Robot AI model
Gemini Robotics-ER 1.5
Gemini Robotics-ER 1.5 supplies high-level planning, spatial reasoning and tool use for robot agents. The system passes language instructions to a VLA and estimates task progress and completion; developer access is through the Gemini API.
Records last verified Oct 13, 2026 · Send a correction
- Organization
- Google DeepMind
- Type
- Foundation model
- Released / introduced
- Sep 25, 2025
- Public weights
- Not established
- Licence / scope
- Not established
- Parameters
- Not disclosed
- Base model
- Gemini family
- Humanoid association
- None reported
- Inputs
- vision, language
- Outputs
- task plans, tool calls, spatial predictions, progress estimates
Release dates can mark an announcement or paper introduction. Public checkpoints, code licences and weight terms are distinct; follow the publisher’s links for the stated scope.
More robot AI models
Evidence
Sources
- [s1] Gemini Robotics 1.5 brings AI agents into the physical world ↗
Google DeepMind · official · published Sep 25, 2025 · accessed Oct 13, 2026
- [s2] Gemini Robotics 1.5 technical report ↗
Google DeepMind · paper · published Oct 2, 2025 · accessed Oct 13, 2026