Google Deepmind has introduced Gemini Robotics 2, its latest and most sophisticated vision-language-action model designed to operate a wide range of robots. According to The Decoder, this new model can control everything from simple tabletop robots to complex full-body humanoid machines.
This advancement marks a significant step forward in robotics AI, combining vision, language understanding, and physical action capabilities into a single system. Such integration allows for more flexible and intelligent robot control across diverse applications.
For Japanese markets, where robotics and automation continue to be critical growth areas, Gemini Robotics 2’s potential for enhancing industrial and service robots could drive further innovation and investment in AI-powered automation technologies.