My research interests comprise:- Optimal Control- Reinforcement Learning- Uncertainty Quantification

The student initative "Stud|Lab" helps students with their MATLAB and Simulink projects by offering regular MATLAB consultation hours for students. Moreover, the initative organizes workshops where students have the opportunity to broaden their MATLAB skills in a relaxed atmosphere.

Responsible for the implementation of a machine learning pipeline (from data labelling and storage to training & testing on LRZ computation cloud) for condition monitoring of gear flanks using image recognition. (Primarily using CNN, R-CNN & Mask R-CNN architectures) - Software: Python (Tensorflow, Keras)

Thesis:"Non-linear Dynamic Inversion Flight Control utilizing Control Allocation Methods for Performance Optimization"(graded with 1.0)Design & implementation of a nonlinear flight control algorithm using- non-linear adaptive control (NDI)- real-time Control Allocation methodsfor a high-performance aircraft.Abstract:Throughout this thesis, the optimal use of control redundancy via dynamic Control Allocationmethods is demonstrated. To this end, a modular flight control algorithm for theADMIRE aircraft model, consisting of non-linear motion control laws and on-line ControlAllocation methods, is designed. Considering the highly non-linear aerodynamiccharacteristics of the delta-canard aircraft model, Non-linear Dynamic Inversion baselinecontrol is chosen for the design of the high-level control laws. Herein, actuatordynamics are accounted for via Pseudo Control Hedging. Once the desired controleffort is specified throughout the non-linear control laws, Control Allocation methodsaddress its optimal distribution among the set of available control effectors. Emphasizeis put on the integration of secondary, flight performance optimizing, Control Allocationobjectives. Throughout multiple test cases, beneficial characteristics of this Control Allocationenhanced flight control system are demonstrated. These include the optimaluse of control redundancy, maximized control potential and failure robustness.

Responsible for the construction and operation of a process engineering plant within an automated production environment- Hardware installation (Installation of sensors & actors)- Connection to the bus system / IDLE: Twin-CAT 3- Anomaly detection by using cyclic data analysis