Job Description

A PhD research position is available at the KU Leuven, Electrical Engineering Department (ESAT), division Processing of Speech and Images (PSI), within the research group EAVISE on the design of acoustic sensing algorithms for autonomous vehicles.

In scene understanding for autonomous vehicles, a representation of the traffic scene is produced using a multi-modal combination of various sensors. Currently, this is largely based on line-of-sight (LoS) sensing using cameras, RADAR, and LiDAR. In addition to these modalities, the use of audible sound has the potential to further extend and enhance the robustness of scene understanding for the following reasons: Firstly, sound bears rich information on the traffic scene (propulsion noise of other vehicles, active vehicle alert systems, tire noise, emergency sirens, …) and secondly, its propagation is not limited to the LoS. Until now, however, the scientific literature on acoustic sensing in autonomous driving is still limited and commercial solutions do not yet exist. The objective of this research project therefore is to develop multi-channel acoustic sensing algorithms for autonomous driving that can track characteristics of other vehicles such as their location under challenging acoustic conditions involving ego-noise and the Doppler effect. Further, fusion with LoS sensing will be explored.

The research will be carried out in an international team at EAVISE. The standard duration of a PhD research project at KU Leuven is 4 years.

Follow @eurasip