Infants improve their motor skills, such as sitting, crawling, and standing, through practicing these skills in everyday life. However, limited tools for measuring infants’ movements in the home are a barrier to understanding the factors that give rise to individual differences in opportunities for movement as well as individual differences in caregiving practices that can predict motor learning outcomes in infancy. This project uses new wearable sensor technologies combined with Artificial Intelligence to record infants’ behavior across a week-long period to understand how the patterns of infants’ movements unfold over time. Results of this research advance understanding of motor development and provide useful information for clinicians to help promote healthy motor development in infancy. This project aims to collect data from families across the United States by mailing wearable sensors for infants to wear over the course of a week. In contrast to current methods that rely on labor-intensive manual coding of infant movement data, this project leverages Artificial Intelligence to (1) measure the amount and types of movement that 7-month old infants engage in at home during a typical week, (2) examine caregiving practices that give rise to individual differences in opportunities for movement, and (3) predict individual differences in motor development outcomes, including sitting and standing proficiency, at 11 months of age. Collecting and sharing a large longitudinal da