Project AURIONAI Use-Cases Research & Innovation
robot policy

Gemini Robotics

Gemini 2.0-based VLA for trusted testers; Apptronik humanoid partner.

Google DeepMindGoogle DeepMindUK / USAGemini RoboticsFamily
Google DeepMind
Levelmodel
Classrobot policy
Parametersnot in the notes
Contextnot in the notes
Released12 Mar 2025
Opennessproprietary
Runs onnot in the notes
Statusactive

Lineage

finetunesuccessor
Gemini 2.0 to Gemini Robotics: finetune, medium confidenceGemini Robotics 1.5 to Gemini Robotics On-Device 2: finetune, low confidenceGemini Robotics to Gemini Robotics 1.5: successor, medium confidenceGemini Robotics to Gemini Robotics On-Device: successor, medium confidenceGemini 2.0Gemini 2.0Google DeepMindGemini RoboticsGemini RoboticsGoogle DeepMind, Mar 2025Gemini Robotics On-DeviceGemini Robotics On-DeviceGoogle DeepMind, Jun 2025Gemini Robotics 1.5Gemini Robotics 1.5Google DeepMind, Sep 2025Gemini Robotics On-Device 2Gemini Robotics On-Device 2Google DeepMind, Jul 2026
Google DeepMindGemini 2.0 is the parent (finetune)medium confidencepress claim
Google DeepMindGemini Robotics 1.5 is a child (successor)medium confidencenotes
Google DeepMindGemini Robotics On-Device is a child (successor)medium confidencenotes
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 5 models. Confidence and evidence are the notes' own.

R&D Topics

Vision-language-action robot policiesproduced by

Identity

Developer
Google DeepMind
Family
Gemini Robotics
Released
12 Mar 2025 sourcessecondary report
Weights published
–
Record checked
10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
not in the notes
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
image, text
Output
action
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
proprietary
Licence
Proprietary sources
Access routes
gated preview
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. aiwiki.ai/wiki/gemini_robotics_2 https://aiwiki.ai/wiki/gemini_robotics_2

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Gemini Robotics", https://aurion.semai.id/models/google-deepmind-gemini-robotics/, records of October 2026.