Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Introducing P1: the cutest and toughest bipedal robot mastering AI reinforcement learning to conquer wild terrains while shrugging off kicks and sticks! 🤖

IntEngineering's profile picture

Interesting Engineering

317,772 subscribers

22,058 görüntüleme • 2 yıl önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

6 Yorum

Prof Guillermo Rein. 🔥🛡️🎓🇪🇸🇬🇧 profil fotoğrafı
Prof Guillermo Rein. 🔥🛡️🎓🇪🇸🇬🇧2 yıl önce

So similar to the All Terrain Scout Transport (AT-ST) of Star Wars.

NICE profil fotoğrafı
NICE1 yıl önce

Stay competitive by balancing cutting-edge AI with automation tools. Forrester shows how.

Deeptanshu Kumar Behera profil fotoğrafı
Deeptanshu Kumar Behera2 yıl önce

One day he will take revenge 😂

another Grunt profil fotoğrafı
another Grunt2 yıl önce

@RiqueCzar

Wuangjah profil fotoğrafı
Wuangjah2 yıl önce

BD-1 is cuter

jackhuang profil fotoğrafı
jackhuang2 yıl önce

Did you know that 95% of companies like yours struggle to find a truly suitable brushless DC motor during the product development process?

Benzer Videolar

LimX Dynamics P1 is a versatile bipedal robot equipped with reinforcement learning capabilities, enabling it to master challenging terrains such as forests and ditches while maintaining its balance.
0:45

LimX Dynamics P1 is a versatile bipedal robot equipped with reinforcement learning capabilities, enabling it to master challenging terrains such as forests and ditches while maintaining its balance.

Science girl

3,295,511 görüntüleme • 2 yıl önce

Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning investigated the application of Deep Reinforcement Learning (Deep RL) for low-cost, miniature humanoid hardware in a dynamic environment, showing the method can synthesize sophisticated and safe movement skills making up complex behavioral strategies in a simplified one-versus-one (1v1) soccer game abs: project page:
4:28

Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning investigated the application of Deep Reinforcement Learning (Deep RL) for low-cost, miniature humanoid hardware in a dynamic environment, showing the method can synthesize sophisticated and safe movement skills making up complex behavioral strategies in a simplified one-versus-one (1v1) soccer game abs: project page:

AK

293,474 görüntüleme • 3 yıl önce

🤖 Introducing the future of cleanliness: an artificial intelligence-assisted cleaning robot! Wave goodbye to tedious chores and let cutting-edge AI technology handle the mess #FutureOfWork #AI
0:59

🤖 Introducing the future of cleanliness: an artificial intelligence-assisted cleaning robot! Wave goodbye to tedious chores and let cutting-edge AI technology handle the mess #FutureOfWork #AI

Evan Kirstel #B2B #TechFluencer

177,550 görüntüleme • 3 yıl önce

🔥Exciting news 🤖 Our latest research by David Hoeller, Nikita Rudin, Eris in Science Robotics unlocks new achievements: Unprecedented agility in quadrupedal robots, mastering locomotion, navigation, and perception through deep reinforcement learning! NVIDIA Robotics
0:25

🔥Exciting news 🤖 Our latest research by David Hoeller, Nikita Rudin, Eris in Science Robotics unlocks new achievements: Unprecedented agility in quadrupedal robots, mastering locomotion, navigation, and perception through deep reinforcement learning! NVIDIA Robotics

Robotic Systems Lab

171,975 görüntüleme • 2 yıl 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!
53:45

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

38,772 görüntüleme • 3 ay önce

Patria TRACKX is the ultimate tracked all-terrain vehicle, designed to conquer the most challenging environments with ease. It is engineered to navigate the toughest terrains silently and swiftly, ensuring smooth operations in any conditions.
2:33

Patria TRACKX is the ultimate tracked all-terrain vehicle, designed to conquer the most challenging environments with ease. It is engineered to navigate the toughest terrains silently and swiftly, ensuring smooth operations in any conditions.

Patria Group

3,025,752 görüntüleme • 2 ay önce

✨ Introducing Keypoint Action Tokens. 🤖 We translate visual observations and robot actions into a "language" that off-the-shelf LLMs can ingest and output. This transforms LLMs into *in-context, low-level imitation learning machines*. 🚀 Let me explain. 👇🧵
0:25

✨ Introducing Keypoint Action Tokens. 🤖 We translate visual observations and robot actions into a "language" that off-the-shelf LLMs can ingest and output. This transforms LLMs into *in-context, low-level imitation learning machines*. 🚀 Let me explain. 👇🧵

Norman Di Palo

23,097 görüntüleme • 2 yıl önce

Introducing 𝗥𝗼𝗯𝗼𝗣𝗶𝗮𝗻𝗶𝘀𝘁 🎹🤖, a new benchmark for high-dimensional robot control! Solving it requires mastering the piano with two anthropomorphic hands. This has been one year in the making, and I couldn’t be happier to release it today! Some highlights below:
1:20

Introducing 𝗥𝗼𝗯𝗼𝗣𝗶𝗮𝗻𝗶𝘀𝘁 🎹🤖, a new benchmark for high-dimensional robot control! Solving it requires mastering the piano with two anthropomorphic hands. This has been one year in the making, and I couldn’t be happier to release it today! Some highlights below:

