Google DeepMind’s new AI model can control a robot’s entire body
https://www.theverge.com/tech/973276/google-deepmind-gemini-robotics-2-whole-body📌 【Google DeepMind】Gemini Robotics 2 實現全身協調，從腳掌到指尖的全面控制
TL;DR：Gemini Robotics 2 讓機器人具備全身動作控制能力，從行走、蹲下到精細的手部操作。
🤖 從上半身控制演進到「全身動作」
過去的機器人模型大多僅專注於控制機器人的上半身，而 Google DeepMind 研發的 Gemini Robotics 2 實現了從腳掌到指尖（feet to fingertips）的全身動作控制。
🧩 實現更複雜的現實世界任務
透過這種全身協調能力，人型機器人現在可以執行更廣泛的動作，包含：
- 行走與蹲下
- 伸展身體
- 操控物體
在 Google 分享的影片中，可以看到 Apptronik 的 Apollo 2 機器人展現了彎腰撿起澆水壺，以及從架子上尋找並取出特定物品的動作。
🖐️ 提升手部靈活性與精細操作
除了大範圍的肢體動作，Gemini Robotics 2 也強化了靈活性，能夠控制更複雜的五指手部，這讓機器人具備執行以下任務的潛力：
- 封口夾鏈袋 (Ziploc)
- 打結垃圾袋
- 旋開燈泡
💡 視覺語言模型 Gemini Robotics ER 的同步升級
除了動作控制，Google DeepMind 也更新了負責「具身推理」（Embodied Reasoning, ER）的視覺語言模型。Gemini Robotics ER 2 能協助機器人分析環境、處理指令並執行多步驟任務。這次更新讓模型在長時間任務的完成度更高，且「能理解任務何時開始與結束」。
⚠️ 動作速度仍有進步空間
儘管具備了全身協調能力，Google DeepMind 也坦言機器人在「動作速度」方面仍有很大的進步空間。但該機構強調，這次更新是邁向完成複雜現實世界任務的重要一步。
🔗 來源
- 標題：Google DeepMind’s new AI model can control a robot’s entire body
- 作者／機構：Emma Roth @ The Verge
- 連結：https://www.theverge.com/tech/973276/google-deepmind-gemini-robotics-2-whole-body
#GoogleDeepMind #GeminiRobotics #HumanoidRobot #Robotics #AI #EmbodiedAI #MachineLearning #Apptronik #Apollo2 #ArtificialIntelligence
原始資料 The Verge AI · 收集於 2026-07-31
摘要原文
Tech AI News Google DeepMind’s new AI model can control a robot’s entire body Gemini Robotics 2 controls a humanoid robot from ‘feet to fingertips.’ Gemini Robotics 2 controls a humanoid robot from ‘feet to fingertips.’ by Emma Roth Jul 30, 2026, 5:18 PM UTC Link Share Gift A pptronik’s Apollo 2 robot takes a baseball glove off of a shelf. Image: Google Emma Roth is a news writer who covers the streaming wars, consumer tech, crypto, social media, and much more. Previously, she was a writer and editor at MUO. Google DeepMind says the latest version of its Gemini Robotics AI model can “control entire humanoid robots.” While the previous model focused on controlling a humanoid robot’s upper body, Gemini Robotics 2 now supports “whole-body motions” ranging from its feet to fingertips, according to an announcement on Thursday . The new model will allow humanoid robots to perform a wider range of actions, as it allows them to walk, crouch, stretch, and manipulate objects. Videos shared by Google show how Apptronik’s Apollo 2 robot can bend over to pick up a watering can, as well as find and take specific items off a shelf. Though Google DeepMind notes that its robots “have more to advance in movement speed,” it adds that this update “is an important step towards the skills needed to complete more complex, real-world tasks that require whole-body coordination.” Additionally, Gemini Robotics 2 supports better dexterity, as it can now control more complex, five-fingered hands. That enables robots to perform tasks like sealing a Ziploc, tying a trash bag, or unscrewing a lightbulb. Google DeepMind is updating Gemini Robotics ER (embodied reasoning) as well, a vision-language model that helps robots to analyze their surroundings, process instructions, and perform multi-step tasks. Gemini Robotics ER 2 is better at completing tasks over an extended period of time and “now understands when tasks begin and end.” Google DeepMind says this update also allows multiple robots of diff
由 tencent/hy3:free 自動生成