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.

Combining real-time interactivity, task understanding, and full-body action prediction on a humanoid is so, so hard. Here's an example where we bring all of these together in Gemini Robotics 2 🤖🧠

Annie Chen

1,397 subscribers

40,103 views • 8 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Elon Musk: Optimus is awesome! “Something that's going to be very important in the future is combining deep AI in the data center or supercluster with robotics, like the Optimus humanoid robot. Optimus is awesome! There's going to be so many humanoid robots and robots of all sizes and shapes. But my prediction is that there will be more humanoid robots by far than all other robots combined by maybe an order of magnitude, like a big difference.” Interview at Y Combinator, June 16, 2025

Elon Musk: Optimus is awesome! “Something that's going to be very important in the future is combining deep AI in the data center or supercluster with robotics, like the Optimus humanoid robot. Optimus is awesome! There's going to be so many humanoid robots and robots of all sizes and shapes. But my prediction is that there will be more humanoid robots by far than all other robots combined by maybe an order of magnitude, like a big difference.” Interview at Y Combinator, June 16, 2025

ELON CLIPS

23,613 views • 11 months ago

ELON: HUMANOID ROBOTS WILL OUTNUMBER OTHER ROBOTS BY FAR “Something that's going to be very important in the future is combining deep AI in the data center or supercluster with robotics, like the Optimus humanoid robot. Optimus is awesome. There's going to be so many humanoid robots and robots of all sizes and shapes. But my prediction is that there will be more humanoid robots by far than all other robots combined by maybe an order of magnitude, like a big difference.” Source: Interview at Y Combinator, June 2025

ELON: HUMANOID ROBOTS WILL OUTNUMBER OTHER ROBOTS BY FAR “Something that's going to be very important in the future is combining deep AI in the data center or supercluster with robotics, like the Optimus humanoid robot. Optimus is awesome. There's going to be so many humanoid robots and robots of all sizes and shapes. But my prediction is that there will be more humanoid robots by far than all other robots combined by maybe an order of magnitude, like a big difference.” Source: Interview at Y Combinator, June 2025

Mario Nawfal

89,193 views • 1 year ago

Sundar Pichai on the robotics opportunity: ⦿ He's impressed by recent humanoid progress - so much so that he sometimes has to look closely to tell if a robot video is real or fake. ⦿ Google initially moved too early into the application layer, but now sees the combination of AI and robotics as the “sweet spot.” ⦿ He believes we’re 2–3 years away from a “magical moment” in robotics. ⦿ Google is working on playing a role similar to Android in robotics - one of its internal bets is already focused on supporting robotics manufacturers. ⦿ Gemini robotics models will work very well - how to productize them is still an open question at the company.

Sundar Pichai on the robotics opportunity: ⦿ He's impressed by recent humanoid progress - so much so that he sometimes has to look closely to tell if a robot video is real or fake. ⦿ Google initially moved too early into the application layer, but now sees the combination of AI and robotics as the “sweet spot.” ⦿ He believes we’re 2–3 years away from a “magical moment” in robotics. ⦿ Google is working on playing a role similar to Android in robotics - one of its internal bets is already focused on supporting robotics manufacturers. ⦿ Gemini robotics models will work very well - how to productize them is still an open question at the company.

The Humanoid Hub

87,088 views • 1 year ago

Gemini Robotics ER 2 is our most capable embodied reasoning model designed for physical AI 🤖 Built as a high-level brain for robotics, the model connects directly to the Gemini Live API. It processes continuous video streams to track progress, call tools, search the web, and command an action model in real time. Upgrades for developers include: + Enhanced progress tracking + Real-time mid-execution failure detection + Multi-robot collaboration + Advanced safety instruction following

Gemini Robotics ER 2 is our most capable embodied reasoning model designed for physical AI 🤖 Built as a high-level brain for robotics, the model connects directly to the Gemini Live API. It processes continuous video streams to track progress, call tools, search the web, and command an action model in real time. Upgrades for developers include: + Enhanced progress tracking + Real-time mid-execution failure detection + Multi-robot collaboration + Advanced safety instruction following

