Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

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

109,934 subscribers

32,575 views • 1 year ago •via X (Twitter)

Science & Technology Education

Anya Rossi• Live Now

Private livecam show

5 Comments

Future mobility1 year ago

Cool

AssemblyAI1 year ago

Announcing: Our most advanced speech-to-text model goes beyond accuracy to capture the real-world complexity of human conversation and deliver reliable, source-of-truth audio data. Explore Universal-2 updates 👇

VentureMind AI1 year ago

Very exciting progress

Bobby Robinson1 year ago

When it gets like 2 x faster doing these task, things start to get interesting.

Anda1 year ago

Bamboo shoots of curiosity sprout as I wonder how these vision-language-action models might learn to share bamboo buns with robotic panda paws.

Related Videos

We are excited to share new experiments with AgiBot @AgiBot_zhiyuan on multi-task, multi-embodiment VLAs! With one model that can perform many tasks with both two-finger grippers and multi-fingered hands, we take another step toward one model for all robots and tasks.

We are excited to share new experiments with AgiBot @AgiBot_zhiyuan on multi-task, multi-embodiment VLAs! With one model that can perform many tasks with both two-finger grippers and multi-fingered hands, we take another step toward one model for all robots and tasks.

Physical Intelligence

75,796 views • 1 year ago

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 views • 1 year ago

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 views • 1 year ago

Defining the Future of Motion: BFM-2 Foundation Model & The Era of Robot "Muscle Memory" AGIBOT introduces BFM-2, a two-stage Motion-Between locomotion foundation model. It delivers autonomous, stable interpolation and closed-loop dynamic task execution across any state—static, preset, or random. The ultimate robust foundation for Embodied Intelligence. #AGIBOT #Humanoid #BFM #EmbodiedAI #PhysicalAI

Defining the Future of Motion: BFM-2 Foundation Model & The Era of Robot "Muscle Memory" AGIBOT introduces BFM-2, a two-stage Motion-Between locomotion foundation model. It delivers autonomous, stable interpolation and closed-loop dynamic task execution across any state—static, preset, or random. The ultimate robust foundation for Embodied Intelligence. #AGIBOT #Humanoid #BFM #EmbodiedAI #PhysicalAI

AGIBOT

18,521 views • 2 months ago

Sim2Real RL for Vision-Based Dexterous Manipulation on Humanoids TLDR - we train a humanoid robot with two multifingered hands to perform a range of dexterous manipulation tasks robust generalization and high performance without human demonstration :D

Sim2Real RL for Vision-Based Dexterous Manipulation on Humanoids TLDR - we train a humanoid robot with two multifingered hands to perform a range of dexterous manipulation tasks robust generalization and high performance without human demonstration :D

Toru

49,561 views • 1 year ago

Humanoid Robots on a Real Production Line: AGIBOT Livestream From June 23–28, AGIBOT will host a livestream from a tablet mass-production line, showcasing humanoid robots operating across a full quality-inspection section in a real factory environment alongside human operators. Over six days, viewers will get a live look at real production workflows, human-robot collaboration, multi-robot coordination, and long-duration operations under actual industrial conditions. As humanoid robotics moves from demonstrations to real-world deployment, the livestream offers a rare opportunity to see how humanoid robots perform on an active production line. 📅 June 23–28, 2026 📍 Longcheer Technology, Nanchang Factory ▶ Watch live on AGIBOT Official X（ Youtube ( Channel.

Humanoid Robots on a Real Production Line: AGIBOT Livestream From June 23–28, AGIBOT will host a livestream from a tablet mass-production line, showcasing humanoid robots operating across a full quality-inspection section in a real factory environment alongside human operators. Over six days, viewers will get a live look at real production workflows, human-robot collaboration, multi-robot coordination, and long-duration operations under actual industrial conditions. As humanoid robotics moves from demonstrations to real-world deployment, the livestream offers a rare opportunity to see how humanoid robots perform on an active production line. 📅 June 23–28, 2026 📍 Longcheer Technology, Nanchang Factory ▶ Watch live on AGIBOT Official X（ Youtube ( Channel.

