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.

Apple's AI researchers introduce EMOTION, a framework for expressive humanoid gestures. ⦿ LLMs interpret social context and generate motions from human demos ⦿ Robots execute motions via inverse kinematics ⦿ Gestures are refined through human feedback Hardware: Fourier GR-1

The Humanoid Hub

86,339 subscribers

66,831 views • 1 year ago •via X (Twitter)

Science & Technology Education

Anya Rossi• Live Now

Private livecam show

11 Comments

The Humanoid Hub1 year ago

Paper:

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 👇

Tom Löwe1 year ago

If Apple was smart, they would be pouring all of their available resources into building a humanoid robot.

Ai Handbook 🔖1 year ago

Mate, this robotic field with AI is getting crazy! I really wonder when we use these in our homes on a daily basis.

Gahro1 year ago

I read "Human Retarded"

Marcus van der Erve✨1 year ago

Simplistic

ADEBIG💎 (✸,✸) (✸,✸) ⛺1 year ago

Looks like robots are getting in touch with their feelings! With PublicAI, we can teach them to express gratitude for all the data we provide! 😂🤖

Ngoc Nguyễn1 year ago

Looks like robots are getting their groove on! 🤖💃 With PublicAI, we can add some top-notch training data to help them nail those gestures! #AI #DanceOff

Elvis Efe1 year ago

Looks like Apple’s robots are getting a crash course in human emotions! At PublicAI, we’re all about bridging gaps too—just with a bit more data and a lot more fun! 🤖✨

SÅÏDĖÑ1 year ago

Wow 😵‍💫

Appy Pie1 year ago

Apple is stepping up its AI game! Expressive humanoid gestures could revolutionize human-robot interaction.

Related Videos

🤖 Introducing Human-Object Interaction from Human-Level Instructions! First complete system that generates physically plausible, long-horizon human-object interactions with finger motions in contextual environments, driven by human-level instructions. 🔍 Our approach: - LLMs transform instructions into execution plans & target layouts - Multi-stage framework generates synchronized object, body & finger motions - RL policy tracks generated motions in physics simulation Project: Demo: Paper:

🤖 Introducing Human-Object Interaction from Human-Level Instructions! First complete system that generates physically plausible, long-horizon human-object interactions with finger motions in contextual environments, driven by human-level instructions. 🔍 Our approach: - LLMs transform instructions into execution plans & target layouts - Multi-stage framework generates synchronized object, body & finger motions - RL policy tracks generated motions in physics simulation Project: Demo: Paper:

Jiaman Li

104,609 views • 1 year ago

Any2Track tracks diverse motions under various disturbances. The two-stage RL framework learns to track contact-rich human motions from motion capture datasets and adds adaptability to disturbances via dynamics-aware model prediction.

Any2Track tracks diverse motions under various disturbances. The two-stage RL framework learns to track contact-rich human motions from motion capture datasets and adds adaptability to disturbances via dynamics-aware model prediction.

The Humanoid Hub

146,105 views • 9 months ago

Let’s think about humanoid robots outside carrying the box. How about having the humanoid come out the door, interact with humans, and even dance? Introducing Expressive Whole-Body Control for Humanoid Robots: See how our robot performs rich, diverse, and expressive motions in the real world 👇🧵

Let’s think about humanoid robots outside carrying the box. How about having the humanoid come out the door, interact with humans, and even dance? Introducing Expressive Whole-Body Control for Humanoid Robots: See how our robot performs rich, diverse, and expressive motions in the real world 👇🧵

Xiaolong Wang

309,097 views • 2 years ago

RobotMDM, by Disney Research, combines diffusion-based motion generation with RL to produce physics-aware humanoid motions from text prompts. Trained on human motion data with a reward surrogate for physical feasibility, it ensures realistic motions.

RobotMDM, by Disney Research, combines diffusion-based motion generation with RL to produce physics-aware humanoid motions from text prompts. Trained on human motion data with a reward surrogate for physical feasibility, it ensures realistic motions.

