The rapid advancement of technology empowered by artificial intelligence is believed to intensify the collaboration between humans and AI as team partners. Successful collaboration requires partners to learn about each other and about the task. This human-AI co-learning can be achieved by presenting situations that enable partners to share knowledge and experiences. In this paper we describe the development and implementation of a task context and procedures for studying co-learning. More specifically, we designed specific sequences of interactions that aim to initiate and facilitate the co-learning process. The effects of these interventions on learning were evaluated in an experiment, using a simplified virtual urban-search-and-rescue task for a human-robot team. The human participants performed a victim rescue- and evacuation mission in collaboration with a wizard-of-Oz (i.e., a confederate of the experimenter who executed the robot-behavior consistent with an ontology-based AI-model). The designed interaction sequences, formulated as Learning Design Patterns (LDPs), were intended to bring about co-learning. Results show that LDPs support the humans understanding and awareness of their robot partner and of the teamwork. No effects were found on collaboration fluency, nor on team performance. Results are used to discuss the importance of co-learning, the challenges of designing human-AI team tasks for research into this phenomenon, and the conditions under which co-learning is likely to be successful. The study contributes to our understanding of how humans learn with and from AI-partners, and our propositions for designing intentional learning (LDPs) provide directions for applications in future human-AI teams.

Much of the research on eXplainable Artificial Intelligence (XAI) has centered on providing transparency of machine learning models. More recently, the focus on human-centered approaches to XAI has increased. Yet, there is a lack of practical methods and examples on the integration of human factors into the development processes of AI-generated explanations that humans prove to uptake for better performance. This paper presents a case study of an application of a human-centered design approach for AI-generated explanations. The approach consists of three components: Domain analysis to define the concept & context of explanations, Requirements elicitation & assessment to derive the use cases & explanation requirements, and the consequential Multi-modal interaction design & evaluation to create a library of design patterns for explanations. In a case study, we adopt the DoReMi-approach to design explanations for a Clinical Decision Support System (CDSS) for child health. In the requirements elicitation & assessment, a user study with experienced paediatricians uncovered what explanations the CDSS should provide. In the interaction design & evaluation, a second user study tested the consequential interaction design patterns. This case study provided a first set of user requirements and design patterns for an explainable decision support system in medical diagnosis, showing how to involve expert end users in the development process and how to develop, more or less, generic solutions for general design problems in XAI.

Personalisation can increase the learning efficacy of educational games by tailoring their content to the needs of the individual learner. This paper presents the Personalised Educational Game Architecture (PEGA). It uses a multi-agent organisation and an ontology to offer learners personalised training in a game environment. The multi-agent organisation's flexibility enables adaptive automation; the instructor can decide to control only parts of the training, while leaving the rest to the intelligent agents.

Serious games allow for adaptive and personalised forms of training; the nature and timing of learning activities can be tailored to the trainee’s needs and interests. Autonomous game-based training requires for the automatic selection of appropriate exercises for an individual trainee. This paper presents a framework for an automated scenario generation system. The underlying notion is that a learning experience is defined by the objects and agents that inhabit the training environment. Our system uses automated planning to assess the behaviour required to achieve the (personalised) training objective. It then generates a scenario by selecting semantically annotated (or 'smart') objects and by assigning goals to the virtual characters. The resulting situations trigger the trainee to execute the desired behaviour. To test the framework, a prototype has been developed to train the First Aid treatment of burns. Experienced instructors evaluated scenarios written by three types of authors: the prototype, first-aid experts, and laymen. The prototype produced scenarios that were at least as good as laymen scenarios. First-aid experts seemed the best scenario writers, although differences were not significant. It is concluded that combining automated planning, smart objects, and virtual agent behaviour, is a promising approach to automated scenario generation.

Virtual training systems with intelligent agents provide an effective means to train people for complex, dynamic tasks like crisis management or firefighting. For successful training, intelligent virtual agents should be able to show believable behav