We present a novel architecture for Human-AI Teaming with a swarm of role-based agents supporting healthy behavior change. The system consists of a Triage Agent, RAG agent, and four specialized agents (Empathic Companion, Persuasive Challenging Coach, Medical Domain Expert, and Neutral Assistant) that communicate decentrally. Evaluated with six participants, results showed positive attitudes toward behavior change, with participants finding the system useful and responding favorably to personalized suggestions across physical activity, nutrition, alcohol, and recovery domains.

Metaphors have for long time been used for describing and explaining the roles of technology in human activity. Such descriptions are embedding an increasing level of ambience, where technology is expected to sense, interpret, and adapt to an individual’s needs and wishes, while at the same time, the demands for transparency and accountability is making way for new regulations and guidelines for systems based on artificial intelligence (AI). The purpose of this research is to explore social roles of humans and AI systems, and to identify open research questions and challenges when designing for transparency and sense of control. A socio-technical relationship framework was developed for assessing the social roles of AI systems, and for designing for change in roles and relationships. The framework was developed based on activity theory, metaphors for human-technology interaction, and emergent research on human-AI collaboration. By focusing on meaningful shared activity, the situations when technology is socially and personally relevant can be distinguished from the situations where technology is functionally relevant. The identified roles are partly overlapping and fluent depending on the situation, which increases the need for transparency and accountability, and consequently, AI techniques that allows explainability, negotiation and adaptation of the enacted roles. The framework is exemplified in two case studies to elicit role transformations in a work and a home environment respectively, where an individual’s changing need for supporting development of capabilities and autonomy through AI-based technology are addressed. We identify a number of open research questions and propose to apply the framework to capture and design for developing capability in humans and AI systems, collaborative capabilities in human-AI teaming, and for eliciting the ethical and moral consequences of AI systems operating within a person’s zone of development.

Health-promoting digital agents, taking on the role of an assistant, coach or companion, are expected to have knowledge about a person’s medical and health aspects, yet they typically lack knowledge about the person’s activities. These activities may vary daily or weekly and are contextually situated, posing challenges for the human-agent interaction. This pilot study aimed to explore the experiences and behaviors of older adults when interacting with an initially unknowledgeable digital agent that queries them about an activity that they are simultaneously engaged in. Five older adults participated in a scenario involving preparing coffee followed by having coffee with a guest. While performing these activities, participants educated the smartwatch-embedded agent, named Virtual Occupational Therapist (VOT), about their activity performance by answering a set of activity-ontology based questions posed by the VOT. Participants’ interactions with the VOT were observed, followed by a semi-structured interview focusing on their experience with the VOT. Collected data were analyzed using an activity-theoretical framework. Results revealed participants exhibited agency and autonomy, deciding whether to adapt to the VOT’s actions in three phases: adjustment to the VOT, partial adjustment, and the exercise of agency by putting the VOT to sleep after the social conditions and activity changed. Results imply that the VOT should incorporate the ability to distinguish when humans collaborate as expected by the VOT and when they choose not to comply and instead act according to their own agenda. Future research focuses on how collaboration evolves and how the VOT needs to adapt in the process.

Mutual understanding of the dialogue purpose and role of participants is vital to co-create meaning and satisfactory outcomes during human and social robot dialogues. This study explored how younger and older adults perceive roles, goals and behaviors of dialogue participants when breakdown situations occur during co-creation of meaning in a dialogue. The aim was to identify intuitive mechanisms that a social robot can use to manage breakdown situations. A set of dialogues were authored, based on activity-theoretical models of human activity and recorded in a Wizard-of-Oz setup with a Nao robot. Results of 8 (four younger and four old adults) participant interviews after observing the recorded dialogues are presented. Thematic analysis of interviews resulted into three themes of perceptions and expectations on roles and relationship, the robot’s understanding of the situation and relevant behavioral norms. Themes were translated into design implications for developing activity-centric dialogue systems to seamlessly manage breakdown situations. Future work includes implementation and further study of the proposed design implications for human robot dialogues.

