Available Masters' Theses

The goal of this thesis is to develop an interactive front-end tool capable of visualizing the effects of traffic policies. At its core, the tool leverages a Graph Neural Network (GNN)-based surrogate model that enables rapid simulations. The aim is to provide decision-makers and citizens with an intuitive platform to test various traffic measures in different urban areas and scales. The impacts of these measures should be displayed accurately and in a visually appealing way. Tasks include selecting a suitable framework (e.g., React, Dash, or Streamlit), seamless integration of the surrogate model, and developing user-friendly visualizations. The tool should be fully operational and ready for practical use. Strong programming skills are a prerequisite for this thesis.

Aligning with micromobility promotion policies in many European cities, ensuring the safety of cyclists has become an increasingly important topic. Despite growing attention, objective investigations of cyclist behavior are still under development and remain limited in scope. This thesis aims to explore attention patterns during cycling by analyzing eye-tracking data. Measures such as fixation locations and durations, blink rates, and head movements will be compared between different conditions: riding a bicycle and sitting at the roadside as a passive observer. Furthermore, attention patterns will be contrasted between distinct environments, including busy traffic roads and calm park streets, in order to assess the influence of environmental context. The comparison will provide insights into how the dynamic task of cycling and the surrounding environments influence visual attention, situational awareness, and cognitive load. The findings are expected to enhance the understanding of cyclist behavior in real traffic conditions. The results can support the design of safer cycling infrastructure and inform policy strategies that foster micromobility-friendly urban development.

This thesis focuses on recognizing the intentions of extra vulnerable road users (eVRU), specifically wheelchair users. The analysis relies on camera and Lidar data, utilizing both conventional algorithms and deep learning approaches.

This thesis focuses on recognizing the intentions of vulnerable road users (VRU), specifically pedestrians and cyclists. The analysis relies on camera and Lidar data, utilizing both conventional algorithms and deep learning approaches.

In the bicycle simulator, the choice of the ridden path and the speed can be decoupled. In this study, we investigate the ridden path and focal points in driving simulator studies in order to use them for microscopic modeling of cyclists.

This thesis focuses on recognizing the intentions of cyclists at bus stops. The analysis relies on camera data, which is already available from a previous bike simulator study. The goal is to find out the importance or relation between body gestures or movements to the final maneuver decision, utilizing both conventional algorithms and deep learning approaches.

This thesis focuses on analyzing the cyclists behavior at bus stops. The analysis relies on both trajectory and the camera data of the cyclitsts, which is already available from a previous bike simulator study. The goal is to find out the correlation between trajectory and body gestures and body movements of cyclists.

This study investigates how different levels of detail (LOD) in 3D city models affect user perception in a virtual reality micromobility simulator. Higher LODs can create more realistic urban environments but also require significantly more data. Experiments conducted in the "CAVE" simulator will be compared with real-world cycling data to identify the most effective resolution that balances data efficiency with perceived realism. Both subjective user feedback and objective behavioral metrics should be addressed.

The main goal of this thesis is to design and conduct a test filed study involving the interaction between VRU and shuttle bus. Data is collected by this study, followed by the development and evaluation of a system that uses both camera data from the vehicle perspective and LiDAR data from an infrastructure perspective to detect, track, and predict the intentions of VRU

Induction loops provide information about traffic flow and occupancy time in urban areas, and in the case of double induction loops, also about vehicle type and speed. This information is available in Munich. However, it is known that the data collected is prone to errors. By collecting trajectory data using a drone at several locations where induction loops are also installed, the error in this induction loop data is to be estimated.

The goal of this project is to integrate a 3D model of a bus in a Unity simulation showing a digital twin of the TUM area, with realistic on-boarding and off-boarding of the passengers. Experience in Unity and C# programming are recommended.

The aim of the thesis is to study the routing of a fleet of vehicles (with big batteries) that can charge other on-demand ride-hailing or ride-pooling vehicles (with smaller batteries). The thesis will first research the available methods for the routing of on-demand charging vehicles, develop a new routing scheme and then evaluate their efficiency in an agent-based simulation framework, called FleetPy.

The aim of the thesis is to study the routing of a fleet of vehicles (with big batteries) that can charge other privately owned electric vehicles (with smaller batteries). The thesis will first research the available methods for the routing of on-demand charging vehicles, develop a new routing scheme and then evaluate their efficiency in an agent-based simulation framework, called FleetPy.

In automated ride-pooling services, trip requests are dynamically processed by a central optimizer to assign new routes to fleet vehicles and serve customer requests. Once a vehicle has completed the route, however, the question arises as to where it should wait for new assignments. Various strategies are conceivable: The search for the next parking lot, or a return to the depot. The aim of the thesis is to work out different strategies and to implement and evaluate them in a simulation. Within the work, the strategies are to be implemented in a framework developed at the chair, consisting of FleetPy and SUMO, and evaluated for operational and traffic effects.

The goal of the thesis is to analyze how different service designs, network structures and demand patterns, which relate to transfers between line-based public transport and a ridepooling service, affect the performance indicators of a ridepooling fleet. The chair’s fleet simulator FleetPy can be used as basis to model a ridepooling service. A small programming extension is necessary to model it as access and egress service for public transport.

