What Do Older Adults Want? Exploring Experiences in Multi-Session Personalized Conversations with Companion Robots

Abstract

With advancements in Large Language Models, conversational companion robots are increasingly recognized for their potential in supporting and caring for older adults. This study examines older adults' experiences and functional preferences for a conversational robot designed to enable personalized interactions across multiple sessions. The robot engages users in open-ended conversations by recalling previous dialogues, integrating personal information, and facilitating memory-stimulating conversations. Thirty healthy older adults participated in three one-hour interaction sessions with the robot, followed by post-interaction surveys. Results showed that participants found the interactions engaging and meaningful, expressing high satisfaction with the robot's ability to remember them and sustain personalized conversations. Among the robot's functions, health monitoring and retrospective memory support were identified as highly valued by older adults. These findings provide insights for developing more adaptive and socially engaging robots, emphasizing the importance of personalized memory retention and user-tailored interactions in enhancing social support and cognitive engagement for older adults.