• News
  • Technology News
  • Google launches Gemini Robotics, CEO Sundar Pichai says 'we’re taking our next step in...'

Google launches Gemini Robotics, CEO Sundar Pichai says 'we’re taking our next step in...'

Google DeepMind has introduced Gemini Robotics and Gemini Robotics-ER, advanced AI models based on Gemini 2.0, aimed at bringing embodied reasoning to robotics. These models enhance robots' ability to interact with the physical world, improving their versatility and performance in complex tasks. By partnering with companies like Apptronik and Boston Dynamics, Google aims to refine these models further.
Google launches Gemini Robotics, CEO Sundar Pichai says 'we’re taking our next step in...'
Google DeepMind – the company’s AI branch – has launched Gemini Robotics and Gemini Robotics-ER, two new AI models based on Gemini 2.0, designed to to bring AI to the field of robotics. These models aim to bring “embodied” reasoning – the ability to understand and interact with the physical world – to robots, enabling them to perform a wider range of complex, real-world tasks.
“We’ve always thought of robotics as a helpful testing ground for translating AI advances into the physical world. Today we’re taking our next step in this journey with our newest Gemini 2.0 robotics models,” Google CEO Sundar Pichai said in a post on X.

What is Gemini Robotics


Gemini Robotics, a vision-language-action (VLA) model, allows robots to be directly controlled through multimodal reasoning across text, images, audio and video. It improves upon previous models in terms of generality, interactivity and dexterity, bringing robots closer to achieving human-like capabilities, Google explains.
As per the company, the model can adapt to novel situations, understand new objects and respond to diverse instructions, demonstrating a significant improvement in generalisation benchmarks. This, in turn, improves interactivity as the model understands natural language commands.
The model is also designed to adapt to various robot embodiments, from bi-arm platforms to humanoid robots like Apptronik's Apollo.

What is Gemini Robotics-ER


Gemini Robotics-ER, an advanced vision-language model, enhances Gemini's spatial understanding, enabling roboticists to run their own programmes using the model’s reasoning abilities. It improves upon Gemini 2.0's perception, state estimation, spatial understanding, planning, and code generation, achieving a 2x-3x success rate in end-to-end control settings, Google claims.
DeepMind is partnering with Apptronik to develop next-generation humanoid robots and is working with testers, including Agile Robots, Agility Robots, Boston Dynamics and Enchanted Tools, to further develop and refine Gemini Robotics-ER.
author
About the Author
TOI Tech Desk

The TOI Tech Desk is a dedicated team of journalists committed to delivering the latest and most relevant news from the world of technology to readers of The Times of India. TOI Tech Desk’s news coverage spans a wide spectrum across gadget launches, gadget reviews, trends, in-depth analysis, exclusive reports and breaking stories that impact technology and the digital universe. Be it how-tos or the latest happenings in AI, cybersecurity, personal gadgets, platforms like WhatsApp, Instagram, Facebook and more; TOI Tech Desk brings the news with accuracy and authenticity.

End of Article

Latest Mobiles

FOLLOW US ON SOCIAL MEDIA