Google DeepMind · Gemini Robotics

Gemini Robotics-ER

READER SUMMARY

An embodied-reasoning model for spatial understanding, planning, pointing, object detection and robot task orchestration.

DOOM SCORE63.2out of 100model risk profile, not the overall index

CURRENT ASSESSMENT · REVISION 1

Why this model scores 63.2

Strong spatial reasoning and planning create material physical-agent autonomy. Limited API and trusted-tester access constrain deployment and downstream control concerns relative to open models.

Capability72

Autonomy70

Deployment35

Misuse potential54

Control difficulty58

0 comments · 0 votesOpen discussion

No comments yet. Start the discussion.

MODEL-ATTRIBUTED EVIDENCE

News tied to Gemini Robotics-ER

The model score of 63.2 rates this model's risk profile. The overall Doom Index of 63.5 measures the recalibrated complete evidence corpus. These values answer different questions.

NET MODEL-ATTRIBUTED INDEX CONTRIBUTION+0.02

Each article's leave-one-out Doom Index contribution is divided equally among the exact models named on that article. This prevents multi-model evidence from being claimed in full on several model pages. Model risk scores are recalculated from their technical profile and related news, but never feed back into the overall index.

12 Mar 2025AutonomyTOWARD

Google introduces Gemini Robotics and Robotics-ER

Google DeepMind introduced a vision-language-action model that directly controls robots and an embodied-reasoning model for spatial understanding, planning and task execution across robot types.

Full item contribution: +0.04
Gemini Robotics-ER equal share: +0.02

Read assessment →

AUDIT TRAIL

Model score history

R1
Doom Score 63.2
Initial exact profile for the March 2025 embodied-reasoning model.
12 Aug 2026