Gemini Robotics

Gemini Robotics is an advanced vision–language–action model developed by Google DeepMind. It is based on the Gemini 2.0 large language model. It is tailored for robotics applications and can understand new situations. There is a related version called Gemini Robotics–ER, which stands for embodied reasoning. The two models were launched on March 12, 2025.

On June 24, 2025, Google DeepMind released Gemini Robotics On-Device, a variant designed and optimized to run locally on robotic devices.

On July 30, 2026, Google DeepMind announced Gemini Robotics ER 2, an upgrade to its embodied reasoning model featuring real-time video understanding, task progress tracking, lower-latency orchestration via the Gemini Live API, tool integration, and multi-robot collaboration. With this release, the model was made publicly available to developers via the Gemini API and Google AI Studio.

Access to earlier Gemini Robotics models was initially restricted to trusted testers, including Agile Robots, Agility Robotics, Boston Dynamics, and Enchanted Tools.

References

  1. ↑ "Gemini Robotics". deepmind.google. Retrieved March 12, 2025.
  2. 1 2 Parada, Carolina (March 12, 2025). "Gemini Robotics brings AI into the physical world". Google DeepMind. Retrieved July 11, 2025.
  3. 1 2 Knight, Will (May 12, 2025). "Google's Gemini Robotics AI Model Reaches Into the Physical World". WIRED. Retrieved March 12, 2025.
  4. ↑ "Google introduces new AI models for rapidly growing robotics industry". Reuters. March 12, 2025. Retrieved March 12, 2025.
  5. 1 2 Roth, Emma (March 12, 2025). "Google DeepMind's new AI models help robots perform physical tasks, even without training". The Verge. Retrieved March 12, 2025.
  6. ↑ Parada, Carolina (June 24, 2025). "Gemini Robotics On-Device brings AI to local robotic devices". Google DeepMind. Retrieved July 11, 2025.
  7. ↑ Hansen, Steven; Xu, Peng (July 30, 2026). "Introducing Gemini Robotics ER 2". Google DeepMind. Retrieved August 2, 2026.
  8. ↑ "Training a Whole-Body Control Foundation Model". Agility Robotics. Archived from the original on September 28, 2025. Retrieved January 6, 2026.