Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

We just released our work on robot soccer. I've been working on this for quite some time with my amazing colleagues at DeepMind. It's exciting how deep RL can produce such beautiful behaviors with low-cost robots. Full paper is available at Enjoy!

haarnoja's profile picture

Tuomas Haarnoja

3,753 subscribers

758,792 Aufrufe • vor 3 Jahren •via X (Twitter)

Wissenschaft & TechnologieNachrichten & PolitikBildung
LIVE

Anya Rossi• Live Now

Private livecam show

10 Kommentare

Profilbild von 🌱Simon🌱
🌱Simon🌱vor 3 Jahren

I never watch football, but I would pay a lot to watch a match between two robot teams.

Profilbild von Jouko Salonen
Jouko Salonenvor 3 Jahren

Congrats! btw, I'm gonna do grandchild babysitting the whole coming 1st of May weekend. Do you happen to have a full 90 min video of this?

Profilbild von Nicholas Horbaczewski
Nicholas Horbaczewskivor 3 Jahren

What, we’re just going to let that handball slide? The future of sports is robotic sports. Proud that @DroneRaceLeague is the first globally televised robotic sport.

Profilbild von Pieter Abbeel
Pieter Abbeelvor 3 Jahren

very nice work @haarnoja, and fun to watch!

Profilbild von Karol Hausman
Karol Hausmanvor 3 Jahren

Some of these behaviors are beautiful! Congrats Tuomas!

Profilbild von Bernhard Jaeger
Bernhard Jaegervor 3 Jahren

Very cute robots. Feels much like small kids playing soccer.

Profilbild von Nolan
Nolanvor 3 Jahren

I could dust both of these

Profilbild von Tony Hansmann
Tony Hansmannvor 3 Jahren

Wow! How low-cost?

Profilbild von Erwin Coumans 🇺🇦
Erwin Coumans 🇺🇦vor 3 Jahren

Very impressing on this low-cost hardware (Dynamixels?) @haarnoja , congrats!

Profilbild von Sélim
Sélimvor 3 Jahren

so cute!! .. and obviously impressive 🤯 @FloMaushart

Ähnliche Videos

Excited to share a new humanoid robot platform we’ve been working on. Berkeley Humanoid is a reliable and low-cost mid-scale research platform for learning-based control. We demonstrate the robot walking on various terrains and dynamic hopping with a simple RL controller.
0:49

Excited to share a new humanoid robot platform we’ve been working on. Berkeley Humanoid is a reliable and low-cost mid-scale research platform for learning-based control. We demonstrate the robot walking on various terrains and dynamic hopping with a simple RL controller.

Qiayuan Liao

80,436 Aufrufe • vor 1 Jahr

🚀Meet Gemini Diffusion, our first diffusion-based and super fast language model, just announced at Google I/O!🚀 Very excited to be able to share what I've been working on for the past little while with our amazing small team Google DeepMind.
0:32

🚀Meet Gemini Diffusion, our first diffusion-based and super fast language model, just announced at Google I/O!🚀 Very excited to be able to share what I've been working on for the past little while with our amazing small team Google DeepMind.

Ivana Balazevic

43,496 Aufrufe • vor 1 Jahr

Working on my board for tonights game and every time I look up I see this face! How can I focus on work with this face looking at me?!?
0:20

Working on my board for tonights game and every time I look up I see this face! How can I focus on work with this face looking at me?!?

Kirk Herbstreit

883,710 Aufrufe • vor 1 Jahr

It's been a rollercoaster with some high highs and low lows, but I've loved my time getting to work and pour my passion into Lost Ark. 9yrs at Amazon, 8 at Amazon Games. 4 Games launched. See you on the next journey. o7
2:18

It's been a rollercoaster with some high highs and low lows, but I've loved my time getting to work and pour my passion into Lost Ark. 9yrs at Amazon, 8 at Amazon Games. 4 Games launched. See you on the next journey. o7

HardcoreHenry

55,331 Aufrufe • vor 4 Monaten

Proud to share what I’ve been working on with my colleagues at Rhoda AI: Direct Video-Action Models (DVA). TL;DR: - We pre-train causal video models from scratch to control robots - They handle complex production tasks for hours without intervention - Only use ~10 hours of robot data How? 🧵👇
6:01

Proud to share what I’ve been working on with my colleagues at Rhoda AI: Direct Video-Action Models (DVA). TL;DR: - We pre-train causal video models from scratch to control robots - They handle complex production tasks for hours without intervention - Only use ~10 hours of robot data How? 🧵👇

Tongzhou Mu 🤖🦾🦿

19,102 Aufrufe • vor 4 Monaten

Meet Cabinet: Paper Clip + KB. for quite some time I've been thinking how LLMs are missing the knowledge base - where I can dump CSVs, PDFs, and most important - inline web app. running on Claude Code with agents with heartbeats and jobs
0:59

Meet Cabinet: Paper Clip + KB. for quite some time I've been thinking how LLMs are missing the knowledge base - where I can dump CSVs, PDFs, and most important - inline web app. running on Claude Code with agents with heartbeats and jobs

