All videos
0:00 / 0:00
research

Intelligent whole-body control with Gemini Robotics 2

Google DeepMind31 July 2026Watch on YouTube

Part of series

Ep. 4 · Gemini Robotics 2 – Google DeepMind

Google DeepMind demonstreert Gemini Robotics 2, een AI-systeem dat humanoid robots voorziet van geavanceerde motoriek en samenwerking.

View the series

What you'll learn

  • Gemini Robotics 2 enables humanoid robots with full whole-body control instead of just upper-body manipulation
  • The AI model allows robots to perform complex tasks in unstructured, human-designed environments
  • The technology expands previous capabilities with whole-body motions including bending, reaching, and balancing

Frequently asked questions

What is the difference between Gemini Robotics 2 and the previous version?
The previous version controlled only the upper-body for table-top tasks, while Gemini Robotics 2 enables full whole-body control with movements like bending, reaching, and balancing.
In what types of environments can Gemini Robotics 2 deploy robots?
The model enables robots to perform tasks in unstructured environments designed for human movements, including tight and cluttered spaces.
What does Google DeepMind mean by 'physical AI' in this context?
Physical AI refers to AI models that give robots physical whole-body control to perform complex, real-world tasks in human-designed spaces.

Topics

In this video

Read next

Description from the channel

The world is built for human movements; it requires us to reach, bend, and balance in tight, cluttered spaces. While our previous models controlled the humanoid’s upper-body to achieve table-top tasks, Gemini Robotics 2 expands physical AI into whole-body motions. Learn more about Gemini for Robotics 2: https://deepmind.google/gemini-robotics ___ Subscribe to our channel https://www.youtube.com/@googledeepmind Find us on X https://twitter.com/GoogleDeepMind Follow us on Instagram https://instagram.com/googledeepmind Add us on Linkedin https://www.linkedin.com/company/deepmind/