LATIDIA · Robótica

DATAFARM: Planificación de tareas y movimientos alineados con la distribución para afinar los modelos de visión-lenguaje-acción

arXiv: 2609.12316v1Tipo de anuncio: nuevo Resumen: La recopilación de datos de robots de alta calidad sigue siendo un desafío fundamental para la formación de modelos de cimientos de robots. La planificación de tareas y movimientos (TAMP) ofrece una forma escalable de generar

La noticia

arXiv:2609.12316v1 Announce Type: new Abstract: Collecting high-quality robot data remains a fundamental challenge for training robot foundation models. Task and motion planning (TAMP) offers a scalable way to generate demonstrations, but our experiments show that raw TAMP trajectories provide surprisingly little benefit when used to fine-tune pretrained vision-language-action (VLA) models, despite successfully solving the target tasks. We hypothesize that this failure arises from a behavioral distribution mismatch between planner-generated trajectories and the data used to pretrain the VLA. To address this mismatch, we introduce DATAFARM: Distribution-Aligned Task And motion planning for Fine-tuning A Robot foundation Model, an approach that incorporates the pretraining distribution directly into TAMP trajectory generation. DATAFARM aligns