Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Anyone skeptical about AI’s ability to perform diverse physical tasks should watch this. Physical Intelligence's π₀ model in action: 18 minutes of bimanual robots autonomously handling complex, dexterous chores.

The Humanoid Hub

108,805 subscribers

210,404 просмотров • 1 год назад •via X (Twitter)

Здоровье и велнес Образование Наука и технологии

Anya Rossi• Live Now

Private livecam show

Комментарии: 11

Фото профиля Victor

Victor1 год назад

watching robots do chores is the new asmr... kinda therapeutic

Фото профиля David Cantone

David Cantone1 год назад

It may not be the best right now, but at least it can work 24 hours a day.

Фото профиля The Humanoid Hub

The Humanoid Hub1 год назад

This is only the initial version with a small team working for just 8 months. The proof of existence is real. The next couple of years will be crazy exciting for foundation models.

Фото профиля Larry Panozzo

Larry Panozzo1 год назад

It’s trying to use one heuristic and it fails many times over and over, stuck making no progress. If the heuristic works then yeah it folds nicely.

Фото профиля The Humanoid Hub

The Humanoid Hub1 год назад

Corrections and recoveries are an emergent feature of pre-training on a large, diverse dataset.

Фото профиля Shane McGrath

Shane McGrath1 год назад

Leaders in the field

Фото профиля MR MR

MR MR1 год назад

Looks teleoperated

Фото профиля Nicholas Shanks

Nicholas Shanks1 год назад

This looks teleoperated by a child.

Фото профиля Robert Newton @robertnewton.bsky.social

Robert Newton @robertnewton.bsky.social1 год назад

I don't understand your point. the robot did a terrible job of folding those clothes.

Фото профиля Vlad

Vlad1 год назад

it's tele operated obviously

Фото профиля The Humanoid Hub

The Humanoid Hub1 год назад

@vzhidkovUSA It's all autonomous. The model is fine-tuned with carefully curated high-quality examples of humans operating the robot in the same settings. This induces the desired pattern of movements and dexterity similar to those in the human operated dataset.

Похожие видео

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 просмотров • 1 год назад

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:

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

196,055 просмотров • 1 год назад

Ray Kurzweil says AI models will exceed human verbal ability in a year or two and the next step is large event models that enable robots to perform physical tasks

Ray Kurzweil says AI models will exceed human verbal ability in a year or two and the next step is large event models that enable robots to perform physical tasks

Tsarathustra

71,501 просмотров • 2 лет назад

.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 просмотров • 6 месяцев назад

We finished evaluating π0.7, our new model at Physical Intelligence. What I'm most excited about with π0.7 is that it's starting to show some surprising emergent compositional generalization, being able to both perform complex tasks and learn new tasks just from instructions.

We finished evaluating π0.7, our new model at Physical Intelligence. What I'm most excited about with π0.7 is that it's starting to show some surprising emergent compositional generalization, being able to both perform complex tasks and learn new tasks just from instructions.

Sergey Levine

60,722 просмотров • 3 месяцев назад

Excited to share our latest progress on DYNA-1 pre-training! 🤖 The base model now can perform diverse, dexterous tasks (laundry folding, package sorting, …) without any post-training, even in unseen environments. This powerful base also allows extremely efficient fine-tuning to ~100% success on challenging new tasks with as little as 1 hour of data! 🤯 Watch it master two of them: cup stacking & celery chopping on repeat, no failures. 👇

Excited to share our latest progress on DYNA-1 pre-training! 🤖 The base model now can perform diverse, dexterous tasks (laundry folding, package sorting, …) without any post-training, even in unseen environments. This powerful base also allows extremely efficient fine-tuning to ~100% success on challenging new tasks with as little as 1 hour of data! 🤯 Watch it master two of them: cup stacking & celery chopping on repeat, no failures. 👇

Dyna Robotics

66,619 просмотров • 8 месяцев назад

🤖Robots that think ahead and act in real time. LingBot-VA 2.0 — the first embodied-native foundation model. Not fine-tuned from a video generator. Built from scratch for the physical world. ✅ 93.6% success on bimanual tasks ⚡ 150 Hz single-GPU inference 🎯 20 demos to generalize. This is what happens when you stop adapting and start building natively. 🧵👇

🤖Robots that think ahead and act in real time. LingBot-VA 2.0 — the first embodied-native foundation model. Not fine-tuned from a video generator. Built from scratch for the physical world. ✅ 93.6% success on bimanual tasks ⚡ 150 Hz single-GPU inference 🎯 20 demos to generalize. This is what happens when you stop adapting and start building natively. 🧵👇

Robbyant

869,787 просмотров • 7 дней назад

⚠️#IMPORTANT: Microsoft is testing what happens when ChatGPT takes control of robots. Microsoft researcher: "Our goal with this research is to see if ChatGPT can think beyond text, and reason about the physical world to help with robotics tasks."

