Throughout our lives, we interact daily in conversations with our friends and family, covering a wide range of topics, known as open-domain dialogue. As we age, these interactions may diminish due to changes in social and personal relationships, leading to loneliness in older adults. Conversational companion robots can alleviate this issue by providing daily social support. Large language models (LLMs) offer flexibility for enabling open-domain dialogue in these robots. However, LLMs are typically trained and evaluated on textual data, while robots introduce additional complexity through multi-modal interactions, which has not been explored in prior studies. Moreover, it is crucial to involve older adults in the development of robots to ensure alignment with their needs and expectations. Correspondingly, using iterative participatory design approaches, this paper exposes the challenges of integrating LLMs into conversational robots, deriving from 34 Swedish-speaking older adults' (one-to-one) interactions with a personalized companion robot, built on Furhat robot with GPT-\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$-$$\end{document}3.5. These challenges encompass disruptions in conversations, including frequent interruptions, slow, repetitive, superficial, incoherent, and disengaging responses, language barriers, hallucinations, and outdated information, leading to frustration, confusion, and worry among older adults. Drawing on insights from these challenges, we offer recommendations to enhance the integration of LLMs into conversational robots, encompassing both general suggestions and those tailored to companion robots for older adults.

Background: Mindfulness-based interventions have been demonstrated to be effective in improving bodily and emotional well-being. However, only a few studies have explored individual differences in the application and use of digital mindfulness among adults aged ≥65 years. Voice-guided mindfulness technologies can increase the accessibility of mindfulness training, but the expected benefits may not be similar in all user groups. Objective: This study aims to understand how older adults incorporate mindfulness into their habits and routines, explore the digital mindfulness design preferences of older adults, and understand if and how digital mindfulness can facilitate self-perceived well-being among older adults. Methods: A qualitative interview study built on an interpretive-constructivist paradigm was conducted among older adults in Sweden who used a voice-guided mindfulness app for a 3-week period in their homes (N=15). Semistructured interviews were conducted one-on-one with participants after using the app. Qualitative thematic analysis was used to explore the lived experiences of digital mindfulness, as articulated by participants, which allowed an open exploration of the subjective experiences of digital mindfulness and their possible effects and outcomes. Results: From the coding stage, 23 codes describing the digital mindfulness experience were identified from the data. These codes were thematized to group the codes together, resulting in 7 subthemes. From these 7 subthemes, three main themes were formed to answer the research objectives: (1) the embeddedness of digital mindfulness in older adults’ daily routines and habits, (2) heterogeneity in older adults’ design preferences for digital mindfulness, and (3) the consequences of digital mindfulness on the self-perceived well-being of older adults. Conclusions: This study concludes that digital mindfulness offers a possibility to enhance the self-perceived well-being of older adults by fostering resilience and self-care. However, adverse effects of mindfulness, such as frustration and discomfort, can also be experienced by older adults. The digital mindfulness experiences and preferences of older adults are highly individual, diverse, and manifold, which indicates that personalized approaches are essential for effective engagement. By acknowledging and addressing the heterogeneous design preferences within this demographic, developers can create more personalized and adaptive voice-guided mindfulness apps.

Voice Agents (VAs) are touted as being able to help users in complex tasks such as cooking and interacting as a conversational partner to provide information and advice while the task is ongoing. Through conversation analysis of 7 cooking sessions with a commercial VA, we identify challenges caused by a lack of contextual awareness leading to irrelevant responses, misinterpretation of requests, and information overload. Informed by this, we evaluated 16 cooking sessions with a wizard-led context-aware VA. We observed more fluent interaction between humans and agents, including more complex requests, explicit grounding within utterances, and complex social responses. We discuss reasons for this, the potential for personalisation, and the division of labour in VA communication and proactivity. Then, we discuss the recent advances in generative models and the VAs interaction challenges. We propose limited context awareness in VAs as a step toward explainable, explorable conversational interfaces.

Storytelling is an effective evidence-based practice as an accepted intervention by therapists for the therapy of children with autism spectrum disorder (ASD). Digital storytelling, particularly using smart tangibles, offers a structured, interactive and engaging environment for children with ASD allowing for repetition, offering feedback with visual supports, and giving the child more authority over the learning experience. This study presents a co-designed approach to digital storytelling activities with smart tangibles for autism therapy, aimed at enhancing multiple social and behavioral skills. Through co-design sessions with therapists, activity flows and scenarios were developed to target specific skill improvements. These include free play exploration, positive stimulus introduction, fostering cooperation to address disturbances, and incorporating magical objects to facilitate peer turn-taking. Additionally, real-life connections were emphasized to promote emotional regulation and multicultural understanding while further activities are designed to overcome routine issues, build tolerance to change, and enhance cognitive structuring. Feasibility was demonstrated through integration into therapy sessions of five children, where therapists independently utilized the system, fostering immersive and interactive storytelling experiences. Overall, the co-designed activities offer insights into enhancing therapy interventions for children with ASD beyond specific contexts, contributing to the broader design of autism therapy activities.

