Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

We are really impressed with Dyna Robotics robot folding demo at Foxglove's Actuate conference. We've come a long way since the early PR2 folding research!

OpenRoboticsOrg's profile picture

Open Robotics

43,532 subscribers

29,532 Aufrufe • vor 11 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Imagine having a personal robot to handle your household chores! At the 2026 World Robot Conference (WRC) in Beijing, a few humanoid robots are bringing that idea closer to reality, demonstrating household tasks like folding clothes and cleaning up desks.
0:24

Imagine having a personal robot to handle your household chores! At the 2026 World Robot Conference (WRC) in Beijing, a few humanoid robots are bringing that idea closer to reality, demonstrating household tasks like folding clothes and cleaning up desks.

People's Daily, China

17,828 Aufrufe • vor 5 Tagen

Introducing Dynamism v1 (DYNA-1) by Dyna Robotics – the first robot foundation model built for round-the-clock, high-throughput dexterous autonomy. Here is a time-lapse video of our model autonomously folding 850+ napkins in a span of 24 hours with • 99.4% success rate — zero human intervention • 60% human throughput speed • 4.3/5 quality ratings (set by the client) A thread on our motivation, insights and results:
2:33

Introducing Dynamism v1 (DYNA-1) by Dyna Robotics – the first robot foundation model built for round-the-clock, high-throughput dexterous autonomy. Here is a time-lapse video of our model autonomously folding 850+ napkins in a span of 24 hours with • 99.4% success rate — zero human intervention • 60% human throughput speed • 4.3/5 quality ratings (set by the client) A thread on our motivation, insights and results:

Jason Ma

520,208 Aufrufe • vor 1 Jahr

Wrapped Day-1 at Conference on Robot Learning - our booth was buzzing all day, and this is why. ⬇️ Here’s a timelapse of Dynasaur folding continuously, shrugging off every interruption researchers threw at it. It’s thrilling to see the crowd erupt in applause after the robot nails a flawless fold Don't miss it! We're here all week - booth 28 #CoRL2025 #Robotics #AI
0:29

Wrapped Day-1 at Conference on Robot Learning - our booth was buzzing all day, and this is why. ⬇️ Here’s a timelapse of Dynasaur folding continuously, shrugging off every interruption researchers threw at it. It’s thrilling to see the crowd erupt in applause after the robot nails a flawless fold Don't miss it! We're here all week - booth 28 #CoRL2025 #Robotics #AI

Dyna Robotics

64,643 Aufrufe • vor 11 Monaten

We've come a long way in the nine years since the Championship's inception ⚡️ With ever-evolving on-track technology and revolutionary changes, we look back at Formula E, through the generations.
0:35

We've come a long way in the nine years since the Championship's inception ⚡️ With ever-evolving on-track technology and revolutionary changes, we look back at Formula E, through the generations.

Formula E

16,416 Aufrufe • vor 3 Jahren

Sharing some exciting DYNA-1 result: zero-shot environment generalization We put DYNA-1 under test in a completely different environment from our training distribution – with an entirely different background (Dyna Robotics banner) and metal table. The table has a reflective and smooth surface, creating a wildly different visual appearance as well as interaction dynamics. The model is able to proceed as usual, adeptly folding and recovering from its own mistakes. By focusing on task mastery, we achieve robust generalization out of the box
4:25

Sharing some exciting DYNA-1 result: zero-shot environment generalization We put DYNA-1 under test in a completely different environment from our training distribution – with an entirely different background (Dyna Robotics banner) and metal table. The table has a reflective and smooth surface, creating a wildly different visual appearance as well as interaction dynamics. The model is able to proceed as usual, adeptly folding and recovering from its own mistakes. By focusing on task mastery, we achieve robust generalization out of the box

