Gemini Robotics-ER 1.6: Powering real-world robotics tasks through enhanced embodied reasoning

Google announced today the release of Gemini Robotics-ER 1.6, an upgraded reasoning-first model designed to enhance robots' ability to understand and interact with the physical world. The company said the model specializes in visual and spatial understanding, task planning, and success detection, acting as a high-level reasoning system capable of natively calling tools such as Google Search and vision-language-action models. Google said the new version shows significant improvement over Gemini Robotics-ER 1.5 and Gemini 3.0 Flash in spatial and physical reasoning capabilities including pointing, counting, and success detection. The update also introduces instrument reading, allowing robots to interpret complex gauges and sight glasses, a capability developed through collaboration with partner Boston Dynamics. Starting today, the model is available to developers via the Gemini API and Google AI Studio, accompanied by a developer Colab with configuration and prompting examples.