Driver State in Automated Driving

 

The introduction of automated vehicles creates the expectation of improving driving comfort, traffic efficiency and traffic safety. The focus of the “Driver state in automated driving” research group is a holistic view on the changes in the driver’s role during an automated driving context.

Traditional driving research views driving as the driver’s primary task, and focusses on minimizing driving distraction as a major challenge. This is in contrast with higher levels of automation (from Level 3, (SAE International, 2014)), where the traditional driving distraction concept loses meaning since, for example, it is permitted to engage in non-driving related tasks or even not performing any driving task at all. Despite this paradigm shift in the driver’s role, the driver is still responsible to take over the vehicle control, e.g. at system boundaries of the automation. . This is called a take-over request. The Chair of Ergonomics has a comprehensive list of publications on this topic, particularly the impact of situational factors, e.g. traffic density or general complexity of the situation on time and quality aspects of take-over performance (Damböck, 2013, Gold, 2016; Radlmayr, Gold, Lorenz, Farid, & Bengler, 2014).

In this research group, we focus on the driver state, namely on fatigue and vigilance (Feldhütter), drowsiness (Goncalves), individual differences (Körber) as well as new research methods (Radlmayr). The main objective is to conceive quantitative prediction models of the driver’s state influence on takeover. In our methodologies, we use an extensive array of sensors and measuring systems ranging from traditional eye-tracking systems, to motion-tracking systems and seat pressure mats. Furthermore, we analyse the validity of driving simulator studies to assess critically the results’ implications for real traffic scenarios.

References

Damböck, D. (2013). Automationseffekte im Fahrzeug – von der Reaktion zur Übernahme (Dissertation). Technische Universität München, München.

Gold, C. (2016). Modeling of Take-Over Performance in Highly Automated Vehicle Guidance (Dissertation). Technische Universität München, Garching. Retrieved from mediatum.ub.tum.de/1296132

Marberger, C., Mielenz, H., Naujoks, F., Radlmayr, J., Bengler, K., Wandtner, B. (2017). Understanding and Applying the Concept of “Driver Availability” in Automated Driving. Paper presented at the 8th Conference on Applied Human Factors and Ergonomics, Los Angeles, USA.

Radlmayr, J., Gold, C., Lorenz, L., Farid, M., & Bengler, K. (2014). How Traffic Situations and Non-Driving Related Tasks Affect the Take-Over Quality in Highly Automated Driving. Proceedings of the Human Factors and Ergonomics Society Annual Meeting, 58(1), 2063–2067. doi.org/10.1177/1541931214581434

SAE International (2014, January 16). Taxonomy and Definitions for Terms Related to On-Road Motor Vehicle Automated Driving Systems. (SAE, J 3016 201401).