Jason Ma

49,008 Aufrufe • vor 1 Jahr

our boy has really come a long way since the start 🤧
2:08

our boy has really come a long way since the start 🤧

gabr @ pokopia

67,162 Aufrufe • vor 7 Monaten

The Samsung #GalaxyZTriFold is coming to the US! Back around The Year Two Thousand I was setting up little folding keyboards with a 160x160 monochrome PDA screen and now I'm setting them up with multi-window multi-tasking on a foldable 10-inch screen. We have come a long way :)
0:54

The Samsung #GalaxyZTriFold is coming to the US! Back around The Year Two Thousand I was setting up little folding keyboards with a 160x160 monochrome PDA screen and now I'm setting them up with multi-window multi-tasking on a foldable 10-inch screen. We have come a long way :)

Dieter Bohn

14,434 Aufrufe • vor 7 Monaten

What the first Super Meat Boy 3D prototype looked like. We've come a long way since then.
0:27

What the first Super Meat Boy 3D prototype looked like. We've come a long way since then.

Sluggerfly

195,733 Aufrufe • vor 8 Monaten

JUST IN: Dyna Robotics just published one of the most important research papers in robotics this year. It could fundamentally change how robot foundation models are trained. A scaling law that transfers from human video to robot performance. Dyna-2 is out and it's 🔥 Here's what that means in plain terms. Dyna-2 was pre-trained on ONE MILLION hours of egocentric human video, 170 years of continuous human experience, cooking, folding, assembling, cleaning. And as that human data scaled, robot performance improved. Predictably. Monotonically. Across 39 tasks on two different robot embodiments the model had never seen. → 1,000 hours pre-training → 20% normalised task performance → 10,000 hours → 28% → 100,000 hours → 45% → 1,000,000 hours → 53% Human video exists at effectively unlimited scale. Every cook, every factory worker, every craftsperson wearing a camera is generating training data for future robots. But the finding that stunned even the researchers, world modeling is what makes the transfer work. A model trained to predict future video AND actions massively outperforms one trained on actions alone. Video is the new scaling axis for robotics. One more jaw-dropping data point. 13 minutes of teleoperation data was enough to fine-tune Dyna-2 to open a bottle cap using two five-fingered robot hands. The robots are coming, and they're learning from us directly :D Read more here: Congrats Jason Ma and team! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
1:35

JUST IN: Dyna Robotics just published one of the most important research papers in robotics this year. It could fundamentally change how robot foundation models are trained. A scaling law that transfers from human video to robot performance. Dyna-2 is out and it's 🔥 Here's what that means in plain terms. Dyna-2 was pre-trained on ONE MILLION hours of egocentric human video, 170 years of continuous human experience, cooking, folding, assembling, cleaning. And as that human data scaled, robot performance improved. Predictably. Monotonically. Across 39 tasks on two different robot embodiments the model had never seen. → 1,000 hours pre-training → 20% normalised task performance → 10,000 hours → 28% → 100,000 hours → 45% → 1,000,000 hours → 53% Human video exists at effectively unlimited scale. Every cook, every factory worker, every craftsperson wearing a camera is generating training data for future robots. But the finding that stunned even the researchers, world modeling is what makes the transfer work. A model trained to predict future video AND actions massively outperforms one trained on actions alone. Video is the new scaling axis for robotics. One more jaw-dropping data point. 13 minutes of teleoperation data was enough to fine-tune Dyna-2 to open a bottle cap using two five-fingered robot hands. The robots are coming, and they're learning from us directly :D Read more here: Congrats Jason Ma and team! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

23,556 Aufrufe • vor 18 Tagen

Not betting on robot barbers anytime soon… but home robots? Oh yeah! In 3 years, your Roomba’s gonna look like a fossil. We’re getting close to real day-to-day robotics like folding laundry, unloading the dishwasher. That’s the dream. More time for the things we care about.
0:36

Not betting on robot barbers anytime soon… but home robots? Oh yeah! In 3 years, your Roomba’s gonna look like a fossil. We’re getting close to real day-to-day robotics like folding laundry, unloading the dishwasher. That’s the dream. More time for the things we care about.

