Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Using reinforcement learning we have expanded the range of techniques the Ultra Mobile Vehicle (UMV) uses to handle terrain and obstacles, including hops, out-of-plane balance, and level-ground flips. Millions of physics-based simulations provide training data to support zero-shot transfers.

RAI Institute

8,419 subscribers

75,272 görüntüleme • 1 yıl önce •via X (Twitter)

Bilim & Teknoloji Oyun Eğitim

Anya Rossi• Live Now

Private livecam show

17 Yorum

RAI Institute profil fotoğrafı

RAI Institute1 yıl önce

Learn more about how we’re building and training UMV:

GrayWolf448 profil fotoğrafı

GrayWolf4481 yıl önce

Can you guys build the torment nexus next?

Master Kenobi profil fotoğrafı

Master Kenobi1 yıl önce

Hey @danny_macaskill 😉

Dan Calle profil fotoğrafı

Dan Calle1 yıl önce

Oof. Ok. Amazing tech, and all I can think of are @itsDanielSuarez's razorbacks.

Harshith profil fotoğrafı

Harshith1 yıl önce

@steveMmattison Wtf is this...

Crypto profil fotoğrafı

Crypto1 yıl önce

in robots ko car ko drift karne se rokna hai bass..arrre tu robot hai sidhe bhaag bhai..cycle kyun chala rha hai.

NINJA RANGER profil fotoğrafı

NINJA RANGER1 yıl önce

so where can you mount the gatling gun on?

Boris profil fotoğrafı

Boris1 yıl önce

Terminator...

Chi Tinh Mai profil fotoğrafı

Chi Tinh Mai1 yıl önce

That UMV sounds like it’s ready for the next season of “Extreme Terrain Challenge”!

Monocle Optical Labs . . 👊🏾`.') profil fotoğrafı

Monocle Optical Labs . . 👊🏾`.')10 ay önce

RAD ✌🏾😎

Raul Verdusco profil fotoğrafı

Raul Verdusco1 yıl önce

Reinforcement learning continues to unlock incredible capabilities for mobile robotics! ⚡🤖 Training UMVs through millions of physics-based simulations enables zero-shot transfers — giving robots advanced techniques like hops, flips, and out-of-plane balance for real-world terrain. 🌍🦾 A strong step forward in creating more adaptable, resilient, and versatile robotic platforms. 🚀🔧 #Robotics #ReinforcementLearning #AI #Automation #Engineering #Innovation #SmartTechnology #FutureOfWork

iRiSh profil fotoğrafı

iRiSh1 yıl önce

What are you doing ? Who needs this ? I'm sorry but we all learned from Arc Raiders that the answer is an A.I trained giant 6 legged spider-crab with lasers for a mouth ... stop wasting time. And Yes ... I am available to hire for more great ideas like this.

euno profil fotoğrafı

euno1 yıl önce

Most people cannot do that, neither can they ride on one wheel.

Rough profil fotoğrafı

Rough1 yıl önce

bonkers

advocAIdo profil fotoğrafı

advocAIdo1 yıl önce

Just add training wheels, but I guess that will kill the cool factor.

arie moby profil fotoğrafı

arie moby1 yıl önce

You also show the failure. Such honesty is not in China.

Roger Goll profil fotoğrafı

Roger Goll1 yıl önce

But seriously: Great project! Huge military and commercial potential. The market will change significantly in the coming years.

Benzer Videolar

Reinforcement learning is used to speed the production of behavior for the Boston Dynamics Atlas humanoid robot. At the heart of the learning process is a physics-based simulator that generates training data for a variety of maneuvers.

Reinforcement learning is used to speed the production of behavior for the Boston Dynamics Atlas humanoid robot. At the heart of the learning process is a physics-based simulator that generates training data for a variety of maneuvers.

