DEPLOYDatabase

Brain

Gemini Robotics

Google DeepMind's robotics VLA family. Gemini Robotics builds on Gemini 2.0 with physical actions as an output modality and adds an intermediate reasoning layer for spatial analysis and safety. Gemini Robotics-ER is an embodied-reasoning VLM companion. Gemini Robotics On-Device runs locally, network-independent, and is fine-tunable with 50-100 demonstrations. Gemini Robotics 1.5 introduced 'think before acting'.

Foundation model · Maturity: Research · Closed · Powers 1 robot

Machine-readable surfaces

Architecture

VLA built on Gemini 2.0 with physical actions as output modality, plus an intermediate reasoning layer for spatial analysis and safety. Gemini Robotics-ER is the embodied-reasoning VLM companion. Gemini Robotics On-Device runs locally, network-independent, and is fine-tunable with 50-100 demonstrations. Gemini Robotics 1.5 emphasizes a 'think before acting' chain-of-thought style.

Key facts

DEPLOY maturity rationale
Most advanced DeepMind VLA; commercializing via Apptronik; not at-scale production. Re-derived as research-to-commercial; recorded here as research given current scale
Announced
March 2025
Apptronik partnership
Confirmed; Gemini Robotics powers Apptronik Apollo in joint roadmap
On-Device variant
First DeepMind VLA available for fine-tuning; 50-100 demonstrations
Cross-embodiment
Trusted-tester robots; cross-platform deployment
Apollo partnership type
The Apollo (Apptronik) relationship is investment-linked: Google led Apptronik's Series A and the Gemini Robotics partnership formalizes the technology integration. Distinct from Atlas-Gemini, which is a dedicated bidirectional co-development with Boston Dynamics. Apollo also operates inside NVIDIA's Isaac ecosystem; primary-source evidence for GR00T as Apollo's onboard brain at runtime is not yet established, so DEPLOY does not record a GR00T powers relation on Apollo (only the Gemini Robotics powers relation).
wikidata
www.wikidata.org/wiki/Q133568202
wikipedia
en.wikipedia.org/wiki/Gemini_Robotics

Developed by (1)

Powers (1)

Common questions

What is Gemini Robotics?
Google DeepMind's robotics VLA family. Gemini Robotics builds on Gemini 2.0 with physical actions as an output modality and adds an intermediate reasoning layer for spatial analysis and safety. Gemini Robotics-ER is an embodied-reasoning VLM companion. Gemini Robotics On-Device runs locally, network-independent, and is fine-tunable with 50-100 demonstrations. Gemini Robotics 1.5 introduced 'think before acting'.
Which robots run on Gemini Robotics?
1 robot model on the DEPLOY registry runs on Gemini Robotics: Apollo.
Who developed Gemini Robotics?
Gemini Robotics is credited to Google DeepMind on the DEPLOY registry. Each developer attribution is verified via primary sources.
Is Gemini Robotics open source?
No. Gemini Robotics is recorded as proprietary on the DEPLOY registry. Model weights and source are not publicly available.
What type of AI is Gemini Robotics?
Gemini Robotics is a foundation model, built on a VLA built on Gemini 2.0 with physical actions as output modality, plus an intermediate reasoning layer for spatial analysis and safety. Gemini Robotics-ER is the embodied-reasoning VLM companion. Gemini Robotics On-Device runs locally, network-independent, and is fine-tunable with 50-100 demonstrations. Gemini Robotics 1.5 emphasizes a 'think before acting' chain-of-thought style. architecture on the DEPLOY registry.

Sources (8)

  1. Google DeepMind: Gemini Robotics (primary) · https://deepmind.google/models/gemini-robotics
  2. Google DeepMind Blog · https://deepmind.google/blog/
  3. https://deepmind.google/blog/gemini-robotics-brings-ai-into-the-physical-world/
  4. https://deepmind.google/blog/gemini-robotics-on-device-brings-ai-to-local-robotic-devices/
  5. https://deepmind.google/blog/gemini-robotics-15-brings-ai-agents-into-the-physical-world/
  6. https://deepmind.google/models/gemini-robotics/
  7. https://arxiv.org/abs/2503.20020
  8. https://www.therobotreport.com/google-deepmind-introduces-on-device-gemini-ai-model-robots/
Methodology: Verified · 8 sources (no primary) · last reviewed 2026-06-03

Verification posture

Verified

Low confidence

Review state

Stable

Last reviewed 2026-06-03

Maturity + lifecycle

Maturity stage: research

Sources by quality tier

6
unclassified
Unclassified source
1
preprint
Preprint
1
secondary-trade-publication
Trade publication

The framework is documented at /methodology. Corrections at /corrections. Reviewer: DEPLOY editorial team.

Methodology surface for Gemini Robotics.

Canonical ID 3ccbb952-c7f9-408a-9534-57eb386761a7