Alexis Ohanian 🗽

11,037 Aufrufe • vor 1 Jahr

At the 2026 World Robot Conference in Beijing, we met a cute crab-shaped robot which can dance, fetch and pass stuff, and even help you take selfies. #WorldRobotConference #Robotics #AI #FutureTech #WRC2026
0:23

At the 2026 World Robot Conference in Beijing, we met a cute crab-shaped robot which can dance, fetch and pass stuff, and even help you take selfies. #WorldRobotConference #Robotics #AI #FutureTech #WRC2026

China Xinhua News

16,853 Aufrufe • vor 9 Tagen

NEW JAKL - Looking for a compact .308 with a folding brace? We've got you. 😎 The JAKL-10 now in a 12.5in pistol! Drops this Friday, July 18th at 4:30pm ET. 🇺🇸
2:25

NEW JAKL - Looking for a compact .308 with a folding brace? We've got you. 😎 The JAKL-10 now in a 12.5in pistol! Drops this Friday, July 18th at 4:30pm ET. 🇺🇸

Palmetto State Armory

98,384 Aufrufe • vor 1 Jahr

Looking back I can't even comprehend how I was happy with the flight at all. We've come a long way! 🥹
0:45

Looking back I can't even comprehend how I was happy with the flight at all. We've come a long way! 🥹

Edenfall ➡ Wishlist on Steam!

60,980 Aufrufe • vor 8 Monaten

Today we are launching 100 early pre-orders for Mr. Tensors eyecandy robotics, an inexpensive opensource lifelike robot character that's cool enough toy for kids (and a human-robot-interaction + reinforcement learning research tool for academia and hobbyists). We are looking for parents and researchers to adopt our handmade cute little dinos! The early 100 people would more or less be our design partners and early supporters to help us manufacture, ship and iterate on the product experience.
1:32

Today we are launching 100 early pre-orders for Mr. Tensors eyecandy robotics, an inexpensive opensource lifelike robot character that's cool enough toy for kids (and a human-robot-interaction + reinforcement learning research tool for academia and hobbyists). We are looking for parents and researchers to adopt our handmade cute little dinos! The early 100 people would more or less be our design partners and early supporters to help us manufacture, ship and iterate on the product experience.

mansin

116,802 Aufrufe • vor 10 Monaten

We really have come a very long way. Just watch till the end 🔥
0:35

We really have come a very long way. Just watch till the end 🔥

Shimorekato

11,604 Aufrufe • vor 11 Monaten

It might not feel like it, Blackhawks fans, but we’ve come a long way since the early days of the rebuild. 😳
1:14

It might not feel like it, Blackhawks fans, but we’ve come a long way since the early days of the rebuild. 😳

CHGO Blackhawks

44,507 Aufrufe • vor 3 Monaten

I spent the last week in Beijing, first at world robot conference, then at the world humanoid robot games. It's very clear that China are way ahead of anyone else in Humanoid robotics, in every field, both complete robots and component supply chains. I had a fantastic time. I put together this short clip from the robot games. Full video coming soon.
1:28

I spent the last week in Beijing, first at world robot conference, then at the world humanoid robot games. It's very clear that China are way ahead of anyone else in Humanoid robotics, in every field, both complete robots and component supply chains. I had a fantastic time. I put together this short clip from the robot games. Full video coming soon.

Barrett

28,841 Aufrufe • vor 3 Tagen

This is the full video of the hardest version of the task: t-shirt folding from unstructured initial states. This setting really requires at least some strategy, since the robot first has to spread the shirt before it can complete the fold. Full details on data collection strategies in the blog below. 👇
1:37

This is the full video of the hardest version of the task: t-shirt folding from unstructured initial states. This setting really requires at least some strategy, since the robot first has to spread the shirt before it can complete the fold. Full details on data collection strategies in the blog below. 👇

LeRobot

53,936 Aufrufe • vor 4 Monaten