Hila Shmuel

495,920 Aufrufe • vor 3 Monaten

My weekend gift to you, my take on billie eilish’s “CHIHIRO” is now available for streaming on YouTube + SoundCloud only! I’ve been eager to share this with you for quite some time now 🙏🏿
7:38

My weekend gift to you, my take on billie eilish’s “CHIHIRO” is now available for streaming on YouTube + SoundCloud only! I’ve been eager to share this with you for quite some time now 🙏🏿

Black Coffee

62,799 Aufrufe • vor 1 Jahr

NEWS: DeepMind teaches robots to play soccer. In a paper released today Google's DeepMind details how they used Deep Reinforcement Learning (Deep RL) to train low-cost, miniature humanoid robots in dynamic environments, allowing them to play a simplified one-versus-one (1v1) soccer game. The robots, equipped with 20 actuated joints, were initially trained in simulation using the MuJoCo physics engine. Through this training, they learned robust and dynamic movement skills like rapid fall recovery, walking, turning, and kicking. The robots seamlessly transitioned between these skills, even surpassing expectations, and developed a basic strategic understanding of the game. During matches, the trained robots demonstrated agile skills such as turning, kicking moving balls, and dynamic defensive blocking. They quickly combined these skills, showcasing their adaptability and outperforming scripted baselines. The robots walked faster, got up quicker, and kicked faster than their counterparts. Individual skills were first trained in isolation within the simulation environment, and then composed in a self-play setting. The robots successfully transferred these skills to real-world scenarios. Full paper can be found here:
2:34

NEWS: DeepMind teaches robots to play soccer. In a paper released today Google's DeepMind details how they used Deep Reinforcement Learning (Deep RL) to train low-cost, miniature humanoid robots in dynamic environments, allowing them to play a simplified one-versus-one (1v1) soccer game. The robots, equipped with 20 actuated joints, were initially trained in simulation using the MuJoCo physics engine. Through this training, they learned robust and dynamic movement skills like rapid fall recovery, walking, turning, and kicking. The robots seamlessly transitioned between these skills, even surpassing expectations, and developed a basic strategic understanding of the game. During matches, the trained robots demonstrated agile skills such as turning, kicking moving balls, and dynamic defensive blocking. They quickly combined these skills, showcasing their adaptability and outperforming scripted baselines. The robots walked faster, got up quicker, and kicked faster than their counterparts. Individual skills were first trained in isolation within the simulation environment, and then composed in a self-play setting. The robots successfully transferred these skills to real-world scenarios. Full paper can be found here:

Dave Lee

372,039 Aufrufe • vor 3 Jahren

"A Bang at the Beach" a commission for: DaJester SFX pack: OpenNSFW A BIG commission I've been working on for quite some time now! I'm glad I can finally reveal it to you guys! 😚❤️❤️❤️ (✨HQ/download available through my bi0✨) #TheAmazingDigitalCircus #TADCEp7
1:12

"A Bang at the Beach" a commission for: DaJester SFX pack: OpenNSFW A BIG commission I've been working on for quite some time now! I'm glad I can finally reveal it to you guys! 😚❤️❤️❤️ (✨HQ/download available through my bi0✨) #TheAmazingDigitalCircus #TADCEp7

🔞✨Morado Arts✨(COMMS 3/5)

51,063 Aufrufe • vor 7 Monaten

Everyone can now train high-dimensional muscle agents with RL, as we just released our code! Come join me at the #MyoChallenge workshop tomorrow at 10:00 in room 354 at #NeurIPS2023 to see my poster. Code is here!
0:28

Everyone can now train high-dimensional muscle agents with RL, as we just released our code! Come join me at the #MyoChallenge workshop tomorrow at 10:00 in room 354 at #NeurIPS2023 to see my poster. Code is here!

Pierre Schumacher

159,528 Aufrufe • vor 2 Jahren

How can robots acquire fine-grained manipulation skills? Introducing ACT: Action Chunking with Transformers 🤖 Key idea: Imitation, but predict actions in chunks instead of one at a time. Here are results with only ~15min of demonstrations, running on low-cost arms:
0:40

How can robots acquire fine-grained manipulation skills? Introducing ACT: Action Chunking with Transformers 🤖 Key idea: Imitation, but predict actions in chunks instead of one at a time. Here are results with only ~15min of demonstrations, running on low-cost arms:

Tony Zhao

247,557 Aufrufe • vor 3 Jahren

I've been working on deformable object manipulation since my PhD. It was totally a nightmare years ago and my PhD advisor was telling me not to work on it for my own good. Today, at ByteDance Seed, we are dropping GR-RL, a new VLA+RL system that manages long-horizon precise dexterous manipulation of deformable objects. This is probably the first real-world RL system to make a robot: ✅ Lace up your shoes end to end ✅ Hit millimeter tolerance repeatedly ✅ Recover from mistakes (See video!) ✅ And complete continuous shoelace threading on a real bimanual platform 📈 Success rate: ↑ from 45.7% → 83.3% Yes, robots can now actually do this. Project page: ArXiv:
3:45

