Google’s latest AI lets robots understand, plan, and act in real environments
Google has introduced a new AI model, Gemini Robotics-ER 1.6, designed to help robots better understand and interact with the physical world. The model enables robots to interpret visual inputs, plan tasks, and determine when a task is complete, marking a shift from command-following machines to systems capable of making context-aware decisions.
Google has introduced a new AI model to improve robot reasoning. The model, Gemini Robotics-ER 1.6, focuses on embodied reasoning, enabling robots to interpret visual inputs and plan tasks. It improves spatial reasoning and multi-view understanding, allowing robots to process information from multiple camera feeds. The model also introduces instrument reading, enabling robots to interpret gauges and indicators. This capability was developed in collaboration with Boston Dynamics. The model is now available to developers through the Gemini API and Google AI Studio.
This content was automatically generated and/or translated by AI. It may contain inaccuracies. Please refer to the original sources for verification.