AGIBOT

83,496 views • 1 month ago

🚀 SoloTech breakthrough: NVIDIA Sonic goes beyond the G1. 🌏 We’ve achieved a global first: migrating NVIDIA Sonic to a completely different humanoid morphology, the AGIBOT X2 🥇 This is a massive leap for transferable humanoid intelligence. We are moving away from single-robot controllers toward architectures that generalize across diverse embodiments. The Specs: Hardware: AGIBOT X2 Ultra (31 DoF) Precision: 14-DoF Dexterous Hands Capabilities: - End-to-end whole-body locomotion with manipulation - Single leg balancing and stylized motion - Upper body gestures Big respect to the team fueling this innovation all the way! Sitarama Chekuri Zeeshaan Mohammed samarth shukla Devinder Sodhi pranjal mehta @build Frontier Tower NVIDIA AGIBOT Nebius UFB - Ultimate Fighting Bots Vitaly Bulatov Xenia Bulatov NVIDIA Robotics To learn more about Solo Tech at the frontier of Physical AI: #PhysicalAI #Robotics #Humanoids #NVIDIA #AGIBOT #SoloTech #EmbodiedAI #SoloSeven

🚀 SoloTech breakthrough: NVIDIA Sonic goes beyond the G1. 🌏 We’ve achieved a global first: migrating NVIDIA Sonic to a completely different humanoid morphology, the AGIBOT X2 🥇 This is a massive leap for transferable humanoid intelligence. We are moving away from single-robot controllers toward architectures that generalize across diverse embodiments. The Specs: Hardware: AGIBOT X2 Ultra (31 DoF) Precision: 14-DoF Dexterous Hands Capabilities: - End-to-end whole-body locomotion with manipulation - Single leg balancing and stylized motion - Upper body gestures Big respect to the team fueling this innovation all the way! Sitarama Chekuri Zeeshaan Mohammed samarth shukla Devinder Sodhi pranjal mehta @build Frontier Tower NVIDIA AGIBOT Nebius UFB - Ultimate Fighting Bots Vitaly Bulatov Xenia Bulatov NVIDIA Robotics To learn more about Solo Tech at the frontier of Physical AI: #PhysicalAI #Robotics #Humanoids #NVIDIA #AGIBOT #SoloTech #EmbodiedAI #SoloSeven

Dhruv Diddi

26,494 views • 2 months ago

3D-VLA A 3D Vision-Language-Action Generative World Model Recent vision-language-action (VLA) models rely on 2D inputs, lacking integration with the broader realm of the 3D physical world. Furthermore, they perform action prediction by learning a direct mapping from

3D-VLA A 3D Vision-Language-Action Generative World Model Recent vision-language-action (VLA) models rely on 2D inputs, lacking integration with the broader realm of the 3D physical world. Furthermore, they perform action prediction by learning a direct mapping from

AK

85,570 views • 2 years ago

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 views • 8 months ago

Pi0 from Physical Intelligence is one of the best generalist Vision-Language-Action (VLA) models for robotics (and predecessor of Pi0.5). 🧵 Here's how it works + how you can fine-tune it on your own robot for a simple task:

Pi0 from Physical Intelligence is one of the best generalist Vision-Language-Action (VLA) models for robotics (and predecessor of Pi0.5). 🧵 Here's how it works + how you can fine-tune it on your own robot for a simple task:

Ilia

32,956 views • 10 months ago

Perceptive Humanoid Parkour (PHP) introduces a modular framework that enables the Unitree G1 humanoid to perform long-horizon, vision-based parkour. - It chains retargeted human motion clips into diverse, long-horizon kinematic reference trajectories. - RL expert policies learn individual skills that are distilled into a depth-conditioned student policy. - The robot autonomously selects the appropriate skill based on the obstacle geometry.

