Gemini Robotics 2.5
Google's most capable vision-language-action robot model, converting sight and instructions into movements across robot types.
Every Gemini Robotics 2.5 story collected by The AI Daily, 2 so far, newest first, refreshed hourly.
Google's most capable vision-language-action robot model, converting sight and instructions into movements across robot types.
Google DeepMind launches Gemini Robotics 2.5, a vision-language-action model improving robot dexterity, reliability, and safety. Tested on over 200 tasks, achieving 96% success rate in pick-and-pack on Mercedes-Benz production lines.