LATIDIA · Robótica

Un diagnóstico LLM, una interfaz de comando y control de drones basada en MAVLink y un arnés agénico utilizando el protocolo de contexto modelo

arXiv: 2601.15486v3Tipo de anuncio: reemplazar Resumen: La inteligencia artificial integrada con el comando y control de drones (IA física) ofrece una ruta hacia la autonomía a través de modelos de lenguaje grandes (LLM), pero un LLM-to-dr unificado

La noticia

arXiv:2601.15486v3 Announce Type: replace Abstract: Artificial intelligence integrated with drone command and control (physical AI) offers a route to autonomy through large language models (LLMs), yet a unified LLM-to-drone interface has been missing. We present an LLM-agnostic command-and-control interface and agentic harness joining the Model Context Protocol (MCP) to MAVLink, the near-universal drone command-and-telemetry standard: "DroneServer" gives any MCP-capable LLM command, telemetry, mission, and safety functions over ArduPilot and PX4. Its 98 tools cover 223 of 238 client-side methods of MavSDK, MAVLink's library; 61 of the 98 were exercised in software-in-the-loop. We treat the LLM as an untrusted commander: zero public ports (externally verified); every command validated server-side (tiers, confirmation