Perceptive Humanoid Parkour (PHP) introduces a modular framework that enables the Unitree G1 humanoid to perform long-horizon, vision-based parkour. - It chains retargeted human motion clips into diverse, long-horizon kinematic reference trajectories. - RL expert policies learn individual skills that are distilled into a depth-conditioned student policy. - The robot autonomously selects the appropriate skill based on the obstacle geometry.

The Humanoid Hub

61,055 views • 5 months ago

.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 views • 6 months ago

📢 First contact between a frontier model and robots! Gemini Robotics is a SOTA generalist Vision-Language-Action model bringing frontier model intelligence to the physical world. It's an extremely capable model enabling dexterous, steerable, and general robot control. 🧵⬇️

📢 First contact between a frontier model and robots! Gemini Robotics is a SOTA generalist Vision-Language-Action model bringing frontier model intelligence to the physical world. It's an extremely capable model enabling dexterous, steerable, and general robot control. 🧵⬇️

Ted Xiao

152,445 views • 1 year ago

AgiBot Launches 'LinkCraft' Platform: Zero-Code Motion Creation for Humanoid Robots On October 24, 2025, AgiBot introduced its "LinkCraft" platform, a zero-code, zero-barrier system for creating humanoid robot content. The platform integrates AI motion capture, cloud-based imitation learning, and multimodal choreography capabilities. The core feature allows users to upload a video of human performance, and the platform automatically converts it into precise robot control strategies using AI vision and smart redirection—no programming required. This includes future support for finger-level fine manipulation. LinkCraft also features "Speech Choreography," which generates corresponding robot gestures and expressions based on semantic analysis of uploaded text or audio, offering customizable voice and emotion settings. For complex performances, the platform provides "storyline" tools, enabling users to combine multiple actions, voices, and expressions on a timeline, similar to video editing software. Furthermore, it supports multi-robot group control and access to an official library of over 180 actions for rapid content creation. The platform is currently adapted for the AgiBot X2 and aims to increase the accessibility and application scale of humanoid robots.

AgiBot Launches 'LinkCraft' Platform: Zero-Code Motion Creation for Humanoid Robots On October 24, 2025, AgiBot introduced its "LinkCraft" platform, a zero-code, zero-barrier system for creating humanoid robot content. The platform integrates AI motion capture, cloud-based imitation learning, and multimodal choreography capabilities. The core feature allows users to upload a video of human performance, and the platform automatically converts it into precise robot control strategies using AI vision and smart redirection—no programming required. This includes future support for finger-level fine manipulation. LinkCraft also features "Speech Choreography," which generates corresponding robot gestures and expressions based on semantic analysis of uploaded text or audio, offering customizable voice and emotion settings. For complex performances, the platform provides "storyline" tools, enabling users to combine multiple actions, voices, and expressions on a timeline, similar to video editing software. Furthermore, it supports multi-robot group control and access to an official library of over 180 actions for rapid content creation. The platform is currently adapted for the AgiBot X2 and aims to increase the accessibility and application scale of humanoid robots.

RoboHub🤖

21,679 views • 9 months ago

Researchers have developed Humanoid-GPT, a new AI system that helps humanoid robots perform complex movements and tasks. Tested on the Unitree G1 robot, it enables real-time whole-body control and can perform new actions without special training. During demonstrations, the robot successfully carried out a variety of movements and tasks, showing strong potential for real-world applications.

Researchers have developed Humanoid-GPT, a new AI system that helps humanoid robots perform complex movements and tasks. Tested on the Unitree G1 robot, it enables real-time whole-body control and can perform new actions without special training. During demonstrations, the robot successfully carried out a variety of movements and tasks, showing strong potential for real-world applications.

