Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
Over-reliance on the automation of transportation systems is understood to be the cause of new types of accidents. In this paper, the automated driving system is augmented with control methods enabling driver intervention without its full deactivation. The proposed control relies on three functions: interaction, arbitration, and inclusion. Following the description of the state-of-the-art and limitations of the available technology, the proposed control framework is introduced to provide continuous driving assistance or override-free operation. It is believed that this contributes to more intuitive steering and consequently improved trust building. Examples of applications for the development of advanced driver assistance system functions are then presented and discussed, supported by experimental data.
Hannes Bleuler, Jürg Alexander Schiffmann, Tomohiro Nakade, Robert Fuchs