Gemini Robotics

{{Use mdy dates|date=March 2025}}

Gemini Robotics is an advanced vision-language-action model developed by Google DeepMind.{{Cite web |title=Gemini Robotics |url=https://deepmind.google/technologies/gemini-robotics/gemini-robotics-model/ |access-date=2025-03-12 |website=deepmind.google}} It is based on the Gemini 2.0 large language model.{{Cite magazine |last=Knight |first=Will |date=May 12, 2025 |title=Google's Gemini Robotics AI Model Reaches Into the Physical World |url=https://www.wired.com/story/googles-gemini-robotics-ai-model-that-reaches-into-the-physical-world/ |access-date=2025-03-12 |magazine=WIRED}} It is tailored for robotics applications and can understand new situations.{{Cite news |date=March 12, 2025 |title=Google introduces new AI models for rapidly growing robotics industry |url=https://www.reuters.com/technology/google-introduces-new-ai-models-rapidly-growing-robotics-industry-2025-03-12/ |access-date=2025-03-12 |work=Reuters}}{{Cite news |last=Roth |first=Emma |date=March 12, 2025 |title=Google DeepMind's new AI models help robots perform physical tasks, even without training |url=https://www.theverge.com/news/628021/google-deepmind-gemini-robotics-ai-models |access-date=2025-03-12 |work=The Verge}} There is a related version called Gemini Robotics-ER, which stands for embodied reasoning. The two models were launched on March 12, 2025.