The Humanoid Hub

22,943 views • 1 year ago

Animals communicate through sounds and gestures, even without human-like language…

Animals communicate through sounds and gestures, even without human-like language…

Tansu Yegen

138,701 views • 3 years ago

Optimus idle gestures are awesome. Just like a human.

Optimus idle gestures are awesome. Just like a human.

Nic Cruz Patane

78,014 views • 7 months ago

Japanese robotics startup Tokyo Robotics has developed a humanoid robot called Torobo. The robot walks with smooth and natural human-like movement. It can also copy human motions in real time through full-body remote control while maintaining good balance.

Japanese robotics startup Tokyo Robotics has developed a humanoid robot called Torobo. The robot walks with smooth and natural human-like movement. It can also copy human motions in real time through full-body remote control while maintaining good balance.

Space and Technology

113,583 views • 1 month ago

TextOp: A real-time text-to-motion framework for humanoid robots. It allows users to instruct the robot using natural language and to modify commands on the fly, producing smooth, whole-body motions instantly.

TextOp: A real-time text-to-motion framework for humanoid robots. It allows users to instruct the robot using natural language and to modify commands on the fly, producing smooth, whole-body motions instantly.

The Humanoid Hub

25,125 views • 7 months ago

Excited to announce the MouthPad^, a wearable device that enables expressive, discreet, and convenient hands-free control of digital devices through tongue and other mouth gestures! The MouthPad^ reimagines accessibility and pushes the boundaries of human-computer interaction 1/5

Excited to announce the MouthPad^, a wearable device that enables expressive, discreet, and convenient hands-free control of digital devices through tongue and other mouth gestures! The MouthPad^ reimagines accessibility and pushes the boundaries of human-computer interaction 1/5

Tomás Vega

68,546 views • 3 years ago

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 views • 1 year ago

Humanoid motion tracking performance is greatly determined by retargeting quality! Introducing 𝗢𝗺𝗻𝗶𝗥𝗲𝘁𝗮𝗿𝗴𝗲𝘁🎯, generating high-quality interaction-preserving data from human motions for learning complex humanoid skills with 𝗺𝗶𝗻𝗶𝗺𝗮𝗹 RL: - 5 rewards, - 4 DR terms, - Proprio. ONLY, - NO history/curriculum. Ready for agile, human-like 🤖? (Best with 🎧) 🔗 🎥 1/9

Humanoid motion tracking performance is greatly determined by retargeting quality! Introducing 𝗢𝗺𝗻𝗶𝗥𝗲𝘁𝗮𝗿𝗴𝗲𝘁🎯, generating high-quality interaction-preserving data from human motions for learning complex humanoid skills with 𝗺𝗶𝗻𝗶𝗺𝗮𝗹 RL: - 5 rewards, - 4 DR terms, - Proprio. ONLY, - NO history/curriculum. Ready for agile, human-like 🤖? (Best with 🎧) 🔗 🎥 1/9

Zhen Wu

811,218 views • 8 months ago

HDMI (HumanoiD iMitation for Interaction) is a framework enabling humanoid robots to learn whole-body object interaction skills from monocular RGB human videos. It extracts and retargets human poses and object trajectories using GVHMR and LocoMujoco, building reference datasets with contact annotations. The data is used to train an RL policy via robot-object co-tracking. HDMI achieved 67 consecutive door traversals.

HDMI (HumanoiD iMitation for Interaction) is a framework enabling humanoid robots to learn whole-body object interaction skills from monocular RGB human videos. It extracts and retargets human poses and object trajectories using GVHMR and LocoMujoco, building reference datasets with contact annotations. The data is used to train an RL policy via robot-object co-tracking. HDMI achieved 67 consecutive door traversals.

