LATIDIA · Robótica

Adaptación de VLA con datos reales y simulados: un estudio de caso sobre ajedrez robótico

arXiv: 2611.12676v1Announce Type: new Abstract: Los modelos de visión-lenguaje-acción (VLA) están entrenados como modelos de base de propósito general para el aprendizaje de robots y requieren un ajuste fino para cada tarea posterior y robot. Esta ra

La noticia

arXiv:2611.12676v1 Announce Type: new Abstract: Vision-language-action (VLA) models are trained as general-purpose foundation models for robot learning, and require fine-tuning for each downstream task and robot. This raises practical questions such as how much data and training updates are needed, how checkpoints should be selected, and whether simulation can be leveraged to alleviate the cost of real data collection. We study these questions on a task that requires both precise manipulation and spatial understanding of the scene. In this task, an SO-101 arm moves a chess king between two squares that are given only by their names, such as e4 and a5. We fine-tune $\pi_{0.5}$ with various dataset sizes and