The goal of the FATE system is decision support with use of state-of-the-art human-AI co-learning, explainable AI and fair, secure and privacy-preserving usage of data. This AI-based support system is a general system, in which the modules can be tuned to specific use cases. The FATE system is designed to address different user roles, such as a researcher, domain expert/consultant and subject/patient, each with their own requirements. Having examined a Diabetes Type 2 use case before, in this paper we slightly iterate the FATE system and focus on a juridical use case. For a given new juridical case the relevant older court cases are suggested by the system. The relevant older cases can be explained using the eXplainable AI (XAI) module, and the system can be improved based on feedback about the relevant cases using the Co-learning module through interaction with a user. In the Bias module, the use of the system is investigated for potential bias by inspecting the properties of suggested cases. Secure Learning offers privacy-by-design alternatives for functionality found in the aforementioned modules. These results show how the generic FATE system can be implemented in a number of real-world use cases. In future work we plan to explore more use cases within this system.

To support effective and successful projects, Service Design practitioners rely on insights that mainly build on qualitative research methodology. The literature on data science promises to help transform how design research is done, adding sophisticated quantitative analyses, complementing existing methods with the power of machines. Due to this potential, data science receives widespread attention from both design practitioners and academics. However, the literature is fragmented and specialized, making it hard for designers to engage with data science. This paper addresses the opportunities and challenges for data science to support Service Design projects, evaluating existing technologies from designers’ perspective and providing an entry-level guide for service designers. These methods can help increase the quality of design research, making hidden information accessible and assisting creative processes. Together, these results are expected to inspire organizations to advance their data science resources for Service Design projects.

Current developments in Artificial Intelligence (AI) led to a resurgence of Explainable AI (XAI). New methods are being researched to obtain information from AI systems in order to generate explanations for their output. However, there is an overall lack of valid and reliable evaluations of the effects on users' experience of, and behavior in response to explanations. New XAI methods are often based on an intuitive notion what an effective explanation should be. Rule- and example-based contrastive explanations are two exemplary explanation styles. In this study we evaluate the effects of these two explanation styles on system understanding, persuasive power and task performance in the context of decision support in diabetes self-management. Furthermore, we provide three sets of recommendations based on our experience designing this evaluation to help improve future evaluations. Our results show that rule-based explanations have a small positive effect on system understanding, whereas both rule- and example-based explanations seem to persuade users in following the advice even when incorrect. Neither explanation improves task performance compared to no explanation. This can be explained by the fact that both explanation styles only provide details relevant for a single decision, not the underlying rational or causality. These results show the importance of user evaluations in assessing the current assumptions and intuitions on effective explanations.

With the progress of Artificial Intelligence, intelligent agents are increasingly being deployed in tasks for which ethical guidelines and moral values apply. As artificial agents do not have a legal position, humans should be held accountable if actions do not comply, implying humans need to exercise control. This is often labeled as Meaningful Human Control (MHC). In this paper, achieving MHC is addressed as a design problem, defining the collaboration between humans and agents. We propose three possible team designs (Team Design Patterns), varying in the level of autonomy on the agent’s part. The team designs include explanations given by the agent to clarify its reasoning and decision-making. The designs were implemented in a simulation of a medical triage task, to be executed by a domain expert and an artificial agent. The triage task simulates making decisions under time pressure, with too few resources available to comply with all medical guidelines all the time, hence involving moral choices. Domain experts (i.e., health care professionals) participated in the present study. One goal was to assess the ecological relevance of the simulation. Secondly, to explore the control that the human has over the agent to warrant moral compliant behavior in each proposed team design. Thirdly, to evaluate the role of agent explanations on the human’s understanding in the agent’s reasoning. Results showed that the experts overall found the task a believable simulation of what might occur in reality. Domain experts experienced control over the team’s moral compliance when consequences were quickly noticeable. When instead the consequences emerged much later, the experts experienced less control and felt less responsible. Possibly due to the experienced time pressure implemented in the task or over trust in the agent, the experts did not use explanations much during the task; when asked afterwards they however considered these to be useful. It is concluded that a team design should emphasize and support the human to develop a sense of responsibility for the agent’s behavior and for the team’s decisions. The design should include explanations that fit with the assigned team roles as well as the human cognitive state.

Decision support systems (DSS) have improved significantly but are more complex due to recent advances in Artificial Intelligence. Current XAI methods generate explanations on model behaviour to facilitate a user's understanding, which incites trust in the DSS. However, little focus has been on the development of methods that establish and convey a system's confidence in the advice that it provides. This paper presents a framework for Interpretable Confidence Measures (ICMs). We investigate what properties of a confidence measure are desirable and why, and how an ICM is interpreted by users. In several data sets and user experiments, we evaluate these ideas. The presented framework defines four properties: 1) accuracy or soundness, 2) transparency, 3) explainability and 4) predictability. These characteristics are realized by a case-based reasoning approach to confidence estimation. Example ICMs are proposed for -and evaluated on- multiple data sets. In addition, ICM was evaluated by performing two user experiments. The results show that ICM can be as accurate as other confidence measures, while behaving in a more predictable manner. Also, ICM's underlying idea of case-based reasoning enables generating explanations about the computation of the confidence value, and facilitates user's understandability of the algorithm.

Artificially intelligent agents will deal with more morally sensitive situations as the field of AI progresses. Research efforts are made to regulate, design and build Artificial Moral Agents (AMAs) capable of making moral decisions. This research is highly multidisciplinary with each their own jargon and vision, and so far it is unclear whether a fully autonomous AMA can be achieved. To specify currently available solutions and structure an accessible discussion around them, we propose to apply Team Design Patterns (TDPs). The language of TDPs describe (visually, textually and formally) a dynamic allocation of tasks for moral decision making in a human-agent team context. A task decomposition is proposed on moral decision-making and AMA capabilities to help define such TDPs. Four TDPs are given as examples to illustrate the versatility of the approach. Two problem scenarios (surgical robots and drone surveillance) are used to illustrate these patterns. Finally, we discuss in detail the advantages and disadvantages of a TDP approach to moral decision making.

Most explainable AI (XAI) research projects focus on well-delineated topics, such as interpretability of machine learning outcomes, knowledge sharing in a multi-agent system or human trust in agent’s performance. For the development of explanations in human-agent teams, a more integrative approach is needed. This paper proposes a perceptual-cognitive explanation (PeCoX) framework for the development of explanations that address both the perceptual and cognitive foundations of an agent’s behavior, distinguishing between explanation generation, communication and reception. It is a generic framework (i.e., the core is domain-agnostic and the perceptual layer is model-agnostic), and being developed and tested in the domains of transport, health-care and defense. The perceptual level entails the provision of an Intuitive Confidence Measure and the identification of the “foil” in a contrastive explanation. The cognitive level entails the selection of the beliefs, goals and emotions for explanations. Ontology Design Patterns are being constructed for the reasoning and communication, whereas Interaction Design Patterns are being constructed for the shaping of the multimodal communication. First results show (1) positive effects on human’s understanding of the perceptual and cognitive foundation of agent’s behavior, and (2) the need for harmonizing the explanations to the context and human’s information processing capabilities.