What can Gemini Robotics 2 do?

It lets robots understand images and language and control their whole body to do tasks like picking up objects.

Which robot was shown in the videos?

Google showed videos of Apptronik's Apollo 2 robot bending to pick up a watering can.

How is this different from the earlier model?

The earlier model only controlled the upper body, while Gemini Robotics 2 controls the whole body from feet to fingertips.

● ImportantTechnology2 outlets covering this

Gemini Robotics 2 Brings Google's AI Into the Physical World

First publishedJul 30, 15:04 UTC

Last updatedJul 30, 20:25 UTC · 21m ago

2 outlets over time — hover a bar for its window & outletslast updated

Gemini Robotics 2 Brings Google's AI Into the Physical World - image 1 — 1 / 2

Gemini Robotics 2 Brings Google's AI Into the Physical World - image 2 — 1 / 2

● Story signals

How strong is this topic?

6.5/10Significanceimpact & urgency

6.5/10Source trustoutlet authority

2Outletsindependent sources

Significance weighs impact, urgency & coverage breadth · Source trust is the outlets' average authority · more outlets means a more confirmed story.

Answer

Google DeepMind just released a new version of its artificial intelligence model Gemini, and it can control a range of different robots—including humanoids capable of dextrous tasks like screwing in lightbulbs and tying trash bags. Gemini Robotics 2 combines several different AI models into a single system.

Reported by 2 outlets — WIRED, The Verge. See all sources ↓

Google DeepMind released Gemini Robotics 2, an updated AI model that can control robots. It combines vision, language, and action models so robots can understand their surroundings and perform tasks. The model lets humanoid robots do whole-body movements like walking, bending, and manipulating objects.

Why it matters

This advance shows how AI is moving from screens to real-world machines, which could help with chores, manufacturing, or caregiving. Readers may see robots becoming more useful in daily life sooner.

In brief

What can Gemini Robotics 2 do?: It lets robots understand images and language and control their whole body to do tasks like picking up objects.
Which robot was shown in the videos?: Google showed videos of Apptronik's Apollo 2 robot bending to pick up a watering can.
How is this different from the earlier model?: The earlier model only controlled the upper body, while Gemini Robotics 2 controls the whole body from feet to fingertips.

Different angles across outlets

Coverage map

How outlets are framing the same story

These are the main editorial angles found across reporting. Use them to quickly compare what different outlets emphasize, omit, or question.

WIRED highlights the AI's multimodal integration and dexterous tasks like screwing in lightbulbs. The Verge stresses the new whole‑body motion capability and shows specific robot movements.

Coverage cardFraming signal
1Angle
Scouting report
Emphasis on multimodal AI integration and dexterous tasks.
Sources1
TypeAngle
WIREDJul 30, 15:04focuses on combining vision, language, action models for dexterous tasks
Coverage cardFraming signal
2Angle
Scouting report
Emphasis on whole‑body control and specific robot demonstrations.
Sources1
TypeAngle
The VergeJul 30, 17:18highlights whole‑body motions and shows Apollo 2 robot demo

Related in the knowledge graph

organizationBrings Google's AI Into organizationGemini organizationGemini Robotics organizationPhysical World. Google DeepMind organizationTaken organizationTwo organizationVLA organizationVLM

Sources (2)

Avg source rating 6.5/10

Processing cluster

A1A2A3B1B2B3

Share this article

X / Twitter LinkedIn WhatsApp

Summarize with AI (opens AI chat with article URL · Gemini: prompt copied to clipboard)

GPT Perplexity Gemini Claude