Companion robots are aimed to mitigate loneliness and social isolation among older adults by providing social and emotional support in their everyday lives. However, older adults’ expectations of conversational companionship might substantially differ from what current technologies can achieve, as well as from other age groups like young adults. Thus, it is crucial to involve older adults in the development of conversational companion robots to ensure that these devices align with their unique expectations and experiences. The recent advancement in foundation models, such as large language models, has taken a significant stride toward fulfilling those expectations, in contrast to the prior literature that relied on humans controlling robots (i.e., Wizard of Oz) or limited rule-based architectures that are not feasible to apply in the daily lives of older adults. Consequently, we conducted a participatory design (co-design) study with 28 older adults, demonstrating a companion robot using a large language model (LLM), and design scenarios that represent situations from everyday life. The thematic analysis of the discussions around these scenarios shows that older adults expect a conversational companion robot to engage in conversation actively in isolation and passively in social settings, remember previous conversations and personalize, protect privacy and provide control over learned data, give information and daily reminders, foster social skills and connections, and express empathy and emotions. Based on these findings, this article provides actionable recommendations for designing conversational companion robots for older adults with foundation models, such as LLMs and vision-language models, which can also be applied to conversational robots in other domains.

Conversational agents (CA) are increasingly used to manage and coordinate household chores and everyday activities at home. However, these technologies should be adaptive to age-specific characteristics in order to be considered beneficial for the ageing population. This study presents a participatory design of a conversational agent to provide cognitive support in recipe following and nutrition advice for adults aged 65 and over. Through a qualitative thematic analysis, the study explores older adults’ expectations, interactions and experiences with the agent in order to identify age-specific challenges of interacting with CAs. Data consists of a participatory design workshop with eight older adults (aged 65 and over), followed by a Wizard of Oz study with ten older adults interacting with the agent in the kitchen environment in a laboratory setting. Results demonstrate that older adults consider conversational agents as beneficial for providing personalised recipe recommendations, advising the user to choose appropriate ingredients and reminding them of their dietary intake. When interacting with the agent older adults displayed challenges with confirmation and repetition, questioning and correcting, the lack of conversational responses, and difficulties in hearing and understanding the multi-modal interaction. Older adults experience agents as collaborators, but not as conversational partners. The study concludes that the accessibility and inclusiveness of conversational agents regarding voice interaction could be improved by further developing participatory methods with older adults.

Background: New social alarm solutions are viewed as a promising approach to alleviate the global challenge of an aging population and a shortage of care staff. However, the uptake of social alarm systems in nursing homes has proven both complex and difficult. Current studies have recognized the benefits of involving actors such as assistant nurses in advancing these implementations, but the dynamics by which implementations are created and shaped in their daily practices and relations have received less attention. Objective: Based on domestication theory, this paper aims to identify the differences in the perspectives of assistant nurses when integrating a social alarm system into daily practices. Methods: We interviewed assistant nurses (n=23) working in nursing homes to understand their perceptions and practices during the uptake of social alarm systems. Results: During the four domestication phases, assistant nurses were facing different challenges including (1) system conceptualization; (2) spatial employment of social alarm devices; (3) treatment of unexpected issues; and (4) evaluation of inconsistent competence in technology use. Our findings elaborate on how assistant nurses have distinct goals, focus on different facets, and developed diverse coping strategies to facilitate the system domestication in different phases. Conclusions: Our findings reveal a divide among assistant nurses in terms of domesticating social alarm systems and stress the potential of learning from each other to facilitate the whole process. Further studies could focus on the role of collective practices during different domestication phases to enhance the understanding of technology implementation in the contexts of complex interactions within a group.

This paper describes the first steps of an ongoing participatory design with teachers from Switzerland to co-create Human-Robot Interaction setups for integrating children with migration history. The herein presented phase had two main goals: (i) initially mapping the current issues and the teachers’ strategy when integrating these children, and (ii) understanding teachers’ perceptions regarding social robots for this goal. Results show that teachers we interviewed are already using technology to communicate with immigrant children, not necessarily for inclusion or promote socialisation with their peers, but simply to understand them. Findings also point to a well-defined application of social robots in inclusion activities, even when never seeing or using them, which contradicts previous results in the literature and which gives potential ways to unfold the next steps of the participatory design.

Neurodivergent children with cognitive and communicative difficulties often experience a lower level of social integration in comparison to neurotypical children. Therefore it is crucial to understand social inclusion challenges and address exclusion. Since previous work shows that gamified robotic activities have a high potential to enable inclusive and collaborative environments we propose using robot-mediated games for enhancing social inclusion. In this work, we present the design of a multiplayer tangible Pacman game with three different inter-player interaction modalities: semi-dependent collaborative, dependent collaborative, and competitive. The initial usability evaluation and the observations of the experiments show the benefits of the game for creating collaborative and cooperative practices for the players and thus also potential for social interaction and social inclusion. Importantly, we observe that inter-player interaction design affects the communication between the players and their physical interaction with the game.

A lack of social support can hinder older adults’ digital inclusion. This chapter examines the connection between social and digital inclusion by focusing on the process of acquiring social support for digital technology use among older adults in Finland. Building on the concept of warm expert, the chapter shows that acquiring support for digital technology use is a reciprocal process that both enhances and requires digital inclusion. A qualitative analysis of 22 participant-induced elicitation interviews was conducted with older adults aged between 57 and 89. The chapter shows that social support reinforces digital inclusion by (a) ensuring older adults’ access to technology, (b) catering for their positive approach towards technology and (c) improving their skills to use technology independently. The connection between social and digital inclusion also operates the other way round. Digital inclusion is required to gain social support that is more readily at hand in a technology-mediated manner.