LATIDIA · Robótica

ROMA: Sistema LLM para la percepción activa multisensorial centrada en objetos del mundo real

arXiv: 2610.06955v1Tipo de anuncio: nuevo Resumen: Los humanos entienden inherentemente el mundo físico a través de un proceso activo. Cuando la evidencia sensorial es insuficiente para inferir propiedades físicas, naturalmente interactuamos con

La noticia

arXiv:2610.06955v1 Announce Type: new Abstract: Humans inherently understand the physical world through an active process. When sensory evidence is insufficient to infer physical properties, we naturally interact with the environment by deciding what information is missing, how to acquire it, and when sufficient evidence has been obtained. In stark contrast, existing multi-sensory robot systems mainly integrate sensory inputs rather than actively acquiring missing evidence through interactions. In this work, we introduce ROMA, an LLM-based system for Real-World Object-Centric Multi-Sensory Active Perception. ROMA integrates vision, audio, tactile, and force sensing into a reasoning-interaction-feedback loop. The model identifies missing evidence and determines the target objects, interactions, and modalities, while a physical interface