LATIDIA · Robótica

Una plataforma de simulación para la recuperación de fallas de AUV: exploración de estrategias de diagnóstico basadas en LLM

arXiv: 2609.20620v1Tipo de anuncio: nuevo Resumen: Los vehículos subacuáticos autónomos (AUV) que operan más allá de las comunicaciones confiables deben recuperarse de fallas sin intervención humana. Investigamos una arquitectura en whic

La noticia

arXiv:2609.20620v1 Announce Type: new Abstract: Autonomous underwater vehicles (AUVs) operating beyond reliable communications must recover from failures without human intervention. We investigate an architecture in which conventional deterministic layered control autonomy manages normal operations, while an invokable large language model (LLM) serves as a diagnostic and recovery planner when onboard anomaly detection identifies performance outside expected limits. Because language models are stochastic, rigorous evaluation requires ensemble testing rather than individual demonstrations. We present a closed-loop simulation architecture that couples real-time C vehicle software with a higher-level orchestration layer for physics-based fault injection, structured prompting, language-model interaction, mission file generation, validation, execution, and LLM-judge scoring. The framework, which we call SPAR