Google DeepMind has unveiled Gemini Robotics, a new vision-language-action model built on Gemini 2.0 designed to help robots understand and interact with the physical world. The company also introduced Gemini Robotics-ER, which enhances spatial understanding capabilities for roboticists. These models represent a significant step toward AI systems that can operate effectively in real-world environments beyond digital spaces.

Gemini Robotics demonstrates improvements in three critical areas: generality, interactivity, and dexterity. The model can adapt to novel situations, understand conversational commands in multiple languages, and perform complex tasks requiring fine motor skills. Google reports it more than doubles performance on generalization benchmarks compared to other state-of-the-art models, marking a substantial advancement in robotic capabilities.

The company is partnering with Apptronik to develop next-generation humanoid robots using Gemini 2.0. Google is also addressing safety concerns by releasing a new dataset for evaluating semantic safety in embodied AI. These developments signal Google's commitment to creating practical, safe robotic systems that can assist humans in everyday tasks, moving beyond theoretical research to real-world applications.