Kevin Zakka

259,990 görüntüleme • 3 yıl önce

Introducing Cyber Syndicate, an NFT project designed to conquer the Metaverse! 🏆 Join our Discord and stay up-to-date with war plans. 💫 🤖
0:29

Introducing Cyber Syndicate, an NFT project designed to conquer the Metaverse! 🏆 Join our Discord and stay up-to-date with war plans. 💫 🤖

Cyber Syndicate VX

1,257,816 görüntüleme • 3 yıl önce

Youtuber Basically Homeless built a RoBot using a Cheat to play CS2 🤖 * Undetectable by a Kernel-Level Anti-Cheat and AI Learning Model 🔎 Mr. Homeless
1:25

Youtuber Basically Homeless built a RoBot using a Cheat to play CS2 🤖 * Undetectable by a Kernel-Level Anti-Cheat and AI Learning Model 🔎 Mr. Homeless

CS2 Vaccoin

365,831 görüntüleme • 1 yıl önce

Introducing RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning. 7 real robot tasks, 900/900 successes. Up to 250 consecutive trials in one task, running 2 hours nonstop without failure. High success rate against physical disturbances, zero-shot, and few-shot adaptation Our first step toward a deployable robot learning system.
3:26

Introducing RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning. 7 real robot tasks, 900/900 successes. Up to 250 consecutive trials in one task, running 2 hours nonstop without failure. High success rate against physical disturbances, zero-shot, and few-shot adaptation Our first step toward a deployable robot learning system.

Kun Lei

92,064 görüntüleme • 11 ay önce

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

64,784 görüntüleme • 11 ay önce

Across the toughest terrains, we deliver the mobility, protection and precision needed to keep missions moving forward.
0:24

Across the toughest terrains, we deliver the mobility, protection and precision needed to keep missions moving forward.

EDGE

106,036 görüntüleme • 1 ay önce

After Xiao Wu, meet Xiao Liu. 🤖 Tencent Robotics X’s latest robot isn’t just learning massage moves. It’s learning the touch behind them — where to press and exactly how hard. A custom data system captures vision, touch, and force from human demonstrations. Using reinforcement learning, Xiao Liu learns to reproduce both the trajectory and the pressure. Getting to the right spot is one thing. Getting the pressure right is another. My shoulders volunteer as tribute.
2:12

After Xiao Wu, meet Xiao Liu. 🤖 Tencent Robotics X’s latest robot isn’t just learning massage moves. It’s learning the touch behind them — where to press and exactly how hard. A custom data system captures vision, touch, and force from human demonstrations. Using reinforcement learning, Xiao Liu learns to reproduce both the trajectory and the pressure. Getting to the right spot is one thing. Getting the pressure right is another. My shoulders volunteer as tribute.

RoboHub🤖

15,397 görüntüleme • 2 ay önce

1/3 Introducing SWOT AI's advanced platform that uses AI to provide comprehensive SWOT analysis tailored specifically for Web3 projects. Features: 🤖Tailored Analysis: Customized SWOT analysis for each Web3 project, based on their specific goals, objectives, and characteristics. 🤖AI-Powered Insights: SWOT AI uses advanced AI techniques, such as natural language processing, machine learning, and deep learning, to generate real-time, data-driven insights for Web3 projects. 🤖Strategic Decision Support: SWOT AI equips Web3 projects with the strategic clarity and guidance necessary to make informed and effective decisions.
0:49

1/3 Introducing SWOT AI's advanced platform that uses AI to provide comprehensive SWOT analysis tailored specifically for Web3 projects. Features: 🤖Tailored Analysis: Customized SWOT analysis for each Web3 project, based on their specific goals, objectives, and characteristics. 🤖AI-Powered Insights: SWOT AI uses advanced AI techniques, such as natural language processing, machine learning, and deep learning, to generate real-time, data-driven insights for Web3 projects. 🤖Strategic Decision Support: SWOT AI equips Web3 projects with the strategic clarity and guidance necessary to make informed and effective decisions.

SWOT AI

14,278 görüntüleme • 2 yıl önce

Frontier models that use reasoning to "think" during inference are generating 5X more AI tokens per year. ✨ "Inference is now a thinking process. And in order to teach AI how to think, reinforcement learning and very significant computation was introduced into post-training," said NVIDIA CEO Jensen Huang in a recent keynote at #CES2026. Reinforcement learning is increasing computation demands across all AI scaling laws: pre-training, post-training, and test-time scaling. Learn more about reinforcement learning and AI scaling ➡️
0:58

Frontier models that use reasoning to "think" during inference are generating 5X more AI tokens per year. ✨ "Inference is now a thinking process. And in order to teach AI how to think, reinforcement learning and very significant computation was introduced into post-training," said NVIDIA CEO Jensen Huang in a recent keynote at #CES2026. Reinforcement learning is increasing computation demands across all AI scaling laws: pre-training, post-training, and test-time scaling. Learn more about reinforcement learning and AI scaling ➡️

NVIDIA AI Infrastructure

13,329 görüntüleme • 8 ay önce