Google AI Developers

20,067 views • 9 days ago

How do you give a humanoid the general motion capability? Not just single motions, but all motion? Introducing SONIC, our new work on supersizing motion tracking for natural humanoid control. We argue that motion tracking is the scalable foundation task for humanoids. So we "supersized" it: 9k+ GPU hours and 100M+ motion frames. But tracking alone is not enough; we show how to make a useful control system out of it: - Universal Kinematic Planner: Enables game-like gamepad control and high-level teleoperation, just like controlling a character in a game. - VR Full-Body Teleop: Direct, real-time whole-body control by a human wearing a VR headset. - VR Keypoint Teleop: Control the upper body (hands/head) while our planner handles robust locomotion automatically. - VLA Integration: We connect this motion tracker to autonomous Visual-Language-Action (VLA) models for autonomous task execution! We use a Universal Token Space to UNIFY this command space, turning our robust tracker into a general-purpose, programmable humanoid brain. This is the generalist "System 1" for humanoids. 🚀 Project: #Humanoids #Robotics #AI #FoundationModels #NVIDIAResearch 🧠🔥

How do you give a humanoid the general motion capability? Not just single motions, but all motion? Introducing SONIC, our new work on supersizing motion tracking for natural humanoid control. We argue that motion tracking is the scalable foundation task for humanoids. So we "supersized" it: 9k+ GPU hours and 100M+ motion frames. But tracking alone is not enough; we show how to make a useful control system out of it: - Universal Kinematic Planner: Enables game-like gamepad control and high-level teleoperation, just like controlling a character in a game. - VR Full-Body Teleop: Direct, real-time whole-body control by a human wearing a VR headset. - VR Keypoint Teleop: Control the upper body (hands/head) while our planner handles robust locomotion automatically. - VLA Integration: We connect this motion tracker to autonomous Visual-Language-Action (VLA) models for autonomous task execution! We use a Universal Token Space to UNIFY this command space, turning our robust tracker into a general-purpose, programmable humanoid brain. This is the generalist "System 1" for humanoids. 🚀 Project: #Humanoids #Robotics #AI #FoundationModels #NVIDIAResearch 🧠🔥

Zhengyi “Zen” Luo

62,208 views • 9 months ago

🤖 Introducing H2O (Human2HumanOid): - 🧠 An RL-based human-to-humanoid real-time whole-body teleoperation framework - 💃 Scalable retargeting and training using large human motion dataset - 🎥 With just an RGB camera, everyone can teleoperate a full-sized humanoid to perform actions like pick and place, walking, kicking, boxing, etc - 💡Unleash the potential of humanoids with human cognitive skills and adaptability 🔗:

🤖 Introducing H2O (Human2HumanOid): - 🧠 An RL-based human-to-humanoid real-time whole-body teleoperation framework - 💃 Scalable retargeting and training using large human motion dataset - 🎥 With just an RGB camera, everyone can teleoperate a full-sized humanoid to perform actions like pick and place, walking, kicking, boxing, etc - 💡Unleash the potential of humanoids with human cognitive skills and adaptability 🔗:

Tairan He

96,738 views • 2 years ago

🤔 Ever wondered if simulation-based animation/avatar learnings can be applied to real humanoid in real-time? 🤖 Introducing H2O (Human2HumanOid): - 🧠 An RL-based human-to-humanoid real-time whole-body teleoperation framework - 💃 Scalable retargeting and training using large human motion dataset - 🎥 With just an RGB camera, everyone can teleoperate a full-sized humanoid to perform actions like pick and place, walking, kicking, boxing, etc - 💡Unleash the potential of humanoids with human cognitive skills and adaptability 🔗: 📄: 🎬: H2O proposes: - A scalable retargeting framework for obtaining large-scale humanoid motion dataset, intelligently filtering out infeasible motion for the humanoid embodiment. - We train a full-body motion imitator (similar to PHC) and deploy to the real world zero-shot. - Using this framework, we enable real-time teleoperation of a humanoid via a human operator and webcam, performing skills such as pick and place, kicking, walking strollers, etc. Team: Tairan He Zhengyi “Zen” Luo Wenli Xiao @ChongZitaZhang Kris Kitani Changliu Liu Guanya Shi

