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。

Physical Intelligence's π₀, a general-purpose robot foundation model that combines Internet-scale vision-language pretraining with robot interaction data to execute tasks. They aim "to develop foundation models that can control any robot to perform any task" Autonomous demos:

The Humanoid Hub

76,436 subscribers

196,055 次观看 • 1 年前 •via X (Twitter)

教育科学技术

Anya Rossi• Live Now

Private livecam show

10 条评论

The Humanoid Hub 的头像

The Humanoid Hub1 年前

According to a media report from last week, the San Francisco-based startup is in talks to raise $300 million at a valuation of around $2 billion. The company was co-founded earlier this year by Karol Hausman, who previously worked on robotics at Google DeepMind.

The Humanoid Hub 的头像

The Humanoid Hub1 年前

Paper:

Welt Meister ❄️ 的头像

Welt Meister ❄️1 年前

Policy 0? Is it 0 short learning?

The Humanoid Hub 的头像

The Humanoid Hub1 年前

It is, and PI (π) stands for Physical Intelligence.

Jack Aiki 的头像

Jack Aiki1 年前

these are amazing times, thanks for all the news and clips, I share them to my Robot fans and tag you under each share, let's go forward together everyone, and reach for the stars 🇺🇲🚨

Tom Löwe 的头像

Tom Löwe1 年前

Just make them humanoid.

Sustanda🇺🇸🇮🇱 的头像

Sustanda🇺🇸🇮🇱1 年前

General laundry and folding is a monstrous challenge in machine learning. Many have failed for years. It will be literally on par with the moon landing if achieved.

Brian Mosley 的头像

Brian Mosley1 年前

By the time robots can fold clothing at 1x speed and put them away, perhaps we will have smart materials that stay clean, crease free, change texture/colour and are waterproof, breathable and delightfully comfortable to wear... Have a look at those millions of new alpha materials

GJ19 的头像

GJ191 年前

Form factor aside. That is incredible autonomy. Wow!

M.A.X. 的头像

M.A.X.1 年前

Wow, nice demo!

相关视频

Vision-language models perform diverse tasks via in-context learning. Time for robots to do the same! Introducing In-Context Robot Transformer (ICRT): a robot policy that learns new tasks by prompting with robot trajectories, without any fine-tuning. [1/N]

Vision-language models perform diverse tasks via in-context learning. Time for robots to do the same! Introducing In-Context Robot Transformer (ICRT): a robot policy that learns new tasks by prompting with robot trajectories, without any fine-tuning. [1/N]

Max Fu

40,392 次观看 • 1 年前

.Lindon Gao, cofounder and CEO of Dyna Robotics, is working on general-purpose foundation models that perform diverse physical tasks at commercial scale. Here’s our chat at CES 2026, while their robot autonomously folded laundry in the background.

.Lindon Gao, cofounder and CEO of Dyna Robotics, is working on general-purpose foundation models that perform diverse physical tasks at commercial scale. Here’s our chat at CES 2026, while their robot autonomously folded laundry in the background.

The Humanoid Hub

36,359 次观看 • 5 个月前

Developing general-purpose robot models is costly due to the need for extensive real-world data. 🤖 #NVIDIAIsaac GR00T addresses these challenges by providing #humanoidrobot developers with robot foundation models & more. #CES2025 📹

Developing general-purpose robot models is costly due to the need for extensive real-world data. 🤖 #NVIDIAIsaac GR00T addresses these challenges by providing #humanoidrobot developers with robot foundation models & more. #CES2025 📹

NVIDIA Robotics

19,055 次观看 • 1 年前

Exciting progress on Vision-Language-Action models from a collaboration between San Francisco-based Physical Intelligence (π) and China’s AGIBOT: (π)’s single model can autonomously perform diverse tasks on the AGIBOT G1 robot, using both humanoid hands and two-finger grippers.

Exciting progress on Vision-Language-Action models from a collaboration between San Francisco-based Physical Intelligence (π) and China’s AGIBOT: (π)’s single model can autonomously perform diverse tasks on the AGIBOT G1 robot, using both humanoid hands and two-finger grippers.

The Humanoid Hub

32,575 次观看 • 1 年前

Every home is different. That means that to build a useful home robot, we must be able to perform zero-shot generalization on a wide range of tasks. Humanoid company 1X has a solution: world models. 1X Director of Evaluations Daniel Ho joins us on RoboPapers to talk about: - why world models are the future for scaling robot learning - how to use world models for robot control - what world models unlock for evaluating robot model performance - how we can hill-climb from here to general purpose robots Watch Episode #61 of RoboPapers, with Michael Cho - Rbt/Acc and Chris Paxton, now!

Every home is different. That means that to build a useful home robot, we must be able to perform zero-shot generalization on a wide range of tasks. Humanoid company 1X has a solution: world models. 1X Director of Evaluations Daniel Ho joins us on RoboPapers to talk about: - why world models are the future for scaling robot learning - how to use world models for robot control - what world models unlock for evaluating robot model performance - how we can hill-climb from here to general purpose robots Watch Episode #61 of RoboPapers, with Michael Cho - Rbt/Acc and Chris Paxton, now!

