Curriculum Vitae

Roland Stolz joined the Cyber-Physical Systems Group as a PhD candidate under the supervision of Prof. Dr.-Ing. Matthias Althoff in June 2023. Previously, he studied Medical Engineering at the Friedrich-Alexander University Erlangen-Nuremberg. in 2022 he visited the Universtiy of Washington in Seattle, to perform research for his Master's thesis about Representation Learning on Sports Movement Data.

His current research focuses on safeguarding reinforcement learning with action-constrained RL using formal methods and set-based predictions - primarily in the context of autonomous driving. Furthermore, he is the lead developer of the data warehouse for the research vehicle EDGAR.

He is a member of the DFG-funded Collaborative Research Center CRC/SFB 1608 Convide.

Offered Thesis Topics

I am always looking for self-motivated students who are interested in writing a thesis related to my area of research. If you are considering one of the currently offered topics or want to discuss your own research idea, please get in touch via email including your CV, transcript of records, and a brief statement of your motivation.

Currently available

[MT/BT] Set-based reinforcment learning - implementation and evaluation

Ongoing

[MT] Provably Safe RL with Continuous Action Masking for Autonomous Vehicles

Finished

[MT] Anomaly Detection for The Violation of Traffic Rules using Representation Learning

[MT] VLM-based tagging of ride data from the research vehicle EDGAR

[BT] Benchmarking Action Masking on the Extended Seeker Reach-Avoid Environment

[MT] Action Masking for Deterministic Policy Gradient Algorithms

Teaching

• Practical Course – Motion Planning for Autonomous Vehicles (MPFAV)

  • WiSe 24/25 - EDGAR Data Warehouse
  • WiSe 24/25 - Benchmarking Provably Safe Reinforcement Learning (co-supervised with Jakob Thumm)
  • SoSe 24 - Conformance Checking of SONIA on the Mona Dataset
  • SoSe 24 - EDGAR Data Warehouse (co-supervised with Sebastian Maierhofer)
  • WiSe 23/24 - Conformance Checking of SONIA on the Mona Dataset
  • WiSe 23/24 - EDGAR Data Warehouse (co-supervised with Sebastian Maierhofer)

• Seminar – Cyber-Physical Systems

  • SoSe 24 - Efficient Shortest Path Computation and Race Trajectory Optimization

• Lecture – Fundamentals of AI

  • WiSe 23/24 - Programming Exercises