Model Learning for Improved Trustworthiness in Autonomous Systems (Dagstuhl Seminar 23492)

The term of a model has different meanings in different communities, e.g., in psychology, computer science, and human-computer interaction, among others. Well-defined models and specifications are the bottleneck of rigorous analysis techniques in practice: they are often non-existent or outdated. The constructed models capture various aspects of system behaviours, which are inherently heterogeneous in nature in contemporary autonomous systems. Once these models are in place, they can be used to address further challenges concerning autonomous systems, such as validation and verification, transparency and trust, and explanation. The seminar brought together the best experts in a diverse range of disciplines such as artificial intelligence, formal methods, psychology, software and systems engineering, and human-computer interaction as well as others dealing with autonomous systems. The goal was to consolidate these understanding of models in order to address three grand challenges in trustworthiness and trust: (1) understanding and analysing the dynamic relationship of trustworthiness and trust, (2) the understanding of mental modes and trust, and (3) rigorous and model-based measures for trustworthiness and calibrated trust.