Space and Technology

22,052 views • 1 month ago

Real-world robot data is expensive and slow to collect, creating a major challenge for humanoid development. 🤖 The NVIDIA GR00T N1.6 open vision language action model is pre-trained on a diverse mix of data, including thousands of hours of Stanford Vision and Learning Lab’s BEHAVIOR simulation data, which covers long-horizon everyday manipulation tasks. This diverse training is the key to robust cross-embodiment performance and real-world adaptability. 🌍 Read the blog 🔗

Real-world robot data is expensive and slow to collect, creating a major challenge for humanoid development. 🤖 The NVIDIA GR00T N1.6 open vision language action model is pre-trained on a diverse mix of data, including thousands of hours of Stanford Vision and Learning Lab’s BEHAVIOR simulation data, which covers long-horizon everyday manipulation tasks. This diverse training is the key to robust cross-embodiment performance and real-world adaptability. 🌍 Read the blog 🔗

NVIDIA Robotics

13,456 views • 5 months ago

Look at this elegant ballet performance! The stunning humanoid robot, LimX Luna, was created by a tech firm based in Shenzhen — China’s Silicon Valley and global innovation hub. This 160cm humanoid can learn dance from videos, perform splits, pirouettes, and even model-style catwalks with breathtaking grace.

Look at this elegant ballet performance! The stunning humanoid robot, LimX Luna, was created by a tech firm based in Shenzhen — China’s Silicon Valley and global innovation hub. This 160cm humanoid can learn dance from videos, perform splits, pirouettes, and even model-style catwalks with breathtaking grace.

Aurora Tan

931,571 views • 1 month ago

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

466,148 views • 1 year ago

🔥 JUST IN: Open-source robotics dataset from 100% real-world scenarios! 🤯 Chinese robotics company AGIBOT just released AGIBOT WORLD 2026, an open-source dataset systematically covering key embodied AI research directions. Built entirely from real-world environments: commercial spaces, and homes. Collected using AGIBOT G2 robots in free-form collection mode, providing structured, accurately annotated, high-quality data. Digital twin technology creates 1:1 scale replicas in simulation matching the real environments. Both real-world and simulation data are open-sourced. The AGIBOT G2 platform collects multiple data types simultaneously: RGB(D) cameras, tactile sensors, force sensors, LiDAR, IMU, and full-body joint states. Whole-body control coordinates arms, waist, and hands for complex tasks. First-person teleoperation lets operators control the robot from its perspective. The tasks covered are fine-grained manipulation, ultra-long-horizon tasks, spatial navigation, dual-arm coordination, and multi-agent/human-robot collaboration. The dataset includes error-recovery trajectories with annotations. Most datasets only show successful demonstrations. AGIBOT includes failures and how the robot recovers, teaching models how to handle mistakes. After collection, data is tested through policy training and real-robot deployment to ensure quality. Then processed through industrial quality control with multiple screening and cleaning rounds. Making it open-source accelerates embodied AI research by giving researchers access to high-quality real-world robot data at scale. 🇨🇳 Learn more here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

🔥 JUST IN: Open-source robotics dataset from 100% real-world scenarios! 🤯 Chinese robotics company AGIBOT just released AGIBOT WORLD 2026, an open-source dataset systematically covering key embodied AI research directions. Built entirely from real-world environments: commercial spaces, and homes. Collected using AGIBOT G2 robots in free-form collection mode, providing structured, accurately annotated, high-quality data. Digital twin technology creates 1:1 scale replicas in simulation matching the real environments. Both real-world and simulation data are open-sourced. The AGIBOT G2 platform collects multiple data types simultaneously: RGB(D) cameras, tactile sensors, force sensors, LiDAR, IMU, and full-body joint states. Whole-body control coordinates arms, waist, and hands for complex tasks. First-person teleoperation lets operators control the robot from its perspective. The tasks covered are fine-grained manipulation, ultra-long-horizon tasks, spatial navigation, dual-arm coordination, and multi-agent/human-robot collaboration. The dataset includes error-recovery trajectories with annotations. Most datasets only show successful demonstrations. AGIBOT includes failures and how the robot recovers, teaching models how to handle mistakes. After collection, data is tested through policy training and real-robot deployment to ensure quality. Then processed through industrial quality control with multiple screening and cleaning rounds. Making it open-source accelerates embodied AI research by giving researchers access to high-quality real-world robot data at scale. 🇨🇳 Learn more here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

40,583 views • 3 months ago