RoboPapers

27,537 次观看 • 4 个月前

How can we build a general-purpose “foundation model” for robot motion? Zhengyi “Zen” Luo joins us to talk about SONIC, which uses motion tracking as a foundational task for humanoid robot control, and scales humanoid control training to 9k GPU hours and 100 million frames worth of data. The result: a model with a generally-useful embedding space that can be controlled by a VLA, or from human video, to perform a wide variety of humanoid whole-body-control tasks, including with zero-shot transfer to previously unseen motions. Watch episode 72 of RoboPapers, with Michael Cho - Rbt/Acc and Jiafei Duan, now!

How can we build a general-purpose “foundation model” for robot motion? Zhengyi “Zen” Luo joins us to talk about SONIC, which uses motion tracking as a foundational task for humanoid robot control, and scales humanoid control training to 9k GPU hours and 100 million frames worth of data. The result: a model with a generally-useful embedding space that can be controlled by a VLA, or from human video, to perform a wide variety of humanoid whole-body-control tasks, including with zero-shot transfer to previously unseen motions. Watch episode 72 of RoboPapers, with Michael Cho - Rbt/Acc and Jiafei Duan, now!

RoboPapers

24,757 次观看 • 2 个月前

Everyone is scaling VLAs with more robot data. TiPToP shows another path. No robot training, no policy learning. Just RGB + language → 3D scene → GPU TAMP planner → trajectory. Foundation models + planning alone can run real manipulation tasks.

Everyone is scaling VLAs with more robot data. TiPToP shows another path. No robot training, no policy learning. Just RGB + language → 3D scene → GPU TAMP planner → trajectory. Foundation models + planning alone can run real manipulation tasks.

Robots Digest 🤖

10,362 次观看 • 3 个月前

Chinese company Robot Era has unveiled their next-gen robot L7, a 5′7″ tall humanoid. The company has also showcased the ERA-42 Vision-Language-Action model running on L7 robot to autonomously execute dexterous tasks.

Chinese company Robot Era has unveiled their next-gen robot L7, a 5′7″ tall humanoid. The company has also showcased the ERA-42 Vision-Language-Action model running on L7 robot to autonomously execute dexterous tasks.

The Humanoid Hub

38,547 次观看 • 11 个月前

Robot foundation models are limited by costly real data, while simulation data is plentiful but visually mismatched to reality. We present Point Bridge, a method that enables zero-shot sim-to-real transfer for robot learning with minimal visual alignment.

Robot foundation models are limited by costly real data, while simulation data is plentiful but visually mismatched to reality. We present Point Bridge, a method that enables zero-shot sim-to-real transfer for robot learning with minimal visual alignment.

Siddhant Haldar

19,765 次观看 • 4 个月前

State-of-the-art robot policies often need hundreds of hours of data. What if we needed none? Introducing TiPToP: a manipulation system that zero-shots open-world tasks from pixels and language using vision foundation models and GPU-parallelized Task and Motion Planning (TAMP).

State-of-the-art robot policies often need hundreds of hours of data. What if we needed none? Introducing TiPToP: a manipulation system that zero-shots open-world tasks from pixels and language using vision foundation models and GPU-parallelized Task and Motion Planning (TAMP).

Nishanth Kumar

77,488 次观看 • 3 个月前

CMU Vision-Language-Autonomy update: The team just released SORT3D, the first general spatial relation toolbox for autonomous vision-language navigation that is fully integrated into real-robot systems! 🤖👀 Simulation and real-robot data is provided!:

CMU Vision-Language-Autonomy update: The team just released SORT3D, the first general spatial relation toolbox for autonomous vision-language navigation that is fully integrated into real-robot systems! 🤖👀 Simulation and real-robot data is provided!:

CMU Robotics Institute

18,234 次观看 • 1 年前

Weights drop ⚠️ We released our pre-trained model for the cup arrangement task trained on 1400 demos! We aim to enable anyone to deploy UMI on their robot to arrange any "espresso cup with saucer" they buy on Amazon.

Weights drop ⚠️ We released our pre-trained model for the cup arrangement task trained on 1400 demos! We aim to enable anyone to deploy UMI on their robot to arrange any "espresso cup with saucer" they buy on Amazon.

Cheng Chi

25,125 次观看 • 2 年前

.Sureform (YC X25) connects real-world workplaces with robotics labs to collect task-specific training data for robot foundation models. Congrats on the launch, Ananth Kashyap!

.Sureform (YC X25) connects real-world workplaces with robotics labs to collect task-specific training data for robot foundation models. Congrats on the launch, Ananth Kashyap!

