Google DeepMind 推出 Gemini Robotics On-Device：為本地機器人設備帶來高效能、具備通用靈巧性與快速適應能力的 AI 模型
Original: Gemini Robotics On-Device brings AI to local robotic devices
Google DeepMind has released the "Gemini Robotics On-Device" model, a significant breakthrough that brings advanced Gemini AI capabilities…
Google DeepMind 宣布推出「Gemini Robotics On-Device」模型。這是一款專為本地（裝置端）運作設計的高效機器人 AI 模型，旨在賦予機器人通用的靈巧操作能力（general-purpose dexterity），並能針對新任務進行快速適應（fast task adaptation），大幅提升邊緣端機器人的自主與反應能力。
Google DeepMind has released the "Gemini Robotics On-Device" model, a significant breakthrough that brings advanced Gemini AI capabilities directly to local robotic hardware. The model's defining characteristics are its "efficiency" and ability to run "on-device," meaning robots do not need to rely entirely on cloud computing to perform real-time reasoning and decision-making locally.
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Google DeepMind Blog →Summaries are AI-generated; the original article is authoritative.