打通大模型与机器人系统的接口，让智能体能统一控制不同硬件。
RoboNeuron: A Middle-Layer Infrastructure for Agent-Driven Orchestration in Embodied AI
- 将机器人中间件ROS2的接口转化为可调用工具，实现统一控制抽象。
- 支持在不重连系统的情况下切换后端模型或运行时配置。
- 已在仿真和真实机器人上验证，适用于多平台任务调度。
视觉-语言-动作（VLA）模型与大语言模型（LLM）智能体发展迅速，但其在物理机器人上的可靠部署常受制于智能体工具API与机器人中间件之间的接口不匹配。现有方案多依赖难以复用的临时封装，当更改VLA后端或服务栈时需大量重新集成。本文提出RoboNeuron，一个连接LLM智能体的模型上下文协议（MCP）与机器人中间件（如ROS2）的中层基础设施。RoboNeuron通过解析ROS2架构直接生成智能体可调用的工具，提供统一执行抽象，支持直接指令与模块化组合，并将后端、运行时及加速配置变更限制在稳定的推理边界内。我们在仿真与硬件上通过多平台基础控制、机械臂运动及基于VLA的抓取任务评估了RoboNeuron，结果表明其可在统一接口下实现模块化系统编排，且支持后端切换而无需系统重连。完整代码已开源：https://github.com/guanweifan/RoboNeuron。
原文摘要 · Abstract (English)
Vision-language-action (VLA) models and LLM agents have advanced rapidly, yet reliable deployment on physical robots is often hindered by an interface mismatch between agent tool APIs and robot middleware. Current implementations typically rely on ad-hoc wrappers that are difficult to reuse, and changes to the VLA backend or serving stack often necessitate extensive re-integration. We introduce RoboNeuron, a middleware layer that connects the Model Context Protocol (MCP) for LLM agents with robot middleware such as ROS2. RoboNeuron bridges these ecosystems by deriving agent-callable tools directly from ROS schemas, providing a unified execution abstraction that supports both direct commands and modular composition, and localizing backend, runtime, and acceleration-preset changes within a stable inference boundary. We evaluate RoboNeuron in simulation and on hardware through multi-platform base control, arm motion, and VLA-based grasping tasks, demonstrating that it enables modular system orchestration under a unified interface while supporting backend transitions without system rewiring. The full code implementation of this work is available at github repo: https://github.com/guanweifan/RoboNeuron
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。