用一句命令自动发现并控制新硬件，省去编写驱动的繁琐工作。
Octopus Protocol: One-Shot Hardware Discovery and Control for AI Agents via Infrastructure-as-Prompts
- 通过五阶段流程，用语言模型自动生成硬件控制工具
- 10-15分钟内完成硬件接入，生成最多30个可用工具
- 适合想快速部署AI机器人系统的研发人员
当前智能体机器人系统依赖已存在的硬件驱动或SDK，而开发这些接口是主要工程成本。本文提出Octopus Protocol，仅需操作系统访问权限和语言模型API密钥，一个编码智能体即可执行探测、识别、接口生成、服务部署等五阶段流程，自动发现设备、推断其能力，并生成带类型定义的模型上下文协议（MCP）服务器，以HTTP接口实时暴露。一个持久守护进程持续监控系统，修复错误代码，并通过自动生成的摄像头工具感知物理状态。核心设计是：协议即提示词，智能体即运行时。在PC/WSL、Apple Silicon macOS、Raspberry Pi 4三类异构平台及带USB摄像头反馈的商用6自由度机械臂上验证，仅需一条命令即可在10-15分钟内完成硬件接入，最多生成30个MCP工具，支持无须人工编写的闭环视觉-运动控制。
原文摘要 · Abstract (English)
Recent agentic-robotics systems, from Code-asPolicies to modern vision-language-action (VLA) foundation models, presuppose that drivers, SDKs, or ROS-style primitives for the target hardware already exist. Writing those primitives is the dominant engineering cost of bringing up new hardware for agent control. We present Octopus Protocol, a system that collapses that cost to a single shell command. Given only raw OS access and a language-model API key, a coding agent executes a five-stage pipeline--PROBE, IDENTIFY, INTERFACE, SERVE, DEPLOY--to discover connected devices, infer their capabilities, generate a Model Context Protocol (MCP) server with typed tools, and deploy it as a live HTTP endpoint. A persistent daemon then monitors the system, heals broken code, and perceives physical state through the camera tools it generated for itself. Two architectural principles make this work: protocols are prompts, not code, and the coding agent is the runtime. We validate the system on three heterogeneous platforms (PC/WSL, Apple Silicon macOS, Raspberry Pi 4) and on a commercial 6-DOF robotic arm with USB camera feedback. One command onboards the hardware in ~10-15 minutes and exposes up to 30 MCP tools; an MCP-compliant client then performs closed-loop visual-motor control through tools no human wrote.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。