What is Gemini Robotics 2.0?

It is Google DeepMind's AI model that can control humanoid robots to perform many physical tasks.

Why is part of the model being shared with developers?

Sharing one sub-model lets developers build their own robot applications.

What new abilities do robots gain with this update?

They can walk, crouch, stretch, and manipulate objects with their whole body.

Technology3 outlets covering this

Google reveals Gemini Robotics 2.0, promising improved dexterity and safety

First publishedJul 30, 15:04 UTC

Last updatedJul 31, 16:22 UTC · 20m ago

111

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

Google reveals Gemini Robotics 2.0, promising improved dexterity and safety - image 1 — 1 / 3

Google reveals Gemini Robotics 2.0, promising improved dexterity and safety - image 2 — 1 / 3

● Story signals

How strong is this topic?

5.9/10Significanceimpact & urgency

6.7/10Source trustoutlet authority

3Outletsindependent sources

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

Answer

Robots powered by Google's Gemini AI models are now more capable. With the debut of Gemini Robotics 2, these physical bots can now accomplish more complex tasks, continuously analyze changing environments, and collaborate with other robots.

Reported by 3 outlets — Ars Technica, WIRED, The Verge. See all sources ↓

Google DeepMind announced Gemini Robotics 2.0, an AI system that can control humanoid robots. The new model lets robots walk, pick up objects, and work together. One part of the system is now available for developers to use.

Why it matters

This advance brings robots closer to helping in homes and factories. It shows how AI can improve everyday tasks.

In brief

What is Gemini Robotics 2.0?: It is Google DeepMind's AI model that can control humanoid robots to perform many physical tasks.
Why is part of the model being shared with developers?: Sharing one sub-model lets developers build their own robot applications.
What new abilities do robots gain with this update?: They can walk, crouch, stretch, and manipulate objects with their whole body.

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.

Ars Technica stresses developer access and the goal of a generalist robot. WIRED highlights the vision‑language models that enable dexterous actions. The Verge emphasizes the shift to whole‑body control and shows a specific robot example.

Coverage cardFraming signal
1Angle
Scouting report
One sub‑model is released publicly for developers.
Sources1
TypeAngle
Ars TechnicaJul 30, 17:58mentions public availability
Coverage cardFraming signal
2Angle
Scouting report
The system uses a vision language model and two vision‑language‑action models to enable dexterous tasks.
Sources1
TypeAngle
WIREDJul 30, 15:04describes VLM and VLA models for tasks like screwing bulbs
Coverage cardFraming signal
3Angle
Scouting report
The update adds whole‑body motion control, allowing walking and object manipulation.
Sources1
TypeAngle
The VergeJul 30, 17:18highlights whole‑body control and Apollo 2 example

Related in the knowledge graph

organizationGemini organizationGemini Robotics organizationGoogle organizationGoogle's Gemini AI organizationInternet organizationRobots organizationVideos organizationWith

Sources (3)

Avg source rating 6.7/10

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