Evaluating the Effect of Fatigue on Driver’s Performance

Jirgl, Miroslav; Sediva, S.; Bradáč, Zdeněk · 2024 · OpenAlex-citations

DOI: 10.1016/j.ifacol.2024.07.407

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This paper presents an experimental cybernetic approach to evaluate driver performance in relation to fatigue, utilizing mathematical modeling and the description of human behavior during a simple lane-changing task. The study aims to quantify the impact of fatigue on driving capabilities by developing a system that calculates the Driver Performance Index (DPI). This index serves as a self-determined relative measure of driver performance, constructed using fuzzy logic. The research is motivated by the need for objective metrics to assess how fatigue influences decision-making and operational performance in driving scenarios. The methodology involves data acquisition from 50 active drivers using an in-house developed car driving simulator under defined conditions. The statistical evaluation of parameters derived from this dataset was used to determine the described drivers’ performance and decision-making characteristics. Based on this initial dataset, a fuzzy logic-based system was built to calculate the DPI. To validate the method’s sensitivity to fatigue, the authors conducted a specific experiment involving three volunteers. These participants underwent a simulated fatigue loading consisting of a 3-hour-long drive on a highway within the simulator. The study compares the DPI values obtained before and after this fatigue-inducing period to assess changes in performance. The results indicate that all three participants reached lower DPI values in the case of fatigue induced by the simulated loading. This decline in the index suggests a measurable decrease in driver performance following prolonged driving. However, the authors note that due to the small sample size of the validation experiment (three volunteers), the results cannot be statistically significantly interpreted. Despite this limitation, the observed trend indicates a potential correlation between fatigue and reduced performance metrics as captured by the DPI. The significance of this work lies in the development of a novel, fuzzy logic-based framework for assessing driver fatigue through objective performance indices. While the current findings require further validation with larger datasets to achieve statistical significance, the study establishes a foundation for deeper research into cybernetic models of human driver behavior. The proposed DPI offers a potential tool for monitoring driver states in real-time or post-hoc analysis, contributing to the broader field of automotive safety and human-machine interaction. The paper concludes that the method shows promise for evaluating fatigue effects, warranting expanded experimental studies to confirm its reliability and applicability.

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.

Summary generated by qwen3.6-27b-prismaquant on 2026-06-25; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• drowsiness detection algorithms
• time on task
• truck driver fatigue
• sleep deprivation
• dms validation

Information type

What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).

• Empirical Findings: physiological data, behavioral performance data
• Methodological Resource: validation psychometrics