Robotics developers can greatly accelerate their work on AI-enabled robots, including humanoids, using new AI and simulation tools and workflows that NVIDIA revealed this week at the Conference for Robot Learning (CoRL) in Munich, Germany.
The lineup includes the general availability of the NVIDIA Isaac Lab robot learning framework; six new humanoid robot learning workflows for Project GR00T, an initiative to accelerate humanoid robot development; and new world-model development tools for video data curation and processing, including the NVIDIA Cosmos tokenizer and NVIDIA NeMo Curator for video processing.
The open-source Cosmos tokenizer provides robotics developers superior visual tokenization by breaking down images and videos into high-quality tokens with exceptionally high compression rates. It runs up to 12x faster than current tokenizers, while NeMo Curator provides video processing curation up to 7x faster than unoptimized pipelines.
Also timed with CoRL, NVIDIA presented 23 papers and nine workshops related to robot learning and released training and workflow guides for developers. Further, Hugging Face and NVIDIA announced they're collaborating to accelerate open-source robotics research with LeRobot, NVIDIA Isaac Lab and NVIDIA Jetson for the developer community.
Accelerating Robot Development With Isaac Lab NVIDIA Isaac Lab is an open-source, robot learning framework built on NVIDIA Omniverse, a platform for developing OpenUSD applications for industrial digitalization and physical AI simulation.
Developers can use Isaac Lab to train robot policies at scale. This open-source unified robot learning framework applies to any embodiment - from humanoids to quadrupeds to collaborative robots - to handle increasingly complex movements and interactions.
Leading commercial robot makers, robotics application developers and robotics research entities around the world are adopting Isaac Lab, including 1X, Agility Robotics, The AI Institute, Berkeley Humanoid, Boston Dynamics, Field AI, Fourier, Galbot, Mentee Robotics, Skild AI, Swiss-Mile, Unitree Robotics and XPENG Robotics.
Project GR00T: Foundations for General-Purpose Humanoid Robots Building advanced humanoids is extremely difficult, demanding multilayer technological and interdisciplinary approaches to make the robots perceive, move and learn skills effectively for human-robot and robot-environment interactions.
Project GR00T is an initiative to develop accelerated libraries, foundation models and data pipelines to accelerate the global humanoid robot developer ecosystem.
Six new Project GR00T workflows provide humanoid developers with blueprints to realize the most challenging humanoid robot capabilities. They include:
GR00T-Gen for building generative AI-powered, OpenUSD-based 3D environments
GR00T-Mimic for robot motion and trajectory generation
GR00T-Dexterity for robot dexterous manipulation
GR00T-Control for whole-body control
GR00T-Mobility for robot locomotion and navigation
GR00T-Perception for multimodal sensing
Humanoid robots are the next wave of embodied AI, said Jim Fan, senior research manager of embodied AI at NVIDIA. NVIDIA research and engineering teams are collaborating across the company and our developer ecosystem to build Project GR00T to help advance the progress and development of global humanoid robot developers.
New Development Tools for World Model Builders Today, robot developers are building world models - AI representations of the world that can predict how objects and environments respond to a robot's actions. Building these world models is incredibly compute- and data-intensive, with models requiring thousands of hours of real-world, curated image or video data.
NVIDIA Cosmos tokenizers provide efficient, high-quality encoding and decoding to simplify the development of these world models. They set a new standard of minimal distortion and temporal instability, enabling high-quality video and image reconstructions.
Providing high-quality compression and up to 12x faster visual reconstruction, the Cosmos tokenizer paves the path for scalable, robust and efficient development of generative applications across a broad spectrum of visual domains.
1X, a humanoid robot company, has updated the 1X World Model Challenge dataset to use the Cosmos tokenizer.
NVIDIA Cosmos tokenizer achieves really high temporal and spatial compression of our data while still retaining visual fidelity, said Eric Jang, vice president of AI at 1X Technologies. This allows us to train world models with long horizon video generation in an even more compute-efficient manner.
Other humanoid and general-purpose robot developers, including XPENG Robotics and Hillbot, are developing with the NVIDIA Cosmos tokenizer to manage high-resolution images and videos.
NeMo Curator now includes a video processing pipeline. This enables robot developers to improve their world-model accuracy by processing large-scale text, image and video data.
