A new arXiv preprint describes an investigation into using human infant motor development scales as a basis for training humanoid robots. The researchers explore how robots can learn a series of motor skills defined by these scales, treating infant milestones as potential benchmarks for robot motor development.

The study's core aim is to evaluate which scales are comprehensive enough to serve as self-contained guides for developing gross motor skills in robots. This suggests a practical test of whether developmental psychology checklists can be directly translated into robotic training curricula.

As presented in the abstract, the work is framed as an investigation and evaluation, but no specific findings or conclusions are included. The announcement only outlines the research question, leaving the outcomes for the full paper.