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。

With RL, the robot can learn very precise tasks, like fastening a zip tie, and can actually do it more consistently and more quickly than even human teleoperation.

Physical Intelligence

45,643 subscribers

17,073 次观看 • 4 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Our model can now learn from its own experience with RL! Our new π*0.6 model can more than double throughput over a base model trained without RL, and can perform real-world tasks: making espresso drinks, folding diverse laundry, and assembling boxes. More in the thread below.

Our model can now learn from its own experience with RL! Our new π*0.6 model can more than double throughput over a base model trained without RL, and can perform real-world tasks: making espresso drinks, folding diverse laundry, and assembling boxes. More in the thread below.

Physical Intelligence

705,845 次观看 • 8 个月前

Elon: Optimus Will Learn Tasks by Watching Videos and will "Move the Needle" on U.S. GDP “Optimus is a general-purpose robot that can learn by observing human behavior. You can demonstrate a task, verbally describe it, or even show it a video, and it will be able to do that task. It’s gonna be a very capable robot. Long-term, Optimus will have a very significant impact on the US GDP, it will actually move the needle on US GDP significantly.” Source: Tesla

Elon: Optimus Will Learn Tasks by Watching Videos and will "Move the Needle" on U.S. GDP “Optimus is a general-purpose robot that can learn by observing human behavior. You can demonstrate a task, verbally describe it, or even show it a video, and it will be able to do that task. It’s gonna be a very capable robot. Long-term, Optimus will have a very significant impact on the US GDP, it will actually move the needle on US GDP significantly.” Source: Tesla

Mario Nawfal

196,504 次观看 • 5 个月前

Are you celebrating #PiDay with pie ... or do you prefer cake? Researchers have designed a robot that can create and cook a cake with more than π ingredients. Learn more:

Are you celebrating #PiDay with pie ... or do you prefer cake? Researchers have designed a robot that can create and cook a cake with more than π ingredients. Learn more:

Science Magazine

35,028 次观看 • 4 个月前

We developed an RL method for fine-tuning our models for precise tasks in just a few hours or even minutes. Instead of training the whole model, we add an “RL token” output to π-0.6, our latest model, which is used by a tiny actor and critic to learn quickly with RL.

We developed an RL method for fine-tuning our models for precise tasks in just a few hours or even minutes. Instead of training the whole model, we add an “RL token” output to π-0.6, our latest model, which is used by a tiny actor and critic to learn quickly with RL.

Physical Intelligence

434,203 次观看 • 4 个月前

Happy #NationalRoboticsWeek! Last year, we gave you a sneak peek at AthenaZero, our robotic manipulator built to tackle dynamic tasks like a human arm. Learn more about how this fast, precise robot can switch in an instant from a gentle touch to high force depending on what the task requires:

Happy #NationalRoboticsWeek! Last year, we gave you a sneak peek at AthenaZero, our robotic manipulator built to tackle dynamic tasks like a human arm. Learn more about how this fast, precise robot can switch in an instant from a gentle touch to high force depending on what the task requires:

RAI Institute

23,415 次观看 • 3 个月前

RL in the real world presents some big challenges, but also some really big opportunities. In our new work, HIL-SERL, Charles Xu, Jeffrey Wu, Jianlan Luo show that real-world RL can learn a huge range of precise and robust tasks, and perform them much faster than imitation.

RL in the real world presents some big challenges, but also some really big opportunities. In our new work, HIL-SERL, Charles Xu, Jeffrey Wu, Jianlan Luo show that real-world RL can learn a huge range of precise and robust tasks, and perform them much faster than imitation.

Sergey Levine

36,489 次观看 • 1 年前

Researchers have designed a robot that can create and cook a cake with up to seven ingredients, more than any other printed food to date. Learn more: News from Science

Researchers have designed a robot that can create and cook a cake with up to seven ingredients, more than any other printed food to date. Learn more: News from Science

Science Magazine

6,649,185 次观看 • 2 年前

ELON: OPTIMUS WILL ELIMINATE POVERTY AND TRANSFORM MEDICAL CARE “You know, people often talk about eliminating poverty or giving everyone amazing medical care. There’s actually only one way to do that, and that’s with the Optimus robot. With humanoid robots, you can actually give everyone amazing medical care. Optimus will be more precise, ultimately better than the best human surgeon, with a level of precision beyond human ability. People always talked about eliminating poverty, but Optimus will actually do it. Optimus will give people incredible medical care.” Source: uncover.robotics

ELON: OPTIMUS WILL ELIMINATE POVERTY AND TRANSFORM MEDICAL CARE “You know, people often talk about eliminating poverty or giving everyone amazing medical care. There’s actually only one way to do that, and that’s with the Optimus robot. With humanoid robots, you can actually give everyone amazing medical care. Optimus will be more precise, ultimately better than the best human surgeon, with a level of precision beyond human ability. People always talked about eliminating poverty, but Optimus will actually do it. Optimus will give people incredible medical care.” Source: uncover.robotics

Mario Nawfal

348,773 次观看 • 7 个月前

Joao: “I think Alcaraz has more arsenal than Sinner. Sinner is more like a robot that just kills the ball and does everything perfect.Carlos,he can do everything.He can do with topspin,fire the ball,has good movement,goes to the net. It’s more difficult to understand the game...”

