Uncertainty-aware explainable AI as a foundational paradigm for digital twins

Abstract

In the era of advanced manufacturing, digital twins have emerged as a foundational technology, offering the promise of improved efficiency, precision, and predictive capabilities. However, the increasing presence of AI tools for digital twin models and their integration into industrial processes has brought forth a pressing need for trustworthy and reliable systems. Uncertainty-Aware eXplainable Artificial Intelligence (UAXAI) is proposed as a critical paradigm to address these challenges, as it allows for the quantification and communication of uncertainties associated with predictive models and their corresponding explanations. As a platform and guiding philosophy to promote human-centered trust, UAXAI is based on five fundamental pillars: accessibility, reliability, explainability, robustness, and computational efficiency. The development of UAXAI caters to a diverse set of stakeholders, including end users, developers, regulatory bodies, the scientific community, and industrial players, each with their unique perspectives on trust and transparency in digital twins.