Bachelor / Master thesis topics

Are you looking for a research-related, interesting topic for your thesis? Then you've come to the right place!
In addition to the topics listed, we always have interesting tasks from our research projects to offer. Please feel free to contact us!
(We are also happy to support students from other faculties who would like to work on one of our topics.)

Towards a Semantically Enriched Mapping System for Mobile Robots Using Large Language Models (LLMs)

Mobile robots often rely on a geometric representation of their environment for navigation, typically a 2D occupancy grid map. However, this representation lacks the semantic context that humans use to describe and understand their surroundings (e.g., "living room," "kitchen," "table"). Recent advancements in Large Language Models (LLMs) and their ability to act as agents open up new possibilities for ... more details

Real-valued Networks and Transformation to Logical Networks

We take trained recurrent neural networks of small/moderate size and analyze their transformation to binary-valued networks. The goal is to compare both versions and assess accuracy, efficiency, and stability ... more details

Secondary Matrices: Incremental Learning by Individual Learning Rates

This project explores secondary matrices to assign individual learning rates for each neuron, balancing stability and flexibility in synaptic updates, with the aim of efficient incremental learning ... more details

Multi-DOF Prosthetic Hand Design

This project focuses on the design, modeling, and preliminary implementation of a multi-degree-of-freedom (Multi-DOF) prosthetic hand that mimics natural upper-limb movements. The aim is to develop a 3D-printed, anthropomorphic hand ... more details

AI-Driven Torque Estimation in Robotic Systems: Leveraging Sensor Fusion for Enhanced Accuracy

Modern robotic systems rely on accurate torque estimation for reliable operation. This thesis focuses on applying AI/ML techniques to estimate motor torque using sensor data recorded from the motor under various operating conditions, such as changes in load, velocity. The dataset includes time-series measurements like... more details

Autonomous Navigation Inspired by the Fruit Fly Brain

We integrate computational models of fruit fly brain areas into robotic systems to enable autonomous navigation. Our research currently uses the fly's visual system and the bee's central complex to demonstrate basic path integration capabilities in robots... more details

Development of a Web Interface for a Human-Robot Workplace

In the context of Industry 5.0, cooperation between humans and robots is becoming increasingly important. However, it is essential that humans are able to understand the robot's intentions. In order to research this area, the professorship has developed an assembly workstation for human-robot interaction. However, as people have different preferences for interaction and communication, a web interface is to be developed and integrated into this work, which will allow ... more details

Bio-Inspired Sensory Maturation

Most living systems, including humans, perceive their environment with a variety of senses (vision, touch, hearing, etc.). When different senses are used simultaneously, a fine-tuned sensory integration (fusion) plays an essential role in ensuring correct perception. However, in human infants and toddlers, for example, sensory organs develop at different rates (maturation of the senses). With that in mind, the aim of this research project is to investigate... more details

Skeleton-based Human Motion Prediction for Safe Human-Robot-Collaboration

There is an increasing trend towards human-centric automation since suitable hardware like collaborative robots became available. Nevertheless, pro-active instead of re-active safety measures are still lacking. Previous research at the professorship developed a deep neural network, which predicts ... more details

Colors and Gazes: Robot Intentions Towards the User

In the context of Industry 5.0, there is a growing focus on collaboration between humans and robots. However, the basis for this is that the human understands the robot's intentions. For this purpose, the robot first task is to add a modifiable color/illuminated band that can be attached to different parts of the robot. Next, methods are to be developed as to ... more details

Understanding and Translation of Everyday Verbal Instructions for a Robotic Agent

Large Language Models (LLMs) are currently a very popular research topic. Our goal is to transfer current developments to real robotic systems as this has a big potential in terms of a more intuitive way to interact with an embodied AI agent.
We will investigate this complex topic in smaller sub-problems. One of ... more details

Investigating the Integration of Large Language Models for Natural Language-Based Robot Navigation using ROS2 and NAV2

This master thesis explores the potential of leveraging Large Language Models (LLMs) and intelligent agents to enable mobile robot navigation through natural language commands. Building upon the established ROS2 and NAV2 frameworks, the research will investigate how LLMs can interpret and translate complex human instructions into ... more details

Interaction Design of a Collaborative Furniture Assembly Process

This student project focuses on collaborative furniture assembly to promote ergonomic working conditions. The aim is for humans and robots to form a symbiotic team and communicate by means of visual and auditory signals. At the same time, safety is ensured by sensory monitoring. The versatile assembly robot should adapt ergonomically to the worker by holding and positioning the workpiece ergonomically. Three processes ... more details

Simple Vision-based Navigation for a Biomimetic Mouse Robot (BA)

Based on NeRmo, a biomimetic mouse robot developed by TUM, we have built our own robot, which is intended for use in research and education. In addition to the ability to perform actions in its environment, the robotic agent's perception capabilities play a significant role. In this bachelor thesis, a microcontroller-based camera module should be integrated into the robot ... more details

Interaction Design of a Collaborative Welding Process

Development of an assistance robot for the individual production of welding processes without time-consuming "teaching". The robot holds the component while the human carries out/suggests the welding process. This division enables the human to react to changes in the joining gap and produce precise welded joints. The flexible object positioning by the robot should enable safety through optimal welding and at the same time increase ergonomics and process efficiency. The aim ... more details

Edge Computing for Local LLM-based HMI

Large Language Models (LLMs) are currently a very popular research topic. Our goal is to transfer current developments to real robotic systems without internet connection. This will improve the possibilities of human-machine interaction.
As part of the bachelor thesis, a sub-project will be carried out. The first step will be a literature review on current methods for speech-interactive local integration of an LLM. In other words ... more details

Adaptive and Collaborative Human-Robot Assembly Planning

In the context of Industry 5.0, the focus is on collaboration between humans and robots through collaborative processes, to enable rapidly adaptable products. However, this requires the robot system to adapt to the user, as is natural in human-human interaction. For this purpose, an assembly process with Lego bricks should be developed on the robot platform of the professorship ... more details