Citation

Zontone P, Affanni A, Bernardini R, Del Linz L, Piras A, Rinaldo R. Sensors (Basel) 2020; 20(9): e2494.

Affiliation

Polytechnic Department of Engineering and Architecture, University of Udine, Via delle Scienze 206, 33100 Udine, Italy.

Copyright

(Copyright © 2020, MDPI: Multidisciplinary Digital Publishing Institute)

DOI

10.3390/s20092494

PMID

32354062

Abstract

The evaluation of car drivers' stress condition is gaining interest as research on Autonomous Driving Systems (ADS) progresses. The analysis of the stress response can be used to assess the acceptability of ADS and to compare the driving styles of different autonomous drive algorithms. In this contribution, we present a system based on the analysis of the Electrodermal Activity Skin Potential Response (SPR) signal, aimed to reveal the driver's stress induced by different driving situations. We reduce motion artifacts by processing two SPR signals, recorded from the hands of the subjects, and outputting a single clean SPR signal. Statistical features of signal blocks are sent to a Supervised Learning Algorithm, which classifies between stress and normal driving (non-stress) conditions. We present the results obtained from an experiment using a professional driving simulator, where a group of people is asked to undergo manual and autonomous driving on a highway, facing some unexpected events meant to generate stress. The results of our experiment show that the subjects generally appear more stressed during manual driving, indicating that the autonomous drive can possibly be well received by the public. During autonomous driving, however, significant peaks of the SPR signal are evident during unexpected events. By examining the electrocardiogram signal, the average heart rate is generally higher in the manual case compared to the autonomous case. This further supports our previous findings, even if it may be due, in part, to the physical activity involved in manual driving.

Language: en

Keywords

autonomous driving; electrocardiogram; skin potential response; stress recognition; supervised learning algorithm