Explainable Cyber-Physical Systems

With the increasing complexity of cyber-physical systems, their behavior and decisions become increasingly difficult to understand and comprehend for users and other stakeholders. Our vision is to build self-explainable systems that can, at run-time, answer questions about the system’s past, current, and future behavior. As hitherto no design methodology or reference framework exists for building such systems, we propose the Monitor, Analyze, Build, Explain (MAB-EX) framework for building self-explainable systems that leverage requirements and explainability models at run-time. The basic idea of MAB-EX is to first Monitor and Analyze a certain behavior of a system, then Build an explanation from explanation models and convey this EXplanation in a suitable way to a stakeholder. We also take into account that new explanations can be learned, by updating the explanation models, should new and yet unexplainable behavior be detected by the system Digital twins seem to be a useful means to this end: they twins are increasingly being used for many purposes in various domains, including manufacturing, health-care, transportation, and urban planning. Moreover, they be complex software systems that digitally rep resent and manipulate cyber-physical systems. Hence, they are equipped with extensive data, information, and models to reason about the represented system and are used by domain experts from various disciplines. For their proper use, it is vital to comprehend the wealth of data, information, and models intrinsic to them. Therefore, we are researching a model-driven software architecture of digital twins that combines this wealth with techniques for the self-explainability of software systems to support domain experts in configuring, deploying, operating, and maintaining them.

Selected Publications

Find other research topics from my research website.