Google DeepMind has launched Gemini Robotics ER 2, an embodied reasoning model designed to serve as a high-level brain for robots. Key improvements over ER 1.6 include continuous video understanding for real-time task progress tracking, precision moment-finding to identify critical task transitions, and multi-robot collaboration enabling diverse machines to coordinate via shared semantic understanding. The model integrates with the Gemini Live API for low-latency bidirectional streaming, supports tool orchestration (including Google Search and user-defined functions), and can hand off motor execution to any VLA model. Safety improvements include better adherence to physical constraints and human proximity detection. The model is now available to developers via the Gemini API, Google AI Studio, and Gemini Enterprise Agent Platform, with sample code and a Boston Dynamics Spot demo on GitHub.