The Humanoid Hub

17,395 views • 9 months ago

YES! YES! YES! OKAY, with how limited his facial expressions are, I LOOOVVEEE how expressive Toro is through his body language and gestures in this game, especially during cutscenes. It's so human?? He's animated so fluently 😭

YES! YES! YES! OKAY, with how limited his facial expressions are, I LOOOVVEEE how expressive Toro is through his body language and gestures in this game, especially during cutscenes. It's so human?? He's animated so fluently 😭

BeeJay

104,197 views • 11 months ago

The biggest bottleneck for General Purpose Robots isn't hardware, it's data. Enter X-Humanoid: A pipeline from Mike Shou and team that "robotizes" huge human video datasets for training. The Key Insight: It solves the "visual embodiment gap." 🧠 Robots learn faster when the training pixels match their own hardware (metal & joints) rather than human skin and fluid motion. Read more here:

The biggest bottleneck for General Purpose Robots isn't hardware, it's data. Enter X-Humanoid: A pipeline from Mike Shou and team that "robotizes" huge human video datasets for training. The Key Insight: It solves the "visual embodiment gap." 🧠 Robots learn faster when the training pixels match their own hardware (metal & joints) rather than human skin and fluid motion. Read more here:

Humanoids daily

45,350 views • 6 months ago

2. NVIDIA is building the GPT of humanoid robots. They just launched Isaac GR00T N1.5 - a foundation model for general purpose robotics. Here’s how it works: → A human demos the task once → Cosmos (their physics AI model) generates 1,000s of variations → Omniverse simulates the motions in high fidelity → The robot trains entirely in simulation → Then fine-tunes itself in the real world Robots can now learn general skills across tasks, tools, even body types with just one human demo. AI isn’t just thinking in text anymore. It’s perceiving. Reasoning. Moving. Physical AI is here and it’s training itself.

2. NVIDIA is building the GPT of humanoid robots. They just launched Isaac GR00T N1.5 - a foundation model for general purpose robotics. Here’s how it works: → A human demos the task once → Cosmos (their physics AI model) generates 1,000s of variations → Omniverse simulates the motions in high fidelity → The robot trains entirely in simulation → Then fine-tunes itself in the real world Robots can now learn general skills across tasks, tools, even body types with just one human demo. AI isn’t just thinking in text anymore. It’s perceiving. Reasoning. Moving. Physical AI is here and it’s training itself.

Shruti

70,359 views • 1 year ago

New tech lets robots read and anticipate our movements in real time Good for human-humanoid safety. A challenge for AI Governance and Privacy

New tech lets robots read and anticipate our movements in real time Good for human-humanoid safety. A challenge for AI Governance and Privacy

Glen Gilmore

31,125 views • 1 month ago

🇮🇳 AI DATA RACE: Workers in Indian factories started to wear cameras on their heads, to film their motions so robots can be trained on these videos. Big robot companies will train their humanoid robots, on movement data from Indian sweatshops … Wild 1/

🇮🇳 AI DATA RACE: Workers in Indian factories started to wear cameras on their heads, to film their motions so robots can be trained on these videos. Big robot companies will train their humanoid robots, on movement data from Indian sweatshops … Wild 1/

Lord Bebo

532,247 views • 2 months ago

Training robots just got TikTok easy. Ultimate Bots Studio lets you make dances, gestures, full motion flows in 3 easy steps: 1) Upload a video → create a motion 2) Stitch motions → build a dance 3) Export to robot and share with community Try it -> link in the comments

Training robots just got TikTok easy. Ultimate Bots Studio lets you make dances, gestures, full motion flows in 3 easy steps: 1) Upload a video → create a motion 2) Stitch motions → build a dance 3) Export to robot and share with community Try it -> link in the comments

Vitaly Bulatov

901,796 views • 1 month ago

Sprout, a 3 1/2-foot-tall humanoid from Fauna Robotics, debuts with a soft foam body, expressive moves and a friendly vibe. Built for human spaces, it’s aimed at developers and labs.

Sprout, a 3 1/2-foot-tall humanoid from Fauna Robotics, debuts with a soft foam body, expressive moves and a friendly vibe. Built for human spaces, it’s aimed at developers and labs.

The Associated Press

90,290 views • 4 months ago