DOOMBENCH.COM
Autonomy and agency

Google releases Gemini Robotics On-Device for local physical control

Google DeepMind released Gemini Robotics On-Device, a vision-language-action model that runs locally on robots, adapts to new tasks and can be fine-tuned with demonstrations.

0 comments · 0 votesOpen discussion

Public discussion is readable by everyone. Sign in to comment, reply, or vote.

No comments yet. Start the discussion.

Send detailed or private feedback →
CURRENT ASSESSMENT · REVISION 1
TOWARD DOOM55confidence 95/100

Why it moved the index

Local low-latency operation, dexterous generalization and rapid adaptation move consequential physical autonomy beyond cloud dependence, while limited trusted-tester access constrains deployment.

Assessment history

  1. R1
    Toward 55 · confidence 95

    New exact physical-autonomy model with no collision with the later Robotics On-Device 2 profile.

    12 Aug 2026

Share this page

DoomBench social sharing card for Google releases Gemini Robotics On-Device for local physical control.

  1. DoomBench assesses “Google releases Gemini Robotics On-Device for local physical control” as evidence moving toward doom, with magnitude 55 and confidence 95 out of 100 in the autonomy and agency category.

  2. The DoomBench assessment of “Google releases Gemini Robotics On-Device for local physical control” is based on reporting from Google DeepMind and records the editorial rationale, source quality, attribution, and revision history.

  3. DoomBench summarizes “Google releases Gemini Robotics On-Device for local physical control” as follows: Google DeepMind released Gemini Robotics On-Device, a vision-language-action model that runs locally on robots, adapts to new tasks...

    https://www.doombench.com/news/google-releases-gemini-robotics-on-device-for-local-physical-control-2025-06-24