Ponuka Eindhoven University of Technology

Názov ponuky na hosťovanie:

Deep Learning Perception for Autonomous Driving

Študijný odbor/vedná disciplína:

Umelá inteligencia (Artificial intelligence), Počítačové videnie (Computer vision), Hlboké učenie (Deep learning)

Mesto sídla inštitúcie, na ktorej by sa pobyt mohol uskutočniť:

Eindhoven

Krajina sídla inštitúcie, na ktorej by sa pobyt mohol uskutočniť:

Holandsko

Komu je ponuka určená:

·         Študent/ka doktorandského štúdia

·         Postdoktorand/ka (do 10 rokov po ukončení PhD štúdia) 

Meno, priezvisko a pracovné zaradenie osoby, ktorá ponúka hosťovanie:

Pavol Jancura, Assistant Professor

Vedúci/ vedúca hosťujúcej výskumnej skupiny:

Gijs Dubbelman, Associate Professor

Názov a adresa pracoviska, na ktorom by sa pobyt mohol uskutočniť:

Mobile Perception Systems lab

Eindhoven University of Technology

De Groene Loper 19, 5612 AZ Eindhoven, Holandsko

Stručná charakteristika pracoviska/výskumnej skupiny:

The Mobile Perception Systems Lab (MPS) researches methods in Artificial Intelligence that allow mobile autonomous systems to perceive their environment. Our long-term goal is to realize AI that can anticipate on future events in highly dynamic and complex environments. We always validate our AI methods ‘in the loop’, meaning in the context of challenging real-world applications, mainly from the industry domains of automotive, transportation, and logistics. Key research areas are computer vision, pattern recognition, robotics, and sensor fusion. Important application domain of MPS are automotive and transportation.

MPS is part of the Signal Processing Systems group and we work closely with the Embedded Systems group, the Dynamics and Control group, the Control Systems Technology group, and the TU/e-wide Strategic Area for Smart Mobility.

The lab is headed by prof. Gijs Dubbelman. His areas of expertise include computer vision and multiple-view geometry and robotics and he has been working on topics such as large-scale visual-odometry, simultaneous localization and mapping, bundle adjustment and on-line camera re-calibration. Gijs also has a background in computer graphics, software engineering and project management. He has designed and developed state-of-the-art computer vision algorithms for obstacle detection, ego-motion estimation, and simultaneous localization and mapping. He contributed the COP-SLAM algorithm for real-time embedded visual-SLAM to the scientific open-source project OpenSLAM.

Zameranie výskumu, ktorý by bolo možné počas hosťovania realizovať:

·         Computer vision for autonomous driving

·         Deep-learning methods for vehicle perception tasks (e.g. collision risk prediction)

·         Domain generalization for rarely occurring scenarios

·         Neural architecture search for automotive 4D imaging radar

·         Explainable deep data-driven AI for autonomous driving

Čo by mali zaslať záujemcovia o realizáciu pobytu na Vašom pracovisku:

·         životopis

·         motivačný list (jedna strana A4)

·         odporúčací list od vedúceho akademického pracovníka alebo školiteľa

Kontaktný e-mail:

p.jancura@tue.nl

Termín pre vyjadrenie záujmu:

·         30.04.2024

·         31.10.2024

·         30.04.2025

·         31.10.2025

·         30.04.2026

·         31.10.2026 

Webové odkazy:

·         Mobile Perception Systems Lab | tue.nl

·         Gijs Dubbelman | tue.nl

·         Pavol Jancura | tue.nl

·         Pavol Jancura | LinkedIn

·         Pavol Jancura | osobna stranka