Google DeepMind Releases Gemini Robotics-ER 1.6: Bringing Enhanced Embodied Reasoning and Instrument Reading to Physical AI

Google DeepMind has released Gemini Robotics-ER 1.6, an embodied reasoning model for robots.

The upgrade improves spatial reasoning, success detection, and multi-view reasoning.

It also adds the ability to read instruments and other physical displays.

The changes should help robots plan more accurately, verify task completion, and operate more reliably in the real world.