Exploring, developing and evaluating in-car HMI to support appropriate use of automated cars
Due to the COVID-19 crisis measures the PhD defence of Anika Boelhouwer will take place online.
The PhD defence can be followed by a live stream.
Anika Boelhouwer is a PhD student in the research group Transport Engineering and Management (TEM). Her supervisors are prof.dr. M.H. Martens and prof.dr.ir. M.C. van der Voort from the Faculty of Engineering Technology.
Commercial cars are increasingly equipped with automated functions to increase traffic safety and driver comfort. However, in order for these benefits to actually arise, it is crucial that the automation is used appropriately. This means that the automation should only be used in traffic situations and conditions that it was designed for (i.e. its Operational Design Domain or ODD). If the automation is used outside its ODD, traffic safety can be jeopardized. Alternatively, if it is not used within its ODD, potential benefits of the automation are lost. To be able to use the automation appropriately however, drivers need to have an accurate understanding of its functions, operation, capabilities and limitations.
This research first explores how drivers are currently supported in understanding and appropriately using automated car functions. This is achieved through nation-wide surveys among car buyers and car sellers, and a review of the HMI (Human Machine Interface) in car currently available partially automated cars. Based on these results, an adaptive Digital In-Car Tutor is proposed to support driver’s understanding and appropriate use of car automation. An observation study among driving instructors is conducted to gain inspiration for such a Digital In-Car Tutor and investigate tutoring strategies in a real-world and driving related context. Finally, the results of all studies are used to design and evaluate an adaptive Digital In-car Tutor prototype.
In conclusion, this thesis reveals that drivers are currently insufficiently supported in understanding and appropriately using partially automated cars. It is crucial that immediate and thorough measures are taken to avoid a negative impact on both traffic safety and the adoption of car automation. Our research further shows that a Digital In-car Tutor that is adaptive to the (complexity of the) driving situation positively affects appropriate automation use. While additional research is necessary with regards to the practical implementation, this research provides a solid base for the improvement of in-car driver support aimed at helping drivers to understand and appropriately use their car’s automation.