Gemini Robotics ER 2: powering robotics with video understanding, task orchestration, and multi-robot collaboration

Google DeepMind News · 55d ago
Model Releases

How-To How to actually use this

What changed: Gemini Robotics ER 2 now offers improved video understanding, task orchestration, and multi-robot collaboration for real-world robotic applications.

How to use it:

  1. Feed the model video input of a task environment to enable situational reasoning.
  2. Define a task goal and let the orchestration layer decompose it into sub-steps.
  3. Deploy across multiple robots and use the collaboration features to coordinate actions.
  4. Monitor execution and refine task plans based on real-time video feedback.

Good for: robotics engineers building systems that reason over video and coordinate multiple robots.

Gemini Robotics ER 2 helps robots reason, collaborate, and solve real-world tasks. It represents a step change in video understanding, tool orchestration, and multi-robot collaboration for robotic applications.

Read original article on Google DeepMind News →