An Integrative and Transdisciplinary Approach for a Human-Centered Design of AI-Based Work Systems

Abstract

Abstract Psychological and ethical criteria are to date not systematically covered in the system design process. We suggest to extend existing model-based system engineering approaches by new elements that are capable to capture these criteria and, in particular, allow for an implementation of psychological risk analysis and ethical evaluation of work systems already in the design phase. The need for a systematic integration of not only safety but also ethical and psychological criteria in the system design is strengthened by the growing complexity of work systems and the increasing use of artificial intelligence-based algorithms, which have the potential to replace distinctive human capabilities and are associated with a shift of responsibility from humans to machines. We identify essentially two factors impeding the development of an innovative integrative system design approach. First, at present, there is no legally predefined iterative process including an open feedback loop between the operator and the system designer that enables continuous risk assessment. Second, available methods do not provide a framework to integrate ethical and psychological criteria. We propose four steps for the development of an integrative system design approach: (1) an in-depth investigation of current methods suitable for holistic system design processes, (2) the development of a transdisciplinary terminology, (3) the development of a procedure which allows to identify ethical criteria meeting both individual and societal requirements and (4) testing of the developed approach in a digital system model by using a suitable use case.