Google DeepMind releases Gemini Robotics-ER 1.6

Google DeepMind released Gemini Robotics-ER 1.6, positioned as a high-level reasoning model for robots. Compared to its predecessors ER 1.5 and Gemini 3.0 Flash, it offers significant improvements in spatial reasoning and multi-view understanding. The model is available to developers through the Gemini API and Google AI Studio. Core upgrades include three key capabilities: 1. Improved pointing accuracy: Enables precise object detection, counting, spatial relationship reasoning (e.g., pointing out all objects that can fit into the blue cup), and motion trajectory planning, while correctly rejecting pointing to objects not present in the frame. 2. Successful multi-view detection: The robot can now integrate multiple camera feeds to determine task completion accuracy, even in occluded or dynamic environments. 3. New instrument reading capabilities: It can interpret various industrial instruments such as circular pressure gauges, vertical level indicators, and digital displays. Through agentic vision (visual reasoning + code execution), it performs step-by-step reasoning, first magnifying detailed areas, then calculating proportions and intervals through pointing and code, and finally combining this with world knowledge to derive the reading.