Google DeepMind launches Gemini Robotics ER 2, a high-level reasoning brain enabling multi-robot collaboration
Category: Physical AI • Robotics
What it is
Google DeepMind launched Gemini Robotics ER 2, a high-level “reasoning brain” for robots that handles spatial reasoning, multi-step planning, and tool orchestration while handing off motor execution to lower-level models. It adds continuous video-based progress tracking, precision moment-finding, and multi-robot collaboration – demonstrated via Boston Dynamics’ Spot and a handoff between Apptronik’s Apollo 2 and Franka’s F3 Duo. It’s available now via the Gemini API and Google AI Studio.
Why it Matters for Enterprises
Physical AI is moving from single-task demos toward orchestrated, multi-robot workflows. Enterprises in manufacturing, logistics, or field operations should start evaluating embodied-reasoning layers now, ahead of broader robotics deployment.
