Using driver monitoring to estimate readiness in automation: a conceptual model based on simulator experimental data

Abstract

This paper provides a theoretical overview of how the concept of driver readiness can be objectively measured, using controlled experimental data. First, a literature review regarding the concept of driver readiness is provided. Then, it highlights challenges for a standardized readiness estimation model. A conceptual readiness estimation model is presented, and a methodology is proposed for defining readiness thresholds for use by Driver State Monitoring (DSM) systems. The paper then explores how this model can be used to estimate readiness thresholds. A proof of concept for the model application is presented, using previously collected experimental involving SAE Level 2 automation. This paper contributes to the state of the art in DSM-development, by providing a methodology for estimating driver readiness, while considering variabilities across individual drivers. The model also allows readiness thresholds to be defined with data from driving simulator experiments, without relying on subjective assessment of readiness as its ground truth.