Detecting cultural identity via robotic sensor data to understand differences during human-robot interaction

AbstractSocially-assistive robots (SARs) have significant potential to help manage chronic diseases (e.g. dementia, depression, diabetes) in spaces where people live, averse to clinic-based care. However, the challenge is designing SARs so that they perform appropriate interactions with people who have different characteristics, such as age, gender, and cultural identity. Those characteristics impact how human behaviors are performed as well as user expectations of robot responses. Although cross-cultural studies with robots have been conducted to understand differing population characteristics, they have mainly focused on statistical comparisons of groups. In this study, we utilize deep learning (DL) and machine learning (ML) models to evaluate whether cultural differences show up in robotic sensor data during human-robot interaction (HRI). To do so, a SAR was distributed to user's homes for three weeks in the US and Korea (25 participants), while collecting data on the human activity and the surrounding environment through on-board sensor devices. DL models based on that data were able to predict the user’s cultural identity with roughly 95% accuracy. Such findings have potential implications for the design and development of culturally-adaptive SARs to provide services across diverse cultural locales and multi-cultural environments where users’ cultural background cannot be assumed a priori.KEYWORDS: Human-robot interactiondeep learningcross-cultural roboticsadaptive robot designhuman activity recognition Disclosure statementNo potential conflict of interest was reported by the author(s).Additional informationFundingThis work was supported by separate funding mechanisms in South Korea and the United States: KOR – Hanyang University Research Fund [grant number HY-2020]; USA – National Science Foundation [grant number IIS-1900683].Notes on contributorsJinjae LeeJinjae Lee is currently a Master’s student in Data Science at the Department of Intelligence Computing at Hanyang University. He is interested in the application of machine learning and human-robot interaction to healthcare problems.Casey C. BennettDr. Casey C. Bennett is an Associate Professor in the Department of Intelligence Computing at Hanyang University in Seoul, Korea. He specializes in artificial intelligence and robotics in healthcare, including the use of data science and machine learning to create better human-robot interaction. He completed his Ph.D. at Indiana University in the US.Cedomir StanojevicDr. Cedomir Stanojevic is an Assistant Professor in the Department of Parks, Recreation & Tourism Management at Clemson University’s College of Behavioral, Social and Health Sciences, SC, U.S.A. He specializes in recreational therapy and interventions related to leisure and improved quality of life, focusing on socially assistive robotics and ecological momentary assessment to improve various populations’ health outcomes. He completed his Ph.D. at Indiana University in the US.Seongcheol KimSeongcheol Kim received his Master’s degree in Data Science at the Department of Intelligence Computing at Hanyang University. He is interested in the deep learning, natural language processing, and human-robot interaction to healthcare problems.Zachary HenkelZachary Henkel is a PhD student in the Department of Computer Science and Engineering at Mississippi State University. He is interested in human-robot interaction and related engineering related problems in social robotics.Kenna BaugusKenna Baugus is a graduate student in the Department of Computer Science and Engineering at Mississippi State University. She is interested in human-robot interaction and related engineering related problems in social robotics.Jennifer A. PiattDr. Jennifer A. Piatt is an Associate Professor in the Department of Health and Wellness Design at Indiana University- Bloomington, School of Public Health. She specializes in recreational therapy and interventions related to community-based rehabilitation. Focusing on Socially Assistive Robotics as a therapeutic intervention, sge aims to understand how emerging technologies can address clinical outcomes.Cindy BethelDr. Cindy Bethel is the Billie J. Ball Endowed Professor of Engineering in the Department of Computer Science and Engineering at Mississippi State University. She is the director of the Social, Therapeutic, and Robotic Systems (STaRS) Lab, focused human-robot interaction and therapeutic robotic pets.Selma SabanovicDr. Selma Sabanovic is a Professor of Informatics and Cognitive Science at Indiana University Bloomington, where she directs the R-House Human-Robot Interaction Lab. Her work combines the social studies of computing with research on human-robot interaction and social robotics. She explores the design, use, and consequences of socially interactive and assistive robots in diverse social and cultural contexts, including various countries, homes, schools, and healthcare environments. She completed her PhD in Science and Technology Studies at Rensselaer Polytechnic Institute.