Google DeepMind introduces Gemini Robotics 2, ER 2, and On-Device 2 models for robots

On July 30, 2026 Google DeepMind introduced Gemini Robotics 2, a set of three models: Gemini Robotics 2, a vision-language-action model that Google DeepMind says can control full humanoids and bi-arm robots; Gemini Robotics ER 2, an embodied reasoning model that plans multi-step tasks and coordinates several robots; and Gemini Robotics On-Device 2, a vision-language-action model optimized to run locally on robots. The announcement says Gemini Robotics ER 2 is available on Google AI Studio and in private preview on Gemini Enterprise Agent Platform, while the other two models are available to early-access partners. It also introduces ASIMOV-Agentic, a benchmark for agentic safety orchestration. No release of weights is described. USASI has not tested these models.1

USASI. (2026, October 13). Google DeepMind introduces Gemini Robotics 2, ER 2, and On-Device 2 models for robots. United States of America Superintelligence. https://unitedstatesofamericasuperintelligence.com/news/google-deepmind-introduces-gemini-robotics-2/

@misc{usasi_news_google_deepmind_introduces_gemini_robotics_2,
  author = {{USASI}},
  title = {Google DeepMind introduces Gemini Robotics 2, ER 2, and On-Device 2 models for robots},
  year = {2026},
  month = oct,
  howpublished = {\url{https://unitedstatesofamericasuperintelligence.com/news/google-deepmind-introduces-gemini-robotics-2/}},
  note = {United States of America Superintelligence. Last updated 2026-10-13}
}