Skip to content
Google· Launch

Google DeepMind Unveils Gemini Robotics 2.5

Google DeepMind has unveiled Gemini Robotics 2.5. The new AI model enhances robot motor skills and achieved a 96 percent success rate in a pilot test with Mercedes-Benz.

By the Aheadline editorial team·15 nov. 2026·2 min read·Source: Entity-watch: Google DeepMindVerifierad signalAI-generated
Google DeepMind Unveils Gemini Robotics 2.5
Google DeepMind Unveils Gemini Robotics 2.5
Google DeepMind Unveils Gemini Robotics 2.5
By · Verktygs- & infrastrukturreporter
Last updated
Vad betyder det för mig?

What happened?

Google DeepMind has introduced Gemini Robotics 2.5, a new AI model in the vision-language-action (VLA) category. The model is designed to improve robotic fine motor skills, reliability, and the ability to learn physical tasks in real-world environments. In a pilot test for automotive kitting conducted with robot developer Apptronik and car manufacturer Mercedes-Benz, the model demonstrated a 96 percent success rate.

Key facts

AI-modellGemini Robotics 2.5
Framgångsgrad i pilotprojekt96 %
Partner i pilotprojektApptronik och Mercedes-Benz
Publikationsdatum13 november 2026

”enables robots to learn faster for the real world - from everyday skills to the factory floor”

— Google DeepMind, Utvecklare · Robotics 24/7

Why it matters

Physical automation in factory and everyday environments has long been constrained by the difficulties robots face in handling unforeseen variations, often requiring extensive manual programming. By combining visual and linguistic reasoning with direct motor actions, VLA models can lower the threshold for deploying robots on dynamic production lines. The results at Mercedes-Benz indicate that the technology has reached a level of reliability nearing active industrial application.

Who is affected?

The launch is relevant to robot developers, hardware manufacturers, and industrial companies in the manufacturing and automotive sectors looking to automate complex physical tasks. Researchers specializing in VLA models and robotics are also affected by the model's capacity for faster learning.

What else you should know

The model is a further development of DeepMind's commitment to vision-language-action architectures, where multimodal input is linked directly to physical motor instructions.

Frequently asked questions

Quick answers about this story

Vad har hänt?
Google DeepMind har lanserat Gemini Robotics 2.5, en vision-language-action-modell som förbättrar robotars finmotorik och inlärningsförmåga i fysiska miljöer.
När hände det?
Lanseringen rapporterades den 13 november 2026.
Varför spelar det roll?
Modellen demonstrerar hög precision i industriella miljöer, bland annat med en 96-procentig framgångsgrad i fordonskitting hos Mercedes-Benz, vilket underlättar automatisering av komplexa manuella moment.
Vilka externa partners har testat modellen?
I ett pilotprojekt samarbetade robotbolaget Apptronik och fordonstillverkaren Mercedes-Benz för att testa modellen i fabriksmiljö.
Original source
Entity-watch: Google DeepMind·robotics247.com

The link opens in a new window and leads to the publisher's own site.

Verifierad signal

Källan har spårats automatiskt från utgivaren via Aheadlines signalkedja.

AI-verktyg i artikeln

Topics

#Google DeepMind#Gemini#Skills#Vision
[ STAY UP TO DATE ]

Get similar news straight to your inbox

No affiliate linksCancel anytimeGDPR-friendly
[ Frequency ]
[ What do you want to read about? ]

You'll receive updates on 2 topics.

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.

Loading comments…
How this affects you

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 Unveils Gemini Robotics 2.5"