Y Combinator

35,876 次观看 • 3 个月前

Training robot foundation models faces two key hurdles: how to get enough data to train an effective model, and how to make sure that new skills can be acquired quickly. The team at Rhoda AI believes that the answer is training Direct Video Action models from web data. Web data is plentiful, to the point where Rhoda can train their base model on hundreds of years of video data. And then, with the addition of robot data, they can quickly adapt it to new tasks with as little as 20 hours of in-domain data, performing complex, multi-step manipulation tasks with their purpose-built video foundation model. Tongzhou Mu 🤖🦾🦿 Eric Chan and Changan Chen joined us to talk more about their approach. Watch Episode #79 of RoboPapers, with Michael Cho - Rbt/Acc, Chris Paxton, and Jiafei Duan, to learn more!

Training robot foundation models faces two key hurdles: how to get enough data to train an effective model, and how to make sure that new skills can be acquired quickly. The team at Rhoda AI believes that the answer is training Direct Video Action models from web data. Web data is plentiful, to the point where Rhoda can train their base model on hundreds of years of video data. And then, with the addition of robot data, they can quickly adapt it to new tasks with as little as 20 hours of in-domain data, performing complex, multi-step manipulation tasks with their purpose-built video foundation model. Tongzhou Mu 🤖🦾🦿 Eric Chan and Changan Chen joined us to talk more about their approach. Watch Episode #79 of RoboPapers, with Michael Cho - Rbt/Acc, Chris Paxton, and Jiafei Duan, to learn more!

RoboPapers

23,976 次观看 • 1 个月前

Over the last few months, we’ve been thinking about how to learn from “off-domain” data - data from non-robot sources like video or simulation. These data sources are not quite good enough to learn policies (even monolithic VLA models) directly, but they still contain lots of information that can be useful for generalizable robot control. How can we develop robot learning models that are able to make use of this type of data for generalizable control? In new work, that we call HAMSTER, we show that VLMs can be useful for enabling robotic learning from off-domain data, but specifically when used through hierarchical VLA architectures. We show that this class of models can learn generalizable robot policies for the real world from large-scale, off-domain data. A 🧵 (1/10)

Over the last few months, we’ve been thinking about how to learn from “off-domain” data - data from non-robot sources like video or simulation. These data sources are not quite good enough to learn policies (even monolithic VLA models) directly, but they still contain lots of information that can be useful for generalizable robot control. How can we develop robot learning models that are able to make use of this type of data for generalizable control? In new work, that we call HAMSTER, we show that VLMs can be useful for enabling robotic learning from off-domain data, but specifically when used through hierarchical VLA architectures. We show that this class of models can learn generalizable robot policies for the real world from large-scale, off-domain data. A 🧵 (1/10)

Abhishek Gupta

11,994 次观看 • 1 年前

Another day, another humanoid robot from china AGIBOT introduces GO-1, a generalist foundation model that integrates a vision-language model with a latent planner for enhanced long-horizon and dexterous manipulation.

Another day, another humanoid robot from china AGIBOT introduces GO-1, a generalist foundation model that integrates a vision-language model with a latent planner for enhanced long-horizon and dexterous manipulation.

Chubby♨️

23,513 次观看 • 1 年前

Introducing a way to convert synthesized robot videos to robot execution without using any action labels! We also release a codebase (with pretrained models) for text-to-video generation. Train your own models for robot control in only 1 day with 4 GPUs!

Introducing a way to convert synthesized robot videos to robot execution without using any action labels! We also release a codebase (with pretrained models) for text-to-video generation. Train your own models for robot control in only 1 day with 4 GPUs!

Yilun Du

20,949 次观看 • 2 年前

Vision-language models can control robots, but what if the prompt is too complex for the robot to follow directly? We developed a way to get robots to “think through” complex instructions, feedback, and interjections. We call it the Hierarchical Interactive Robot (Hi Robot).

Vision-language models can control robots, but what if the prompt is too complex for the robot to follow directly? We developed a way to get robots to “think through” complex instructions, feedback, and interjections. We call it the Hierarchical Interactive Robot (Hi Robot).

Physical Intelligence

116,845 次观看 • 1 年前

How to master multi-robot cooperative mapping? We're excited to release MR.ScaleMaster, which masters the scales to scale - any feed-forward Visual SLAM (MASt3R-SLAM, π³, VGGT-SLAM 2.0, LoGeR, …) - across any robot (legged, wheeled, handheld, …) 🔗

How to master multi-robot cooperative mapping? We're excited to release MR.ScaleMaster, which masters the scales to scale - any feed-forward Visual SLAM (MASt3R-SLAM, π³, VGGT-SLAM 2.0, LoGeR, …) - across any robot (legged, wheeled, handheld, …) 🔗

Giseop Kim

28,728 次观看 • 2 个月前

Orange you glad our robot can stack? Other tasks GEN-1 can do: Read more about GEN-1, our latest foundation model for the physical world:

Orange you glad our robot can stack? Other tasks GEN-1 can do: Read more about GEN-1, our latest foundation model for the physical world:

Generalist

22,849 次观看 • 2 个月前