Joao: “I think Alcaraz has more arsenal than Sinner. Sinner is more like a robot that just kills the ball and does everything perfect.Carlos,he can do everything.He can do with topspin,fire the ball,has good movement,goes to the net. It’s more difficult to understand the game...”

alcaraz archive

1,075,562 次观看 • 4 个月前

If you want a robot to do something well, you need to know how to talk to it. If you don't, you can learn, with Semantic Action RL! In our paper, Jagdeep Bhatia @ RSS 2026, Andrew Wagenmaker, Will Chen show how RL over VLA prompts enables new tasks and learns blazing fast in the real world!

If you want a robot to do something well, you need to know how to talk to it. If you don't, you can learn, with Semantic Action RL! In our paper, Jagdeep Bhatia @ RSS 2026, Andrew Wagenmaker, Will Chen show how RL over VLA prompts enables new tasks and learns blazing fast in the real world!

Sergey Levine

29,139 次观看 • 16 天前

🎁 Introducing Oscar Unlocks, our new digital rewards program for Oscar members. With Oscar Unlocks, members can gain rewards, fun badges, and more just by completing simple tasks that help them personalize and make the most of their plan. How it works: – Members complete easy, digital tasks, like creating their account or setting up autopay. – Members can earn exclusive badges and access to the best of Oscar the more they engage in the program: the more they do, the more they can unlock. Learn more:

🎁 Introducing Oscar Unlocks, our new digital rewards program for Oscar members. With Oscar Unlocks, members can gain rewards, fun badges, and more just by completing simple tasks that help them personalize and make the most of their plan. How it works: – Members complete easy, digital tasks, like creating their account or setting up autopay. – Members can earn exclusive badges and access to the best of Oscar the more they engage in the program: the more they do, the more they can unlock. Learn more:

Oscar

101,490 次观看 • 9 个月前

Tesla Optimus can arrange batteries in their factories, ours can do skincare (on Yuzhe Qin)! We opensource Bunny-VisionPro, a teleoperation system for bimanual hand manipulation. The users can control the robot hands in real time using VisionPro, flexible like a bunny. 🐇 We also have kitchen tasks, playing Rubik's Cube, and dynamic motion tasks. Imitation learning policies are trained on sweeping with a broom, serving a drink, and wiping glasses. Check our website for more details: The project is led by Runyu Ding Runyu Ding, Yuzhe Qin Yuzhe Qin , and Jiyue Zhu

Tesla Optimus can arrange batteries in their factories, ours can do skincare (on Yuzhe Qin)! We opensource Bunny-VisionPro, a teleoperation system for bimanual hand manipulation. The users can control the robot hands in real time using VisionPro, flexible like a bunny. 🐇 We also have kitchen tasks, playing Rubik's Cube, and dynamic motion tasks. Imitation learning policies are trained on sweeping with a broom, serving a drink, and wiping glasses. Check our website for more details: The project is led by Runyu Ding Runyu Ding, Yuzhe Qin Yuzhe Qin , and Jiyue Zhu

Xiaolong Wang

90,902 次观看 • 2 年前

In 2023, researchers designed a robot that can create and cook a cake with up to seven ingredients, more than any other printed food to date. Learn more: #ScienceMagArchives News from Science

In 2023, researchers designed a robot that can create and cook a cake with up to seven ingredients, more than any other printed food to date. Learn more: #ScienceMagArchives News from Science

Science Magazine

88,287 次观看 • 1 年前

What happens when robot world models learn from human experience at scale? 🤔 DreamDojo from NVIDIA Research is a generalist robot world model pretrained on 44K hours of egocentric human videos and then post-trained on robot data to generalize across new objects and environments. After distillation, it runs at 10 FPS for live teleoperation, policy evaluation, and model-based planning. Read the ICML paper to learn more 📄

What happens when robot world models learn from human experience at scale? 🤔 DreamDojo from NVIDIA Research is a generalist robot world model pretrained on 44K hours of egocentric human videos and then post-trained on robot data to generalize across new objects and environments. After distillation, it runs at 10 FPS for live teleoperation, policy evaluation, and model-based planning. Read the ICML paper to learn more 📄