Many studies of on-demand mobility services assume constant travel times as their focus is on operational algorithms rather than traffic dynamics. FleetPy is a modular framework to simulate on-demand services and by default also uses deterministic travel times. The goal of this thesis is to adapt the network model within FleetPy to be dynamic and efficient; more specifically, a dynamic MFD-based model will be implemented in this thesis. Thereafter, the thesis will analyze fleet performance indicators for both deterministic and dynamic scenarios, as well as study the impacts of traffic congestion caused by ODM on mode choice.

In ride-pooling services, customers book a trip with the provider via an app and the trips are dynamically integrated into the route planning of fleet vehicles. No-shows of a booked trip can result in costs for the operator as well as for other customers. The goal of this work is to integrate no-shows into the existing simulation environment "FleetPy" and to simulate the effects on the overall system.

Research question: how to choose a right map matching algorithm balancing accuracy and computational time? By comparing the performances of different map-matching algorithms, the student is expected to find a balance in the accuracy of map-matching of GPS trajectory data to network graph for a dynamic and static use case within a reasonable computational time.

This thesis explores integrating autonomous vehicle navigation through urban construction sites into existing path planning algorithms, focusing on adapting for safe passage. The evaluation of the adapted planning behavior is conducted and assessed within a simulator, forming a vital part of the research.

This thesis focuses on integrating dynamic stops into the route planning of automated shuttle buses, aiming to efficiently adapt existing planning systems for urban transport networks. The evaluation of the planning behavior is conducted and assessed in a simulator, constituting a central part of the study.

This thesis explores Facial Emotion Recognition through Convolutional Neural Networks, aiming to advance human-computer interaction by accurately identifying human emotions from facial expressions.

This project focuses on integrating e-scooter simulation within Unity and VR environments, employing an actual electric scooter for immersive and realistic user experiences. It aims to bridge the gap between virtual simulations and real-world scooter maneuvering, enhancing training and entertainment applications.

This thesis explores the use of AI techniques to convert traffic safety rules from human language into machine-readable formats, enhancing the ability of autonomous vehicles to understand and adhere to safety guidelines. By employing natural language processing (NLP) and formal logic-based models, this work aims to bridge the gap between human-expressed regulations and machine interpretation, facilitating precise adherence to complex traffic rules. This formalization process is crucial for enabling autonomous systems to exhibit compliant and predictable behaviors across varying traffic scenarios, contributing to safer and more reliable transportation systems.

In this thesis motion planners, mainly used in the domain of automated driving, should be applied to cyclists and validated using real-world data

This thesis evaluates the influence of autonomous vehicles in a variety of traffic scenarios, such as highways, intersections, and roundabouts. Using SumoWare, which integrates SUMO and Autoware, the effect of a full autonomous driving stack on traffic flow and efficiency is analyzed under different traffic conditions.

This thesis explores how users respond to changes in traffic system dynamics using Elastic Dynamic Traffic Assignment. It investigates the potential for improving system resilience through demand-oriented policies. By analysing user sensitivity and demand shifts under various scenarios.

This thesis investigates urban traffic flow dynamics during large-scale evacuations, aiming to design effective evacuation plans that minimise congestion, reduce evacuation time, and improve overall system performance under emergency conditions.

Disruptions and delays impacting the planned schedules of public transportation services are common and typically met with disposition strategies from the operator. The dynamic modeling of these disruptions with simulation softwares is however limited. An overview of possible disruptions and disposition strategies is to be carried out. GTFS files reflecting the disruptions and strategies are to be created and simulated (using for e.g. MATSim, Fleetpy). The thesis seeks to evaluate the behavior of different disposition strategies under a determined disruption scenario.

This master's thesis investigates the impact of public transport (PT) strikes on individual mobility behavior using the Mobilität.Leben GPS tracking dataset. The student will analyze short- and long-term behavioral changes due to PT disruptions, applying statistical and econometric methods. Proficiency in R or Python and experience with data analysis are required.

Public transportation reliability is often undermined by delays not reflected in static GTFS schedules. This thesis proposes a framework to address this gap by accurately predicting PT delays. The primary objective is to develop a generalizable methodology for collecting historic PT delays. This process will populate a comprehensive historical delay database. Using this database, the research will then develop and evaluate predictive models. The study will explore various techniques, potentially including statistical analysis, heuristic rules, and machine learning algorithms.

With the introduction of Connected Autonomous Vehicles (CAVs), there is a growing interest in Lane-Free Traffic (LFT), where CAVs drive without managed lanes. The movement of CAVs in LFT is controlled by control algorithms that coordinate their movements. However, the performance of this controller can be severely affected by the presence of human drivers. Therefore, this thesis develops a control strategy for CAVs capable of dealing with mixed traffic where humans and CAVs share the same road without degrading the performance of CAVs in LFT. The simulation will be conducted in a customized SUMO for LFT and requires some basic programming skills in C++.

This thesis explores the implementation of a two-directional roundabout in SUMO with adaptive lane configurations for the two directions based on real-time traffic demand. The student will develop a dynamic lane allocation system, fine-tune its parameters, and analyze its potential for different roundabout configurations.

This thesis aims to explore methods for dynamically assessing link criticality based on network demand and topology. It further investigates the optimal sequence of link repairs to minimise total recovery time and enhance system throughput following a disruptive event.