🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

🚨 New Model Alert! 🚨 Gemini 2.0 Flash is an extremely strong multimodal model which showcases impressive spatial reasoning capabilities: understanding that we live in a 3D world with consistent rules of physics and geometric/semantic relationships. 🌎 Examples below! 🧵

The ultimate test of any physics simulator is its ability to deliver real-world results. With MuJoCo Playground, we’ve combined the very best: MuJoCo’s rich and thriving ecosystem, massively parallel GPU-accelerated simulation, and real-world results across a diverse range of

Pleased to announce that Alishba Imran and I not only finished writing our textbook “AI for Robotics” but that it is now available for preorder! We hope that this book will serve to democratize knowledge of robotics in the age of AI & raise a new generation of roboticists!

What a fantastically useful resource! Thank you to all the authors for taking the time and effort both to write and release this. Really looking forward to reading it.

This looks cool. Love the open-endedness angle on characterizing frontier model capabilities.

We’re hosting RoboLetics 2.0: Workshop on Athletic Robots and Dynamic Motor Skills at #ICRA2025! 🎉 Join us for engaging talks, insightful panel discussions, and participate in our paper & demo tracks 🤖⚽️🎾🏓 Learn more: https://sites.google.com/view/roboletic…

Meet Gemini Robotics: our latest AI models designed for a new generation of helpful robots. 🤖 Based on Gemini 2.0, they bring capabilities such as better reasoning, interactivity, dexterity and generalization into the physical world. 🧵 goo.gle/gemini2-roboti…

Our model Gemini Robotics-ER allows roboticists to tap into the embodied reasoning of Gemini. 🌐 For example, if a robot came across a coffee mug, it could detect it, use ‘pointing’ to recognize parts it could interact with - like the handle - and recognize objects to avoid when

📢 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. 🧵⬇️

A delightful example of interactive instruction following by the Gemini Robotics VLA

Last month we announced Gemini Robotics (GR) and Gemini Robotics-ER (GR-ER). GR-ER is a powerful VLM specialised for spatial understanding, including detecting object poses in 2D/3D, pointing, and even *predicting grasp poses*. Take a look at this demo. Details below. 🧵

Watch Gemini 2.5 Pro implement a landmark Google DeepMind research paper. 🕹️ It codes the reinforcement learning algorithm, visualizes the training live and even debugs errors. ↓

I spent some time last week vibe-coding "The Beginner's RL Playground" a simple web tool for exploring many basic concepts in reinforcement learning. Users can adjust all sorts of parameters of the algorithm and environment and see the effects of those changes in realtime.

We’re helping robots self-improve with the power of LLMs. 🤖 Introducing the Summarize, Analyze, Synthesize (SAS) prompt, which analyzes how they perform tasks based on previous actions and then suggests ways for them to get better using the medium of table tennis. 🏓

Today we are releasing the dataset of table tennis ball trajectories used to train the Google DeepMind robot that can play amateur table tennis with humans (sites.google.com/corp/view/comp…). This work was accepted for presentation at #ICRA2025 and we hope to see you there!

We collected almost 16,000 (5,000 shown) balls from human play, ball throwers, and the robot itself in the real world, and augmented them with random noise. The data is split into serves and rallies. @Github goo.gle/4jCZLHO. Happy to serve up some training data 🤖🏓.

Gemini now coaches table tennis robots 🤖🏓: In our latest paper, we introduce SAS Prompt – a technique for robot self-improvement with LLMs. Here is how it works 🧵

David D'Ambrosio Laura Graesser GitHub Great work, David and the team 🙌 Here is even more ball data [1] from this project [2]. [1] edmond.mpg.de/dataset.xhtml?… [2] webdav.tuebingen.mpg.de/aimy/