Affecting roughly 2 in 1000 infants in the USA, Cerebral Palsy (CP) is the most common cause of motor impairment in children. CP has no cure, but motor therapy is an effective tool for providing rehabilitation. Although therapy is most effective before the age of 2, early CP detection is difficult and labor-intensive, making the processes inaccessible in low-resource settings. To remedy this inaccessibility, we seek to create an accessible technology-based tool to make detecting neuromotor impairment in infants less easier. Studies have shown promising results in quantifying infant impairment by observing changes in the Center of Pressure (COP), as they lie supine. Although a useful metric, the force plates necessary to capture COP are often not readily accessible in low-resource settings due to factors such as high price and a lack of portability. In response, my goal is to make COP easier to obtain by predicting supine infant COP through human pose data gathered with cameras. I seek to derive a generalized physics-based model of the infant’s dynamics that calculates COP based on insights gained from examining how infant movement interacts with changes in COP. I will then use this physics-based model to improve the ability to use machine learning to derive COP from only camera information. As a result, I will create a novel framework involving the use of physics-based modeling and data-driven modeling to predict COP.