Google DeepMind releases Gemini Robotics 2.5 vision-language-action model for real-world robot tasks

Google DeepMind released Gemini Robotics 2.5, a vision-language-action model tested across more than 200 distinct tasks to improve robot dexterity, reliability and safety in unstructured environments. Google DeepMind said the model broadens the range of skills robots can learn and speeds up skill acquisition, building on robotics research capabilities from Gemini 4 Argon. Google is rolling Gemini Robotics 2.5 out to robotics partners.

Google DeepMind releases Gemini Robotics 2.5 vision-language-action model for real-world robot tasks According to Google DeepMind, Gemini Robotics 2.5 is a vision-language-action model tested across over 200 distinct tasks to increase robot dexterity, reliability, and safety in unstructured environments. The model expands the breadth of skills robots can learn and accelerates acquisition speed, building on Gemini 4 Argon's robotics research capabilities. Google is rolling the model out to robotics partners. Topics Sources - Official Read article https://deepmind.google/blog/gemini-robotics-2-5-accelerates-real-world-physical-intelligence/ - Official Read article https://deepmind.google/models/model-cards/gemini-4-hydrogen/ Go deeper This intelligence is sourced automatically from public sources across the web and synthesised by the Prefactor AI pipeline. Stories are reviewed before publication.