Towards Self-Explainable Cyber-Physical Systems
This addresses the need for improved transparency in cyber-physical systems for users and stakeholders, but it is incremental as it builds on existing concepts without introducing a new paradigm.
The paper tackles the problem of understanding complex cyber-physical systems by proposing the MAB-EX framework to build self-explainable systems that can answer questions about behavior at run-time, leveraging requirements and explainability models.
With the increasing complexity of CPSs, 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 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 un-explainable behavior be detected by the system.