A socio-technical holistic agent based model to assess cockpit supporting tools performance variability

Abstract

Abstract The mesh of information that influence a human actor in its decision-making process is difficult to formalize and more difficult to validate. Stochastic approaches to represent human performance provides a fast modelling approach that can be statistically validated, however, do not contribute to a better understanding of performance variability consequences neither the design of mitigation mechanisms in critical processes. Better modelling approaches are needed to support a deeper understanding of the causes of a poor performance and the propagation mechanisms that spark emergent behavior and its effects. In this paper it is presented an agent based modeling framework to identify those factors that affects the performance of the pilot flying cockpit functionalities considering different socio-technical operational conditions. As a result, it is expected the design of new cognitive computing supporting tools to improve pilot situational awareness.