System design of group communication activator

Abstract

Our community is facing serious Aging Society especially in Japan. We have investigated in one of daycare centers which are facilities for elderly care. As the result, we realized that communication is needed for its own sake in these facilities and active communication can cure even depression and dementia. Therefore we propose to cope with these problems using a robot as a communication activator in order to improve group communication. We define group communication as one of types of communication which is formed by several persons. This time, we focus on a recreation game named "Nandoku. " Nandoku is a quiz which can be described as group communication with a master of ceremony (MC). The system always selects its behavior and target (a participant in the game) to maximize "communication activeness. " Communication activeness is defined as amount of several panelists'(ordinary three: A, B, C) participation, which are calculated with panelists' face direction using camera information. For instance, if participant A is not fully participating by not making eye contact, the system is expected to select one of the behaviors such as "Can you answer, Mr.A?" to encourage A to participate in the game. We experimented with the system in a daycare center. As the result, obvious increase in participation was observed. That offers evidence that the robot can serve a practical role in improving the group communication as a communication activator especially for entertainment use.

Application Scenarios for Artificial Intelligence in Nursing Care: Rapid Review (Preprint)

“…People with dementia or cognitive impairment were included in 3 studies [36,42,45]. Home care clients or community-dwelling elderly were included in 6 studies [46][47][48][49][50][51]313], 3 studies specifically focused on nurses or nursing students [34,52,53], and 1 study targeted elderly people at a daycare facility [54]. The more or less detailed reporting of heterogeneous study designs included experimental designs, field experiments [54], real-life use-cases [55], case studies with a single subject design [36], cross-sectional and longitudinal observational designs as well as comparative designs, and an economic evaluation nested within a cluster-randomized controlled trial [18,45], and different mixed methods designs (such as the studies by Amato et al [35], Ala-Kitula et al [46], and Alwan et al [47]).…”

“…For studies including robotic systems, Mervin et al [45] found marginally greater values in terms of incremental cost per Cohen-Mansfield Agitation Inventory Short Form point averted from a provider's perspective for a plush-toy alternative than an emotional robot seal, but deemed the robot seal a cost-effective psychosocial treatment option for reducing agitation in people with dementia in long-term care as well, as costs are much lower than those estimated for psychosocial group activities and sensory interventions. Matsuyama et al [54] introduced a communication robot to activate and improve group communication and observed an increase in participation in terms of the frequency of smiles and answers in response to the robot system. Carros et al [41] explored, among other outcomes, stakeholders' attitudes, social and organizational practices, and expectations of the Pepper robot in individual and group-based performances and revealed the potential for humanoid robots working in nursing homes, as well as the necessity of a person in control of the robot acting as a moderator.…”