The usefulness of physiological data as indicator for situation awareness in semi-autonomous driving


Abstract of the poster :

Car manufacturers are developing semi-autonomous cars in order to increase road safety and driver strain. In the near future, drivers in automated cars will be able to perform a secondary task while the car is driving autonomously, without requiring them to monitor the vehicle environment. In critical situations however, the driver may have to take over control of the vehicle. In order to propose an optimal support to the driver when a takeover is required, knowledge about their level of situation awareness might be useful. This piece of research addresses the question whether it is possible to use physiological indicators of drivers in order to evaluate their level of situation awareness in different takeover situations. Ninety participants took part in a semi-autonomous driving session in a fixed-base driving simulator. Half of them performed backward counting in order to manipulate cognitive workload. In addition to driving behavior, subjective data and physiological measures such as electrodermal activity and electrocardiogram have been recorded. Data analysis indicates that physiological data might be an interesting indicator for situation awareness in automated driving.