DeepMind发了三个机器人模型：一个控全身，一个做推理，一个快速适应新身体。只公开了ER 2，感兴趣可以直接试。
Google DeepMind推出Gemini Robotics 2，包含三个模型：一个视觉-语言-动作模型用于全身人形控制，Gemini Robotics ER 2用于具身推理与任务编排，以及一个设备端VLA可在数小时内适应新机器人躯体。单一检查点驱动Apptronik Apollo 2和Franka Duo两款机器人。仅ER 2模型公开发布。
Google DeepMind Ships Three Physical AI Models For Whole Body Control, Dexterity And Multi Robot Collaboration
Google DeepMind has released Gemini Robotics 2, the intelligence layer for its next generation of robots. The release ships three models: a vision-language-action model for whole body humanoid control, Gemini Robotics ER 2 for embodied reasoning and task orchestration, and an on-device VLA that adapts to new robot bodies in hours. One checkpoint drives Apptronik Apollo 2 and a Franka Duo. Only ER 2 is publicly available. The post Google DeepMind Ships Three Physical AI Models For Whole Body Control, Dexterity And Multi Robot Collaboration appeared first on MarkTechPost .