University of Perugia
Paper & code under review!
An audio-visual simulator for urban scenarios
A simulator was developed to render what a vehicle sees and what it hears in urban scenes.
For Italian speakers, or AI Italian speakers
Katérina Vinciguerra
I am a PhD candidate at the Department of Engineering and Architecture, University of Parma, Italy, supervised by Prof. Letizia Marchegiani. My research focuses on teaching machines, such as autonomous vehicles, to perceive (audio, video, etc.) and understand the world in order to plan and navigate through it.
I previously worked for three years as a data scientist at Schneider Electric, then at KPMG, after graduating with my master's degrees from Grenoble Ecole de Management and Grenoble INP (Ensimag).
Always happy to do research on topics of interest, feel free to reach out by email or on LinkedIn!
Collaborations
Fraunhofer IDMT‑HSA
& CARIAD
Data & code will be released soon!
Audio-visual driving data, from clear skies to snow
A research collaboration with Fraunhofer IDMT-HSA, and with CARIAD for the use of vehicles, to collect audio-visual data, with GPS and odometry, in a controlled environment and under adverse weather conditions.
- Sunny
- Cloudy
- Rainy
- Snowy
For a first view on the project
- Predictive audio representations for early detection and tracking of hidden dynamic objects arXiv
- Learning to Hear Motion Before Naming It ICML 2026 Workshop on Machine Learning for Audio — non-archival
NXP
The data are being processed, let's talk another day!
Long-tail scenarios, with every sensor on board
A research collaboration with NXP to collect long-tail driving scenarios with a full multimodal sensor suite.
Competitions of 2026
2nd&3rd
ECCV 2026 Wearable AI Grand Challenge
Second place in the EgoConv Small track and third place in the EgoConv Large track, with Brownstafford Abraham and Everyday Intelligence.
Code & technical report will be released soon!
1st
2026 IEEE PhD3M Competition
First place.