⚠️#IMPORTANT: Microsoft is testing what happens when ChatGPT takes control of robots. Microsoft researcher: "Our goal with this research is to see if ChatGPT can think beyond text, and reason about the physical world to help with robotics tasks."

Mario Nawfal

808,243 просмотров • 3 лет назад

We’re rolling out an upgrade designed to help robots reason about the physical world. 🤖 Gemini Robotics-ER 1.6 has significantly better visual and spatial understanding in order to plan and complete more useful tasks. Here’s why this is important 🧵

We’re rolling out an upgrade designed to help robots reason about the physical world. 🤖 Gemini Robotics-ER 1.6 has significantly better visual and spatial understanding in order to plan and complete more useful tasks. Here’s why this is important 🧵

Google DeepMind

553,378 просмотров • 3 месяцев назад

Scaling vision-language-action (VLA) models to high-DoF dexterous hands has long been a "holy grail" challenge due to the high-dimensional action space and data scarcity. As a wrap up of the year 2025, we are releasing GR-Dexter, a holistic hardware-model-data framework for generalist manipulation on a bimanual dexterous-hand robot. This is the first VLA system to achieve: ✅ High-DoF Control: Managing a 56-DoF bimanual system (21-DoF per hand). ✅ Long-Horizon Tasks with tool use: Vacuuming, bread serving with tongs, and table decluttering. ✅ Open-World Generalization: Robust performance with unseen objects and abstract instructions. Project page: ArXiv:

Scaling vision-language-action (VLA) models to high-DoF dexterous hands has long been a "holy grail" challenge due to the high-dimensional action space and data scarcity. As a wrap up of the year 2025, we are releasing GR-Dexter, a holistic hardware-model-data framework for generalist manipulation on a bimanual dexterous-hand robot. This is the first VLA system to achieve: ✅ High-DoF Control: Managing a 56-DoF bimanual system (21-DoF per hand). ✅ Long-Horizon Tasks with tool use: Vacuuming, bread serving with tongs, and table decluttering. ✅ Open-World Generalization: Robust performance with unseen objects and abstract instructions. Project page: ArXiv:

Xiao Ma

93,749 просмотров • 6 месяцев назад

Alphabet (Google's parent company) acquired a stake in Physical Intelligence. San Francisco-based Physical Intelligence, an AI and robotics startup, has secured $600 million in fresh funding, pushing its post-money valuation to $5.6 billion. - The round was led by Alphabet's independent growth fund CapitalG. - Existing backers who participated in this round include Lux Capital, Thrive Capital, and Jeff Bezos. - New participants include Index Ventures and T. Rowe Price, among others. Physical Intelligence is building general-purpose AI foundation models and learning algorithms designed to act as the "brain" for robots. Here's their latest π*0.6 model in actio

Alphabet (Google's parent company) acquired a stake in Physical Intelligence. San Francisco-based Physical Intelligence, an AI and robotics startup, has secured $600 million in fresh funding, pushing its post-money valuation to $5.6 billion. - The round was led by Alphabet's independent growth fund CapitalG. - Existing backers who participated in this round include Lux Capital, Thrive Capital, and Jeff Bezos. - New participants include Index Ventures and T. Rowe Price, among others. Physical Intelligence is building general-purpose AI foundation models and learning algorithms designed to act as the "brain" for robots. Here's their latest π*0.6 model in actio

The Humanoid Hub

244,972 просмотров • 7 месяцев назад

Generalist AI has just broken the "impossible triangle" of speed, reliability, and intelligence in robotics. They’ve pushed their embodied foundation model forward in a big way: GEN-1 hits “Mastery” on simple physical tasks,99% average success rate, and it can improvise when things go wrong. Smooth, natural, fast(factory owners must be very interested)👇 >Folding boxes: 200 runs at 99% success in ~12 seconds ( ~34s before) >Packing phones, folding T-shirts, servicing robot vacuums,hundreds of reps with almost zero failures > Intelligent improvisation, handling uncertain tasks >Needs only about 1 hour of robot-specific data per task This feels like a real step toward humanoid robots that are actually reliable enough for factories, warehouse or homes. Physical AGI is accelerating

