TY - GEN
T1 - A Novel Online Robot Design Research Platform to Determine Robot Mind Perception
AU - Pittman, Daniel E.
AU - Haring, Kerstin S.
AU - Kim, Pilyoung
AU - Dossett, Benjamin
AU - Ehman, Gillian
AU - Gutierrez-Gutierrez, Elizabeth
AU - Patil, Sneha
AU - Sanchez, Ashley
N1 - Funding Information:
We especially grateful to our students Marley Bogran, Sergio Gonzales, Esabella Irby, Henry Jaffray, Nicholas Ninos, Max Peterson, Raghav Thapa, Ulises A. Heredia Trinidad, and Ralph Vrooman for their work as listed on our website at https://www.dubuildabot.com. Without their significant contributions, this project would not be as advanced as it is today. This research has been sponsored by the University of Denver under the Professional Research Opportunities for Faculty (PROF) opportunity to Drs. Haring, Kim, and Pittman under grant # 142101-84994 and by the University of Denver under the Faculty Research Funds (FRF) to Drs. Haring and Pittman under grant # 142101-84694.
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
KW - fNIRS
KW - machine learning
KW - robot design
UR - http://www.scopus.com/inward/record.url?scp=85140752004&partnerID=8YFLogxK
U2 - 10.1109/HRI53351.2022.9889539
DO - 10.1109/HRI53351.2022.9889539
M3 - Conference contribution
AN - SCOPUS:85140752004
T3 - ACM/IEEE International Conference on Human-Robot Interaction
SP - 986
EP - 990
BT - HRI 2022 - Proceedings of the 2022 ACM/IEEE International Conference on Human-Robot Interaction
PB - IEEE Computer Society
T2 - 17th Annual ACM/IEEE International Conference on Human-Robot Interaction, HRI 2022
Y2 - 7 March 2022 through 10 March 2022
ER -