LATIDIA · Robótica

AtomEgo: Explorando la integración de Ego-Robot para el preentrenamiento del modelo de cimentación incorporado

arXiv: 2609.21461v1Tipo de anuncio: nuevo Resumen: Los modelos de cimientos incorporados están limitados por la escala limitada y la diversidad de las demostraciones de robots, lo que motiva el uso de datos de interacción humana egocéntricos a gran escala.

La noticia

arXiv:2609.21461v1 Announce Type: new Abstract: Embodied foundation models are constrained by the limited scale and diversity of robot demonstrations, motivating the use of large-scale egocentric human interaction data. However, how to effectively incorporate such data into embodied-model pre-training remains unclear because of substantial embodiment and action-space gaps between humans and robots. We present AtomEgo, a systematic study of ego--robot co-training supported by a curated corpus of approximately 2,659 hours and a scalable data processing pipeline. Across vision--language--action and world--action model architectures, we investigate three representative paradigms: joint co-training with domain-specific action heads, progressive ego-to-robot transfer through embodiment alignment, and joint video--action modeling. We evaluate these paradigms through multi-task real-robot experiments