RAI Institute

76,751 görüntüleme • 1 yıl önce

Soccer players have to master a range of dynamic skills, from turning and kicking to chasing a ball. How could robots do the same? ⚽ We trained our AI agents to demonstrate a range of agile behaviors using reinforcement learning. Here’s how. 🧵

Soccer players have to master a range of dynamic skills, from turning and kicking to chasing a ball. How could robots do the same? ⚽ We trained our AI agents to demonstrate a range of agile behaviors using reinforcement learning. Here’s how. 🧵

Google DeepMind

448,145 görüntüleme • 2 yıl önce

Robots can now walk blind with Figure AI's Helix Walking Controller. Instead of using cameras, the controller relies on the robot's internal sensors and reinforcement learning to maintain balance while walking. The controller, unveiled last year, allows the robot to stay balanced, recover from pushes, and move confidently across difficult terrain.

Robots can now walk blind with Figure AI's Helix Walking Controller. Instead of using cameras, the controller relies on the robot's internal sensors and reinforcement learning to maintain balance while walking. The controller, unveiled last year, allows the robot to stay balanced, recover from pushes, and move confidently across difficult terrain.

Space and Technology

28,904 görüntüleme • 3 ay önce

Robot policies must be both reliable and highly capable to be useful; the best way to achieve this level of performance is with reinforcement learning. However, for reinforcement learning you are usually stuck between two difficult options: reinforcement in the real world is often risky and expensive, while reinforcement learning in a traditional simulator takes a lot of engineering work and has a persistent sim-to-real gap. What if instead you could train your robot purely in a world model? RISE by Jiazhi Yang et al. uses a compositional world model to predict the future and evaluate progress. This allows for a self-improving pipeline, which learns a world model from real data and then learns how the robot should perform different tasks. This pipeline results in a data-driven way to improve policy performance from real data but without real-world reinforcement learning. Watch Episode #86 of RoboPapers, with Chris Paxton and Jiafei Duan, to learn more!

Robot policies must be both reliable and highly capable to be useful; the best way to achieve this level of performance is with reinforcement learning. However, for reinforcement learning you are usually stuck between two difficult options: reinforcement in the real world is often risky and expensive, while reinforcement learning in a traditional simulator takes a lot of engineering work and has a persistent sim-to-real gap. What if instead you could train your robot purely in a world model? RISE by Jiazhi Yang et al. uses a compositional world model to predict the future and evaluate progress. This allows for a self-improving pipeline, which learns a world model from real data and then learns how the robot should perform different tasks. This pipeline results in a data-driven way to improve policy performance from real data but without real-world reinforcement learning. Watch Episode #86 of RoboPapers, with Chris Paxton and Jiafei Duan, to learn more!

RoboPapers

38,867 görüntüleme • 4 ay önce

Zero-shot navigation of complex terrain. The true advantages of humanoid robots are their ability to work in the true difficulty of human environments. All using onboard sensing and compute. Take a look ->

Zero-shot navigation of complex terrain. The true advantages of humanoid robots are their ability to work in the true difficulty of human environments. All using onboard sensing and compute. Take a look ->

Chris Paxton

10,945 görüntüleme • 1 ay önce

Helix is now learning directly from human video data We have already trained on data collected in the real world, including Brookfield residential units To our knowledge, this is the first instance of a humanoid robot learning navigation end-to-end using only human video

Helix is now learning directly from human video data We have already trained on data collected in the real world, including Brookfield residential units To our knowledge, this is the first instance of a humanoid robot learning navigation end-to-end using only human video

Figure

46,041 görüntüleme • 1 yıl önce

Simulating entry… Using our LAVA software, Ames engineers performed simulations of a conceptual Mars spacecraft during entry. Here, the vehicle travels at supersonic speed (Mach 2.4) and uses retro-propulsion to decelerate further.

Simulating entry… Using our LAVA software, Ames engineers performed simulations of a conceptual Mars spacecraft during entry. Here, the vehicle travels at supersonic speed (Mach 2.4) and uses retro-propulsion to decelerate further.

NASA Ames

80,321 görüntüleme • 2 ay önce

👋 Wonderful to meet the community of Barking this morning! The King and Queen visited the Barking Learning Centre Community and Family Hub. This community-based learning facility houses Barking Library and brings together a range of council services, and local groups. 💬 Their Majesties spent time with families and staff, who work at the centre to provide advice on employment, support those who are homeless, and encourage reading in the library.

