Loading video...

Video Failed to Load

Go Home

Google just announced Gemini Robotics 2, extending its physical AI models beyond tabletop manipulation. A robot tying a trash bag sounds routine, but might be a bigger breakthrough than it seems:

TheRundownAI's profile picture

The Rundown AI

224,837 subscribers

19,002 views • 14 days ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Gemini Robotics 2 moves physical AI beyond tabletop tasks, enabling intelligent whole-body control for humanoids. Watch Apptronik's Apollo 2 process a single prompt to reach, bend, and pick up a watering can ↓
1:29

Gemini Robotics 2 moves physical AI beyond tabletop tasks, enabling intelligent whole-body control for humanoids. Watch Apptronik's Apollo 2 process a single prompt to reach, bend, and pick up a watering can ↓

Google DeepMind

41,342 views • 14 days ago

Google DeepMind just introduced Gemini Robotics 2. It's a single VLA that unlocks physical dexterity across different end effectors, hands or grippers, from one model checkpoint. Apptronik's Apollo 2 humanoid, with the 22-DoF SharpaWave hand, ties knots and seals a ziplock bag
2:03

Google DeepMind just introduced Gemini Robotics 2. It's a single VLA that unlocks physical dexterity across different end effectors, hands or grippers, from one model checkpoint. Apptronik's Apollo 2 humanoid, with the 22-DoF SharpaWave hand, ties knots and seals a ziplock bag

The Humanoid Hub

131,993 views • 14 days ago

Boston Dynamics and Google DeepMind announced a partnership to integrate Gemini Robotics AI models with the new electric Atlas humanoid robots. Got to say hi to Carolina Parada before the presentation
0:31

Boston Dynamics and Google DeepMind announced a partnership to integrate Gemini Robotics AI models with the new electric Atlas humanoid robots. Got to say hi to Carolina Parada before the presentation

The Humanoid Hub

14,689 views • 7 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
2:59

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

28,107 views • 14 days ago

Watching someone easily bypass ChatGPT's safety rules on this Unitree G1 robot to fire a BB gun at its operator is definitely cause for alarm. It might be about time we dust off Isaac Asimov's Three Laws of Robotics/physical AI👇
1:05

Watching someone easily bypass ChatGPT's safety rules on this Unitree G1 robot to fire a BB gun at its operator is definitely cause for alarm. It might be about time we dust off Isaac Asimov's Three Laws of Robotics/physical AI👇

ORO AI

10,326 views • 6 months ago

Google just made an incredible AI video breakthrough with its latest diffusion model, Lumiere. 2024 is going to be a massive year for AI video, mark my words. Here's what separates Lumiere from other AI video models:
1:54

Google just made an incredible AI video breakthrough with its latest diffusion model, Lumiere. 2024 is going to be a massive year for AI video, mark my words. Here's what separates Lumiere from other AI video models:

Rowan Cheung

335,184 views • 2 years 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.
2:43

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

We teamed up with Boston Dynamics to power their robot Spot with Gemini Robotics embodied reasoning models. This means it can better understand its surroundings, identify objects and follow simple commands - like tidying up a room.
0:37

We teamed up with Boston Dynamics to power their robot Spot with Gemini Robotics embodied reasoning models. This means it can better understand its surroundings, identify objects and follow simple commands - like tidying up a room.

Google DeepMind

153,265 views • 3 months ago

World Robot Conference 2025 is underway in China from August 9 to 13, bringing together the latest breakthroughs in robotics. From today, we’ll be reporting live from the exhibition floor. First up: Astribot demonstrating a remarkably smooth manipulation task — packing items neatly into a bag. Powered by AI for routine actions and assisted by teleoperation for rare corner cases, its design mirrors the operational logic of L3 autonomous driving systems.
0:21

World Robot Conference 2025 is underway in China from August 9 to 13, bringing together the latest breakthroughs in robotics. From today, we’ll be reporting live from the exhibition floor. First up: Astribot demonstrating a remarkably smooth manipulation task — packing items neatly into a bag. Powered by AI for routine actions and assisted by teleoperation for rare corner cases, its design mirrors the operational logic of L3 autonomous driving systems.

Reborn

29,241 views • 1 year ago

🤖What if a robot could perform a new task just from a natural language command, with zero demonstrations? Our new work, NovaFlow, makes it possible! We use pre-trained video generative model to create a video of the task, then translate it into a plan for real-world robot execution. 1/6 #Robotics #AI #ZeroShot #Manipulation
0:27

🤖What if a robot could perform a new task just from a natural language command, with zero demonstrations? Our new work, NovaFlow, makes it possible! We use pre-trained video generative model to create a video of the task, then translate it into a plan for real-world robot execution. 1/6 #Robotics #AI #ZeroShot #Manipulation

Hongyu Li

105,669 views • 10 months ago

We’ve just stepped into the future. Our AI, CERE, no longer just talks… It walks, moves, and interacts with you in real time! Cere Thanks to our integration with Robot TEMI, CERE is now embodied as a physical being: Meet Robot CERE! And with its GenAI integration, it can now talk to you on the spot. We’ve brought artificial intelligence into the physical world. Unveiled today at the expo — Tomorrow, it might be in your home, your office, or even on the street. Get ready: Technology is no longer just code — Cerebrum Tech #CERE #RobotCERE #ArtificialIntelligence #Robotics #CerebrumTech #AI #FutureTech
0:49

We’ve just stepped into the future. Our AI, CERE, no longer just talks… It walks, moves, and interacts with you in real time! Cere Thanks to our integration with Robot TEMI, CERE is now embodied as a physical being: Meet Robot CERE! And with its GenAI integration, it can now talk to you on the spot. We’ve brought artificial intelligence into the physical world. Unveiled today at the expo — Tomorrow, it might be in your home, your office, or even on the street. Get ready: Technology is no longer just code — Cerebrum Tech #CERE #RobotCERE #ArtificialIntelligence #Robotics #CerebrumTech #AI #FutureTech

Dr. R.Erdem ERKUL

367,264 views • 1 year ago

So cool! Can you even tell this is a robot horse? 🤖🐎 DEEP Robotics has built a robot horse, seemingly a special Year of the Horse limited edition based on their M20 Pro. The bionic details on this machine are incredible, especially those lifelike hooves. It looks like a living creature rather than just another quadruped robot. It is amazing to see a quad robot move so smoothly while having such a realistic animal appearance. Source: DEEP Robotics #Robot #Quadruped #Robotics #AI #EmbodiedAI #PhysicalAI #DEEPRobotics #Bionics #TechDesign
0:51

So cool! Can you even tell this is a robot horse? 🤖🐎 DEEP Robotics has built a robot horse, seemingly a special Year of the Horse limited edition based on their M20 Pro. The bionic details on this machine are incredible, especially those lifelike hooves. It looks like a living creature rather than just another quadruped robot. It is amazing to see a quad robot move so smoothly while having such a realistic animal appearance. Source: DEEP Robotics #Robot #Quadruped #Robotics #AI #EmbodiedAI #PhysicalAI #DEEPRobotics #Bionics #TechDesign

RoboHub🤖

94,254 views • 5 months ago

California startup announces breakthrough in general-purpose robotics with π0.5 AI — a vision-language-action model. Everything the robot sees, it sees for the first time. The robot has not been trained to recognize its surroundings. We are getting there! Only a few more years until we finally have household robots. A dream is coming true!
1:27

California startup announces breakthrough in general-purpose robotics with π0.5 AI — a vision-language-action model. Everything the robot sees, it sees for the first time. The robot has not been trained to recognize its surroundings. We are getting there! Only a few more years until we finally have household robots. A dream is coming true!

Chubby♨️

218,435 views • 1 year ago

Google Chief Scientist, Jeff Dean "AI now generates 25% of Google's integrated code" Google has already trained a Gemini model on its internal codebase to help developers this doesn’t cover everything, but it improves AI-assisted coding by integrating code into its parameters
0:35

Google Chief Scientist, Jeff Dean "AI now generates 25% of Google's integrated code" Google has already trained a Gemini model on its internal codebase to help developers this doesn’t cover everything, but it improves AI-assisted coding by integrating code into its parameters

Haider.

173,506 views • 1 year ago

Why LLMs are a dead end for human-level intelligence, and especially for Physical AI / Robotics. The next leap isn’t bigger language models. It’s World Models. I just dropped a full 1-hour presentation from Shanghai: “World Models: the ChatGPT moment for robotics?” → Why LLMs hit a wall → Why action-conditioned world models planning in latent space are the real path → Live World Forge demo with LeWorldModel + Hugging Face LeRobot Watch here. The future of intelligence is embodied, not just chatty.
1:16:13

Why LLMs are a dead end for human-level intelligence, and especially for Physical AI / Robotics. The next leap isn’t bigger language models. It’s World Models. I just dropped a full 1-hour presentation from Shanghai: “World Models: the ChatGPT moment for robotics?” → Why LLMs hit a wall → Why action-conditioned world models planning in latent space are the real path → Live World Forge demo with LeWorldModel + Hugging Face LeRobot Watch here. The future of intelligence is embodied, not just chatty.

abdel

37,570 views • 2 months ago

Robotics needs data. OVER delivers it. Robots aren’t just machines anymore, they’re becoming autonomous agents. The secret? A new generation of Physical AI Models. And the fuel? A global dataset built for scale. Let’s dive in 👇🧵
0:31

Robotics needs data. OVER delivers it. Robots aren’t just machines anymore, they’re becoming autonomous agents. The secret? A new generation of Physical AI Models. And the fuel? A global dataset built for scale. Let’s dive in 👇🧵

Over the Reality 🌐

24,975 views • 10 months 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
2:31

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

20,856 views • 14 days ago

A few months ago we set out to understand exactly how our models can be used to accelerate progress in robotics and other AI systems that don’t just represent the world, but are actually able to interact with it. We’ve been collaborating with leading companies in the space and we’ve developed an initial approach that we're now opening up to accelerate development across the industry. Our fifth announcement is GWM Robotics. GWM Robotics is a learned simulator that generates synthetic data for scalable robot training and policy evaluation, removing the bottlenecks of physical hardware.
1:14

A few months ago we set out to understand exactly how our models can be used to accelerate progress in robotics and other AI systems that don’t just represent the world, but are actually able to interact with it. We’ve been collaborating with leading companies in the space and we’ve developed an initial approach that we're now opening up to accelerate development across the industry. Our fifth announcement is GWM Robotics. GWM Robotics is a learned simulator that generates synthetic data for scalable robot training and policy evaluation, removing the bottlenecks of physical hardware.

Runway

35,040 views • 8 months ago