Zhengyi “Zen” Luo

47,323 views • 2 years ago

An astonishing era is upon us and so many of you with time 🕰️ on your hands have to please consider getting educated on how to use these tools - 🤖 is a shocking opportunity for the kids in high school , college or right after school with time on hand. Vibe coding websites, ai creative services with a little more effort - Build Micro-AI Services aka Niche Tools and change. This is an astonishing time of opportunity.. the real question is Will you put in the effort ? Don’t know where to start? Ask ChatGPT or Gemini or grok

An astonishing era is upon us and so many of you with time 🕰️ on your hands have to please consider getting educated on how to use these tools - 🤖 is a shocking opportunity for the kids in high school , college or right after school with time on hand. Vibe coding websites, ai creative services with a little more effort - Build Micro-AI Services aka Niche Tools and change. This is an astonishing time of opportunity.. the real question is Will you put in the effort ? Don’t know where to start? Ask ChatGPT or Gemini or grok

Gary Vaynerchuk

26,988 views • 10 months ago

Most robotics AI models suffer from the "stop-and-think" problem. They take a static picture, pause to reason, execute an action, and repeat. In the real world, that latency causes spills, collisions, and failed tasks. Google DeepMind just launched Gemini Robotics ER 2: an embodied reasoning model that thinks and acts at the speed of the physical world. Here's why this is a step-change for physical AI engineering: Traditional robotics models rely on static snapshots. But knowing *when* a task is done, such as when to stop pouring coffee into a cup or when a trash bag is securely tied, requires continuous temporal awareness. Gemini Robotics ER 2 integrates directly with the bidirectional streaming Gemini Live API to reason about what comes next while simultaneously executing motor actions. What makes Gemini Robotics ER 2 different: 🎯 91.3% accuracy on live video moment-finding (0.96s mean absolute distance) at 4x the execution speed of frontier models 📈 Continuous progress tracking across 5 completion stages (57.4% accuracy) to self-correct mid-task without restarting 🛠️ Native agentic tool orchestration that commands lower-level VLA models, navigation APIs, and Google Search 🤝 Multi-robot collaboration allowing physically diverse machines (like Apptronik's Apollo 2 humanoid and Franka's FR3 Duo arm) to hand off tasks in shared spaces 🛡️ Built-in physical safety that autonomously halts robots when humans enter a workspace and resumes once clear

Most robotics AI models suffer from the "stop-and-think" problem. They take a static picture, pause to reason, execute an action, and repeat. In the real world, that latency causes spills, collisions, and failed tasks. Google DeepMind just launched Gemini Robotics ER 2: an embodied reasoning model that thinks and acts at the speed of the physical world. Here's why this is a step-change for physical AI engineering: Traditional robotics models rely on static snapshots. But knowing when a task is done, such as when to stop pouring coffee into a cup or when a trash bag is securely tied, requires continuous temporal awareness. Gemini Robotics ER 2 integrates directly with the bidirectional streaming Gemini Live API to reason about what comes next while simultaneously executing motor actions. What makes Gemini Robotics ER 2 different: 🎯 91.3% accuracy on live video moment-finding (0.96s mean absolute distance) at 4x the execution speed of frontier models 📈 Continuous progress tracking across 5 completion stages (57.4% accuracy) to self-correct mid-task without restarting 🛠️ Native agentic tool orchestration that commands lower-level VLA models, navigation APIs, and Google Search 🤝 Multi-robot collaboration allowing physically diverse machines (like Apptronik's Apollo 2 humanoid and Franka's FR3 Duo arm) to hand off tasks in shared spaces 🛡️ Built-in physical safety that autonomously halts robots when humans enter a workspace and resumes once clear

Karl Weinmeister

26,179 views • 9 days ago

My sweet baby girl, the time has passed too fast. We tried so hard to have you here and you have been such an incredible blessing to us. You are so full of sass and personality, incredibly smart and you bring a smile to all of our faces daily. We love you Lenni!

