Three new robotics models demonstrated whole-body humanoid control, dexterous manipulation, several-minute planning, self-correction, multi-robot collaboration, and rapid on-device adaptation, with reasoning access available in AI Studio.
Sign in to join the discussion →
No comments yet. Start the discussion.
The models move agentic capability into physical systems through whole-body control, hundreds of decisions over several minutes, self-correction, and multi-robot coordination. Access remains staged and reported success is uneven, especially for multifinger tasks; published safety tooling and human-proximity controls also reduce the residual risk.
Reviewed videos from Artificial Intelligence Videos. These links add context and never change a DoomBench score.
New historical physical-autonomy model release with verified robot demonstrations and access details.
11 Aug 2026DoomBench assesses “Google DeepMind releases Gemini Robotics 2 for whole-body and multi-robot tasks” as evidence moving toward doom, with magnitude 62 and confidence 88 out of 100 in the autonomy and agency category.
The DoomBench assessment of “Google DeepMind releases Gemini Robotics 2 for whole-body and multi-robot tasks” is based on reporting from Google DeepMind and records the editorial rationale, source quality, attribution, and revision history.
DoomBench summarizes “Google DeepMind releases Gemini Robotics 2 for whole-body and multi-robot tasks” as follows: Three new robotics models demonstrated whole-body humanoid control, dexterous manipulation, several-minute planning,...
