Google DeepMind launches Gemini Robotics 2 family with whole-body humanoid control
On 30 July 2026 Google DeepMind released Gemini Robotics 2 — a VLA model for whole-body humanoid control and dexterous manipulation, the Gemini Robotics ER 2 embodied-reasoning "brain" (public in the Gemini API), and a lightweight On-Device 2 model that adapts to new robot bodies in hours. Partners include Apptronik, Boston Dynamics, Franka and Agile Robots.
Key facts
- Three models: Gemini Robotics 2 (vision-language-action), Gemini Robotics ER 2 (embodied reasoning), Gemini Robotics On-Device 2
- Whole-body control: walking, crouching and manipulating; multi-fingered hands and grippers; multi-robot collaboration; tasks lasting several minutes
- ER 2 adds real-time video understanding, task-progress tracking, tool calls and low-latency orchestration via the Live API
- ER 2 moment-finding accuracy 91.3% (mean abs. error 0.96 s) at ~4x the speed of the previous generation (per third-party summary of Google's numbers)
- API IDs: gemini-robotics-er-2-preview and gemini-robotics-er-2-streaming-preview; ER 1.6 preview shut down 2026-08-31
- Partners: Apptronik (Apollo 2), Franka Duo, Boston Dynamics, Agile Robots; VLA and On-Device via early-access program
What happened
Google DeepMind announced its second-generation robotics foundation models. Gemini Robotics 2 converts vision and language into motor control for humanoids and bi-arm robots, now including whole-body control; ER 2 plans multi-step tasks, talks to humans and coordinates several robots; On-Device 2 runs locally and adapts to new embodiments quickly. ER 2 is publicly available to developers in the Gemini API/AI Studio; the VLA models are limited to partners.
Why it matters
It moves Google's robotics stack from tabletop arm manipulation to general-purpose humanoid bodies, with a hosted "robot brain" API developers can use today — a key piece in the 2026 race for physical AI.
Changelog
- 2026-09-29: created
Models
- Gemini Robotics 2 Google DeepMind · preview
- Gemini Robotics ER 2 Google DeepMind · preview
- Gemini Robotics On-Device 2 Google DeepMind · preview
Videos (3)
Gemini Robotics 2 brings whole body intelligence to robots
Google DeepMind · 2026-07-30 · officialThis video is an official launch showcase from Google DeepMind introducing Gemini Robotics 2, a multimodal generalist foundation model designed to serve as an intelligent physical "brain" across diverse robotic embodiments. Researchers including Jie Tan, Marissa Giustina, Kanishka Rao, Konstantinos Bousmalis, and…
Introducing Gemini Robotics 2
Google for Developers · 2026-07-30 · officialIn this episode of Google AI's Release Notes, host Logan Kilpatrick sits down with Google DeepMind robotics leaders Carolina Parada, Stuart Bowers, Kanishka Rao, and Jie Tan to discuss the announcement of Gemini Robotics 2. The panel covers advances in whole-body control, dexterous manipulation, multi-robot…
Intelligent whole-body control with Gemini Robotics 2
Google DeepMind · 2026-07-30 · officialThis video is a demonstration by Google DeepMind showcasing "Gemini Robotics 2" running on an Apptronik Apollo humanoid robot. It is presented by Jie Tan, Principal Research Scientist and Director at Google DeepMind, who explains the integration of embodied reasoning and vision-language-action (VLA) models for…
Related events
- Google I/O 2026: Gemini 3.5 Flash, Gemini Spark agent and Antigravity 2.0 ★★★★
- Apptronik raises $520M at $5B valuation to scale Apollo humanoid ★★★
- Google DeepMind releases Gemini Robotics-ER 1.6; Boston Dynamics' Spot uses it to read gauges ★★
Sources (6)
- officialGemini Robotics 2 brings whole body intelligence to robots (DeepMind blog)
- officialIntroducing Gemini Robotics ER 2 (Google blog)
- officialGemini Robotics ER 2 model card
- pressSiliconANGLE: DeepMind debuts Gemini Robotics 2 for humanoid robots
- pressMarkTechPost: three physical AI models
- videoGemini Robotics 2 brings whole body intelligence to robots (video)
id: 2026-07-30-gemini-robotics-2 · updated 2026-09-29 · open in the interactive timeline