Successful Doctorate at ITIV: Matthias Stammler Earns His Ph.D. with Magna cum laude

Dissertation develops a holistic approach to integrating machine learning and dynamic operating modes into safety-critical vehicle systems

The Institute for Information Processing Technology (ITIV) warmly congratulates Matthias Stammler on successfully completing his doctorate. The oral examination took place on October 6, 2026. The dissertation was awarded the distinction of magna cum laude.

In his dissertation, titled “Dynamic Multi-Mode Scheduling and Deployment with Early Exit Neural Network Integration,” Matthias Stammler explores novel approaches for the efficient and reliable deployment of AI applications on high-performance embedded platforms.

Abstract of the Dissertation

“The dissertation examines the challenges of modern, increasingly centralized vehicle architectures, which are characterized by software-defined vehicles, hardware abstraction layers, and the increased use of machine learning. To this end, a holistic scheduling approach is developed that combines classical periodic control tasks, machine learning-based applications, and dynamic operating modes within a secure time-triggered scheduling scheme. The approach combines a correct-by-construction proof for safe execution with anytime neural networks and a mode-change mechanism that enables flexible responses to errors, anomalies, or changes in system state. Evaluation using real-world use cases and synthetic task sets shows that the scheduler efficiently handles even complex scenarios and is therefore suitable for practical automotive systems.”

The work was conducted at ITIV in the research group led by Prof. Dr.-Ing. Jürgen Becker. Associate Prof. PhD Arvind Easwaran from Nanyang Technological University (NTU Singapore) served as co-examiner.

The dissertation builds on Matthias Stammler’s research interests. These include, among other things, the certification of machine learning components, the monitoring of safety-critical events in autonomous vehicles, and the development of graceful degradation strategies for embedded systems. The target of his research is to combine powerful AI methods with the high requirements for safety, predictability, and reliability of future vehicle systems.

Through his research, Matthias Stammler is making an important contribution to the development of safe and efficient scheduling and runtime concepts for the next generation of software-defined vehicle systems.

The ITIV extends its heartfelt congratulations on the successful completion of his doctorate and wishes him all the best in his future professional and personal endeavors.