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.

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.

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.