Loading video...

Video Failed to Load

Go Home

Our Seattle #Robotics Lab introduces a new, faster, & more efficient method for teaching robot manipulation tasks in real-life scenarios — like opening drawers or dispensing soap — training 36x faster than the current standard. #NVIDIAResearch Learn more:

NVIDIARobotics's profile picture

NVIDIA Robotics

146,682 subscribers

20,090 views • 3 years ago •via X (Twitter)

Science & Technology#Robotics#NVIDIAResearch
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Introducing GEN-1. Our latest milestone in scaling robot learning. We believe it to be the first general-purpose AI model to master simple physical tasks. 99% success rates, 3x faster speeds, adapts in real time to unexpected scenarios, w/ only 1 hour of robot data. More🧵👇
3:21

Introducing GEN-1. Our latest milestone in scaling robot learning. We believe it to be the first general-purpose AI model to master simple physical tasks. 99% success rates, 3x faster speeds, adapts in real time to unexpected scenarios, w/ only 1 hour of robot data. More🧵👇

Generalist

389,781 views • 7 months ago

Our latest research introduces "color codes" requiring fewer qubits and allows for faster logical operations compared to surface codes. Learn more →
1:16

Our latest research introduces "color codes" requiring fewer qubits and allows for faster logical operations compared to surface codes. Learn more →

Google Quantum AI

17,277 views • 1 year ago

Unitree founder Wang Xingxing: In robotics, locomotion and basic motion is mostly solved. But grasping and manipulation—anything related to haptics—hasn’t been solved. That’s the key bottleneck preventing them from being deployed at scale in factories and homes. He says that simulation is much faster for training but for manipulation tasks you still need real-world training data—for now.
16:10

Unitree founder Wang Xingxing: In robotics, locomotion and basic motion is mostly solved. But grasping and manipulation—anything related to haptics—hasn’t been solved. That’s the key bottleneck preventing them from being deployed at scale in factories and homes. He says that simulation is much faster for training but for manipulation tasks you still need real-world training data—for now.

Kyle Chan

67,761 views • 6 months ago

Can my robot cook my food, rearrange my dresser, tidy my messy table and do so much more without ANY demos or real-world training data? Introducing ManipGen: A generalist agent for manipulation that can solve long-horizon robotics tasks entirely zero shot, from text input! 1/N
2:19

Can my robot cook my food, rearrange my dresser, tidy my messy table and do so much more without ANY demos or real-world training data? Introducing ManipGen: A generalist agent for manipulation that can solve long-horizon robotics tasks entirely zero shot, from text input! 1/N

Murtaza Dalal

149,278 views • 2 years ago

Since 1961, taxes have grown much faster than incomes or basic costs. For young Canadians, that means less left for rent, loans, and savings. Learn more through the link in our bio or click here: #cdnpoli
0:50

Since 1961, taxes have grown much faster than incomes or basic costs. For young Canadians, that means less left for rent, loans, and savings. Learn more through the link in our bio or click here: #cdnpoli

The Fraser Institute

32,136 views • 1 month ago

Today, we announced the opening of our 70K sq ft CryoEM lab in Andover, Mass – among the largest privately owned labs of its kind in the U.S. – which will help drive faster and more efficient therapeutic development. Take an up-close look at the space:
0:58

Today, we announced the opening of our 70K sq ft CryoEM lab in Andover, Mass – among the largest privately owned labs of its kind in the U.S. – which will help drive faster and more efficient therapeutic development. Take an up-close look at the space:

Generate:Biomedicines

17,124 views • 3 years ago

It’s time… the all new TaylorMade Golf Qi4D Drivers are HERE. Faster face. Enhanced aero. More customizable than ever before. Learn more:
0:47

It’s time… the all new TaylorMade Golf Qi4D Drivers are HERE. Faster face. Enhanced aero. More customizable than ever before. Learn more:

Fore Play

58,466 views • 9 months ago

Can robot foundation models scale? Xiaomi-Robotics-1 explores this question with over 100,000 hours of real-world manipulation data. Pre-trained on large-scale real-world trajectories and post-trained with cross-embodiment robot data, Xiaomi-Robotics-1 demonstrates consistent scaling across data and model size, strong generalization in unseen environments, and efficient adaptation to new tasks. 🔗 #Robotics #EmbodiedAI #FoundationModels #RobotLearning #XiaomiAI #XiaomiRobotics
0:29

Can robot foundation models scale? Xiaomi-Robotics-1 explores this question with over 100,000 hours of real-world manipulation data. Pre-trained on large-scale real-world trajectories and post-trained with cross-embodiment robot data, Xiaomi-Robotics-1 demonstrates consistent scaling across data and model size, strong generalization in unseen environments, and efficient adaptation to new tasks. 🔗 #Robotics #EmbodiedAI #FoundationModels #RobotLearning #XiaomiAI #XiaomiRobotics

