A common issue in Human-Robot Interaction is a gap in understanding how robot designs are perceived by the user. A common issue encountered by practitioners of Machine Learning (ML) is a lack of salient data to use in training. The 'Build-A-Bot' project is developing a novel research platform implemented as a web-accessible 3D game that affords data collection of many user-provided robot designs. The designs are used to train ML models to better evaluate robot designs, predict how a design will be perceived using Convolutional Neural Networks (CNNs), and create new robot designs using Generative Adversarial Networks (GANs). This paper outlines the current and future work accomplished by an interdisciplinary undergraduate student team at the University of Denver across Computer Science, Music, Psychology, and other related STEM fields that have created Build-A-Bot.