Thesis Topics

Filter:
BSc MSc TDK

Adversarial attack against a Smart City

Supervisor: Balázs Varga

Devise small scale cyberattacks (e.g., GPS spoofing, manipulating traffic lights, injecting phantom vehicles to a navigation app, etc.) that creates the most chaos to the traffic flow on the network. Model their impact on a calibrated traffic simulator. 

BSc MSc

Managing Highway Congestion Caused by Reduced Capacity Using Vehicular Communication

Supervisor: Tamás Ormándi

A sudden reduction in a highway’s cross-section (such as a dropping lane or a lane closure) creates a traffic shockwave and leads to congestion. To counteract this, the goal is to develop an algorithm based on vehicular communication that mitigates this effect.

MSc TDK

Co-simulation of road traffic and computational fluid dynamics

Supervisor: Balázs Varga

Define use cases where the co-simulation of traffic (or vehicle dynamics) and CFD has added value (e.g., road tunnel ventilation, active aero elements, impact of tailpipe emissions on vulnerable road users using species transport simulation) and realize them. The co-simulation framework is available.

BSc MSc

Delay-Aware Road Safety Metric: Deviation Quantification and Compensation Based on Multi-Level Timestamps

Supervisor: Xinzhe Zhang

This research quantifies the state deviation between a vehicle’s real and perceived position caused by V2X communication latency using a multi-level timestamping architecture. The student will develop a compensation algorithm, such as a Kalman filter or predictive model, to reconstruct real-time safety metrics (e.g., TTC) from delayed data packets. The final solution will be validated through a SUMO and network co-simulation to demonstrate enhanced collision avoidance under varying network loads.

BSc MSc TDK

Edge AI implementation and optimization on microcontrollers

Supervisor: Tamás Wágner

The implementation of Edge AI and TinyML on resource-constrained embedded systems is a critical step toward sustainable computing. This project focuses on deploying machine learning models on low-power hardware to reduce cloud dependency, latency, and overall energy consumption. The student will select, hardware-optimize (e.g., via quantization or pruning), and deploy neural networks directly onto a microcontroller platform. A core requirement of the research is the critical evaluation of the necessary trade-offs between model accuracy, execution time, and power efficiency to achieve a viable and sustainable local AI solution.

BSc MSc TDK

Generative AI-based traffic scenario planning for the SUMO microsimulation environment

Supervisor: Tamás Tettamanti

Building a natural language interface (e.g., Python-based framework Gemini or OpenAI engine) for generating SUMO-based traffic scenarios. The student’s task is to develop a framework that generates the necessary files based on English text descriptions (e.g., “Create a 2-lane 1 km highway section, etc.”). The research question is to what extent the LLM is able to interpret traffic engineering terminology and convert it into syntactically correct SUMO xml files. The output is essentially a “Prompt-to-Simulation” software tool.

MSc

Simulation of hybrid V2X communication (802.11p and 5G) with the help of OMNeT++, INET and Simu5G

Supervisor: Tamás Ormándi

Vehicle-to-Everything (V2X) communication can be implemented through various standardized technologies, primarily DSRC (Dedicated Short Range Communication) and the 5G-based Cellular V2X (C-V2X), which leverages mobile networks. The objective of this thesis topic is to enable a hybrid application of these two standards within a V2X simulation environment. The core task involves the integration and configuration of different simulation frameworks to achieve this.

MSc TDK

Large language models in macroscopic traffic modeling

Supervisor: Balázs Varga

Using a natural description of an intersection or simple road network, generate a road network file, realistic flows, turning ratios, etc. The objective is to use a set of appropriate prompts to generate text output from the LLM that can be parsed into a valid simulation.

BSc MSc TDK

Development of PLC-based intelligent traffic light control

Supervisor: Tamás Wágner

PLCs (Programmable Logic Controllers) are embedded devices that are widely used in automation and manufacturing technology. These devices are renowned for their reliability in safety-critical application environments and their ease of programming compared to other embedded systems. The student’s task is to design an intelligent traffic light or VJT control system based on a PLC system.

BSc MSc TDK

Validity of co-simulation

Supervisor: Balázs Varga

Assess the trade-off of using the co-simulation of vehicle dynamics (e.g., CARLA, IPG CarMaker) and microscopic road traffic simulation (e.g., SUMO). Assuming individual simulators are well-calibrated, evaluate how the accuracy of the co-simulation is reduced compared to a full-scale vehicle dynamics simulation. Different co-simulation ideas and use-cases are welcome.

MSc

Development of a Dynamic Transit Signal Priority (TSP) System Based on Real-Time GTFS Data

Supervisor: Tamás Ormándi

The objective of this thesis is to design and implement an intelligent traffic control module capable of modulating traffic signal timings using real-time transit data feeds (GTFS-RT). The student is required to develop a Conditional Signal Priority algorithm that correlates the real-time position of transit vehicles with their static schedules. The proposed system aims to grant selective signal priority at intersections specifically to vehicles experiencing schedule deviation (latency), thereby optimizing schedule adherence and improving the overall efficiency of the public transport network.