LATIDIA · Robótica

ADM-Planner: LLM-Guided Long-Horizon Planning for Mobile Manipulators with Attention-Enhanced Dynamic Memory

arXiv: 2609.29212v1Announce Type: new Resumen: Los modelos de lenguaje grandes pueden descomponer los objetivos de manipulación móvil en secuencias de acción largas, pero los planes resultantes siguen siendo confiables solo mientras su contexto mundial esté actualizado.

La noticia

arXiv:2609.29212v1 Announce Type: new Abstract: Large language models can decompose mobile-manipulation goals into long action sequences, but the resulting plans remain reliable only while their world context is current. A fixed scene description becomes stale when objects are discovered, moved, or completed while retaining every observation instead produces a growing history with redundant and conflicting state. To resolve this tension, we present an LLM-guided planning framework ADM-Planner with attention-enhanced dynamic memory (ADM). Persistent workspace knowledge is separated from object-centric state, asynchronous observations and action outcomes update that state, and a bounded retriever exposes only the entries that can affect the next decision. The LLM replans when an update invalidates the