Google DeepMind introduced Gemini Robotics-ER 1.6, a reasoning-first model designed to help robots understand physical environments through enhanced spatial reasoning and multi-view understanding. The model improves over prior versions in spatial and physical reasoning capabilities, adding a new instrument reading feature developed with Boston Dynamics. It is available to developers via the Gemini API and Google AI Studio, functioning as a high-level reasoning layer that can call external tools.
No score is assigned. Sources and their independence are shown in the citation chain below.