Over four million older adults living in long-term care (LTC) communities experience loneliness, adversely impacting their health. Increased contact with friends and family is an evidence-based intervention to reduce loneliness, but in-person visits are not always possible. Augmented Reality (AR)-based telepresence activities can offer viable alternatives with increased immersion and presence compared to video calls. However, its feasibility as an interaction technology for older adults is not known. In this paper, we detail the design of two dyadic collaborative AR activities that accommodate diminished physical and cognitive abilities of older adults. The findings include a general design framework based on an iterative participatory design focusing on preferred activities, modes of interaction, and overall AR experience of eight older adults, two family members, and five LTC staff. Results demonstrate the potential of collaborative AR as an effective means of interaction for older adults with their family, if designed to cater to their needs.

Adaptive human–computer systems require the recognition of human behavior states to provide real-time feedback to scaffold skill learning. These systems are being researched extensively for intervention and training in individuals with autism spectrum disorder (ASD). Autistic individuals are prone to social communication and behavioral differences that contribute to their high rate of unemployment. Teamwork training, which is beneficial for all people, can be a pivotal step in securing employment for these individuals. To broaden the reach of the training, virtual reality is a good option. However, adaptive virtual reality systems require real-time detection of behavior. Manual labeling of data is time-consuming and resource-intensive, making automated data annotation essential. In this paper, we propose a semi-supervised machine learning method to supplement manual data labeling of multimodal data in a collaborative virtual environment (CVE) used to train teamwork skills. With as little as 2.5% of the data manually labeled, the proposed semi-supervised learning model predicted labels for the remaining unlabeled data with an average accuracy of 81.3%, validating the use of semi-supervised learning to predict human behavior.

Background and Objectives: Augmented reality (AR) telepresence is a novel interactive communication modality that maps a user’s 3D photorealistic avatar to another user’s physical environment. However, AR’s application with older adult populations is understudied. As such, we examined young and older adults’ perceptions of utilizing this modality for social communication. Additionally, we tested the participants’ ability to recognize 6 common emotions displayed by 3D photorealistic avatars compared to video clips of real people, examining whether age differences existed in communication perceptions and emotion recognition accuracy. Research Design and Methods: To assess participants’ perceptions, older (n = 31) and younger (n = 31) adults interacted with a volunteer’s 3D photorealistic avatar using a structured conversational activity through a head-mounted display (HMD). Participants rated the quality of the HMD-AR communication based on physical and human realism, comfort while talking to the avatar, and the degree of social presence offered by the HMD-AR. Participants then identified 6 basic emotions exhibited by (1) video clips of a real person and (2) an animation of their 3D photorealistic avatars via an HMD. Each participant viewed a total of 36 video and avatar stimuli. Subgroup analyses were conducted by age group. Results: Participants reported a positive communication experience with the 3D photorealistic avatar, with older adults rating the quality higher. Ratings were generally lowest for how life-like the model appeared (68% younger adults; 61% older adults). Most younger participants (93%) were able to accurately identify nonverbal emotions displayed by the avatar; older adults had less overall accuracy (80%). Discussion and Implications: Participants, including older adults, were enthusiastic regarding AR telepresence for interpersonal communication. Most were able to accurately identify emotions displayed by the 3D photorealistic avatars, although younger adults outperformed older adults. Further technology development will likely enhance the quality of AR communication for everyday use.