LATIDIA · Robótica

Asistencia humana bajo demanda para la continuación de tareas bajo fallas de acción física en la planificación basada en LLM

arXiv: 2603.28156v2Tipo de anuncio: reemplazar Resumen: Si bien la planificación de acciones del robot basada en modelos de lenguaje grandes (LLM) ha avanzado notablemente, continuar una tarea después de una falla de acción física durante la ejecución sigue siendo un

La noticia

arXiv:2603.28156v2 Announce Type: replace Abstract: While robot action planning based on large language models (LLMs) has advanced remarkably, continuing a task after a physical action failure during execution remains a key challenge. For example, after failing to grasp an object, the robot may not notice that it has fallen off the table and keep trying to detect and pick it up, stalling the task. Existing approaches either rely on closed-loop autonomous re-planning, which fails when errors exceed the robot's capabilities, or on human intervention without updating the LLM's plan, hindering subsequent planning. We present a system for LLM-based robot action planning that integrates remote human intervention with feedback-based replanning. When