Curriculum Vitae

Eivind Meyer joined the Cyber-Physical Systems Group in 2021 as a research assistant and Ph.D. student under the supervision of Prof. Dr.-Ing. Matthias Althoff. Previously, he received his Master's degree in Cybernetics and Robotics from the Norwegian University of Science and Technology with the thesis "On Course Towards Model-Free Guidance" about reinforcement learning-based autonomous vessel guidance.

His research at TUM revolves around deep learning-based autonomous driving, with a special focus on graph-based state representations.

Offered Thesis Topics

My research is particularly focused on the adoption of graph neural networks for autonoumous driving. Within this domain, there are multiple candidate topics that I can offer to interested master or bachelor students. In general, feel free to contact me by email if you are interested in any of the currently available topics or have specific ideas for potential research directions yourself (please attach your grades and a resume).

All the topics would leverage CommonRoad-Geometric, our Python framework for enabling GNN-based autonomous driving research (for which we also offer HiWi positions to interested students).  

The topics listed below are generally available; however, the proposals might be outdated - please reach out to clarify the research direction.

• [MA] Graph Neural Networks for Deep Behavior Prediction in Traffic Scenes
• [BA/MA] Encoding the Future: Deep Representations for Traffic using Graph Neural Networks
• [BA/MA] Learning Isometric Embeddings of Road Networks using Multidimensional Scaling
• [MA] Deep Multi-Step Planning for Autonomous Driving
• [MA] Deep Generative Models for Road Network Synthesis

Thesis students:

• Maurice Brenner (BA): "Learning Isometric Embeddings of Road Networks using Multidimensional Scaling"'
• Max Schickert (MA): "Predictive Representations for Traffic Scenes using Graph Neural Networks"
• Bilal Musani (MA): "Learning Reconstructive Representations of Highway Traffic Scenes using Graph-based Autoencoders"
• Sijia Liu (MA): "Multi-step Trajectory Planning for Autonomous Vehicles using Recurrent Neural Networks"
• Salih Can Yurtkulu (MA): "Deep Generative Models for Road Network Synthesis"
• Jan Jukl (MA): "Multi-modal Interpretable Trajectory Prediction and Planning for Autonomous Driving using Graph Neural Networks"
• Yevhenii Patrushev (MA): "Encoding Road Occupancy in Autonomous Driving: A GNN-Based Approach"
• Roman Canals (MA): "Application of Predictive Representations of Traffic Scenes for Autonomous Driving"

Teaching

• Exercise Lectures: Techniques in Artificial Intelligence

  • WiSe 21/22: Rational Decisions, Learning
  • WiSe 22/23: Rational Decisions, Learning

• Practical course: Motion planning for autonomous vehicles

  • WiSe 21/22: Graph Representations for Predictive Modelling in Traffic Scenes (co-supervised with Luis Gressenbuch)
  • WiSe 21/22: Developing an Autonomous Vessel Simulation (co-supervised with Hanna Krasowski)
  • SoSe 22: Graph Neural Network Reinforcement Learning for Autonomous Driving (co-supervised with Luis Gressenbuch)
  • SoSe 22: A Principled Approach to Post-Collection Cleaning of Traffic Datasets (co-supervised with Luis Gressenbuch)
  • SoSe 22: Developing a Visualization Tool for Set-based Prediction  (co-supervised with Josefine Gaßner)

• Seminar: Cyber-Physical Systems

  • WiSe 21/22: Distance-Preserving Embeddings of Lanelet Networks
  • SoSe 22: Advanced Topics in Deep Reinforcement Learning for Autonomous Driving: Inverse RL, Hierarchical RL, Sequential RL
  • WiSe 22/23: Graph Neural Networks for Motion Planning, Graph Neural Networks for Traffic Prediction