Periodic Reporting for period 1 - Detect and React (Distracted drivers in autonomous cars: Do drivers safely detect and react to unexpected warning signals?)
Okres sprawozdawczy: 2016-09-01 do 2018-08-31
The results of our study demonstrated that driver's ability to detect alerts is reduced under automated driving conditions, especially when participants are passively (and less attentively) listening to the sounds. This is a challenge for current (semi-) automated vehicles, which rely on auditory alerts to warn drivers to take-over control of the car from the automated vehicle. Given the reduced ability to detect such alerts, drivers might miss these warnings.
Based on our results, I have further studied the effecive use of early warnings to warn a driver (also referred to as ""pre-alerts""). The results demonstrated that such early warnings lead to better reactions to alerts by drivers in driving studies.
I also published a new framework (building on Hidden Markov Models) to consider human confusion when interacting with automated systems, and to guide further scientific dialogue on these matters."
The results have provided fundamental new insights about human behaviour in higher-level automated vehicles before these systems are released on the road. This knowledge will inform the design of safer technology and better policy for autonomous vehicles.
The work has been published in multiple scientific publications. I have also co-organized a workshop on human behavior in automated driving.
Apart from that, I have given presentations at international scientific conferences, workshops, and international research labs for in total over 1,000 people.
I have also given various public lectures on automation, artificial intelligence, and automated vehicles, for in total over 800 people. My work was also mentioned in various national and international news items.
Finally, I have started a public youtube channel in which I communicate the results from my scientific efforts through video."
The impact of this work is that it demonstrates that auditory alerts on their own are not sufficient per se to warn a driver of critical events. This is an important finding, as current systems rely heavily on auditory alerts.