Gemini Robotics ER 2：以视频理解、任务编排和多机器人协作驱动机器人技术
英文标题：Gemini Robotics ER 2: powering robotics with video understanding, task orchestration, and multi-robot collaboration
Google DeepMind 发布 Gemini Robotics ER 2，这是一款面向机器人的高阶“具身推理”模型，可支持人机对话、物理世界理解、多步骤任务规划及工具调用。该模型能够持续分析视频流，跟踪任务进度、在出错时调整，并在执行动作的同时规划下一步。相较 Gemini Robotics ER 1.6，新版本新增多机器人协作能力，使多台机器人可在共享空间中完成单个机器人难以独立完成的复杂工作流。开发者现可通过 Gemini API、Google AI Studio 使用该模型，并可在 Gemini Enterprise Agent Platform 的私有预览中体验。
9.8 KB
中文
要让机器人在人类日常环境中提供协助，仅具备准确的空间推理能力还不够。机器人还必须能够快速思考，使其决策时机和推理速度与真实物理世界的实时节奏保持一致。
因此，我们今天发布 Gemini Robotics ER 2，这是我们能力最强的机器人“具身推理”模型。可以将 Gemini Robotics ER 2 视为机器人的高阶大脑：它让机器人能够与人类交谈、理解物理世界并规划多步骤任务，随后将运动执行交给任意低层级的视觉-语言-动作（VLA）模型。Gemini Robotics ER 2 还可以原生调用 Google Search 等工具来查找信息，也可以调用任何其他由用户定义的函数。Gemini Robotics ER 2 的设计使机器人能够在执行动作的同时，“思考”接下来该做什么。
相较于 Gemini Robotics ER 1.6，Gemini Robotics ER 2 实现了重大升级。通过观看连续视频流，机器人如今可以跟踪自身任务进展、在出现问题时进行调整，并准确判断何时进入下一步。我们还引入了多机器人协作能力，使机器人能够在共享空间中共同工作，完成单台机器人无法独自完成的复杂工作流。
Gemini Robotics ER 2 现已通过 Gemini API、Google AI Studio 向开发者公开提供，并在 Gemini Enterprise Agent Platform 中以私有预览形式提供。为帮助开发者快速上手，我们分享了有关如何配置模型并通过提示词驱动更实用物理 AI 任务的示例。
推进物理 Agent 能力
物理世界中的大多数任务都很复杂，需要多个步骤才能完成。Gemini Robotics ER 2 是一个物理 Agent，能够为机器人编排任务步骤，使其具备自我纠错能力，并可泛化到更多新颖场景。为构建 Agent 设置，开发者可以将低层控制接口——例如视觉-语言-动作（VLA）模型或导航 API——声明为工具，并将多模态视频、音频或文本直接流式传输至模型。
Gemini Robotics ER 2 改进了这一工具编排工作流。我们可以在仿真环境中使用机器人、通过真实世界机器人控制，甚至将其与远程操控机器人的人类协同配合，以评估其性能。
English / 原文
For robots to assist humans in everyday environments, accurate spatial reasoning is not enough. Robots must also think fast, timing their decisions and reasoning with the real-time speed of the physical world.
That’s why today we’re launching Gemini Robotics ER 2, our most capable “embodied reasoning” model for robotics. Think of Gemini Robotics ER 2 as a high-level brain for robots. It allows robots to chat with humans, understand the physical world, and plan multi-step tasks. It then hands off motor execution to any given lower level vision-language-action (VLA) model. Gemini Robotics ER 2 can also natively call tools like Google Search to find information, or any other user-defined function. The design of Gemini Robotics ER 2 allows the robot to “think” about what comes next while simultaneously performing its actions.
Gemini Robotics ER 2 represents a significant upgrade over Gemini Robotics ER 1.6. By watching continuous video feeds, robots can now track their own progress, adapt if something goes wrong, and know exactly when to move on to the next step. We are also introducing multi-robot collaboration, enabling robots to work together in shared spaces and complete complex workflows a single robot could not do alone.
Gemini Robotics ER 2 is now publicly available to developers via the Gemini API, Google AI Studio, and in private preview on Gemini Enterprise Agent Platform. To help you get started, we’re sharing examples of how to configure the model and prompt it to power more useful physical AI tasks.
Advancing physical agentic capabilities
Most tasks in the physical world are complex and require multiple steps to complete. Gemini Robotics ER 2 is a physical agent, orchestrating steps for the robot and enabling it to self-correct, and generalize to more novel situations. To build an agentic setup, developers can declare low-level control interfaces — like Vision-Language-Action (VLA) models or navigation APIs — as tools, and stream multimodal video, audio, or text directly into the model.
Gemini Robotics ER 2 improves this tool orchestration workflow. We can evaluate its performance with robots in simulation, using real-world robot control, and even pair it with a human controlling the robot remotely.