👋 Wonderful to meet the community of Barking this morning! The King and Queen visited the Barking Learning Centre Community and Family Hub. This community-based learning facility houses Barking Library and brings together a range of council services, and local groups. 💬 Their Majesties spent time with families and staff, who work at the centre to provide advice on employment, support those who are homeless, and encourage reading in the library.

The Royal Family

79,483 görüntüleme • 8 ay önce

We open-sourced all components of the HTD whole-body controller (WBC): -Play our WBC on your browser: -Main HTD codebase entry: (data collection and HTD policy soon!) Highlighted features: -Lightweight decoupled WBC that can be trained on a single GPU -A stable control base for humanoid loco-manipulation (in a mobile-manipulation style) -Support a wide range of body poses including extreme ones -Isaac Sim/Lab training, zero-shot deployment

We open-sourced all components of the HTD whole-body controller (WBC): -Play our WBC on your browser: -Main HTD codebase entry: (data collection and HTD policy soon!) Highlighted features: -Lightweight decoupled WBC that can be trained on a single GPU -A stable control base for humanoid loco-manipulation (in a mobile-manipulation style) -Support a wide range of body poses including extreme ones -Isaac Sim/Lab training, zero-shot deployment

Yaru Niu

23,076 görüntüleme • 1 ay önce

We own 24 million users and 1 billion refined data records, and we plan to provide this data free of charge to all AI startup companies for one month. Meet Data Hedge now the most powerful LLM user-based data layer.

We own 24 million users and 1 billion refined data records, and we plan to provide this data free of charge to all AI startup companies for one month. Meet Data Hedge now the most powerful LLM user-based data layer.

DATAHEDGE

140,263 görüntüleme • 4 ay önce

We support over 5.9 million Palestine Refugees. 30,000 of us do this. Day in, day out. We do it in: 📍Jordan 📍The Gaza Strip 📍The occupied West Bank, including East Jerusalem 📍Syria 📍Lebanon We are uniquely able to provide healthcare, learning, and more. Support UNRWA. Support Palestine Refugees. #UNRWAworks

We support over 5.9 million Palestine Refugees. 30,000 of us do this. Day in, day out. We do it in: 📍Jordan 📍The Gaza Strip 📍The occupied West Bank, including East Jerusalem 📍Syria 📍Lebanon We are uniquely able to provide healthcare, learning, and more. Support UNRWA. Support Palestine Refugees. #UNRWAworks

UNRWA

20,849 görüntüleme • 8 ay önce

Trump: "We send hundreds of millions of gallons of water a day to the Pacific Ocean. They turn a valve and the valve heads out. And we turned the valve back. I actually had to do it using force. We turned the valve back and now they have water."

Trump: "We send hundreds of millions of gallons of water a day to the Pacific Ocean. They turn a valve and the valve heads out. And we turned the valve back. I actually had to do it using force. We turned the valve back and now they have water."

Aaron Rupar

2,703,236 görüntüleme • 1 yıl önce

#webgi engine is revolutionizing the world of real time jewellery rendering! Using cutting-edge physics-based simulations, we can now create stunning virtual jewellery with jaw-dropping realism. Prepare to be mesmerized by the sparkle and shine! 💍✨ #PhysicsSimulation #JewelleryInnovation #threejs #webgl

#webgi engine is revolutionizing the world of real time jewellery rendering! Using cutting-edge physics-based simulations, we can now create stunning virtual jewellery with jaw-dropping realism. Prepare to be mesmerized by the sparkle and shine! 💍✨ #PhysicsSimulation #JewelleryInnovation #threejs #webgl

iJewel3D (Pixotronics)

15,756 görüntüleme • 3 yıl önce

CHECK THIS OUT… How to lift millions of children out of poverty and aid middle-class families with the cost of raising kids: Kamala Harris’s plan to provide a $6,000 tax credit for parents of newborns as well as bringing back the pandemic-era expanded Child Tax Credit.

CHECK THIS OUT… How to lift millions of children out of poverty and aid middle-class families with the cost of raising kids: Kamala Harris’s plan to provide a $6,000 tax credit for parents of newborns as well as bringing back the pandemic-era expanded Child Tax Credit.

Christopher Webb

143,143 görüntüleme • 2 yıl önce