The purpose of this research is to explore how an intelligent digital companion (agent) can support persons (human) with stress-related exhaustion to manage daily activities. In this paper, we explore in particular how information about a person's emotions can be communicated to the agent with means of non-verbal communication through tangible interfaces. The purpose is to explore how different individuals approach the task of designing their own tangible interfaces for communicating emotions with a digital companion, and the range of different preferences and expectations. Six participants were interviewed and created tangible prototypes during a co-creation workshop. The data was analysed using theories about human emotions and activity, and translated into a generic user model, an architecture for a multiagent system and interface design proposals. The results include increased understanding of how different individuals would like to express their emotions with tangible interfaces, and informed the design of the information models regarding representing emotions. The study illuminated the importance of personalisation of functionality and interface design to address the diversity among individuals, as well as the design of the adaptive behaviour of a digital companion. Future work includes further studies involving additional participants, the development of the stress management application and conducting user studies where prototypes are used in daily activities.

In this paper, we propose a multi-agent framework to deal with situations involving uncertain or inconsistent information located in a distributed environment which cannot be combined into a single knowledge base. To this end, we introduce an inquiry dialogue approach based on a combination of possibilistic logic and a formal argumentation-based theory, where possibilistic logic is used to capture uncertain information, and the argumentation-based approach is used to deal with inconsistent knowledge in a distributed environment. We also modify the framework of earlier work, so that the system is not only easier to implement but also more suitable for educational purposes. The suggested approach is implemented in a clinical decision-support system in the domain of dementia diagnosis. The approach allows the physician to suggest a hypothetical diagnosis in a patient case, which is verified through the dialogue if sufficient patient information is present. If not, the user is informed about the missing information and potential inconsistencies in the information as a way to provide support for continuing medical education. The approach is presented, discussed, and applied to one scenario. The results contribute to the theory and application of inquiry dialogues in situations where the data are uncertain and inconsistent.

Based on an argumentation theory approach, we present a novel method for evaluating complex goal-based activities by generalizing a notion of qualifier defined in the health domain. Three instances of the general qualifier are proposed: Performance, Actuation and Capacity; the first one evaluates what a person does, the second how an individual follows an action plan, and the third one how “well” or “bad” an activity is executed. Qualifiers are intended to be used by autonomous systems for evaluating human activity. We exemplify our approach using a health domain assessment protocol. Main results of this test show a partial correlation between ambiguities assessed by experts and our argument-based approach; and a multi-dimensional perspective how an activity is executed when a combined evaluation of qualifiers is used. This last outcome was interesting for some therapists consulted. Results also show differences between values of qualifiers using different argumentation semantics; two scenarios were proposed by therapist for using different semantics: preliminary activity screening and time-span follow-up evaluation.

We introduce the Assisted Living system ALI, which is a novel approach to providing assistance and support in activities of daily life. We integrate a human behavior theory with a default reasoning decision making framework. This integration allows us to model a decision making problem from a human activity centric point of view and at the same time, formalize these elements using a possibilistic argumentation theory. ALI sends personalized notifications suggesting the most suitable activities to perform and determines what activities were performed during a time period.

We investigate an ongoing user-driven collaborative knowledge engineering and interaction design process. The anticipated outcomes are knowledge-based support applications for health care professionals and other actors in the dementia domain. The two major goals for the activity in focus are: (1) to accomplish international collaboration across organizational, language and professional boundaries in the modeling of knowledge and design of interaction, and (2) in a local community provide ICT-support for collaboration and communication between organizations, increase knowledge development in individual actors and increase the quality of dementia care. The semantic web-based prototype system ACKTUS is introduced as a tool for modeling and communicating knowledge and interaction, and its role in the process is evaluated. The activity is organized as a part of a collaborative work between different organizations to develop their local clinical practice. Obstacles and success factors when enabling the endusers to design their own tools are detected and discussed.