Gemini Robotics 1.5 brings AI agents into the physical world
20 hours ago
- #Physical Agents
- #Gemini Models
- #AI Robotics
- Gemini Robotics 1.5 introduces AI agents into the physical world, enabling robots to perceive, plan, think, use tools, and act.
- Two models are introduced: Gemini Robotics 1.5 (vision-language-action model) and Gemini Robotics-ER 1.5 (vision-language model).
- Gemini Robotics-ER 1.5 is now available to developers via the Gemini API in Google AI Studio.
- The models work together in an agentic framework to solve complex, multi-step tasks.
- Gemini Robotics 1.5 can think before acting, generating internal reasoning and analysis in natural language.
- The models show remarkable ability to learn across different robot embodiments, accelerating skill learning.
- Safety measures include high-level semantic reasoning, alignment with Gemini Safety Policies, and triggering low-level safety sub-systems.
- Gemini Robotics 1.5 marks a milestone towards solving AGI in the physical world, enabling robots to reason, plan, and generalize.