Google DeepMind's Gemini Robotics-ER 1.6 gives robots a sharper brain for planning and perception

Google DeepMind launched Gemini Robotics-ER 1.6, an upgraded embodied reasoning model for robots.

It acts as a high-level planning layer and can call tools like Google Search or vision-language-action models.

The model reportedly improves object pointing, counting, and task verification over earlier versions.

It also boosts inspection work, including reading pressure gauges and sight glasses with zooming, pointing, code-based measurement, and world knowledge.

Gemini Robotics-ER 1.6 is available through the Gemini API and Google AI Studio, with a Colab example for developers.