Human-in-the-loop: probabilistic predictive modelling, its role,attributes, challenges and applications

摘要

Traditional human-factor-oriented approaches are based on experimentations followedrnby statistical analyses. Our novel probabilistic predictive modelling (PPM) concept isrnbased on physically meaningful and flexible predictive modelling followed byrnexperimentations geared to the appropriate models. The concept enables one tornquantify, on the probabilistic basis, the outcome of a particular effort, situation or arnmission. This cost-effective and insightful approach is applicable to numerous humanin-rnthe-loop (HITL) situations, when a human acting as a part of the complex man–rninstrumentation–equipment–vehicle–environment system encounters an uncertainrnenvironment or a hazardous off-normal situation, and when there is an incentive tornimprove his/her role in a particular mission or a situation. The application of the PPMrnconcept could improve dramatically the state-of-the-art in the HITL field in variousrnvehicular technologies and beyond. The examples are taken mostly from the field ofrnavionic safety.