A method of driver distraction evaluation using fuzzy logic: Phone usage as a driver's secondary activity: Case study

Abstract

A novel method for evaluating driver distraction and situation awareness while performing a secondary task using a fuzzy set theory is proposed in this paper. A fuzzy inference engine realization process based on simple matrix operations is described in detail. The drivers' performance is evaluated referring to the vehicle behavior, in particular, the abilities to keep the vehicle in the center of the lane and to observe the speed limit. The evaluation technique was tested on a vehicle mock-up driving simulator. Text messaging on a cell phone is studied as a secondary distractive activity. Driver-in-the-loop experimental results as well as the conclusions regarding different age, gender, and driving experience groups are discussed.

Hardware-in-the-Loop Test of an Open-Loop Fuzzy Control Method for Decoupled Electrohydraulic Antilock Braking System

“…When the input singleton does not intersect a MF, its array position value equals to zero. Thereafter, a dyadic product of two arrays is calculated resulting in matrix C [35]:…”

“…The same principle is applied to other rule bases. Finally, fuzzy inference is done via Hadamard product of two matrices of the same dimensions: C from the fuzzification interface, and R from the rule base [35]:…”

A Fuzzy-Logic Approach to Dynamic Bayesian Severity Level Classification of Driver Distraction Using Image Recognition

“…Aksjonov et al [4] developed a novel method for the evaluation of driver distraction while performing a secondary task. The system involved a development of a fuzzy inference system based on simple matrix operations.…”

“…This can compromise the prevention of accidents. In a related system, the prediction of vehicle crash severity using a fuzzy-logic model has been carried out using acceleration data from vehicle dynamics (vehicle jerk) [4]. However, here we used a system for the detection and classification of multi-class distractions, including hand position, face orientation, distraction activity and previous driver distractions.…”

Deep Learning Applied to Scenario Classification for Lane-Keep-Assist Systems

“…On one side, we have advanced vehicle state estimation [2][3][4], followed by safe and agile maneuvering in extreme conditions [5], and improved control of steering feedback to the driver [6]. On the other side, improved safety is considered in several areas, starting from a shared control system where the human and ADFs are working in synergy [7], to research focusing on pedestrian safety [8], and in the development of future human-machine interfaces that should reduce driver distraction [9]. Optimal and efficient driving will play a huge role in the future of automation as more and more vehicles become aware of their dynamic surroundings [10].…”