Xiaomi Tech

23,920 views • 3 months ago

The biggest bottleneck in AI for biology is still the wet lab. AI can generate more ideas than our labs can test. Closing that gap is how we turn better models into faster discovery. Today, we’re introducing X-Automate at Xaira: bringing agentic AI and physical robotics into the lab. 🧵
2:46

The biggest bottleneck in AI for biology is still the wet lab. AI can generate more ideas than our labs can test. Closing that gap is how we turn better models into faster discovery. Today, we’re introducing X-Automate at Xaira: bringing agentic AI and physical robotics into the lab. 🧵

Bo Wang

32,915 views • 9 days ago

With RL, the robot can learn very precise tasks, like fastening a zip tie, and can actually do it more consistently and more quickly than even human teleoperation.
0:58

With RL, the robot can learn very precise tasks, like fastening a zip tie, and can actually do it more consistently and more quickly than even human teleoperation.

Physical Intelligence

19,117 views • 7 months ago

Vidu Q3 Suite Upgraded: Faster and More Efficient Built for Storytelling. Designed for More Creative Scenarios. Enter code VIDUQ3GVL to start your free trial. RT + Follow + Reply = 300 Credits in DMs (72H only) #Vidu #ViduQ3 #AI
0:43

Vidu Q3 Suite Upgraded: Faster and More Efficient Built for Storytelling. Designed for More Creative Scenarios. Enter code VIDUQ3GVL to start your free trial. RT + Follow + Reply = 300 Credits in DMs (72H only) #Vidu #ViduQ3 #AI

Vidu AI

22,369 views • 5 months ago

🚀 Code faster and smarter with AI-powered enhancements to @androidstudio! Learn about techniques like retrieval augmentation, filtering low-confidence completions, and smarter post-processing to make code completion faster and more efficient. →
0:37

🚀 Code faster and smarter with AI-powered enhancements to @androidstudio! Learn about techniques like retrieval augmentation, filtering low-confidence completions, and smarter post-processing to make code completion faster and more efficient. →

Android Developers

13,177 views • 2 years ago

Watch our introduction of Fluid compute—a faster and more cost efficient way to build dynamic applications.
24:07

Watch our introduction of Fluid compute—a faster and more cost efficient way to build dynamic applications.

Vercel

28,252 views • 1 year ago

Introducing Standard Bots AI “We chose Standard Bots for two reasons: the speed of development is highly compressed, and the interface for programming the robot is so much simpler. With Standard Bots AI, that's even faster.” — Adrian Nistler, President and CEO, Path Machining & Automation Standard Bots AI robots deliver dramatically faster setups, faster changeovers, and faster paybacks. This is why robots are the new essential power tool of the 21st century. Our mission is to expand human capacity with the world’s most accessible robots. We’re building this future in Glen Cove, New York, and on hundreds of factory floors, and counting. Say yes to more:
2:52

Introducing Standard Bots AI “We chose Standard Bots for two reasons: the speed of development is highly compressed, and the interface for programming the robot is so much simpler. With Standard Bots AI, that's even faster.” — Adrian Nistler, President and CEO, Path Machining & Automation Standard Bots AI robots deliver dramatically faster setups, faster changeovers, and faster paybacks. This is why robots are the new essential power tool of the 21st century. Our mission is to expand human capacity with the world’s most accessible robots. We’re building this future in Glen Cove, New York, and on hundreds of factory floors, and counting. Say yes to more:

Standard Bots

132,858 views • 16 days ago

Stretch 3 is here, and it’s our best robot yet! Collect real world data. Explore tasks with real users. Create real impact. Learn more:
1:22

Stretch 3 is here, and it’s our best robot yet! Collect real world data. Explore tasks with real users. Create real impact. Learn more:

Hello Robot

48,164 views • 2 years ago

🚑 Faster deliveries = better patient care. Our beloved Medbot ensures critical supplies get where they’re needed- WITHOUT DELAY. Watch it navigate the halls like a pro! Learn more about Medbot at $RR #Robotics #AI #hospital #Medical #MedicalInnovation
1:03

🚑 Faster deliveries = better patient care. Our beloved Medbot ensures critical supplies get where they’re needed- WITHOUT DELAY. Watch it navigate the halls like a pro! Learn more about Medbot at $RR #Robotics #AI #hospital #Medical #MedicalInnovation

Richtech Robotics

14,451 views • 1 year ago

RL in the real world presents some big challenges, but also some really big opportunities. In our new work, HIL-SERL, Charles Xu, Jeffrey Wu, Jianlan Luo show that real-world RL can learn a huge range of precise and robust tasks, and perform them much faster than imitation.
0:37

RL in the real world presents some big challenges, but also some really big opportunities. In our new work, HIL-SERL, Charles Xu, Jeffrey Wu, Jianlan Luo show that real-world RL can learn a huge range of precise and robust tasks, and perform them much faster than imitation.

Sergey Levine

36,618 views • 2 years ago