Really cool to see the smooth motion and it's quite impressive that this is achieved without teleop data. Congrats @chenwang_j @zipengfu and team!

🧐

We'll be organizing a World Model for Robotics workshop at NeurIPS 2026 this year. Submission ddl Aug 29th, robowm-ws.github.io/. Looking forward to the submissions from everyone and hearing insights from our amazing speakers!

Playing with Gemini Robotics 2 on Apollo is so fun! The incredible thing about whole body generalization in 3D space on humanoids is that all the recovery, retry and reactive behaviors look very human-like - like having a proto human intelligence in a metal body in your lab. Unseen task, unscripted motions.

Let's talk #safety. #GeminiRobotics ER 2 is our safest model yet, SOTA in safe instruction following and human proximity detection. Intelligent general purpose robots need "physical common sense", one of many layers. Lots more work to do. Learn more from our safety report: lnkd.in/gNrHpyG7 Asimov-agentic benchmark: lnkd.in/gZRCfAXg Check out a fun red-teaming exercise: @GoogleDeepMind #Robotics

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 🤖🧠

Gemini Robotics 2 learned diverse whole body skills and here’s one I like a lot: Apollo uses side of the finger to open the trash can lid and throw the trash in just like how I would do it. So much more we can do now with the whole body intelligence!

Excited to share what we've been working on! 🤖 With Gemini Robotics 2 we can bridge the sim2real gap and learn new tasks entirely from simulation! Here it is performing an automotive kitting task, handling bimanual grasping, 3D reorientations, and tight insertions. 👇

We got many comments saying the release videos are cool, but do the models actually work? We stress tested Gemini Robotics 2 to show its impressive robustness and recovery capabilities. It's amazing to see how it keeps trying until the task is done

Really excited to share what we’ve been cooking. There has been so many magical moments when the robot took its first steps, tied the first knot, inserted the first cassette and so on. Super proud of the team!

🧐

We’re rolling out an upgrade designed to help robots reason about the physical world. 🤖 Gemini Robotics-ER 1.6 has significantly better visual and spatial understanding in order to plan and complete more useful tasks. Here’s why this is important 🧵

My favorite part of working on Genie for the past few years has been seeing the unexpected things people do with it. Super excited to share Project Genie with US Ultra Users, can't wait to see what you all create with it!!😀😀😀

Exciting time ahead!

Generalist robots need a generalist evaluator. But how do you test safety without breaking things? 💥 🌎 Introducing our new work from @GoogleDeepMind: Evaluating Gemini Robotics Policies in a Veo World Simulator veo-robotics.github.io 🧵👇

Interacting with Gemini Robotics 1.5 is so fun! Our Embodied Reasoning model planned the multi-step task and orchestrated our Vision Language Action model for precise execution!

Gemini Robotics 1.5 is not only general, but also fairly dexterous! Enjoy some fun videos of robot doing insertion, zipping, and more (remember this is the *same checkpoint* that also controls two other very different robots) 😆

Excited to share our latest work on Gemini Robotics 1.5! Our model can effectively learn from experience of drastically different robots, think on its own, and act as an agent. It’s an important step towards creating a general, intelligent, and friendly robot!

How do imbue robots with the ability to imagine the world and complete tasks better? Join us at CoRL 25 workshop on Robotics World Modeling and share your latest work in this area!

Deadline extended! You now have until May 25th (10 days post-NeurIPS) to submit to our ICML World Model Workshop. Looking forward to your papers!