Abstract
The use of artificial intelligence (AI) for drone control can have a transformative impact on drone capabilities, especially when real world information can be integrated with drone sensing, command, and control, part of a growing field of physical AI. Large language models (LLMs) can be advantageous if trained at scale on general knowledge, but especially and in particular when the training data includes information such as detailed map geography topology of the entire planet, as well as the ability to access real time situational data such as weather. However, challenges remain in the interface between drones and LLMs in general, with each application requiring a tedious, labor intensive effort to connect the LLM trained knowledge to drone command and control. Here, we solve that problem, using an interface strategy that is LLM agnostic and drone agnostic, providing the first universal, versatile, comprehensive and easy to use drone control interface. We do this using the new model context protocol (MCP) standard, an open standard that provides a universal way for AI systems to access external data, tools, and services. We develop and deploy a cloud based Linux machine hosting an MCP server that supports the Mavlink protocol, an ubiquitous drone control language used almost universally by millions of drones including Ardupilot and PX4 this http URL demonstrate flight control of a real unmanned aerial vehicle. In further testing, we demonstrate extensive flight planning and control capability in a simulated drone, integrated with a Google Maps MCP server for up to date, real time navigation information. This demonstrates a universal approach to integration of LLMs with drone command and control, a paradigm that leverages and exploits virtually all of modern AI industry with drone technology in an easy to use interface that translates natural language to drone control.
Abstract (translated)
使用人工智能（AI）进行无人机控制可以在很大程度上改变无人机的能力，特别是在将现实世界的信息与无人机的感知、指令和控制系统相结合时，这已成为物理AI这一新兴领域的一部分。大规模语言模型（LLMs），如果经过全面的知识训练，并且训练数据包括整个地球的地图地理学拓扑信息以及实时环境数据如天气情况，会特别有用。 然而，在无人机和LLM之间接口方面仍然存在挑战，每个应用都需要费时、劳力密集的过程来将训练好的知识连接到无人机的指令与控制。在这里，我们解决了这个问题，采用了一种对LLM和无人机都无特定依赖的界面策略，提供了一个通用的、灵活的、全面且易于使用的无人机控制系统接口。为此，我们使用了新的模型上下文协议（Model Context Protocol, MCP）标准，这是一个开放的标准，为AI系统提供了访问外部数据、工具和服务的统一方式。 我们在云端部署了一台基于Linux的操作服务器，该服务器支持Mavlink协议——一种几乎被全球数百万无人机使用的通用无人机控制语言。我们通过此接口展示了一个真实无人驾驶飞行器的飞行控制演示。在进一步测试中，我们还在模拟无人机上展示了广泛的飞行规划和控制系统能力，并与Google Maps MCP服务器集成以获得最新的实时导航信息。 这证明了将LLMs与无人机指令和控制系统进行集成的一种通用方法，这种方法利用并挖掘现代AI产业几乎所有的资源来支持无人机技术，同时提供了一种易于使用的界面，能够将自然语言转换为无人机控制。
URL
https://arxiv.org/abs/2601.15486