Generalist AI has just broken the "impossible triangle" of speed, reliability, and intelligence in robotics. They’ve pushed their embodied foundation model forward in a big way: GEN-1 hits “Mastery” on simple physical tasks,99% average success rate, and it can improvise when things go wrong. Smooth, natural, fast(factory owners must be very interested)👇 >Folding boxes: 200 runs at 99% success in ~12 seconds ( ~34s before) >Packing phones, folding T-shirts, servicing robot vacuums,hundreds of reps with almost zero failures > Intelligent improvisation, handling uncertain tasks >Needs only about 1 hour of robot-specific data per task This feels like a real step toward humanoid robots that are actually reliable enough for factories, warehouse or homes. Physical AGI is accelerating

CyberRobo

25,519 просмотров • 3 месяцев назад

After operating in stealth for the last 18 months , we’re excited today to finally show the world what we’ve been working on. We believe we’re on a path to physical AGI with the launch of our brand new foundation model, the Direct Video Action (DVA) model.

Jagdeep Singh

258,360 просмотров • 4 месяцев назад

Happy to share what I’ve been working on since joining Genesis! GENE-26.5 is a one-of-a-kind, robotics-native multimodal foundation model that learns from diverse, in-the-wild data across modalities and outputs actions enabling a 54-DoF robot system to perform the most dexterous, long-horizon manipulation tasks to date—approaching human-level capability. This is the result of innovations across the full stack—data collection and processing, robot systems, model architecture, training strategies, and scalable evaluation infrastructure.

Happy to share what I’ve been working on since joining Genesis! GENE-26.5 is a one-of-a-kind, robotics-native multimodal foundation model that learns from diverse, in-the-wild data across modalities and outputs actions enabling a 54-DoF robot system to perform the most dexterous, long-horizon manipulation tasks to date—approaching human-level capability. This is the result of innovations across the full stack—data collection and processing, robot systems, model architecture, training strategies, and scalable evaluation infrastructure.

Zu Wang

19,252 просмотров • 2 месяцев назад

🏁 This weekend, 44 student teams from across the world competed in our 2026 #RoverChallenge in Huntsville, Alabama. Watch this recap to see these teams navigate challenging obstacles and perform complex tasks with their human-powered and remote-controlled rovers. Learn more about #NASAHERC at

🏁 This weekend, 44 student teams from across the world competed in our 2026 #RoverChallenge in Huntsville, Alabama. Watch this recap to see these teams navigate challenging obstacles and perform complex tasks with their human-powered and remote-controlled rovers. Learn more about #NASAHERC at

NASA Marshall

13,606 просмотров • 3 месяцев назад

A new robot policy just cleaned up a kitchen it had never seen before [watch what happens. paper included ⬇️] Pi-0.5 builds on top of Pi-0 and shows how smart co-training with diverse data can unlock real generalization in the home. It doesn’t just learn from one setup but adapts to many, including homes it’s never seen. What it does ✅ Handles new homes without training in them ✅ Follows complex language instructions ✅ Cleans, places dishes, handles spills ✅ Matches in-home training models using cross-embodiment and web data Robots that understand tasks and adapt to new spaces are finally within reach. More in the blog: Read the paper ⬇️ Physical Intelligence, co-founded by UC Berkeley professor Sergey Levine, is a robotics startup developing general-purpose AI foundation models that enable robots to perform a wide variety of real-world tasks with human-like adaptability, recently raising $400 million to advance this vision.

A new robot policy just cleaned up a kitchen it had never seen before [watch what happens. paper included ⬇️] Pi-0.5 builds on top of Pi-0 and shows how smart co-training with diverse data can unlock real generalization in the home. It doesn’t just learn from one setup but adapts to many, including homes it’s never seen. What it does ✅ Handles new homes without training in them ✅ Follows complex language instructions ✅ Cleans, places dishes, handles spills ✅ Matches in-home training models using cross-embodiment and web data Robots that understand tasks and adapt to new spaces are finally within reach. More in the blog: Read the paper ⬇️ Physical Intelligence, co-founded by UC Berkeley professor Sergey Levine, is a robotics startup developing general-purpose AI foundation models that enable robots to perform a wide variety of real-world tasks with human-like adaptability, recently raising $400 million to advance this vision.

