Gemini Robotics Models

Technology

Specialized versions of the Gemini model that have been fine-tuned with robotics data to translate natural language commands into physical motor movements.


First Mentioned

9/13/2025, 5:47:54 AM

Last Updated

9/13/2025, 5:52:27 AM

Research Retrieved

9/13/2025, 5:52:27 AM

Summary

Gemini Robotics Models represent a family of advanced multimodal AI models developed by Google DeepMind, designed to revolutionize robotics by enabling machines to perceive, reason, and interact intelligently within the physical world. Built upon the foundation of Gemini 2.0 and further enhanced with robot-specific data, these models extend traditional multimodal capabilities (text, vision, audio) to include direct robotic control and motor actions. Key models like Gemini Robotics and Gemini Robotics-ER offer advanced features such as understanding natural language commands, recognizing and manipulating objects with dexterity, adapting to novel environments, and performing embodied reasoning with spatial understanding. Launched on March 12, 2025, these models are a critical step in Google DeepMind's broader mission to accelerate scientific discovery and advance fields like embodied AI, ultimately contributing to the development of Artificial General Intelligence.

Referenced in 1 Document
Research Data
Extracted Attributes
  • Type

    Vision-Language-Action (VLA) model

  • Status

    Being made available to trusted testers and partners

  • Purpose

    Advance Robotics and Embodied AI

  • Developer

    Google DeepMind

  • Key Capability

    Spatial understanding

  • Foundation Model

    Gemini 2.0

  • Foundation Model (latest generation)

    Gemini 2.5 Pro and Flash

Timeline
  • Google DeepMind launched the Gemini Robotics model family, including Gemini Robotics and Gemini Robotics-ER, designed for robotics applications. (Source: web_search_results)

    2025-03-12

Web Search Results
  • How we built the new family of Gemini Robotics models - Google Blog

    Google DeepMind has released a new family of Gemini Robotics models designed to power robots. These models are trained on a vast amount of data and can perform a wide range of tasks, including understanding natural language, recognizing objects, and manipulating them with dexterity. The models are being made available to trusted testers and partners, and Google DeepMind believes they have the potential to revolutionize robotics, making robots more useful in a variety of settings, including [...] The Gemini Robotics models are highly dextrous, interactive and general, meaning they can drive robots to react to new objects, environments and instructions without further training. Helpful, given the team’s ambitions. [...] This all-rounder robot was powered by a Gemini Robotics model that is part of a new family of multimodal models for robotics. The models build upon Gemini 2.0 through fine-tuning with robot-specific data, adding physical action to Gemini’s multimodal outputs like text, video and audio. "This milestone lays the foundation for the next generation of robotics that can be helpful across a range of applications," said Google CEO Sundar Pichai when announcing the new models on X.

  • Powering Smart Robots With Google Gemini Robotics Models

    Google’s Gemini Robotics is an advanced AI model designed to give robots the ability to perceive, reason, and interact in the physical world. As a vision-language-action (VLA) model, it allows robots to process instructions, interpret their environment, and execute complex tasks with high precision. [...] Meanwhile, the Gemini Robotics-ER model improves a robot’s ability to understand spatial relationships of how objects are positioned, how they move, and how they interact. This helps robots anticipate actions and adjust their movements accordingly. [...] Specifically, with Gemini Robotics, Google is taking a step closer to the technology needed to build smarter robots. Launched on March 12, 2025, the Gemini Robotics model and its companion model, Gemini Robotics-ER (Embodied Reasoning), are Google DeepMind’s latest innovations.

  • Gemini Robotics: A new era of AI-Powered RobotsPlain Concepts

    Gemini Robotics: Gemini Robotics is the general AI model for robotics built on top of DeepMind’s Gemini 2.0. It extends the foundation model’s multimodal capabilities, text, vision, and audio by adding robotic control as a new output. This means that instead of just processing and responding to information in the digital realm (as Gemini 2.0 does with text and images), Gemini Robotics can generate motor actions and control robotic systems in real-world environments. [...] ## Gemini robotics model family Google DeepMind has introduced two AI models under the Gemini Robotics initiative: [...] Gemini Robotics has made a significant impact by demonstrating that a single AI model can equip robots with a wide range of capabilities from understanding human commands to adapting to new tasks and manipulating objects with precision. Unlike previous approaches, Gemini Robotics is designed to be more general, integrated, and adaptable, introducing groundbreaking technologies that could shape the future of robotics AI.

  • New Gemini AI models for robotics - Google Blog

    Google DeepMind is announcing two new models, based on Gemini 2.0, that are designed for robotics. Gemini Robotics is our most advanced vision-language-action model, which enables robots to perform a wider range of real-world tasks than ever before. Gemini Robotics-ER lets roboticists run their own programs using Gemini’s embodied reasoning. They’re currently testing these models with partners and trusted testers. Read more on the Google DeepMind blog. [...] Published Time: 2025-03-12T15:05:00+00:00 Gemini Robotics: New Gemini AI models for robotics Skip to main content The Keyword Gemini Robotics and Gemini Robotics-ER are two new Gemini models designed for robotics. Share TwitterFacebookLinkedInMail Copy link Home Product news Product news Android, Chrome & Play Android Chrome Chromebooks Google Play Wear OS See all

  • Gemini 2.5 for robotics and embodied intelligence

    In March, we launched our Gemini Robotics models, including Gemini Robotics-ER, our advanced embodied reasoning model optimized for the unique demands of robotics applications. We’re also excited to share how our Gemini Robotics trusted testers are already demonstrating the power of Gemini in robotics applications. We are including examples from Agile Robots, Agility Robotics, Boston Dynamics, and Enchanted Tools. Join the Gemini Robotics-ER trusted tester program waitlist. [...] The latest generation of Gemini models, 2.5 Pro and Flash, are unlocking new frontiers in robotics. Their advanced coding, reasoning, and multimodal capabilities, now combined with spatial understanding, provide the foundation for the next generation of interactive and intelligent robots. This post explores how developers can leverage Gemini 2.5 to build sophisticated robotics applications. We'll provide practical examples with prompts to show using Gemini 2.5 and the Live API for: