正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Miniature humanoid robots master a simplified soccer game using Deep Reinforcement Learning, showcasing surprising agility, quick fall recovery, and strategic understanding of the game. #engineering

Interesting Engineering

314,732 subscribers

75,943 次观看 • 3 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 条评论

drlewtz 的头像

drlewtz3 年前

The machines will remember this...

Soccer Bot™ 的头像

Soccer Bot™1 年前

Experience the bot completely reimagined. 🌟 A completely new design, reminders for match prediction, notifications when games are interrupted, continued or postponed. New commands like /features and /standings and new languages and much more.

Russell Irion 的头像

Russell Irion3 年前

Already flopping?!

alberto benarroch 的头像

alberto benarroch3 年前

Amazing

My name is M. Only M 的头像

My name is M. Only M3 年前

Con empujarlo una vez alcanzaba, cuando crezca, sea semáforo, la reconozca y no le de luz verde que no se queje.. Y mejor que no forme su propio partido y gane las elecciones xq..

Wagner Paiva Fernandes (Tesla is CHOAM) 的头像

Wagner Paiva Fernandes (Tesla is CHOAM)3 年前

@BenShead1 So cruel.

Tempered 的头像

Tempered3 年前

Computers never forget. On day that lil mufker is going to upload itself into a drone and kill every tech who ever pushed it around.

N.Delgado 的头像

N.Delgado3 年前

Hate that b.t.c.h 😡

Huanchi X 的头像

Huanchi X3 年前

Estamos a un paso de los T800 😱😱😱

AngelTyrael 的头像

AngelTyrael3 年前

can you stop pushing him? first 3 times i get it , it learned to get up but 6 times later it was fucking annoying

相关视频

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:

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

293,339 次观看 • 3 年前

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:

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 次观看 • 3 年前

DeepMind training bipedal robots to play soccer using deep reinforcement learning.

DeepMind training bipedal robots to play soccer using deep reinforcement learning.

MachinePix

16,986,259 次观看 • 2 年前

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

447,662 次观看 • 2 年前

The AMO (Adaptive Motion Optimization) project, developed by researchers at UC San Diego, introduces a novel framework for enhancing the dexterity and adaptability of humanoid robots. This system integrates simulation-to-real reinforcement learning with trajectory optimization to achieve real-time, adaptive whole-body control Video Credit: USD #engineering #technology #robotics #robots

The AMO (Adaptive Motion Optimization) project, developed by researchers at UC San Diego, introduces a novel framework for enhancing the dexterity and adaptability of humanoid robots. This system integrates simulation-to-real reinforcement learning with trajectory optimization to achieve real-time, adaptive whole-body control Video Credit: USD #engineering #technology #robotics #robots

Wevolver

13,632 次观看 • 1 年前

Our CoRL 2024 paper shows Reinforcement Learning can allow robots to learn skills via real-world practice, without any demonstrations or simulation engineering. Rewards are provided using language/vision models, and mobility of robots enables autonomous exploration. 1/N

Our CoRL 2024 paper shows Reinforcement Learning can allow robots to learn skills via real-world practice, without any demonstrations or simulation engineering. Rewards are provided using language/vision models, and mobility of robots enables autonomous exploration. 1/N

Russell Mendonca

38,454 次观看 • 1 年前

TWIST: a real-time teleoperation system for humanoid robots to mimic whole-body motions. Reference motion data is generated by retargeting human motion-capture data to the robot. Then, the controller is trained in simulation using reinforcement learning and behavior cloning.

TWIST: a real-time teleoperation system for humanoid robots to mimic whole-body motions. Reference motion data is generated by retargeting human motion-capture data to the robot. Then, the controller is trained in simulation using reinforcement learning and behavior cloning.

The Humanoid Hub

46,715 次观看 • 1 年前

A fast-paced compilation of humanoid robots failing, falling, and occasionally surprising with real athletic progress

A fast-paced compilation of humanoid robots failing, falling, and occasionally surprising with real athletic progress

Massimo

75,999 次观看 • 5 个月前

I trained a humanoid robot to play famous anime openings on the piano with reinforcement learning (Attack on Titan, Evangelion, SAO, and more) how I did it + surprising discoveries in thread🧵

I trained a humanoid robot to play famous anime openings on the piano with reinforcement learning (Attack on Titan, Evangelion, SAO, and more) how I did it + surprising discoveries in thread🧵

anandmaj

24,589 次观看 • 1 年前

When will a team of robots be able to beat a professional soccer team in the game of soccer? 🤔 Many in robotics have thought that it would take at least 15-20 years for robots to reach that point. But today 60 Minutes showed some of Google Deep Mind's work on robots playing soccer. Robots are using neural nets to learn how to walk, kick and play soccer, and they're improving very rapidly. It might be a lot sooner than most people think before we have robots able to beat professional athletes at their own sports.

