Technical University of Munich
Institute of Informatics
85748 Garching b. München
Place of employment
Informatics 6 - Associate Professorship of Cyber Physical Systems (Prof. Althoff)
85748 Garching b. München
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 state representation learning and behavior planning. 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).
- [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 Generative Models for Road Network Synthesis
- Salih Can Yurtkulu (MA): "Deep Generative Models for Road Network Synthesis"
- [MA] Deep Multi-Step Planning for Autonomous Driving
- Sijia Liu (MA): "Multi-step Trajectory Planning for Autonomous Vehicles using Recurrent Neural Networks"
- 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"
Exercise Lectures: Techniques in Artificial Intelligence
- WiSe 21/22: 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
- Meyer E, Heiberg A, Rasheed A, and San O: COLREG-Compliant Collision Avoidance for Unmanned Surface Vehicles using Deep Reinforcement Learning, 2020
- Meyer E, Robinson H, Rasheed A, and San O: Taming an Autonomous Surface Vehicle for Path Following and Collision Avoidance using Deep Reinforcement Learning, 2020