Analysis of braking intention based on fNIRS in driving simulation experiments. Issue 7 (17th April 2019)

• Record Type: Journal Article
• Authors: Zhu, Lei; Li, Shuguang; Li, Yaohua; Wang, Min; Zhang, Chenyang; Li, Yanyu; Yao, Jin; Ji, Hao
• Is Part Of: IET intelligent transport systems. Volume 13:Issue 7(2019)
• Page Start: 1181
• Page End: 1189
• Publication Date: 2019-04-17
• Subjects: braking -- vision -- learning (artificial intelligence) -- brain -- road vehicles -- neurophysiology -- biomedical MRI -- cognition; fNIRS -- driving simulation experiments -- advanced driver assistance system -- functional near‐infrared spectroscopy -- cerebral cortex activity mechanism; Intelligent transportation systems -- Periodicals; Electronics in transportation -- Periodicals; 388.31205
• DOI: 10.1049/iet-its.2018.5304
• Languages: English
• ISSNs: 1751-956X

Abstract

Abstract : Cooperative driving refers to a notion that advanced driver assistance system (ADAS) sharing the control with human driver and completing driving task together. One of the key technologies is that the ADAS can identify the driver's driving intention in real time to implement consistent driving decisions. Based on driving simulator (DS) and functional near‐infrared spectroscopy (fNIRS) experiments, this study established a model of driver's brake intention identification with machine‐learning algorithms and analysed cerebral cortex activity mechanism of the driver's brake intention with parametric test. This study suggested that the test accuracy of the model established here was 90.91%. Moreover, the activity in the Brodmann area 7 (BA7), BA17, and BA40 in cerebral cortex was significantly different between the driver with braking intention and those with driving at constant speed ( p < 0.05). The study presented here not only identified the driver's driving intention through fNIRS for the first time, but also analysed the brain activity of the drivers when he had the braking intention. It lays a foundation for the future research on the driving cognitive model about human perception and driver's driving intention identification.