jzuern.github.io

Home ResearchProjects AboutRSS

Research

Research Statement

In my daily reseach I aim at bringing Robotics and Artificial Intelligence, especially Deep Learning, closer together. My goal is to enable autonomous robots to better understand their surroundings with the sensors they have and to allow them to more accurately and robustly navigate through those surroundings in precence of adversarial influences such as sensor noise, uncertainties, and occlusion. Self-supervised learning with multiple sensor modalities plays a particularly important role in this endeavour as it allows us to avoid expensive and time-consuming labeling of data which is necessary for standard supervised learning.

Projects

EUROPA2: European Robotic Pedestrian Assistant 2.0

OpenDR: Open Deep Learning Toolkit for Robotics

Publications

[2020] J Vertens, J Zürn, W Burgard:
HeatNet: Bridging the Day-Night Domain Gap in Semantic Segmentation with Thermal Images
ArXiv preprint | Website
[2019] J Zürn, W Burgard, A Valada:
Self-Supervised Visual Terrain Classification from Unsupervised Acoustic Feature Learning
ArXiv preprint | Video | Website
[2019] C Megnin, B Moradi, J Zürn, H Ossmer, M Gueltig, M Kohl:
Shape memory alloy based controllable multi-port microvalve
Publisher link
[2018] J Zürn:
Neural Networks for Steady-State Fluid Flow Prediction (M.Sc. Thesis)
PDF version
[2016] M Rottmann, J Zürn, U Arslan, K Klingel, O Dössel: Effects of fibrosis on the extracellular potential based on 3D reconstructions from histological sections of heart tissue
Publisher Link

Reviewer

  • IEEE Robotics and Automation Letters (RAL)
  • International Conference on Intelligent Robots and Systems (IROS)
  • International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)

Teaching

Theses supervised

I have supervised a number of theses of very bright students:

  • Y. Satyawan: Semantic Segmentation of Curb and Curb Cuts in Street Imagery, 2019, Bachelor’s Thesis

  • T. Krautschneider: Multimodal Object Tracking with Deep Learning, 2019/20, Bachelor’s Thesis

  • G. Stief: Glass Detection via Double Optical Flow, 2020, Bachelor’s Thesis

  • S. Al-Rawi: Sound Event Localizaton and Detection, 2020, Master’s Thesis

Lectures

I have participated as instructor or lecturer in the following courses: