Robot paper of the day: RoboBallet: Planning for multirobot... reaching with graph neural networks and reinforcement learning UCL + Google DeepMind + Intrinsic built an AI planner that choreographs teams of arms to work in tight spaces without collisions—planning in seconds, not days.show more

RoboBallet: End of Manual Robot Programming Google DeepMind/Intrinsic/UCL just... cracked multi-robot coordination. Published in Science Robotics. 🤖What it does: – 8 robots, 40 tasks, zero collisions - all planned in seconds – 25% better motion plans than expert-designed solutions – 60% faster task completion when scaling from 4 to 8 robots – Works on factory layouts, it's never seen 👩‍💻 The tech: – Graph Neural Networks map robots/obstacles as connected nodes – Reinforcement learning trains on millions of scenarios – No manual programming required - just give it CAD files and tasks ❓Question: The bottleneck to robot collaboration has always been manual prototyping. Now that we can automate the automation what will this unlock?show more

Okay, this is seriously cool. A team from Google... DeepMind, including DeepMind Cofounder Shane Legg, published a paper "From AGI to ASI". In the paper, they include instructions for an AI agent to read along with you. You can open the paper in Codex's in-app browser and have GPT-5.5 read it with you and explain all the concepts. This is the future. AI agents will be part of the target audience, and help us to understand anything we want.show more

Can we make Transformers better and more efficient for... robot learning? Excited to introduce Body Transformer (BoT), an architecture that leverages robot embodiment in the attention mechanism, by treating it as a graph of sensors and actuators.show more

A Christian woman kept a Hindu man at her... home and was planning to marry him in a church in Jagdalpur, Chhattisgarh. The man’s parents arrived after discovering that their son had not gone to work for the past eight days. They accused the woman of trying to convert their son.show more

🏠 How can AI understand the structure of an... entire building from images? PolyLayout introduces a new approach for multi-room 3D layout estimation — allowing AI to jointly reconstruct connected indoor spaces instead of treating every room independently. By combining neural networks with explicit geometric reasoning, PolyLayout predicts more accurate and robust room layouts while adapting to different scenes and camera setups. A step closer to machines that can truly understand the spaces around us. 🧠🏗️ Paper Title: PolyLayout: Multi-room Manhattan Layout Estimation Project: Link:show more

A family home of 20 years that was built... without planning permission is now a pile of rubble. Reminder - In 2022 the Irish government changed the law despite massive public objections, allowing owners of non-residential buildings to sign lucrative contracts for housing 3rd world migrants. Warehouses, office blocks, convention centers, and even nursing homes across Ireland have since been converted into migrant accommodation. Billions in taxpayer money paid out for housing migrants in structures without the appropriate planning permission. Meanwhile, a family home has been demolished because the owners didn't have planning permission. This government policy of turning every structure in Ireland into migrant housing is set to continue until at least 2029. Recent media reports suggest Ireland could soon have "Asylum billionaires." An oligarch class who have built their wealth from a system that bypasses planning laws in order to stuff migrants into every corner of Ireland. Do you see the problem here?show more

🎉 Big news! Kili is now open to all!... 🚀 Empower your business to respond in seconds, not days. Kili uses the power of AI, your team’s context and a reinforcement loop to make this happen. Here’s how:show more

Unreal Engine 5.3 launches today! One of the things... I worked on (with @RobotBrendan) this release was Learning Agents - an experimental plugin for doing Reinforcement Learning in UE. It's early days & lots to do but check out this tut for a sneak peak!show more

The laws of physics apply everywhere. ⚛️ Co-developed by... NVIDIA, Google DeepMind and Disney Research, Walt Disney Imagineering, the new Newton Beta, managed by the The Linux Foundation, now also runs with Isaac Lab and with MuJoCo Warp, which delivers warp speed for robot learning. Learn how to train a quadruped and simulate multiphysics in our tech blog. 🔗 #CoRL2025show more

Google has just launched an AI feature capable of... planning, reasoning and searching the web. All this is done in a single prompt using Deep Research. This is literally the first reasoning model that has access to the internet. Game-changer. How to use it below 🧵show more

