Search for: All records

Deploying socially assistive robots (SARs) at home, such as robotic companion pets, can be useful for tracking behavioral and health-related changes in humans during lifestyle fluctuations over time, like those experienced during CoVID-19. However, a fundamental problem required when deploying autonomous agents such as SARs in people’s everyday living spaces is understanding how users interact with those robots when not observed by researchers. One way to address that is to utilize novel modeling methods based on the robot’s sensor data, combined with newer types of interaction evaluation such as ecological momentary assessment (EMA), to recognize behavior modalities. This paper presents such a study of human-specific behavior classification based on data collected through EMA and sensors attached onboard a SAR, which was deployed in user homes. Classification was conducted using generative replay models, which attempt to use encoding/decoding methods to emulate how human dreaming is thought to create perturbations of the same experience in order to learn more efficiently from less data. Both multi-class and binary classification were explored for comparison, using several types of generative replay (variational autoencoders, generative adversarial networks, semi-supervised GANs). The highest-performing binary model showed approximately 79% accuracy (AUC 0.83), though multi-class classification across all modalities only attained 33% accuracy (AUC 0.62, F1 0.25), despite various attempts to improve it. The paper here highlights the strengths and weaknesses of using generative replay for modeling during human–robot interaction in the real world and also suggests a number of research paths for future improvement. 

This paper presents an intensive case study of 10 participants in the US and South Korea interacting with a robotic companion pet in their own homes over the course of several weeks. Participants were tracked every second of every day during that period of time. The fundamental goal was to determine whether there were significant differences in the types of interactions that occurred across those cultural settings, and how those differences affected modeling of the human-robot interactions. We collected a mix of quantitative and qualitative data through sensors onboard the robot, ecological momentary assessment (EMA), and participant interviews. Results showed that there were significant differences in how participants in Korea interacted with the robotic pet relative to participants in the US, which impacted machine learning and deep learning models of the interactions. Moreover, those differences were connected to differences in participant perceptions of the robot based on the qualitative interviews. The work here suggests that it may be necessary to develop culturally-specific models and/or sensor suites for human-robot interaction (HRI) in the future, and that simply adapting the same robot's behavior through cultural homophily may be insufficient.