Stress Evaluation in Simulated Autonomous and Manual Driving through the Analysis of Skin Potential Response and Electrocardiogram Signals

• DOI: 10.3390/s20092494
• Publication Date: 2020-04-28T14:30:58Z
• Authors: Pamela Zontone; Antonio Affanni; Riccardo Bernardini; Leonida Del Linz; Alessandro Piras; Roberto Rinaldo
• Keywords: SIGNAL (programming language); Driving simulator

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