HomeTechnologyGoogle DeepMind unveils Gemini Robotics, its new AI models to power humanoid and other real-world robots

Google DeepMind unveils Gemini Robotics, its new AI models to power humanoid and other real-world robots

Google DeepMind introduces Gemini Robotics, an AI-powered model designed for humanoid robots, enabling advanced vision, language, and action capabilities to perform real-world tasks with enhanced dexterity, interactivity, and spatial reasoning.

March 12, 2025 / 22:06 IST
Story continues below Advertisement
Gemini robotics
Gemini robotics

Google has taken a step forward in the world of AI development with its all-new Gemini Robotics and Gemini Robotics-ER AI models. Google DeepMind has introduced Gemini, the  AI models based on Gemini 2.0 that are designed to implement AI into real-world robotics These models, according to the blog post, bring vision-language-action (VLA) capabilities and embodied reasoning (ER) to robots, enabling them to perform complex physical tasks with greater adaptability, interactivity, and dexterity. Google DeepMind is partnering with Apptronik to integrate these advancements into humanoid robots.

Gemini Robotics: Vision-language-action model

Story continues below Advertisement

Gemini Robotics extends the capabilities of Gemini 2.0 by integrating physical actions as an output modality. The company says that It allows robots to interact dynamically with their environment and adapt to changes in real-time.

The model generalises across new environments, objects, and instructions, more than doubling performance on generalization benchmarks compared to previous VLA models. It also understands and responds to natural language commands in multiple languages, adapting its actions based on changing conditions.
Moreover, the model enables fine motor control, allowing robots to perform precise tasks such as origami folding or packing items into a bag.