Curating video data poses challenges due to its massive size, requiring scalable pipelines and efficient orchestration for load balancing across GPUs. Additionally, models for filtering, captioning and embedding need optimization to maximize throughput.
NeMo Curator overcomes these challenges by streamlining data curation with automatic pipeline orchestration, reducing processing time significantly. It supports linear scaling across multi-node, multi-GPU systems, efficiently handling over 100 petabytes of data. This simplifies AI development, reduces costs and accelerates time to market.
Advancing the Robot Learning Community at CoRL The nearly two dozen research papers the NVIDIA robotics team released with CoRL cover breakthroughs in integrating vision language models for improved environmental understanding and task execution, temporal robot navigation, developin
Most recent headlines
09/12/2024
Dalet, a leading technology and service provider for media-rich organizations, today announced that it has been named an IDC Innovator in the IDC Innovators: ...
09/11/2024
Dalet, a leading technology and service provider for media-rich organizations, today announced three new members of its executive team. Tara Bryant joins as Chi...
06/11/2024
PARK CITY, UTAH - JANUARY 21: Director Dawn Porter at the 2024 Sundance Film Festival Luther: Never Too Much premiere at Eccles Theatre on January 21, 2024, i...
06/11/2024
PARK CITY, UTAH - JANUARY 19: (L-R) Suraj Bhattarai, Arun Bhattarai, Dorottya Zurb and M t Artur Vincze attend the 2024 Sundance Film Festival Agent of Happi...
06/11/2024
Emirates is taking inflight entertainment to new heights by partnering with Spotify, the world's most popular audio-streaming subscription service. Starting...
06/11/2024
BELLEVUE, Wash. T-Mobile said that working with Ericsson and Qualcomm Technologies, it has broken another world record with its 5G standalone (SA) network reach...
06/11/2024
Shared Storage For Creative Teams: Challenges And Solutions
Melanie Ciotti November 6, 2024
0 Comments
Many creative teams struggle with inefficient s...
06/11/2024
We're Entering Untested Entertainment Territory
Andy Marken November 6, 2024
0 Comments
Ventress wants to face it. You want to fight it. But I do...
06/11/2024
Resizing Motion Graphic boxes in After Effects
Graham Quince November 6, 2024
0 Comments
Based on some recent forum questions, I've put together a...
06/11/2024
Embedded into ITV Studios Daytimes post production workflows, Limecraft enables the platform to drive efficiencies and boost creative collaboration
By Matthew ...
06/11/2024
The company has also expanded its Portuguese customer support operation
By Matthew Corrigan
Published: November 6, 2024
The company has also expanded its ...
06/11/2024
Joining forces enables Avid to leverage Wolftechs story-centric newsroom solutions, driving digital-first collaborations, said the company
By Matthew Corrigan ...
06/11/2024
NEW YORK NBC Sports and IMAX have announced that they will be offering the first-ever live college football game at select IMAX locations nationwide with the 20...
06/11/2024
MONTREAL BCE, Canada's largest telecom company, is expanding into the U.S. with a deal by its Bell Canada subsidiary to acquire Ziply Fiber, a fiber interne...
06/11/2024
NEW YORK As the TV industry grapples with the measurement problems that have been produced by rapid changes in the way people watch programming, the Coalition f...
06/11/2024
Learn Cinema 4D Fields in 15 Minutes
Marc Potocnik November 5, 2024
0 Comments
Learn the essentials of Cinema 4D Fields in 15 minutes. For Cinema 4D R...
06/11/2024
Where did the Essential Graphics panel go in Premiere Pro?!
Colin Smith November 5, 2024
0 Comments
This tutorial shows you where you can find the new...
06/11/2024
Nashville Predators' Bridgestone Arena Has a New Broadcast Infrastructure The downtown Nashville mainstay is finally fully recovered from a devastating floo...
06/11/2024
New WMAS Standard Promises More-Flexible, Protected Wireless Operations Shure, Sennheiser establish early beachheads in what could be a game-changer By Dan Dal...
06/11/2024
Euronaval 2024: Unlock real-time insights across all domains with TARAN Effortlessly integrating data from various sources to deliver real-time situational aw...
06/11/2024
Fraport installs advanced passenger scanners from Rohde & Schwarz at Frankfurt A...
06/11/2024
Back to All News
The Final Chapter Begins: BEASTARS Final Season Part 1' A...
06/11/2024
Back to All News
Trailer for Thai Anthology Drama Series Tomorrow and i' T...
06/11/2024
Back to All News
Love Is Blind: Argentina comes to Netflix in three parts, star...
06/11/2024
Back to All News
Pedro P ramo Brought In 375M MXN to the Mexican Economy
Entertainment
06 November 2024
GlobalMexico
Link copied to clipboard
Pedro P ramo...
06/11/2024
NAB NY 2024 Preview NAB NY Booth 1005 November 6, 2024
Cobalt Digital NAB SHOW New York 2024 Plans Include Award-Winning Products Targeting Every Application ...
06/11/2024
The RT Concert Orchestra and guests mark 55 years of the Dublin Simon Community...
06/11/2024
Explore the future with Science Week on RT
Dive into a week of innovative, th...
06/11/2024
At the Conference for Robot Learning (CoRL) in Munich, Germany, Hugging Face and...
06/11/2024
Robotics developers can greatly accelerate their work on AI-enabled robots, incl...
06/11/2024
Editor's note: This post is part of the AI Decoded series, which demystifies AI by making the technology more accessible, and showcases new hardware, softwa...
06/11/2024
Facebook
Twitter
LinkedIn
Thales has concluded an agreement with FEBUS Opt...
05/11/2024
Somaiyah Hafeez, a journalist and writer from Balochistan, Pakistan, stands out for her commitment to telling the stories of overlooked communities in her regio...
05/11/2024
Aisha Farrukh a multimedia journalist from Pakistan focuses on human interest stories and aims to create change through her storytelling. Twenty eight year old ...
05/11/2024
One of the three finalists for the Young Journalist of the Year 2024 is a woman journalist working in secret in Afghanistan because of the restrictions imposed ...
05/11/2024
Many creative teams struggle with inefficient storage solutions that hinder productivity and stifle creativity. We know this because we constantly receive inqui...
05/11/2024
As Gen Zers continue to put their stamp on the world, the conversation around these tastemakers is becoming noisier than ever. Understanding what inspires, capt...
05/11/2024
Exclusive to SBS, watch LIVE coverage of the 2024 US election: an SBS World News...
05/11/2024
New early careers starters join Tewkesbury office for induction week....
05/11/2024
(LYNCHBURG, Va. and MELBOURNE, Fla. - Nov. 4, 2024) - BWX Technologies, Inc. (NY...
05/11/2024
Compact Multi-Channel Solution Tailored for Versatile Production Needs
Montrea...
05/11/2024
Calrec's Regional Sales Manager Dave Lewty says that Calrec's close relationships with its customers are a key factor in the company's success.
Ca...
05/11/2024
BURLINGTON, Mass. Avid said it completed the acquisition of Wolftech Broadcast Solutions, a provider of cloud-based, multiplatform news planning, production and...
05/11/2024
A new study from The Myers Report estimates that U.S. political ad spending for the 2024 campaign will top $12 billion, eclipsing the $9.02 billion spent in 202...
05/11/2024
Claudio Del Bravo, colourist, Frame by Frame
Caroline Shawley November 5, 2024
0 Comments
Claudio Del Bravo is a senior colourist and head of long for...
05/11/2024
RuPaul's DragCon LA Pink Carpet Live Streamed with Blackmagic Design
Brie Clayton November 5, 2024
0 Comments
Blackmagic Design workflow helps Wor...
05/11/2024
DENVER Comcast Technology Solutions (CTS) today unveiled its Cloud TV platform, a centralized ingest, transcoding and video-processing solution supporting live ...
05/11/2024
Neither Redstone nor her son, Tyler Korff, will join the new entitys board, said the report
By Matthew Corrigan
Published: November 5, 2024 Updated: Novemb...
05/11/2024
QuickLink, the leading global provider of multi-camera video productions and remote contribution solutions, announces the expansion of its reseller partner netw...
Robotics developers can greatly accelerate their work on AI-enabled robots, including humanoids, using new AI and simulation tools and workflows that NVIDIA revealed this week at the Conference for Robot Learning (CoRL) in Munich, Germany.