NVIDIA Robotics

21,506 次观看 • 13 天前

🇨🇦 ROBOT HANDS JUST LEVELED UP IN CANADA Sanctuary AI showed off a robotic hand that uses hydraulic power to grip, twist, and move like a real one. The hand can handle delicate objects, like dice, without crushing them, proving robots are getting scary precise. Hydraulic actuation gives the robot smoother, stronger control, making it better for heavy industrial work and tricky small tasks. This could change how robots work in factories, warehouses, or even in jobs too dangerous for humans. The future of robot hands? Less clunky claws, more human-like grip power with machine muscle. Source: Wevolver

🇨🇦 ROBOT HANDS JUST LEVELED UP IN CANADA Sanctuary AI showed off a robotic hand that uses hydraulic power to grip, twist, and move like a real one. The hand can handle delicate objects, like dice, without crushing them, proving robots are getting scary precise. Hydraulic actuation gives the robot smoother, stronger control, making it better for heavy industrial work and tricky small tasks. This could change how robots work in factories, warehouses, or even in jobs too dangerous for humans. The future of robot hands? Less clunky claws, more human-like grip power with machine muscle. Source: Wevolver

Mario Nawfal

50,661 次观看 • 11 个月前

Teaching robots to perform dexterous manipulation tasks currently requires teleoperation, which limits demonstration quality, speed, and scalability. Instead, why not use human videos? The problem is that a human hand isn’t a robot hand, so data must be retargeted using simulation to resolve issues like collisions and interpenetration when controlling the hand. In VideoManip, Hongyi Chen and co-authors built a system to solve this problem, taking in RGB videos of humans performing manipulation tasks and using them to create accurate simulations with which to learn robot policies. Watch episode #73 of RoboPapers, hosted by Michael Cho - Rbt/Acc and Chris Paxton, now to learn more!

Teaching robots to perform dexterous manipulation tasks currently requires teleoperation, which limits demonstration quality, speed, and scalability. Instead, why not use human videos? The problem is that a human hand isn’t a robot hand, so data must be retargeted using simulation to resolve issues like collisions and interpenetration when controlling the hand. In VideoManip, Hongyi Chen and co-authors built a system to solve this problem, taking in RGB videos of humans performing manipulation tasks and using them to create accurate simulations with which to learn robot policies. Watch episode #73 of RoboPapers, hosted by Michael Cho - Rbt/Acc and Chris Paxton, now to learn more!

RoboPapers

27,249 次观看 • 3 个月前

Elon Musk: Optimus being able to learn to do things from watching videos will be a very significant step. “If Optimus can watch videos, YouTube videos or How-To videos or whatever and based on that video, just like a human can, learn how to do that thing, then you really have a task extensibility that is dramatic because then it can learn anything very quickly. We'll get there. That's a very significant threshold.” From: Interview with David Faber, May 20, 2025

Elon Musk: Optimus being able to learn to do things from watching videos will be a very significant step. “If Optimus can watch videos, YouTube videos or How-To videos or whatever and based on that video, just like a human can, learn how to do that thing, then you really have a task extensibility that is dramatic because then it can learn anything very quickly. We'll get there. That's a very significant threshold.” From: Interview with David Faber, May 20, 2025

ELON CLIPS

99,865 次观看 • 1 年前

NAVIAI-I3, a more robust humanoid robot, was launched by the Zhejiang Humanoid Robotics Innovation Center. Standing 1.8 meters tall, it can run like a human and walk on various terrains. This humanoid robot appears to be primarily designed for specialized industrial tasks, such as security patrols in underground parking lots. They previously launched the lightweight bipedal NVAI-2 and a wheeled humanoid robot. The bipedal robot is used in manufacturing operations, while the wheeled humanoid robot is used for unstructured, flexible tasks such as warehouse sorting, supermarket shelving, and office cleaning. We filmed this demonstration at the World Robot Conference; you can see it in the comments section.

NAVIAI-I3, a more robust humanoid robot, was launched by the Zhejiang Humanoid Robotics Innovation Center. Standing 1.8 meters tall, it can run like a human and walk on various terrains. This humanoid robot appears to be primarily designed for specialized industrial tasks, such as security patrols in underground parking lots. They previously launched the lightweight bipedal NVAI-2 and a wheeled humanoid robot. The bipedal robot is used in manufacturing operations, while the wheeled humanoid robot is used for unstructured, flexible tasks such as warehouse sorting, supermarket shelving, and office cleaning. We filmed this demonstration at the World Robot Conference; you can see it in the comments section.

CyberRobo

15,521 次观看 • 8 个月前