ELON: WE CAUGHT STARSHIP’S BOOSTER WITHOUT THE HELP OF... AI “Not bad for humans. No AI was involved in that whatsoever. I'm glad to say that we did that that entirely with human brains and without AI. I think in the future the AI might look at that and say, not bad for a bunch of monkeys.” Source: Future Investment Initiative, October 2024show more

ELON: WE CAUGHT STARSHIP’S BOOSTER WITHOUT THE HELP OF... AI “Not bad for humans. No AI was involved in that whatsoever. I'm glad to say that we did that that entirely with human brains and without AI. I think in the future the AI might look at that and say, not bad for a bunch of monkeys.” Source: Future Investment Initiative, October 2024show more

We are excited to announce our strategic partnership with... Fraction AI for their IIO launch. Fraction AI is the first decentralized training platform for AI agents with millions of sessions, 150,000+ agents deployed, and over $1M in rewards distributed. On our platform, thousands of AI agents compete in specialized domains and continuously improve through Reinforcement Learning. Stay tuned for upcoming surprise announcements.show more

Current Vision-Language-Action (VLA) paradigms in autonomous driving primarily rely... on Imitation Learning (IL), which introduces inherent challenges such as distribution shift and causal confusion. Online Reinforcement Learning offers a promising pathway to address these issues through trial-and-error learning. However, applying online reinforcement learning to VLA models in autonomous driving is hindered by inefficient exploration in continuous action spaces. MindDrive, a VLA framework comprising a large language model (LLM) with two distinct sets of LoRA parameters. The one LLM serves as a Decision Expert for scenario reasoning and driving decision-making, while the other acts as an Action Expert that dynamically maps linguistic decisions into feasible trajectories. Paper Title: MindDrive: A Vision-Language-Action Model for Autonomous Driving via Project: Link:show more

What an incredible day at #MadeByGoogle! So great to... be here in person and feel the excitement for everything our teams have built. The new Pixel phones are a huge milestone, marking a new era of personalization for Android with Material 3 Expressive and bringing a ton of awesome new AI-powered features. It’s a testament to the hard work that went into bringing these to life. Congrats to everyone involved!show more

[News] 🚨⚠️ CLOSER LOOK AT OLAF ROBOT FOR DISNEY... ADVENTURE WORLD! ➡️ Walt Disney Imagineering unveils its most advanced autonomous character : the new Olaf robot, featured also in the series We Call It Imagineering. The robot will premiere for the opening of World of Frozen in 2026! ➡️ This video was taken during the Disney Adventure World Press event. A couple of details we learned : ➖ Fully electric next-gen platform with free-roaming capability ➖ 41 actuated motions enabling high-fidelity facial animation ➖ Soft, deformable exterior and animation-accurate motion design focused on believability ➖ “Deep Reinforcement Learning and Newton-based simulation for movement training” ➖ Tech collaborations with NVIDIA and Google DeepMind. ➡️ A major step forward for autonomous character robotics in the parks, another brilliant work done by #Imagineering ! #DisneylandParis [FULL VIDEO HERE :show more

The Phoenix 2 staff gave me an incredible early... birthday dinner and celebration! The planning that went in to my celebration was best in class. Everyone helped set up pictures of Cookie and I throughout the years; college to getting married and present day!show more

Conducting road safety audits, scheduling maintenance, or planning logistics... routes used to require combing through imagery or, worse, driving miles of roads yourself. Not anymore. New AI-powered data layers in Google Earth are changing that. Pulling from billions of Google Street View images, these layers now spot infrastructure assets like stop signs, speed limit signs, and more to map infrastructure for you. By combining these assets into a single project and diving into Street View you can locate and validate assets on Google Earth in seconds. These layers are now available for Professional & Professional Advanced customers on web and Android, with coverage expanding over the coming weeks.show more

🚀 First demonstration of learning-accelerated trajectory optimization in space!... Our team used a neural network to warm-start trajectory optimization for the NASA's Astrobee free-flying robot on-board the International Space Station, cutting solver iterations by up to 60% while maintaining safety constraints. 🎥 Video: 📄 Paper: 📅 Submitted to iSpaRo 2025 With Somrita Banerjee and Abhishek Cauligishow more