Search for: All records

Socially assistive robots can be used as therapeutic technologies to address depression symptoms. Through three sets of workshops with individuals living with depression and clinicians, we developed design guidelines for a personalized therapeutic robot for adults living with depression. Building on the design of Therabot™, workshop participants discussed various aspects of the robot’s design, sensors, behaviors, and a robot connected mobile phone app. Similarities among participants and workshops included a preference for a soft textured exterior and natural colors and sounds. There were also differences – clinicians wanted the robot to be able to call for aid, while participants with depression differed in their degree of comfort in sharing data collected by the robot with clinicians. 

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. 

Triangulation by walking is a method that has been used to measure perceived distance, where observers walk a triangular path. This method has been used at action space distances of approximately 1.5 to 30 meters. In this work, a conceptual replication of these triangulation by walking methods are discussed and evaluated for use in measuring the perceived distance of an object seen through a window set into a wall. The motivation for this work is to use triangulation by walking to study how perceived distance operates when augmented reality (AR) is used to visualize objects located behind opaque surfaces, in an AR application termed “x-ray vision.” This paper reports on experiences replicating an implementation of triangulation by walking as reported by Fukusima, Da Silva, and Loomis (1997). Their method was conceptually replicated in both outdoor and indoor settings, and the method was further extended to measure perceived distances of objects seen through a wall. These extensions are discussed in some detail, focusing on the modifications to the triangulation by walking method as well as the ramifications of these changes. Problems arising from using triangular geometry in calculations of perceived target locations are also introduced, and an alternate method is proposed that works to diminish the problematic effects. 

Accurate and usable x-ray vision is a significant goal in augmented reality (AR) development. X-ray vision, or the ability to comprehend location and object information when it is presented through an opaque barrier, needs to successfully convey scene information to be a viable use case for AR. Further, this investigation should be performed in an ecologically valid context in order to best test x-ray vision. This research seeks to experimentally evaluate the perceived object location of stimuli presented with x-ray vision, as compared to real-world perceived object location through a window, at action space distances of 1.5 to 15 meters.