My sweet baby girl, the time has passed too fast. We tried so hard to have you here and you have been such an incredible blessing to us. You are so full of sass and personality, incredibly smart and you bring a smile to all of our faces daily. We love you Lenni!

Samantha Busch

44,092 views • 2 years ago

the raw input podcast is back!! thank you for all your support so far, we're gonna shoot for an episode every 2-3 weeks. full video in the replies! here's a segment where we theorycraft competitive kovaaks LOL

the raw input podcast is back!! thank you for all your support so far, we're gonna shoot for an episode every 2-3 weeks. full video in the replies! here's a segment where we theorycraft competitive kovaaks LOL

pinguefy

64,442 views • 1 year ago

This video I'm replying to is a good example of not understanding certain fundamental jungle things on a base level, as well as completely not understanding laning at all, and so I felt like replying

This video I'm replying to is a good example of not understanding certain fundamental jungle things on a base level, as well as completely not understanding laning at all, and so I felt like replying

LS

119,786 views • 3 months ago

🚨PUSH THE BUTTON🚨 Live video editing is a form of video editing where the footage is not pre-recorded. I create this on my own in real time- live. My mind, body & tech integrate to allow me to enter 🌸Flow State🌸 Here's an example of that #KickStreamers #TwitchStreamers

🚨PUSH THE BUTTON🚨 Live video editing is a form of video editing where the footage is not pre-recorded. I create this on my own in real time- live. My mind, body & tech integrate to allow me to enter 🌸Flow State🌸 Here's an example of that #KickStreamers #TwitchStreamers

BBJESS

119,016 views • 3 years ago

.travis kalanick on why specialized robots beat humanoids for real work: "I'm not anti-humanoid, I'm non-humanoid. There are tasks that are good for humanoids, low scale, high diversity, in human environments, humanoid all the way. But the minute you have a machine doing a high-scale task, we're no longer in humanoid land, we're in specialized robotics land." "There was a moment nine months ago where humanoids were the mega rage of all time. When your hairdresser says he's getting into the humanoid business, we know something's wrong." "If I had to make 1,000 pancakes an hour, I'd never have a humanoid do it, you'd need 100 humanoids going gg-gg-gg. It's like the humanoid Olympics in Beijing, they're doing the marathon and it's cool, but all I could think is, imagine if you put wheels on them. Would you ever put a humanoid in a car to drive it?" "High scale, repetitive tasks do not need to be in human form, and they won't be, because humans are meant to do lots of things at low scale."

.travis kalanick on why specialized robots beat humanoids for real work: "I'm not anti-humanoid, I'm non-humanoid. There are tasks that are good for humanoids, low scale, high diversity, in human environments, humanoid all the way. But the minute you have a machine doing a high-scale task, we're no longer in humanoid land, we're in specialized robotics land." "There was a moment nine months ago where humanoids were the mega rage of all time. When your hairdresser says he's getting into the humanoid business, we know something's wrong." "If I had to make 1,000 pancakes an hour, I'd never have a humanoid do it, you'd need 100 humanoids going gg-gg-gg. It's like the humanoid Olympics in Beijing, they're doing the marathon and it's cool, but all I could think is, imagine if you put wheels on them. Would you ever put a humanoid in a car to drive it?" "High scale, repetitive tasks do not need to be in human form, and they won't be, because humans are meant to do lots of things at low scale."

MTS

52,573 views • 17 days ago

Supercomputer is so good people are actually questioning if the results are real. So here's a recording of an actual workflow and all of the agents at work. Actually nuts.

