting part will be seeing the impact of these new capabilities for our partners and end customers,” she said.
James Davidson, chief AI officer at Teradyne Robotics, which has owned Universal Robots since 2015, said the AI accelerator can decrease the time it takes to deploy solutions on its platform while also de-risking the development of AI-based solutions.
“With our objective to take physical AI to an entirely new level, AI accelerator is just the first to market of a series of AI-powered products and capabilities in UR's pipeline, all with the focused goal of making robotics more accessible than ever before,” he said.
This article was first published in AI Business's sister publication IoT World Today.
About the Author
You May Also Like