Gemini Robotics — Google DeepMindSkip to main content
Google DeepMind
Build with Gemini<br>Try Gemini
Slide 1 of 4<br>Gemini Robotics 2
The intelligence layer to power any kind of robot
Try Gemini Robotics ER 2
Your browser does not support the video tag. Your browser does not support the video tag.
Gemini Robotics 2
Our most advanced VLA model: capable of intelligently controlling any type of robot, from bi-arms to full humanoids
Learn more
Your browser does not support the video tag. Your browser does not support the video tag.
Gemini Robotics ER 2
Our embodied reasoning model: capable of real-world understanding and complex, multi-step planning
Learn more
Try Gemini Robotics ER 2
Your browser does not support the video tag. Your browser does not support the video tag.
Gemini Robotics On-Device 2
Our most efficient VLA model, optimized to run locally on robotic devices
Learn more
Your browser does not support the video tag. Your browser does not support the video tag.
Explore the latest
Our models enable robots of every shape to think, act, and interact with the world around them. With delicate precision and full-body mastery, they autonomously solve a range of complex tasks – using their intelligence to figure out new situations on the fly.
Your browser does not support the video tag.
Models<br>Capabilities<br>Hands-on<br>Partners<br>Responsibility
Models<br>Our vision-language-action (VLA) model and embodied reasoning (ER) model work together to interact with the physical world. Each has a specialist role, but they operate as one powerful and versatile system.
Slide 1 of 3
Gemini Robotics 2<br>Our most advanced vision-language-action model (VLA) that converts vision and language input into motor control, enabling a robot to take action
Learn more
Gemini Robotics ER 2<br>Our embodied reasoning model: capable of reasoning within physical spaces to make detailed plans, coordinating with humans and other robots
Learn more
Gemini Robotics On-Device 2<br>A lightweight version of our VLA model, optimized to run locally on robotic hardware
Learn more
Gemini Robotics 2<br>Our most advanced vision-language-action model (VLA) that converts vision and language input into motor control, enabling a robot to take action
Learn more
Gemini Robotics ER 2<br>Our embodied reasoning model: capable of reasoning within physical spaces to make detailed plans, coordinating with humans and other robots
Learn more
Gemini Robotics On-Device 2<br>A lightweight version of our VLA model, optimized to run locally on robotic hardware
Learn more
Capabilities<br>Gemini Robotics 2 is the next step on our journey towards general, useful robotics. It brings whole-body intelligence to humanoids, enables advanced dexterity, and can coordinate multiple robots to work together in shared spaces.
Slide 1 of 6
General<br>Most robots are trained to do one specific task over and over. But Gemini Robotics 2 can complete a variety of tasks – even if it hasn’t been trained on them before. It’s able to adapt to new and unfamiliar situations on the fly.
Powers any embodiment<br>Can be adapted to any bi-arm robot in just a few hours, scaling its intelligence from arms to complex humanoid bodies.
Advanced dexterity<br>Enabling a new level of dexterity that enables robots to complete delicate actions requiring finesse, like screwing in a light bulb and tying knots.
Intelligent whole-body control<br>Controls entire humanoid bodies from feet to fingertips. Enabling robots to perform full-range human-like movements from bending to reaching.
Agentic<br>Understands and reasons within the real, physical world. Gemini Robotics 2 pairs deep spatial reasoning with long-horizon planning, enabling robots to map multi-step sequences and complete complex, unfamiliar tasks. Supports multi-robot collaboration, allowing two robots to collaborate, and divide labor to complete a single task.
Interactive<br>Understands and responds to everyday commands. Gemini Robotics 2 can explain its approach while performing an action, while users can redirect it without using technical language. This makes it ideal for instructing robots through volatile, hazardous environments.
Hands-on<br>See how Gemini Robotics handles a range of different tasks.
Slide 1 of 3<br>Your browser does not support the video tag.
Intelligent whole-body control<br>Controls entire humanoid robots from feet to fingertips, translating intent into whole-body control to reach, bend, and balance.
Your browser does not support the video tag.
Advanced dexterity<br>Controls complex humanoid hands and parallel grippers to unlock a new level of physical dexterity.
Your browser does not support the video tag.
Multi-robot collaboration<br>Enables different types of robots to communicate and work together to solve complex workflows a single robot could not do alone.
Research partners<br>We collaborate with leading robotics hardware developers to push the frontiers of physical AI. Through our deep research partnerships, we're building the next...