A Novel Driver Performance Model Based on Machine Learning. Issue 9 (2018)

• Record Type: Journal Article
• Authors: Aksjonov, Andrei; Nedoma, Pavel; Vodovozov, Valery; Petlenkov, Eduard; Herrmann, Martin
• Is Part Of: IFAC-PapersOnLine. Volume 51:Issue 9(2018)
• Page Start: 267
• Page End: 272
• Publication Date: 2018
• Subjects: Neural networks -- Neural fuzzy modelling -- control -- Machine learning for environmental applications -- Vehicle dynamic systems -- Human factors in vehicular system -- Learning -- adaptation in autonomous vehicles -- Safety; Automatic control -- Periodicals; 629.805
• DOI: 10.1016/j.ifacol.2018.07.044
• Languages: English
• ISSNs: 2405-8963

Abstract

Abstract: Models of road vehicle driver behaviour are widely used in several disciplines, like driver distraction and autonomous driving. In this paper, a novel driver performance model, which is unique for every driver, is introduced. The driver is modelled with machine learning algorithms, namely artificial neural network and adaptive neuro-fuzzy inference system. Every model is trained and validated with the data collected during the real-time driver-in-the-loop experiment on a vehicle simulator for each driver separately. In total, 18 participants contributed to the experiment. Although the prediction accuracy of the models depends on the algorithm specifications, the artificial neural network was slightly more accurate in driver performance prediction comparing to the adaptive neuro-fuzzy inference system. The driver models may be used in detection of driver distraction induced by in-vehicle information system.