Google DeepMind Launches Gemini Robotics-ER 1.6 With Enhanced Spatial Reasoning and New Industrial Gauge Reading Capability
Summary
Google DeepMind launches Gemini Robotics-ER 1.6, a major upgrade featuring enhanced spatial reasoning, multi-view understanding, and a new industrial gauge-reading capability built with Boston Dynamics — now available to developers via the Gemini API.
Key Points
- Google DeepMind is launching Gemini Robotics-ER 1.6, a significant upgrade to its embodied reasoning model that delivers enhanced spatial reasoning, multi-view understanding, and a new instrument reading capability developed in collaboration with Boston Dynamics.
- The model powers real-world robotics tasks including precision object detection, success detection across multiple camera views, and the ability to read complex industrial gauges and sight glasses using agentic vision combined with code execution.
- Gemini Robotics-ER 1.6 is now available to developers via the Gemini API and Google AI Studio, and stands as the safest robotics model to date, outperforming previous generations on safety instruction following and physical hazard identification.