ROSBag MCP 服务器：利用 LLM 分析机器人数据以支持智能体具身 AI 应用
ROSBag MCP Server: Analyzing Robot Data with LLMs for Agentic Embodied AI Applications
AI总结：
本文提出一个 ROSBag MCP 服务器，使 LLM/VLM 能通过自然语言分析 ROS/ROS 2 机器人数据，并通过基准测试揭示不同模型在工具调用能力上的显著差异。
摘要：
智能体 AI 系统与物理或具身 AI 系统一直是人工智能和机器人学前沿的两个关键研究方向，而模型上下文协议（MCP）正日益成为智能体应用的关键组成部分和使能技术。然而，在这些研究方向交叉领域，即智能体具身 AI，相关文献仍然十分匮乏。本文介绍了一个用于分析 ROS 和 ROS 2 bag 的 MCP 服务器，能够通过 LLM 和 VLM 以自然语言对机器人数据进行分析、可视化和处理。我们描述了基于机器人领域知识构建的具体工具，初始版本聚焦于移动机器人，并原生支持轨迹、激光扫描数据、变换或时间序列数据的分析。此外，该服务器还提供了标准 ROS 2 CLI 工具（"ros2 bag list" 或 "ros2 bag info"）的接口，以及按主题子集过滤 bag 或按时间裁剪 bag 的能力。与 MCP 服务器配套，我们提供了一个轻量级 UI，用于在不同 LLM 上对工具进行基准测试，涵盖专有模型（Anthropic、OpenAI）和开源模型（通过 Groq）。我们的实验结果包括对八种不同最先进 LLM/VLM 模型的工具调用能力分析，涵盖专有和开源、大型和小型模型。实验表明，各模型的工具调用能力存在巨大差距，其中 Kimi K2 和 Claude Sonnet 4 表现出明显优越的性能。我们还得出结论，影响成功率的因素有很多，包括工具描述模式、参数数量以及模型可用的工具数量。代码以宽松许可证发布在 https://github.com/binabik-ai/mcp-rosbags。
英文摘要：
Agentic AI systems and Physical or Embodied AI systems have been two key research verticals at the forefront of Artificial Intelligence and Robotics, with Model Context Protocol (MCP) increasingly becoming a key component and enabler of agentic applications. However, the literature at the intersection of these verticals, i.e., Agentic Embodied AI, remains scarce. This paper introduces an MCP server for analyzing ROS and ROS 2 bags, allowing for analyzing, visualizing and processing robot data with natural language through LLMs and VLMs. We describe specific tooling built with robotics domain knowledge, with our initial release focused on mobile robotics and supporting natively the analysis of trajectories, laser scan data, transforms, or time series data. This is in addition to providing an interface to standard ROS 2 CLI tools ("ros2 bag list" or "ros2 bag info"), as well as the ability to filter bags with a subset of topics or trimmed in time. Coupled with the MCP server, we provide a lightweight UI that allows the benchmarking of the tooling with different LLMs, both proprietary (Anthropic, OpenAI) and open-source (through Groq). Our experimental results include the analysis of tool calling capabilities of eight different state-of-the-art LLM/VLM models, both proprietary and open-source, large and small. Our experiments indicate that there is a large divide in tool calling capabilities, with Kimi K2 and Claude Sonnet 4 demonstrating clearly superior performance. We also conclude that there are multiple factors affecting the success rates, from the tool description schema to the number of arguments, as well as the number of tools available to the models. The code is available with a permissive license at https://github.com/binabik-ai/mcp-rosbags.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
