# Towards Self-Explainable Cyber-Physical Systems

## TL;DR

This paper proposes the MAB-EX framework for designing self-explainable cyber-physical systems that can generate and update explanations of their behavior in real-time, addressing the complexity challenge.

## Contribution

It introduces a novel framework, MAB-EX, providing a methodology for building systems that can explain their past, present, and future actions at run-time.

## Key findings

- Framework enables real-time explanations
- Supports updating explanations with new behavior
- Addresses lack of design methodologies for self-explainability

## Abstract

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.