Taking driver frustration into account: Towards a speech-based emotion regulation in-car assistant

Frustration is regarded as an emotion that can turn into anger and (road) rage. These negative emotions and the aggressive driving behavior associated with them are in turn relevant causes of accidents and road fatalities. Adaptive driving assistance systems with the ability to detect the driver’s emotional state could prevent driver’s losses of driving performance caused by frustration through targeted intervention in emotion regulation processes. Here, speech interventions are particularly promising, because verbal communication with human passengers is familiar in such emotional states. Additionally, the cognitive strain burdened by spoken language and auditory interaction is quite little while executing at the same time the primary driving task. So far, little is known about the exact nature of speech interaction with voice user interface assistants in order to reduce the driver’s frustration. Our experimental study focuses on the appropriate timing for intervention. The theoretical basis is Gross' process model of emotion regulation. Since in road traffic both situation selection and situation modification are only possible in exceptional cases, this study concentrates on the three subsequent strategies of emotion regulation proposed by Gross. In two driving scenarios, the influence of different sources of frustration was manipulated. Results of the study show that the success of the speech intervention is not only determined by timing, but it is to a large extent situation-dependent. Implications for a refined design of such assistants as well as for further research will be pointed out