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

Google DeepMind launched Gemini Robotics ER 2, an embodied reasoning model for robotics, now publicly available via the Gemini API and Google AI Studio.

• Available via the Gemini API, Google AI Studio, and private preview on Gemini Enterprise Agent Platform
• Achieves 57.4% accuracy on progress classification and 91.3% on moment-finding with 0.96s mean absolute distance
• Enables multi-robot collaboration, demonstrated with Apptronik's Apollo 2 and Franka F3 Duo
• Integrates with the Gemini Live API for sub-second latency, delivering 4x the execution speed of larger models

Robotics developers can now build robots that reason about multi-step tasks, track their own progress, and collaborate with other robots using a publicly available model.

Sources

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

Read this as text

Back to the AI news