Bayesian network approach to building an affective module for a driver behavioural model

TL;DR

This paper employs Bayesian networks to model driver mental states like fatigue and mental load, aiming to enhance understanding of driver behavior for improved traffic safety and autonomous vehicle systems.

Contribution

It introduces a Bayesian network framework to model and estimate driver mental states based on physiological and demographic data, advancing driver behavior modeling.

Findings

Bayesian networks effectively capture dependencies between driver states and variables.

The model estimates mental states with promising accuracy.

Potential applications in traffic safety and autonomous driving systems.

Abstract

This paper focuses on the affective component of a Driver Behavioural Model (DBM), specifically modelling some driver's mental states, such as mental load and active fatigue, which may affect driving performance. We used Bayesian networks (BNs) to explore the dependencies between various relevant variables and estimate the probability that a driver was in a particular mental state based on their physiological and demographic conditions. Through this approach, our goal is to improve our understanding of driver behaviour in dynamic environments, with potential applications in traffic safety and autonomous vehicle technologies.