Most robotics AI models suffer from the "stop-and-think" problem.
They take a static picture, pause to reason, execute an action, and repeat.
In the real world, that latency causes spills, collisions, and failed tasks.
Google DeepMind just launched Gemini Robotics ER 2: an embodied reasoning model that thinks and acts at the speed of the physical world.
Here's why this is a step-change for physical AI engineering:
Traditional robotics models rely on static snapshots. But knowing *when* a task is done, such as when to stop pouring coffee into a cup or when a trash bag is securely tied, requires continuous temporal awareness.
Gemini Robotics ER 2 integrates directly with the bidirectional streaming Gemini Live API to reason about what comes next while simultaneously executing motor actions.
What makes Gemini Robotics ER 2 different:
๐ฏ 91.3% accuracy on live video moment-finding (0.96s mean absolute distance) at 4x the execution speed of frontier models
๐ Continuous progress tracking across 5 completion stages (57.4% accuracy) to self-correct mid-task without restarting
๐ ๏ธ Native agentic tool orchestration that commands lower-level VLA models, navigation APIs, and Google Search
๐ค Multi-robot collaboration allowing physically diverse machines (like Apptronik's Apollo 2 humanoid and Franka's FR3 Duo arm) to hand off tasks in shared spaces
๐ก๏ธ Built-in physical safety that autonomously halts robots when humans enter a workspace and resumes once clear