Skin potential response for stress recognition in simulated urban driving

In this paper, we address the problem of possible stress conditions arising in car drivers, thus affecting their driving performance. We apply various Machine Learning (ML) algorithms to analyse the stress of subjects while driving in an urban area in two different situations: one with cars, pedestrians and traffic along the course, and the other characterized by the complete absence of any of these possible stress-inducing factors. To evaluate the presence of a stress condition we use two Skin Potential Response (SPR) signals, recorded from each hand of the test subjects, and process them through a Motion Artifact (MA) removal algorithm which reduces the artifacts that might be introduced by the hand movements. We then compute some statistical features starting from the cleaned SPR signal. A binary classification ML algorithm is then fed with these features, giving as an output a label that indicates if a time interval belongs to a stress condition or not. Tests are carried out in a laboratory at the University of Udine, where a car driving simulator with a motorized motion platform has been prearranged. We show that the use of one single SPR signal, along with the application of ML algorithms, enables the detection of possible stress conditions while the subjects are driving, in the traffic and no traffic situations. As expected, we observe that the test individuals are less stressed in the situation without traffic, confirming the effectiveness of the proposed slightly invasive system for detection of stress in drivers.

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

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.