Gemini Robotics makes first contact with the outside world at #GoogleIO this week! “this is the first time in my life that I’ve been able to control robots using nothing but my voice. That is basically the very definition of cool.” Android Authority “Gemini Robotics is exactly the

Our live and interactive demo of Gemini Robotics is up at Google I/O until 5pm today!

For the last 1.5 days, we've been demoing Gemini Robotics *live* to guests at Google I/O! The robot can converse with you while solving a large range of dexterous tasks 🤖 AI + robotics is so exciting, and we're cooking up a storm Google DeepMind. Can't wait to share more 🚀

Was super fun to demo Gemini Robotics @ Google I/O! This was a big effort with the Google DeepMind team including Coline Devin, Sudeep Dasari, and many others. Here's a fun uncut video of me playing with the demo :)

One of the nicest reviews I’ve ever seen, for our live robotics demo at Google I/O! Walk up to our booth, greet our friendly ALOHA robot, and just talk to it and it will try to do *anything* you ask! ✅ instruction following ✅ generalist ✅ dexterous h/t Brady Snyder

We're also launching the Gemini Robotics software development kit (SDK) to help developers fine-tune the model for their own applications, including by testing it in the MuJoCo physics simulator. 🌐

Excited to release Gemini Robotics On-Device and bunch of goodies today 🍬 on-device VLA that you can run on a GPU 🍬 open-source MuJoCo sim (& benchmark) for bimanual dexterity 🍬 broadening access to these models to academics and developers deepmind.google/discover/blog/…

🔥Gemini Robotics On-Device is here! VLA with similar generalization, instruction following, and fast adaptation as our March release, now fits on a 4090! More exciting: we're 🚀an SDK and a model dev service (flywheel) alongside it 🎯= democratizing model development!

We shipped a robot on device and brought to RSS! Please come and check it out 🤖🦾

Gemini Robotics is On-Device at RSS live right now! deepmind.google/discover/blog/…

We are living through the inflection point where general robotics evolves from cute academic sub-field to a ubiquitous technology. For those passionate about realizing this dream, consider joining my team at Google DeepMind! If you believe in the trends that have powered

Is that… a robot… two robots??… at the GDM booth at #CoRL2025?! 👀 Come check out the Google DeepMind sponsor booth this afternoon for a fun surprise!

We are Conference on Robot Learning with robots and another interactive VLA demo! Come to the Google DeepMind booth to check out the Gemini Robotics 1.5 VLA in action on Frankas and Aloha — bring your objects and ask anything 🦾

GR 1.5 live demo all week at CoRL!

Two geminis running in parallel, one as agent and one as VLA, empowers our robots with reason-based manipulation that can use tools like search to better understand the world (e.g. identifying vegetarian ingredients)

Had so much fun at CoRL 2025! If only I had some robots to pack my bag for my way home... Gemini Robotics 1.5 finetuned with some additional data on this scene:

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) 😆

Fundamental spatial and temporal understanding is the bedrock upon which robots will learn motor control. These types of Embodied Reasoning capabilities enable policy learning but also inference abilities like image or video conditioning. We just released a new SOTA ER model!