Ilir Aliu - eu/acc

18,120 просмотров • 1 год назад

Robots might learn better from video than from language! 📼 Most Vision-Language-Action (VLA) models learn what to do from text, but still struggle with how things move in the real world. That makes them data-hungry and slow to train. mimic video takes a different route. Instead of grounding robot control in text, it grounds it in video, using large pre-trained video models that already capture physical motion and dynamics. The idea is straightforward: let the video model handle “what will happen next,” and let a smaller control model focus only on turning that visual plan into robot actions. The result is big gains in practice. Robots trained this way need 10× less data, converge twice as fast, and perform better on both simulated benchmarks and real bimanual manipulation tasks. If robots can “imagine” motion using video, control becomes a much simpler problem. Shoutout to Jonas Pai, Liam Achenbach, Oier Mees, Elvis Nava and the rest of the team! Here's the project page: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Robots might learn better from video than from language! 📼 Most Vision-Language-Action (VLA) models learn what to do from text, but still struggle with how things move in the real world. That makes them data-hungry and slow to train. mimic video takes a different route. Instead of grounding robot control in text, it grounds it in video, using large pre-trained video models that already capture physical motion and dynamics. The idea is straightforward: let the video model handle “what will happen next,” and let a smaller control model focus only on turning that visual plan into robot actions. The result is big gains in practice. Robots trained this way need 10× less data, converge twice as fast, and perform better on both simulated benchmarks and real bimanual manipulation tasks. If robots can “imagine” motion using video, control becomes a much simpler problem. Shoutout to Jonas Pai, Liam Achenbach, Oier Mees, Elvis Nava and the rest of the team! Here's the project page: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

49,920 просмотров • 6 месяцев назад

Excited to announce GR00T N1, the world’s first open foundation model for humanoid robots! We are on a mission to democratize Physical AI. The power of general robot brain, in the palm of your hand - with only 2B parameters, N1 learns from the most diverse physical action dataset ever compiled and punches above its weight: - Real humanoid teleoperation data. - Large-scale simulation data: we are open-sourcing 300K+ trajectories! - Neural trajectories: we apply SOTA video generation models to “hallucinate” new synthetic data that features accurate physics in pixels. Using Jensen’s words, “systematically infinite data”! - Latent actions: we develop novel algorithms to extract action tokens from in-the-wild human videos and neural generated videos. GR00T N1 is a single end-to-end neural net, from photons to actions: - Vision-Language Model (System 2) that interprets the physical world through vision and language instructions, enabling robots to reason about their environment and instructions, and plan the right actions. - Diffusion Transformer (System 1) that “renders” smooth and precise motor actions at 120 Hz, executing the latent plan made by System 2. We deploy N1 on GR1 robot, 1X Neo robot, and a large collection of simulation benchmarks. N1 achieves up to +30% boost in diverse manipulation tasks for household and industrial settings. While humanoid robots are the main focus of N1, our model also supports cross-embodiment. We finetune it to work on the $110 HuggingFace LeRobot SO100 robot arm! Open robot brain runs on open hardware. Sounds just right. Let’s solve robotics, together, one token at a time. Links to our Whitepaper, Github repo, HuggingFace model, and open dataset page in the thread: 🧵

Excited to announce GR00T N1, the world’s first open foundation model for humanoid robots! We are on a mission to democratize Physical AI. The power of general robot brain, in the palm of your hand - with only 2B parameters, N1 learns from the most diverse physical action dataset ever compiled and punches above its weight: - Real humanoid teleoperation data. - Large-scale simulation data: we are open-sourcing 300K+ trajectories! - Neural trajectories: we apply SOTA video generation models to “hallucinate” new synthetic data that features accurate physics in pixels. Using Jensen’s words, “systematically infinite data”! - Latent actions: we develop novel algorithms to extract action tokens from in-the-wild human videos and neural generated videos. GR00T N1 is a single end-to-end neural net, from photons to actions: - Vision-Language Model (System 2) that interprets the physical world through vision and language instructions, enabling robots to reason about their environment and instructions, and plan the right actions. - Diffusion Transformer (System 1) that “renders” smooth and precise motor actions at 120 Hz, executing the latent plan made by System 2. We deploy N1 on GR1 robot, 1X Neo robot, and a large collection of simulation benchmarks. N1 achieves up to +30% boost in diverse manipulation tasks for household and industrial settings. While humanoid robots are the main focus of N1, our model also supports cross-embodiment. We finetune it to work on the $110 HuggingFace LeRobot SO100 robot arm! Open robot brain runs on open hardware. Sounds just right. Let’s solve robotics, together, one token at a time. Links to our Whitepaper, Github repo, HuggingFace model, and open dataset page in the thread: 🧵

Jim Fan

465,968 просмотров • 1 год назад