Gemini Robotics 2.5 accelerates real-world general dexterity
What happened
Gemini Robotics 2.5, DeepMind’s latest vision‑language‑action model, expands the range and speed of skills robots can learn, demonstrating improved dexterity, reliability and safety across more than 200 tasks. In a real‑world test on a Mercedes‑Benz production line, the model helped Apptronik’s Apollo 2 humanoid robot pick and pack parts with a 96% success rate.
Why it matters
The advances suggest robots can move beyond controlled labs into unstructured environments, handling everyday and delicate objects more reliably, which could free humans from repetitive work and enable broader automation.
Is this a big deal?
Get stories like this every morning
The day's AI news in plain English, in your inbox at 8:30 IST. Free.
More from Google
Google Search gets a major upgrade with Gemini 4 HydrogenGoogle · 12 Nov 2026Introducing Gemini 4 HydrogenGoogle · 12 Nov 2026Gemini 4 HydrogenGoogle · 12 Nov 2026Gemini Decisions API: Fast, calibrated multimodal decisionsGoogle · 11 Nov 2026Try Tabletop: Customizable, collaborative spaces for groups to plan, play and do more together.Google · 11 Nov 2026This page was collected from deepmind.google and summarised automatically by AIPulsee's pipeline. See how it runs.