DU want to Build a Bot

A common issue encountered by practitioners of Artificial Intelligence (AI) and Machine Learning (ML) is a lack of salient data to use in training. A common issue in Human-Robot Interaction is a gap in understanding how robot designs are perceived by the user. The ” D U Want to Build A Bot” (Build-A-Bot) project is developing a novel robotic design research platform implemented as a web-accessible 3D game that will allow us to quickly gather many user-provided robot design examples. These examples are then used to train ML models to better evaluate robot designs, predict how a design will be perceived, and create new robot designs. It is anticipated that we use Convolutional Neural Networks (CNNs) to predict how an existing robotic design will be perceived, and Generative Adversarial Networks (GANs) to create new robot designs based on the user provided examples. Build-A-Bot is maintained by an interdisciplinary student team at the University of Denver consisting of 14 undergraduate students across Computer Science, Music, Emergent Digital Practices, Psychology, and other related STEM fields.
 

In the last few years, robots have been increasingly surrounding us. This has come from something as simple as our phones to fully automated cars. Said robots provide a sense of knowledge to our world, but in reality, how do we as humans perceive these robots? Do we view them with a kind eye, or see them as the inevitable evil that could one day take over? By being able to learn how we as humans perceive said emotions, we are able to create more robots that depict a certain emotion. Imagine you are at the store, there is a type of emotion that you feel, imagine now that being transplanted into a robot.