Google DeepMind launches Gemini Robotics 2.5 for real-world robotics
Google DeepMind is launching Gemini Robotics 2.5, a vision-language-action model that improves robots' fine motor skills and learning speed in real-world environments.
What happened?
Google DeepMind has unveiled Gemini Robotics 2.5, the organisation's most capable vision-language-action (VLA) model to date. The model enables robots to learn skills more quickly and with greater breadth, ranging from everyday chores to factory floor tasks. The aim is to improve fine motor skills, reliability and safety in unstructured environments outside the laboratory.
Key facts
| Lanseringsdatum | 10 november 2026 |
|---|---|
| Modelltyp | Vision-language-action (VLA) |
| Underliggande forskningsmodell | Gemini 4 Argon |
”Today, we are introducing Gemini Robotics 2.5, our most capable vision-language-action (VLA) model to date.”
Why it matters
Training robots for unstructured environments in the physical world has long been a major challenge in artificial intelligence. By increasing learning speed and precision, robots can handle more varied physical tasks in a safer and more flexible way.
Who is affected?
Researchers and robotics developers, as well as hardware manufacturers building autonomous systems and humanoid robots, are primarily affected by these advancements.
What else you should know
The development is based in part on Gemini 4 Argon, which, according to DeepMind, has accelerated research and the development of the model's physical manipulation capabilities.
Quick answers about this story
Vad har hänt?
När hände det?
Varför spelar det roll?
Vilka typer av robotar omfattas?
The link opens in a new window and leads to the publisher's own site.
Källan har spårats automatiskt från utgivaren via Aheadlines signalkedja.
AI-verktyg i artikeln
Topics
Get similar news straight to your inbox
The reader's room
Send in a question or an addition. The newsroom reads everything before it's published and replies when relevant. No AI-generated text – just people.
Sign in to submit a comment or question.
Read the article through your role
- Decide whether this affects strategy over 6–12 months or is just noise.
- Discuss with leadership: do we own the right question or does ownership need to move?
- Ask: what risk are we taking by NOT acting on this this quarter?
Generated angle — not editorial analysis of "Google DeepMind launches Gemini Robotics 2.5 for real-world "