--- title: Gemini Robotics Embodied Reasoning 2 is now available on... description: Google Cloud has launched Gemini Robotics Embodied Reasoning 2 (ER 2) in public preview on the Gemini platform. The model acts as a robot's high-level... canonical: https://daily.dev/posts/gemini-robotics-embodied-reasoning-2-is-now-available-on-google-cloud-6zayfgcj0 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Gemini Robotics Embodied Reasoning 2 is now available on Google Cloud | daily.dev og:description: Google Cloud has launched Gemini Robotics Embodied Reasoning 2 (ER 2) in public preview on the Gemini platform. The model acts as a robot's high-level... og:url: https://daily.dev/posts/gemini-robotics-embodied-reasoning-2-is-now-available-on-google-cloud-6zayfgcj0 og:image: https://api.daily.dev/og/posts/6ZayFGcJ0.png og:image:alt: Gemini Robotics Embodied Reasoning 2 is now available on Google Cloud og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Gemini Robotics Embodied Reasoning 2 is now available on Google Cloud **[Google Cloud](https://daily.dev/sources/gcp)** · 7 min read · 0 upvotes · 0 comments ## Summary Google Cloud has launched Gemini Robotics Embodied Reasoning 2 (ER 2) in public preview on the Gemini platform. The model acts as a robot's high-level reasoning layer, combining spatial-temporal video understanding with long-horizon planning across any robot embodiment, from stationary arms to humanoids. It pinpoints critical events in video, such as when to stop pouring a liquid, with 91.3% accuracy and a 0.96-second mean absolute frame distance, running at 4x the execution speed and a fraction of the compute cost of many larger model categories. It can also read values across over 10 instrument types like dials and digital displays. Developers can simulate in MuJoCo-Warp or NVIDIA Isaac Sim, train custom VLA models, and deploy via Google Distributed Cloud and GKE. Boston Dynamics, Arm, DeepReach, and A*STAR IMRE are quoted as customers building with the model. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is Gemini Robotics ER 2 and what does it do for robots? Gemini Robotics ER 2 is a specialized Gemini model that acts as a robot's high-level reasoning brain, combining spatial and temporal video understanding with long-horizon planning. It lets robots converse naturally, orchestrate low-level action models and hardware APIs, execute multi-minute tasks with hundreds of decisions, and collaborate across multi-robot teams, working across embodiments from stationary arms to humanoids. _Teams evaluating physical AI stacks can track robotics model releases like this one on daily.dev._ ### How accurate is Gemini Robotics ER 2 at detecting critical events in video for robot tasks? It pinpoints the exact video frame where a critical event occurs, such as when to stop pouring a liquid, with 91.3% accuracy and a 0.96-second mean absolute frame distance. It runs at 4 times the execution speed and a fraction of the compute cost of many larger model categories, while also reading over 10 instrument categories like dials, sight glasses, and digital displays. _Developers comparing physical AI models on accuracy and cost follow benchmark details like these on daily.dev._ ### What tools can I use to simulate and train robots with Gemini Robotics ER 2 on Google Cloud? Robot behaviors can be tested before touching hardware using MuJoCo-Warp and NVIDIA Isaac Sim simulations, with synthetic scenario generation and workcell imagery auto-labeling on the Gemini platform. Demonstration videos can be curated and labeled using spatial pointing, moment finding, and progress classification, then used to train custom Vision-Language-Action models via the Gemini platform, GKE, or Cluster Director. _Engineers planning a robotics simulation and training pipeline keep up with platform options like this on daily.dev._ ## Similar posts on daily.dev - [Google releases Gemini 3 Flash, enabling faster, more cost effective reasoning](https://daily.dev/posts/google-releases-gemini-3-flash-enabling-faster-more-cost-effective-reasoning-1y9yu2yfb) · SD Times · 0 upvotes · 0 comments --- Tags: [#gcp](https://daily.dev/tags/gcp), [#robotics](https://daily.dev/tags/robotics) [View this post on daily.dev](https://daily.dev/posts/gemini-robotics-embodied-reasoning-2-is-now-available-on-google-cloud-6zayfgcj0) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Gemini Robotics Embodied Reasoning 2 is now available on Google Cloud","url":"https://daily.dev/posts/gemini-robotics-embodied-reasoning-2-is-now-available-on-google-cloud-6zayfgcj0","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/gemini-robotics-embodied-reasoning-2-is-now-available-on-google-cloud-6zayfgcj0"},"datePublished":"2026-10-27T15:09:42.530Z","dateModified":"2026-10-27T15:12:31.865Z","description":"Google Cloud has launched Gemini Robotics Embodied Reasoning 2 (ER 2) in public preview on the Gemini platform. The model acts as a robot's high-level...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/531560115e4ae46b91c8a6355e8f7d36?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/531560115e4ae46b91c8a6355e8f7d36?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Google Cloud","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Google Cloud","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/gcp","url":"https://daily.dev/sources/gcp"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/gemini-robotics-embodied-reasoning-2-is-now-available-on-google-cloud-6zayfgcj0","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"gcp,robotics","timeRequired":"PT7M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Google Cloud","item":"https://daily.dev/sources/gcp"},{"@type":"ListItem","position":3,"name":"Gemini Robotics Embodied Reasoning 2 is now available on Google Cloud"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/gemini-robotics-embodied-reasoning-2-is-now-available-on-google-cloud-6zayfgcj0#faq","mainEntity":[{"@type":"Question","name":"What is Gemini Robotics ER 2 and what does it do for robots?","acceptedAnswer":{"@type":"Answer","text":"Gemini Robotics ER 2 is a specialized Gemini model that acts as a robot's high-level reasoning brain, combining spatial and temporal video understanding with long-horizon planning. It lets robots converse naturally, orchestrate low-level action models and hardware APIs, execute multi-minute tasks with hundreds of decisions, and collaborate across multi-robot teams, working across embodiments from stationary arms to humanoids. Teams evaluating physical AI stacks can track robotics model releases like this one on daily.dev."}},{"@type":"Question","name":"How accurate is Gemini Robotics ER 2 at detecting critical events in video for robot tasks?","acceptedAnswer":{"@type":"Answer","text":"It pinpoints the exact video frame where a critical event occurs, such as when to stop pouring a liquid, with 91.3% accuracy and a 0.96-second mean absolute frame distance. It runs at 4 times the execution speed and a fraction of the compute cost of many larger model categories, while also reading over 10 instrument categories like dials, sight glasses, and digital displays. Developers comparing physical AI models on accuracy and cost follow benchmark details like these on daily.dev."}},{"@type":"Question","name":"What tools can I use to simulate and train robots with Gemini Robotics ER 2 on Google Cloud?","acceptedAnswer":{"@type":"Answer","text":"Robot behaviors can be tested before touching hardware using MuJoCo-Warp and NVIDIA Isaac Sim simulations, with synthetic scenario generation and workcell imagery auto-labeling on the Gemini platform. Demonstration videos can be curated and labeled using spatial pointing, moment finding, and progress classification, then used to train custom Vision-Language-Action models via the Gemini platform, GKE, or Cluster Director. Engineers planning a robotics simulation and training pipeline keep up with platform options like this on daily.dev."}}]} ```