When will a team of robots be able to beat a professional soccer team in the game of soccer? 🤔 Many in robotics have thought that it would take at least 15-20 years for robots to reach that point. But today 60 Minutes showed some of Google Deep Mind's work on robots playing soccer. Robots are using neural nets to learn how to walk, kick and play soccer, and they're improving very rapidly. It might be a lot sooner than most people think before we have robots able to beat professional athletes at their own sports.

Dave Lee

177,070 次观看 • 3 年前

robot named CyberRunner, developed by researchers at ETH Zurich, which uses Al and model-based reinforcement learning to master the classic Labyrinth board game in just six hours

robot named CyberRunner, developed by researchers at ETH Zurich, which uses Al and model-based reinforcement learning to master the classic Labyrinth board game in just six hours

Science girl

120,161 次观看 • 10 个月前

What if we could teach an AI to master the strategic game of 2048 through pure reinforcement learning? I did exactly that with "Agent 2048" - fine-tuning Qwen 7B model using GRPO to develop spatial reasoning and merge strategies with zero prior gameplay SFTdata! Thanks to Hugging Face and Unsloth AI for their easy to use implementation kalomaze and will brown you might like this :)

What if we could teach an AI to master the strategic game of 2048 through pure reinforcement learning? I did exactly that with "Agent 2048" - fine-tuning Qwen 7B model using GRPO to develop spatial reasoning and merge strategies with zero prior gameplay SFTdata! Thanks to Hugging Face and Unsloth AI for their easy to use implementation kalomaze and will brown you might like this :)

Hrishbh Dalal

31,856 次观看 • 1 年前

The Self-Manufacturing Future: Humanoid #Robots Building Robots by Tuo Liu #Robotics #Engineering #ArtificialIntelligence #Innovation #Technology

The Self-Manufacturing Future: Humanoid #Robots Building Robots by Tuo Liu #Robotics #Engineering #ArtificialIntelligence #Innovation #Technology

Ronald van Loon

35,485 次观看 • 6 个月前

Miniature 3-axis robotic arm A short demonstration of a miniature 3-axis robotic arm using ultra-precise Harmonic Drive gearheads, high-performance brushless motors, high-resolution absolute encoders, and integrated controllers. Video Credit: Oleksandr Stepanenko #engineering #technology #robots #robotics -------------------------------- Stay ahead of the curve! Follow us now on our WhatsApp ( and Telegram ( channels and stay updated about the cutting edge.

Miniature 3-axis robotic arm A short demonstration of a miniature 3-axis robotic arm using ultra-precise Harmonic Drive gearheads, high-performance brushless motors, high-resolution absolute encoders, and integrated controllers. Video Credit: Oleksandr Stepanenko #engineering #technology #robots #robotics -------------------------------- Stay ahead of the curve! Follow us now on our WhatsApp ( and Telegram ( channels and stay updated about the cutting edge.

Wevolver

15,371 次观看 • 11 个月前

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

76,576 次观看 • 1 年前

🎮 React Three Game on Three.js Resources Learn how to build 3D games using React Three Fiber and #threejs. A great starting point for understanding game logic, interactivity, and real-time 3D on the web. 👉 #threejs #WebGL #GameDev #ReactThreeFiber #3D #Learning

🎮 React Three Game on Three.js Resources Learn how to build 3D games using React Three Fiber and #threejs. A great starting point for understanding game logic, interactivity, and real-time 3D on the web. 👉 #threejs #WebGL #GameDev #ReactThreeFiber #3D #Learning

Three.js Resources

15,838 次观看 • 5 个月前

Love this scene, a perfect combination of Phoebe using her agility, and Piper using quick responses with both of her powers #Charmed

Love this scene, a perfect combination of Phoebe using her agility, and Piper using quick responses with both of her powers #Charmed

Charmed fan

16,476 次观看 • 2 年前

The rate Chinese humanoid robots are evolving is faster than most people think. This is Unitree's robots at 2026 Chinese Spring Festival Gala Dozens of G1 robots, in the world’s 1st fully autonomous humanoid robot cluster Kung Fu show. Quick movement showcasing its motion limits. H2 showed up at both the Beijing main venue and the Yiwu sub-venue, dressed in the Monkey King’s heavy armor and riding a “somersault cloud” acted by B2W robot dogs.

The rate Chinese humanoid robots are evolving is faster than most people think. This is Unitree's robots at 2026 Chinese Spring Festival Gala Dozens of G1 robots, in the world’s 1st fully autonomous humanoid robot cluster Kung Fu show. Quick movement showcasing its motion limits. H2 showed up at both the Beijing main venue and the Yiwu sub-venue, dressed in the Monkey King’s heavy armor and riding a “somersault cloud” acted by B2W robot dogs.

Rohan Paul

169,133 次观看 • 4 个月前