PhD Research on Multi-Channel Acoustic Sensing for Autonomous Vehicles

The research group EAVISE is a multidisciplinary research group, based on Campus De Nayer Sint-Katelijne-Waver and belongs to the research divisions PSI (Processing of Speech and Images) of the Electrical Engineering Department (ESAT) and DTAI (Declarative Languages and Artificial Intelligence) of the Computer Science Department. The EAVISE group conducts research in demand-driven applications of state-of-the-art algorithms for artificial intelligence, computer vision, and machine listening in industry-specific applications. To meet stringent requirements on execution speed, energy footprint, cost and price requirements, the developed algorithms are often implemented and optimized on embedded systems. Application domains include industrial automation, product inspection, traffic monitoring, e-health, agriculture, eye-tracking, microscopic image processing, camera surveillance, and cinematography. The EAVISE research group can build upon a solid research infrastructure, an extensive international network, connections with companies and non-profit organizations, and a supportive work environment.
Website unit

Project

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.

Profile

• Candidates must hold a Master’s degree in electrical or computer engineering (or equivalent), have a solid mathematical background (e.g. in matrix algebra), and have taken specialized courses in some of the following disciplines: digital signal processing, audio signal processing, machine learning, and/or machine listening.
• Research experience (e.g. through Master thesis work or research internships) in audio signal processing or machine learning is considered a strong asset.
• Programming experience in Python or MATLAB is required, and experience with other programming languages (C/C++...) is considered beneficial.
• Excellent proficiency in the English language is required, as well as good communication skills, both oral and written.

Offer

• A high-level and exciting international research environment.
• A PhD title from one of Europe's top universities (after approximately 4 years of successful research).
• A thorough scientific education in the frame of a doctoral training program.
• A competitive salary or tax-free PhD grant.
• The possibility to participate in local as well as international courses, workshops and conferences.
• A one-year position with the possibility of extension for a second, third, and fourth year.

Interested?

For more information please contact Prof. dr. Thomas Dietzen, tel.: +32 16 37 67 47, mail: thomas.dietzen@kuleuven.be.

KU Leuven strives for an inclusive, respectful and socially safe environment. We embrace diversity among individuals and groups as an asset. Open dialogue and differences in perspective are essential for an ambitious research and educational environment. In our commitment to equal opportunity, we recognize the consequences of historical inequalities. We do not accept any form of discrimination based on, but not limited to, gender identity and expression, sexual orientation, age, ethnic or national background, skin colour, religious and philosophical diversity, neurodivergence, employment disability, health, or socioeconomic status. For questions about accessibility or support offered, we are happy to assist you at this email address.