NVIDIA and Alphabet’s Intrinsic Put Next-Gen Robotics Within Grasp – Automation.com

Summary

Intrinsic, a software and AI robotics company at Alphabet, has integrated NVIDIA AI and Isaac platform technologies to advance the complex field of autonomous robotic manipulation.

Intrinsic, a software and AI robotics company at Alphabet, has integrated NVIDIA AI and Isaac platform technologies to advance the complex field of autonomous robotic manipulation.

This week at the Automate trade show, in Chicago, Intrinsic is spotlighting leaps in robotic grasping and industrial scalability assisted by foundation models enabled by NVIDIA Isaac Manipulator, unlocking new value in industrial automation with AI.

NVIDIAunveiled Isaac Manipulatorat GTC in March.Isaac Manipulatoris a collection of foundation models and modular GPU-accelerated libraries that help industrial automation companies build scalable and repeatable workflows for dynamic manipulation tasks by accelerating AI model training and task reprogramming.

Foundation modelsare based on atransformerdeep learning architecture that allows a neural network to learn by tracking relationships in data. Theyre generally trained on huge datasets and can be used to process and understand sensor and robot information as magically as ChatGPT for text. This enables robot perception and decision-making like never before and provides zero-shot learningthe ability to perform tasks without prior examples.

NVIDIAs collaboration with Intrinsic, a leading robotics software and AI company, demonstrates the potential for a universally applicable robotic-grasping skill to work across grippers, environments and objects.

For the broader industry, our work with NVIDIA shows how foundation models can have a profound impact, including making todays processing challenges easier to manage at scale, creating previously infeasible applications, reducing development costs, and increasing flexibility for end users, said Wendy Tan White, CEO at Intrinsic,in a blog postannouncing the collaboration with NVIDIA. (White will deliver a keynote address at Automate about what the rise of AI means for innovation and growth, on Thursday, May 9, at 7 a.m. PT.)

Grasping has been a long sought after robotics skill. So far its been time-consuming, expensive to program and difficult to scale. As a result, many repetitive pick-and-place conditions havent been seamlessly handled to date by robots.

Simulation is changing that. EnlistingNVIDIA Isaac Simon theNVIDIA Omniverseplatform, Intrinsic generatedsynthetic datafor vacuum grasping using computer-aided design models of sheet metal and suction grippers. This allowed Intrinsic to create a prototype for its customerTrumpf Machine Tools, a leading maker of industrial machine tools.

The prototype uses IntrinsicFlowstate, a developer environment for AI-based robotics solutions, for visualizing processes, associated perception and motion planning. With a workflow that includes Isaac Manipulator, one can generate grasp poses and CUDA-accelerated robot motions, which can first be evaluated in simulation with Isaac Sima cost-saving stepbefore deployment in the real world with the Intrinsic platform.

Under the collaboration, NVIDIA and Intrinsic plan to bring state-of-the-art dexterity and modular AI capabilities for robotic arms, with a robust collection of foundation models and GPU-accelerated libraries to accelerate a greater number of new robotics and automation tasks.

On Tuesday, May 7, at 11 a.m. CT, NVIDIA Senior Research Scientist Adithya Murali and Intrinsic Chief Science Officer Torsten Kroeger will demonstrate the companies work in the session Automating Smart Pick-and-Place With Intrinsic Flowstate and NVIDIA Isaac Manipulator in the Intrinsic booth 2808 at Automate.Joinourspeaking sessionsat Automate

Check out our free e-newsletters to read more great articles..

The rest is here:

NVIDIA and Alphabet's Intrinsic Put Next-Gen Robotics Within Grasp - Automation.com