--- title: Advancements in Robotic Reasoning: The Launch of Gemini... description: Google DeepMind has launched Gemini Robotics 1.5 and Gemini Robotics-ER 1.5, advanced AI models that enable robots to convert visual information and language... canonical: https://daily.dev/posts/advancements-in-robotic-reasoning-the-launch-of-gemini-robotics-er-1-5-mxwlb0giq twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Advancements in Robotic Reasoning: The Launch of Gemini Robotics-ER 1.5 | daily.dev og:description: Google DeepMind has launched Gemini Robotics 1.5 and Gemini Robotics-ER 1.5, advanced AI models that enable robots to convert visual information and language... og:url: https://daily.dev/posts/advancements-in-robotic-reasoning-the-launch-of-gemini-robotics-er-1-5-mxwlb0giq og:image: https://api.daily.dev/og/posts/mxwLB0gIq.png og:image:alt: Advancements in Robotic Reasoning: The Launch of Gemini Robotics-ER 1.5 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. # Advancements in Robotic Reasoning: The Launch of Gemini Robotics-ER 1.5 **[Collections](https://daily.dev/sources/collections)** · 2 min read · 3 upvotes · 0 comments ## Summary Google DeepMind has launched Gemini Robotics 1.5 and Gemini Robotics-ER 1.5, advanced AI models that enable robots to convert visual information and language instructions into motor commands. These systems feature sophisticated vision-language-action capabilities, embodied reasoning, and integration with Google Search for autonomous information retrieval. The models excel at breaking down complex tasks, spatial understanding, and cross-robot skill transfer, while incorporating safety measures through the ASIMOV benchmark. Available via Google AI Studio and Gemini API, these tools support diverse robotic applications from humanoid robots to haptic exosuits. ## Content Google DeepMind has unveiled a significant upgrade to its robotics technology with the introduction of Gemini Robotics 1.5 and Gemini Robotics-ER 1.5. These advanced models aim to revolutionize the way robots interpret and interact with the world through sophisticated vision-language-action systems and embodied reasoning techniques. Gemini Robotics 1.5 specializes in converting visual information and linguistic instructions into motor commands, allowing robots to undertake complex multi-step tasks by effectively thinking before acting. Complementing it, Gemini Robotics-ER 1.5 enhances high-level planning and reasoning by integrating visual understanding, spatial awareness, and task planning. Together, these models facilitate transparent decision-making, cross-embodiment learning, and seamless tool usage. Among their key capabilities, the new models are adept in breaking down complicated instructions into actionable steps, locating objects in both 2D and 3D spaces, and understanding temporal sequences. Enhanced with configurable thinking budgets, these models balance latency and accuracy effectively. Moreover, safety measures are strengthened through the ASIMOV benchmark, ensuring secure operation across various scenarios. An interesting feature of this system is its integration with Google Search, enabling robots to independently access information required for task execution. This capability allows robots to perform diverse tasks such as sorting laundry by color, packing for weather changes, and managing waste according to local regulations. Additionally, the models support skill transfer between different robot designs, thus broadening the applicability and adaptability of these robotic technologies. Available through Google AI Studio and the Gemini API, Gemini Robotics is poised to aid developers in crafting the next generation of robotic applications by providing state-of-the-art spatial understanding benchmarks and safety protocols. The robotics community can now explore varied uses, including humanoid robots, quadruped locomotion, soft robotics investigations, and innovative haptic exosuits, promising a new horizon of technological possibilities. --- Tags: [#ai](https://daily.dev/tags/ai), [#machine-learning](https://daily.dev/tags/machine-learning), [#google](https://daily.dev/tags/google), [#computer-vision](https://daily.dev/tags/computer-vision), [#robotics](https://daily.dev/tags/robotics) [View this post on daily.dev](https://daily.dev/posts/advancements-in-robotic-reasoning-the-launch-of-gemini-robotics-er-1-5-mxwlb0giq) ```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":"Advancements in Robotic Reasoning: The Launch of Gemini Robotics-ER 1.5","url":"https://daily.dev/posts/advancements-in-robotic-reasoning-the-launch-of-gemini-robotics-er-1-5-mxwlb0giq","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/advancements-in-robotic-reasoning-the-launch-of-gemini-robotics-er-1-5-mxwlb0giq"},"datePublished":"2025-09-25T16:04:52.004Z","dateModified":"2025-09-26T15:32:04.408Z","description":"Google DeepMind has launched Gemini Robotics 1.5 and Gemini Robotics-ER 1.5, advanced AI models that enable robots to convert visual information and language...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/9d27ed9b7aa8fc2eeb07a7fc6ad52380?_a=AQAEulh","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/9d27ed9b7aa8fc2eeb07a7fc6ad52380?_a=AQAEulh","isAccessibleForFree":true,"articleSection":"Collections","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":"Collections","logo":"https://media.daily.dev/image/upload/s--fk_6ycEi--/f_auto,q_auto/v1780996001/logos/collections?_a=BAMAMiWQ0","url":"https://daily.dev/sources/collections"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/advancements-in-robotic-reasoning-the-launch-of-gemini-robotics-er-1-5-mxwlb0giq","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":3},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai,machine-learning,google,computer-vision,robotics","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Collections","item":"https://daily.dev/sources/collections"},{"@type":"ListItem","position":3,"name":"Advancements in Robotic Reasoning: The Launch of Gemini Robotics-ER 1.5"}]} ```