LATIDIA · Robótica

Diseño y evaluación de la planificación de tareas basada en encadenamiento LLM para robots de servicio de propósito general

arXiv: 2609.29043v1Tipo de anuncio: nuevo Resumen: las tareas de Robot de Servicio de Propósito General (GPSR), como se define en el punto de referencia RoboCup@Home, requieren que los robots interpreten diversos comandos de lenguaje natural y generen múltiples pasos

La noticia

arXiv:2609.29043v1 Announce Type: new Abstract: General Purpose Service Robot (GPSR) tasks, as defined in the RoboCup@Home benchmark, require robots to interpret diverse natural language commands and generate multi-step action sequences in real home environments. Conventional Single Prompt (SP) approaches suffer from context bloat and the "Lost in the Middle" phenomenon, leading to unreliable task planning. We propose an LLM chaining architecture that separates instruction classification and action generation into two specialized stages, reducing per-inference prompt length by approximately 45% while improving planning consistency. We evaluate our method using 100 randomly generated GPSR commands across three language models spanning local open-source and frontier cloud deployment contexts. Results show consistent planning improvements