Stage-oe-small.jpg

Daniel Bogdoll

Aus Aifbportal
Wechseln zu:Navigation, Suche
Daniel 8 Square.png



Hello, let me introduce myself :) I'm Daniel and I studied Computational Engineering Science at RWTH Aachen University from 2011 to 2019 with a focus on Machine Learning. In my theses, I worked on A*-based trajectory planning and LCSS-based route matching. In 2017, I completed a research stay in the Silicon Valley in the area of sensor data augmentation. Subsequently, in 2018, I founded the shared mobility startup SAYM.

Since November 2020, I am a research scientist at the FZI Research Center for Information Technology in the Technical Cognitive Systems (TKS) department and a PhD student at AIFB. My focus is on anomaly detection for autonomous vehicles. I am also deeply interested in the societal implications of autonomous vehicles in the (near) future.

Open Bachelor/Master Theses

  1. Benchmarking Anomaly Detection on Camera and Lidar Data with 3D Voxel Representation (PDF)
  2. Deep Learning World Models with Latent States for Autonomous Driving (PDF)
  3. Anomaly Detection with World Models for Autonomous Driving (PDF)
  4. Specialized Evaluation Metrics for Perception Tasks in Autonomous Driving (PDF)


Ongoing and completed theses

  1. Deep Learning Anomaly Detection with Model Contradictions for Autonomous Driving (PDF)
  2. 3D Voxel Benchmark for Anomaly Detection in Autonomous Driving (PDF)
  3. Reinforcement Learning for Controlled Traffic Rule Exceptions
  4. Sustainability Assessment of Autonomous Vehicles
  5. Anomaly Detection in the Latent Space of VAEs
  6. Anomaly Detection in 3D Space for Autonomous Driving
  7. Anomaly Detection in Lidar Data by Combining Supervised and Self-Supervised Methods
  8. Ontology-based Corner Case Scenario Simulation for Autonomous Driving


If you are interested in a student position in one of these fields, just send me an e-mail with your CV, your grades, and two sentences, why you are interested in the position. No cover letter necessary :)

Publications


Open Source


Let's connect









Forschungsgebiete
Deep Learning, Anomaly Detection