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.

Teamwork makes the dream work. To test multi-robot collaboration with Gemini Robotics 2, we challenged our Apollo and Duo robots to tidy up a messy garage. The high-level reasoning model breaks down what to do, where to go, and identifies the exact moment to hand over control ↓

Google DeepMind

1,500,709 subscribers

22,872 views • 14 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

For decades, we’ve dreamed of robots that can seamlessly step into our world and lend a hand. Today, we take a major stride toward making that dream a reality: Introducing Gemini Robotics 2 from Google DeepMind, the intelligence layer powering the next generation of truly adaptable robots. This major advance unlocks intelligent whole-body control, advanced dexterity, and even multi-robot collaboration 🤯. Ok but... how does a robot actually "think"? Real-world tasks take time and planning. To manage that complexity, our new embodied reasoning model, Gemini Robotics ER 2, acts as the robot’s high-level brain, enhancing the robot’s capabilities to: — Observe the environment — Reason about the actions needed to complete the task — Coordinate with the vision-language-action model to carry out actions — Track progress until the job is done This setup allows robots to execute complex multi-step workflows, self-correct if a step fails, and adapt to completely novel situations. Learn more about Gemini Robotics ER 2 (and our two other brand new models) here:

Google AI

481,014 views • 14 days ago

Control a robot in simulation with the Gemini Robotics Embodied Reasoning model 🤖 Direct tasks like object localization and placement by simply prompting a robotic arm to pick up and place objects.

Control a robot in simulation with the Gemini Robotics Embodied Reasoning model 🤖 Direct tasks like object localization and placement by simply prompting a robotic arm to pick up and place objects.

Google AI Developers

1,296,656 views • 6 months ago

A conversation with the Google DeepMind Robotics team about our latest Gemini Robotics 2 model, the arc of robotics progress, and where we go next 🤖

A conversation with the Google DeepMind Robotics team about our latest Gemini Robotics 2 model, the arc of robotics progress, and where we go next 🤖

Logan Kilpatrick

122,386 views • 13 days ago

One brain. For any robot. 🤖 We’re launching Gemini Robotics 2: our next-generation physical AI bringing full body intelligence to humanoids, advanced dexterity, multi-robot teamwork and more.

One brain. For any robot. 🤖 We’re launching Gemini Robotics 2: our next-generation physical AI bringing full body intelligence to humanoids, advanced dexterity, multi-robot teamwork and more.

Google DeepMind

1,961,913 views • 14 days ago

Welcome to Robot Park, where we’re building the future with Apollo 2. Robot Park is where Apollo learns today, getting the experience needed to make a difference tomorrow. #Apptronik #Robotics #AI #Humanoids

Welcome to Robot Park, where we’re building the future with Apollo 2. Robot Park is where Apollo learns today, getting the experience needed to make a difference tomorrow. #Apptronik #Robotics #AI #Humanoids

Apptronik

182,509 views • 1 month ago

Excited to share RoCo: Dialectic Multi-Robot Collaboration with Large Language Models. We propose a novel approach to multi-robot collaboration that leverages LLMs for both high-level communication and low-level path planning. w/ Shreeya Jain, Shuran Song

Excited to share RoCo: Dialectic Multi-Robot Collaboration with Large Language Models. We propose a novel approach to multi-robot collaboration that leverages LLMs for both high-level communication and low-level path planning. w/ Shreeya Jain, Shuran Song

Mandi Zhao

88,722 views • 3 years ago

Google DeepMind introduces Gemini Robotics 1.5, enabling robots to perceive, plan, think, use tools, and act on complex tasks. The agentic framework comprises: ⦿ Gemini Robotics-ER 1.5 (VLM): Orchestrates high-level embodied reasoning and planning. ⦿ Gemini Robotics 1.5 (VLA): Converts visuals and instructions provided by ER 1.5 into actions.

Google DeepMind introduces Gemini Robotics 1.5, enabling robots to perceive, plan, think, use tools, and act on complex tasks. The agentic framework comprises: ⦿ Gemini Robotics-ER 1.5 (VLM): Orchestrates high-level embodied reasoning and planning. ⦿ Gemini Robotics 1.5 (VLA): Converts visuals and instructions provided by ER 1.5 into actions.

The Humanoid Hub

65,928 views • 10 months ago

We took a robot to RSS in LA running our new Gemini Robotics On-Device VLA model. People interacted with the model with new objects and instructions in a brand new environment and the results were amazing!

Ayzaan Wahid

19,688 views • 1 year 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

152,458 views • 1 year 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

28,107 views • 14 days ago

Humanoid robots are cool. But most of them aren’t ready for real-world work. X-Humanoid just launched Embodied Tien Kung 3.0 - a full-size humanoid robot built to actually operate in industrial and commercial environments. What makes it different? • Strong, high-torque joints for heavy tasks • Can move dynamically and stay stable • Handles complex motions (even over obstacles) • Millimeter-level precision for detailed work It runs on the Wise KaiWu AI platform, which allows the robot to see, think, and act in a continuous loop with less human control and support for multi-robot collaboration. It also supports ROS2, MQTT, and TCP/IP, and offers more open hardware + software interfaces to make development easier for teams. The goal is simple: make humanoid robots practical, easier to build on, and ready for real-world use. Visit: Check out the official launch video below to see what it can do! 👇 #Robotics #HumanoidRobot #AI

