Modelling perception failures in autonomous vehicles

As the automated vehicles (AVs) increasingly depend on data, policy makers need to be able to assess reliability of various AI-based AV subsystems. RDW (Dienst Wegverkeer) is responsible for developing assessment guidelines for type approval of future automated vehicles in the Netherlands, for which good understanding of AI and its technical and ethical aspects is essential. In your internship or MSc thesis project at RDW you will have an opportunity to impact policy making by developing AI prototypes and contributing to methodologies to assess autonomous vehicles.

Assignment

A failure in an autonomous system can have multiple effects on the system. Some common effects are wrongful detection or misclassification. These effects can be modelled without inducing the failures using some specific triggering conditions. This can support the assessment of robustness of the system. The idea of this research is to find out different effects modelling techniques and how can they be used in type approval by determining the robustness of the system.

Supervisors at TU Delft: Justin Dauwels (j.h.g.dauwels@tudelft.nl), Arkady Zgonnikov (a.zgonnikov@tudelft.nl), Luca Laurenti (l.laurenti@tudelft.nl)

Supervisor at RDW: Shubham Koyal (skoyal@rdw.nl)

Location: RDW office, Zoetermeer
Monthly stipend: 672.30 €

Contact

Last modified: 2024-06-29