I've been working on deformable object manipulation since my PhD. It was totally a nightmare years ago and my PhD advisor was telling me not to work on it for my own good. Today, at ByteDance Seed, we are dropping GR-RL, a new VLA+RL system that manages long-horizon precise dexterous manipulation of deformable objects. This is probably the first real-world RL system to make a robot: ✅ Lace up your shoes end to end ✅ Hit millimeter tolerance repeatedly ✅ Recover from mistakes (See video!) ✅ And complete continuous shoelace threading on a real bimanual platform 📈 Success rate: ↑ from 45.7% → 83.3% Yes, robots can now actually do this. Project page: ArXiv:

Xiao Ma

109,573 Aufrufe • vor 7 Monaten

Rad New World☢️ [Dialogue System] This little project is something I've been tinkering with on and off for quite a while now — it's basically my love letter to some of my all-time favorite games: Fallout 1,2 & Tactics. Cheers!🫡
1:35

Rad New World☢️ [Dialogue System] This little project is something I've been tinkering with on and off for quite a while now — it's basically my love letter to some of my all-time favorite games: Fallout 1,2 & Tactics. Cheers!🫡

Frontline: Games Series

29,488 Aufrufe • vor 1 Monat

"RAD New World☢️" [Concept] This little project is something I've been tinkering with on and off for quite a while now — it's basically my love letter to some of my all-time favorite games: Fallout 1,2 & Tactics. Cheers!🫡
1:19

"RAD New World☢️" [Concept] This little project is something I've been tinkering with on and off for quite a while now — it's basically my love letter to some of my all-time favorite games: Fallout 1,2 & Tactics. Cheers!🫡

Frontline: Games Series

32,325 Aufrufe • vor 4 Monaten

Really excited to share what I've been working on with my colleagues at Physical Intelligence! We've developed a prototype robotic foundation model that can fold laundry, assemble a box, bus a table, and many other things. We've written a paper and blog post about it. 🧵👇
5:10

Really excited to share what I've been working on with my colleagues at Physical Intelligence! We've developed a prototype robotic foundation model that can fold laundry, assemble a box, bus a table, and many other things. We've written a paper and blog post about it. 🧵👇

Sergey Levine

114,997 Aufrufe • vor 1 Jahr

I have Post-Doc, PhD, and Research Assistant positions available, for a new project working with me on dexterous robot learning! Come and join me, my team, and our robots, at Imperial College London! 🤖🧑‍💻🇬🇧💂🤖 See for more info. Please share/retweet!
0:32

I have Post-Doc, PhD, and Research Assistant positions available, for a new project working with me on dexterous robot learning! Come and join me, my team, and our robots, at Imperial College London! 🤖🧑‍💻🇬🇧💂🤖 See for more info. Please share/retweet!

Edward Johns

25,053 Aufrufe • vor 1 Jahr

Excited to finally share Generative Value Learning (GVL), my Google DeepMind project on extracting universal value functions from long-context VLMs via in-context learning! We discovered a simple method to generate zero-shot and few-shot values for 300+ robot tasks and 50+ datasets using SOTA VLMs like Gemini (Try out the demo on our website on your robot video today!) I worked a lot on leveraging foundation models as guidance for robots in my PhD, and to me, this result forges a new frontier in how we can use foundation models for robot learning, given its broad applicability independent of embodiment and task types. Quite excited about how we can build on this work as a community!
0:32

Excited to finally share Generative Value Learning (GVL), my Google DeepMind project on extracting universal value functions from long-context VLMs via in-context learning! We discovered a simple method to generate zero-shot and few-shot values for 300+ robot tasks and 50+ datasets using SOTA VLMs like Gemini (Try out the demo on our website on your robot video today!) I worked a lot on leveraging foundation models as guidance for robots in my PhD, and to me, this result forges a new frontier in how we can use foundation models for robot learning, given its broad applicability independent of embodiment and task types. Quite excited about how we can build on this work as a community!

Jason Ma

98,090 Aufrufe • vor 1 Jahr

So happy to finally share something I've been working on for some time. I'm releasing a new low level programming fundamentals course! It's called "The Simple Joy Of Programming", and you can find out more in this video:
12:03

So happy to finally share something I've been working on for some time. I'm releasing a new low level programming fundamentals course! It's called "The Simple Joy Of Programming", and you can find out more in this video:

Nic Barker

59,201 Aufrufe • vor 11 Monaten

As we wrap up the appropriations process & with it my time on House Appropriations Democrats, I shared my gratitude for serving on this powerful committee and all I’ve been able to accomplish. It’s been an honor to work with my colleagues on both sides of the aisle to benefit our kids & families.
3:47

As we wrap up the appropriations process & with it my time on House Appropriations Democrats, I shared my gratitude for serving on this powerful committee and all I’ve been able to accomplish. It’s been an honor to work with my colleagues on both sides of the aisle to benefit our kids & families.

Rep. Jennifer Wexton

20,648 Aufrufe • vor 2 Jahren