Humanoid robots are cool. But most of them aren’t ready for real-world work. X-Humanoid just launched Embodied Tien Kung 3.0 - a full-size humanoid robot built to actually operate in industrial and commercial environments. What makes it different? • Strong, high-torque joints for heavy tasks • Can move dynamically and stay stable • Handles complex motions (even over obstacles) • Millimeter-level precision for detailed work It runs on the Wise KaiWu AI platform, which allows the robot to see, think, and act in a continuous loop with less human control and support for multi-robot collaboration. It also supports ROS2, MQTT, and TCP/IP, and offers more open hardware + software interfaces to make development easier for teams. The goal is simple: make humanoid robots practical, easier to build on, and ready for real-world use. Visit: Check out the official launch video below to see what it can do! 👇 #Robotics #HumanoidRobot #AI

Chidanand Tripathi

69,604 views • 5 months ago

Vision-language models can control robots, but what if the prompt is too complex for the robot to follow directly? We developed a way to get robots to “think through” complex instructions, feedback, and interjections. We call it the Hierarchical Interactive Robot (Hi Robot).

Vision-language models can control robots, but what if the prompt is too complex for the robot to follow directly? We developed a way to get robots to “think through” complex instructions, feedback, and interjections. We call it the Hierarchical Interactive Robot (Hi Robot).

Physical Intelligence

117,221 views • 1 year ago

John: "Over in China, they’re doing robot Olympics. They’re doing marathons and all sorts of stuff." Figure founder Brett Adcock: “We look at the distribution of what humans do that is useful, and we [designed our humanoid] to do as much of that as possible.” “These things where we run marathons, or we do backflips, or we do karate moves—they’re not in the main part of the distribution. They don’t matter. And if you really want to size for those, you’re going to build a really expensive and unsafe robot that’s hard to manufacture.” “People want the $10,000 humanoid that can do general-purpose work. We want it to do laundry and dishes and be a companion. I want to ship robots at scale into the workforce to do logistics and healthcare, and build buildings and data centers.” "I don't need [our humanoid] to do backflips to do any of that work. I want robots building other robots."

John: "Over in China, they’re doing robot Olympics. They’re doing marathons and all sorts of stuff." Figure founder Brett Adcock: “We look at the distribution of what humans do that is useful, and we [designed our humanoid] to do as much of that as possible.” “These things where we run marathons, or we do backflips, or we do karate moves—they’re not in the main part of the distribution. They don’t matter. And if you really want to size for those, you’re going to build a really expensive and unsafe robot that’s hard to manufacture.” “People want the $10,000 humanoid that can do general-purpose work. We want it to do laundry and dishes and be a companion. I want to ship robots at scale into the workforce to do logistics and healthcare, and build buildings and data centers.” "I don't need [our humanoid] to do backflips to do any of that work. I want robots building other robots."

TBPN

15,419 views • 6 months ago

Generative models (diffusion/flow) are taking over robotics 🤖. But do we really need to model the full action distribution to control a robot? We suspected the success of Generative Control Policies (GCPs) might be "Much Ado About Noising." We rigorously tested the myths. 🧵👇

Generative models (diffusion/flow) are taking over robotics 🤖. But do we really need to model the full action distribution to control a robot? We suspected the success of Generative Control Policies (GCPs) might be "Much Ado About Noising." We rigorously tested the myths. 🧵👇

Chaoyi Pan

112,064 views • 8 months ago

A brotherhood that lives up to the phrase "teamwork makes the dream work" 🙌🏀 #ShootingStars premieres June 2, only on Peacock.

A brotherhood that lives up to the phrase "teamwork makes the dream work" 🙌🏀 #ShootingStars premieres June 2, only on Peacock.

Marquis Cook™️

12,033 views • 3 years ago

Elon Musk: “America needs to be strong enough to last long enough to extend life to other planets and to get AI and robotics to the point where we can ensure that the future is good On the other hand, if we were to descend into, say, communism or some situation where the state was extremely oppressive, that would mean that we might not be able to become multi-planetary and the state might snuff out our progress in AI and robotics”

Elon Musk: “America needs to be strong enough to last long enough to extend life to other planets and to get AI and robotics to the point where we can ensure that the future is good On the other hand, if we were to descend into, say, communism or some situation where the state was extremely oppressive, that would mean that we might not be able to become multi-planetary and the state might snuff out our progress in AI and robotics”

Elonogy

16,116 views • 1 month ago

Gm only if you’re willing to listen and learn Teamwork also makes the dream work Together we will prevail

Gm only if you’re willing to listen and learn Teamwork also makes the dream work Together we will prevail

Books

34,623 views • 1 year ago

🤖 The robots have arrived. Now, we bring them to life with Robotics OS, the first end-to-end decentralized stack. Each robot will receive an on-chain machine identity within the Edge Network, joining the decentralized future of robotics. A new era where robots run on $EDGE.

🤖 The robots have arrived. Now, we bring them to life with Robotics OS, the first end-to-end decentralized stack. Each robot will receive an on-chain machine identity within the Edge Network, joining the decentralized future of robotics. A new era where robots run on $EDGE.

Edge Network — The Supercloud

36,910 views • 10 months ago

Our cobot, Proxie, now self-identifies work, tells you what it’s going to do, and completes the work autonomously… thousands of times a day, with 100% completion. Listen to the update to hear more.

Our cobot, Proxie, now self-identifies work, tells you what it’s going to do, and completes the work autonomously… thousands of times a day, with 100% completion. Listen to the update to hear more.

Brad Porter

62,020 views • 9 months ago