From Prediction to Planning With Goal Conditioned Lane Graph Traversals
Hallgarten, M., Stoll, M., & Zell, A. (2023). From Prediction to Planning With Goal Conditioned Lane Graph Traversals. arXiv preprint arXiv:2302.07753.
CV
Education
- PhD in Behaviour Planning for Autonomous Driving, University of Tuebingen, 2024 (expected)
Fields of Research: Robust Imitation Learning w.r.t. distributional shifts and generalization to realistic adversarial examples, interactive behaviour planning, integration of prediction and planning. - M.S. in Mechanical Engineering, Karlsruhe Institute of Technology, 2021
Fields of study: Machine Learning, Machine Vision, Automotive Engineering
Masters Thesis: “A Method for Early Evaluation of Timeseries Datasets without Prior Knowledge”
Final Grade 1.0 - Graduated with Distinction - B.S. in Mechanical Engineering, Karlsruhe Institue of Technology, 2019
Fields of study: Machine Learning, Data Science, Data Analytics
Bachelors Thesis: “Synthetic Training Data Generation with Generative Adversarial Networks”
Final Grade 1.3 - Awarded for being among the best four graduates of the year
Publications
Stay on Track: A Frenet Wrapper to Overcome Off-road Trajectories in Vehicle Motion Prediction
Hallgarten, M., Kisa, I.,Stoll, M., & Zell, A. (2023). Stay on Track: A Frenet Wrapper to Overcome Off-road Trajectories in Vehicle Motion Prediction. arXiv preprint arXiv:arXiv:2306.00605.
Parting with Misconceptions about Learning-based Vehicle Motion Planning
Dauner, D., Hallgarten, M., Geiger, A. & Chitta, K. (2023). Parting with Misconceptions about Learning-based Vehicle Motion Planning. arXiv preprint arXiv:arXiv:2306.07962.
Rethinking Integration of Prediction and Planning in Deep Learning-Based Automated Driving Systems: A Review
Hagedorn, S., Hallgarten, M., Stoll, M. & Condurache, A. (2023). Rethinking Integration of Prediction and Planning in Deep Learning-Based Automated Driving Systems: A Review. arXiv preprint arXiv:2308.05731.
Conditional Unscented Autoencoders for Trajectory Prediction
Janjoš, F., Hallgarten, M., Knittel, A., Dolgov, M., Zell, A., & Zöllner, J. M. (2023). Conditional Unscented Autoencoders for Trajectory Prediction. arXiv preprint arXiv:2310.19944.
Experience
- Summer 2018: Internship at EM-Motive GmbH
- Intern in the development of methods for reliability engineering in development of electric drives
- Fall 2019: Student Assistant at KIT
- Supervised students in the development of an intelligent system for the robot control using C++
- Summer 2021: Masters Thesis at Robert Bosch GmbH
- Master’s Thesis on developing a method for early, automated, and fast evaluation of timeseries datasets with regard to their informational value
Talks
Multimodal Prediction and Planning for Autonomous Driving
Talk at CS Group Tuebingen, Zoom
From Prediction to Planning with Goal Conditioned Lane Graph Traversals
Talk at CS Group Tuebingen, Zoom
1st Place in the 2023 nuPlan Planning Challenge
Talk at CVPR Workshop End-to-End Autonomous Driving: Emerging Tasks and Challenges, Vancouver
Teaching
Engagements
student group linkit at KIT (2021 - 2022)
- led the student group of >100 members as a chairman
- mentored the “tech research group” reading club
Hallgarten Media Engineering GbR
- founded a web design company
Interests
Teaching
- taking over teaching duties every semester
- committed to creating an engaging and supportive learning environment
Leadership
- constantly working on improving my skills in this area
- actively seeking out mentors to guide me
- training my skills when supervising students