Open Topics for Master Theses
If you are interested in perfoming a smaller research project at MSV (Bachelor Thesis, Research Internship, etc.), please contact Professor Utschick or one of the group members. It will either be possible to work on a limited aspect of one of the following topics, or we will look for another current research question whose complexity fits to the intended type of research project.
Open Topics for Master Theses
Robust Design of an Automatic Emergency Braking System for Increasing the Vehicular Safety in the Presence of Multiple Sensor Measurement Errors
Vehicular safety functions that intervene in dangerous situations the driver is not able to control like automatic emergency braking (AEB) help to reduce the number as well as the severity of collisions and thus increase vehicular safety. A variety of sensors are used for the perception of the environment of a car. Based on the measurements of the sensors, vehicular safety functions have to interpret the driving situation and trigger appropriate actions in order to defuse critical driving situations. Unavoidable measurement errors made by the sensors can have a severe impact on the interpretation of the driving situation and thus on the performance of the whole system . Therefore, designing functions and sensors such that the performance is robust to measurement errors is crucial. Probabilistic modelling of the uncertainty caused by measurement errors allows to determine the parameters of vehicular safety functions and to derive sensor accuracy requirements such that the desired performance is achieved .
The goal of this thesis is to study the robust design of an AEB system in the presence of multiple sensor measurement errors. This design problem of determining the function and sensor parameters should be formulated as an optimization problem, and investigated both analytically and numerically. If it turns out that an analytical solution of the optimization problem in closed form is impossible, it can be solved numerically using MATLAB.
 T. Dirndorfer, M. Botsch and A. Knoll, "Model-based analysis of sensor-noise in predictive passive safety algorithms," Proceedings of the 22nd Enhanced Safety of Vehicles Conference, Washington, D.C., June 13-16, 2011
 J. E. Stellet, J. Schumacher, W. Branz and J. M. Zöllner, "Uncertainty propagation in criticality measures for driver assistance," 2015 IEEE Intelligent Vehicles Symposium (IV), Seoul, June 28 - July 1, 2015, pp. 1187-1194.
- profound knowledge in stochastics
- basic knowledge in (convex) optimization
- knowledge in vehicular safety is helpful, but can also be acquired while working on the topic
Deep Learning for Bayesian Channel Estimation in Millimeter Wave Communication Systems
Channel estimation based on structural prior information is a crucial topic in future millimeter wave communication systems. This is in contrast to current systems where channel estimation is model-free because of rich scattering. Of particular interest are conditionally normal channel models. In these models, the channel vector is assumed to be Gaussian distributed with a covariance matrix that depends on a hidden variable, which cannot be observed. The channel matrix is assumed to be approximately low rank. Thus, the coefficients of the channel vector have a very strong correlation structure and this can be exploited to improve channel estimation.
Recently, we proposed a neural network based approach that approximates the minimum mean squared error (MMSE) estimator of the channel vector . This estimator was designed as a proof-of-concept for a very simple flat-fading uplink scenario. In more realistic scenarios, not all receive antennas are equipped with their own analog-digital converters. Instead, an analog network of phase shifters and combiners is employed to reduce power consumption. The goal of this thesis is to derive the MMSE estimator for this particular model and design an appropriate neural network that can be used as an efficient alternative to the MMSE estimator.
 D. Neumann, T. Wiese, and W. Utschick, "Learning the MMSE Channel Estimator," IEEE Trans. Signal Processing, vol. 66, no. 11, pp. 2905-2917, June 1, 2018.
- familiarity with numerical linear algebra, statistical signal processing, and Bayesian estimation
- some programming experience