

Google's SOTA robotics model for visual & spatial reasoning!
Gemini Robotics-ER 1.6 is a vision-language model for robot reasoning. It handles spatial pointing, multi-view success detection, and instrument reading. For robotics engineers and developers building physical agents via the Gemini API.
还没有评论,来抢沙发吧!
X 上关于 Gemini Robotics ER 1.6 的真实讨论
去 X 发帖