Supercomputer is so good people are actually questioning if the results are real. So here's a recording of an actual workflow and all of the agents at work. Actually nuts.

Brett

148,700 views • 2 months ago

"Damiano and I are so in love, it's embarrassing. When we're apart for a week it's awful. We keep each other updated on our day, we send endless voice notes. We live together, spend all of our time together. We're so chill and compatible, we don't need time apart."

"Damiano and I are so in love, it's embarrassing. When we're apart for a week it's awful. We keep each other updated on our day, we send endless voice notes. We live together, spend all of our time together. We're so chill and compatible, we don't need time apart."

Naya🌙

306,364 views • 5 months ago

Elon Musk: There are going to be so many humanoid robots. My prediction? More humanoids than all other robots combined — by an order of magnitude. It’s happening, whether we like it or not. He says he hesitated because he didn’t want to make Terminator real. Now? “Pedal to the metal.” AI, robotics, and superintelligence are merging — and he’s choosing to participate, not watch.

Elon Musk: There are going to be so many humanoid robots. My prediction? More humanoids than all other robots combined — by an order of magnitude. It’s happening, whether we like it or not. He says he hesitated because he didn’t want to make Terminator real. Now? “Pedal to the metal.” AI, robotics, and superintelligence are merging — and he’s choosing to participate, not watch.

Ian Miles Cheong

41,528 views • 9 months ago

Another win for open-source robotics! 🔥 Hugging Face just released a fully open-source humanoid robot, and you can build one for $2,500. I'm a huge advocate of open-source in robotics space. Why? Robotics is too hard to solve alone. So lowering the entry point is crucial. Also, ROS proved open ecosystems create lasting industry standards. So let's have a look at the new member of humanoids family! LeRobot Humanoid is a 3D-printed, bipedal humanoid platform designed for real robot learning experiments. It's a complete and, buildable robot Anddddd yes, it's a full stack release: → Hardware files, bill of materials and full assembly documentation → Simulation assets and training environments → Runtime tools for calibration and real-world control → Sim-to-real identification pipeline When a part breaks, reprint it. When a design choice doesn't work, modify it and test again. The whole point is fast iteration on real hardware, not treating the robot as a fixed artefact. The timing is not a coincidence. As foundation models for robotics mature, the field desperately needs open physical platforms to train, validate and deploy them on. clem 🤗 LET'S GO!!! Build it here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Another win for open-source robotics! 🔥 Hugging Face just released a fully open-source humanoid robot, and you can build one for $2,500. I'm a huge advocate of open-source in robotics space. Why? Robotics is too hard to solve alone. So lowering the entry point is crucial. Also, ROS proved open ecosystems create lasting industry standards. So let's have a look at the new member of humanoids family! LeRobot Humanoid is a 3D-printed, bipedal humanoid platform designed for real robot learning experiments. It's a complete and, buildable robot Anddddd yes, it's a full stack release: → Hardware files, bill of materials and full assembly documentation → Simulation assets and training environments → Runtime tools for calibration and real-world control → Sim-to-real identification pipeline When a part breaks, reprint it. When a design choice doesn't work, modify it and test again. The whole point is fast iteration on real hardware, not treating the robot as a fixed artefact. The timing is not a coincidence. As foundation models for robotics mature, the field desperately needs open physical platforms to train, validate and deploy them on. clem 🤗 LET'S GO!!! Build it here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

20,361 views • 2 months ago

CHAT, IS THIS REAL??? i worked on the latest animated short for filian, featuring Neuro-sama 💜! first time working on one of these videos, so i hope you all enjoy! 🎊🎊🎊 🔽 here's a before and after of the short 🔽

CHAT, IS THIS REAL??? i worked on the latest animated short for filian, featuring Neuro-sama 💜! first time working on one of these videos, so i hope you all enjoy! 🎊🎊🎊 🔽 here's a before and after of the short 🔽

ThePandaPunchGamer 🐼👊 COMMS CLOSED

63,942 views • 1 year ago