Driver State Regulation via Real-Time Neurofeedback in Partially Automated Driving

Improving driver performance in critical driving situations is the key to increased road safety. In SAE Level 3 of automation, the driver is retained as a fallback in critical situations. Once the system reaches its limits, the distracted driver must overtake the driving task and is responsible for the present and upcoming situations. This contribution proposes a new method to impact driver performance by regulating the driver's arousal level. The arousal level of the driver is determined by detecting the driver's brain activity, and proper auditory feedback is issued to reduce the arousal towards the optimal value. The suggested approach utilizes neurofeedback to downregulate the driver's arousal via self-regulation in critical driving situations. The results show that the proposed neurofeedback supports the drivers to self-regulate their arousal during simple and difficult driving tasks and reach the optimal arousal level. The proposed approach is especially helpful in driving intervals with high criticality where the driver has to consecutively make decisions and react under demanding conditions.

I. Introduction

The cognitive state of the driver plays a significant role in driver performance since the decision-making process and working memory retrieval build the core of the cognitive process. Yerkes-Dodson law [1] shows the empirical relation between arousal level and performance for each specific task. This relationship differs for simple tasks and difficult tasks. For simple tasks, an increase of arousal level leads to an improvement in the quality of performance. For difficult tasks, however, the optimal performance is achieved with a certain amount of arousal. Difficult tasks such as multitasking require divided attention and impair working memory. In this case, the relationship between arousal and performance is a bell-shaped curve. The performance quality elevates with increasing arousal level, reaches a maximum amount for a certain value of arousal, and decreases again for higher arousal levels. The arousal value, at which the performance has the highest quality, is the optimal arousal value for the specified task.