What are the thesis guidelines

Word processor

We believe that the best way to write a technical paper is by using LaTeX. Therefore, we provide a LaTeX template for you which you can download at the end of this page. Furthermore, we recommend the lecture notes form Prof. O’Leary’s lecture “Engineering and Scientific Documentation” for a basic introduction in writing technical papers and LaTeX. At this point we would like to thank Prof. O’Leary for allowing us to link to his lecture notes.

Text structure

There are no general guidelines for text structure. Since each thesis is unique, the structure will be discussed in detail with the supervisor. The same applies to the scope of the paper. A basic setup is nevertheless available in the LaTeX-template.


Basically, you can write your thesis in German or English. However, you have to coordinate this with your supervisor, since we also have international staff at our chair who support your work and can do this better in English.

Realization of the thesis

For Bachelor’s theses, the total duration of the work should be approximately 3 months and concludes with the presentation of the thesis to the chair staff. Master’s theses should take about 6 months. Within the scope of the thesis, you have to make an interim presentation at the chair, as well as a final presentation within the scope of the master’s examination. More details can be found in the article “Completion of the master’s program”.


Template and Script

Basic Workstation Build

The basic build of a workstation computer is described in the following entry:

Hardware Components

  • Mainboard: Gigabyte Z590 D
  • Processor: Intel Core i9-10850K
  • RAM: AEGIS DDR4 F4-3000C16D-32GISB
  • Graphics Card: NVIDIA Geforce GT710
  • SSD: VIPER VPN100 PCIe m.2 SSD 512GB

Standard Software Package on Workstation

You can find a backup of the standard software package at the technicans repository. Don’t use the backup but clone it. This software package includes the following software:

  • OS: Ubuntu 20.04
  • Driver: Nvidia GPU
  • Office and Latex
    • WPS Office
    • Texmaker – LaTeX Editor
    • Tex Live – LaTeX Distribution
    • Mailspring
  • Browser
    • Firefox
    • Chrome
  • Programming
    • Visual Studio Code
    • Pycharm community
    • Matlab 2020b
    • Github Desktop
    • Python 3.8 – included with Ubuntu 20.04
    • Arduino IDE
  • Video and Images
    • VLC Video Player
    • Inkscape
  • Conference Tools
    • Webex
    • Skype
    • Zoom
  • Cloud Storage and Password Management
    • Dropbox
    • Keypassx
  • Process Manager
    • htop
  • ROS:
    • ROS is not included in the standard software package due to employee preferences – some prefare ROS 1 other ROS 2.

How to write a thesis at the chair of cyber-physical systems

What is a bachelor or a master thesis?

At the end of your bachelor or master studies you have to write a thesis. In case of the bachelor’s study programme your workload should be around 180 to 200 netto work hours (7.5 ECTS credits) and your master’s thesis workload should be around 600 to 650 netto work hours (25 ECTS credits). In these theses, you as a student should independently research the topic and prove your scientific problem-solving strategies. To solve this difficult task, we will help you with our expertise.

What are the requirements to write a thesis?

The bachelor’s programme at MUL requires that you have already completed the courses of the first four semesters to start your thesis. The prerequisite for writing your master’s thesis is to be enrolled in a master’s programme.

How do I get a thesis at the chair of cyber-physical systems?

First, you can check our homepage to see if you find a topic that interests you. If this is not the case, you can contact our chair and propose your own topic. In any case, you should ask for a personal appointment at the secretary’s office so that possible questions or topics can be discussed.

Important Information

If you want to write your thesis at the chair of cyber-physical systems, do not start writing the thesis until it is approved by the chair. Otherwise, it is possible that your topic can change during writing.
At University of Leoben we have a guideline for good scientific practice, therefore the university wants you to stick to this practice.
Finally, the chair of cyber-physical systems has an internal guideline for the implementation of a thesis. More about this on the wiki article “thesis guideline”.


Meeting on the 13th of August 2021

Meeting on the 13th of August 2021

Location: Chair of CPS

Date & Time: 13th Aug. 2021, 9 am to 9:30 am

Participants: Univ.-Prof. Dr. Elmar RueckertNikolaus Feith, BSc



  1.  Concept for master thesis

Top 1: Organisational Update

Thema: Probabilistic Motion planning

Goal: Model based planning via message passing and Kalman Smoothing(KS)
(planning as Inference)


1) 1-D cart+sensor-simulation – proof of concept( physics+dynamics sim, planning and KS)
2) 2-D robot sim as kinematic chain with beam sensor and orientations constraints
3) CopelliaSim (+ ROS with own planning algorithm)
4) Franka Panda

1) Toy task – 1-D physics and dynamics simulation of the cart
2) Toy task – baseline planning (positioning via Euler-distance)
3) Toy task – implementing Kalman Smoother
4) Toy task 2 – 2-D Robot arm (2 links with endeffector)
5) Toy task 2 – Planning in Cartesian space – Inverse kinematic + Kalman Smoother
6) CoppeliaSim of Franka with 3-D printed tool – simple tool guiding (orientation!!)
7) Real world testing with Franka
optional: ROS Implementation of the planning algoritm

Literature: Bayesian Modeling and Machine Learning (Chapter 23, p 493 – KS)

Leander Busch: Learning Motion Models for Local Path Planning Strategies

Supervisors: Elmar Rückert, Nils Rottmann

Finished: 15.Februar.2021


The Segway Loomo is a self-balancing segway robot, which is constantly balanced by an internal control system. A local path planning strategy was developed in advance for this robot. For local path planning, a motion model of the robot is needed to determine the effect of velocity commands on the robot’s pose. In the implemented local path planner, a simple motion model of the robot is used, which does not model the effect of the segway robot’s internal control on its motion. In this work, it was investigated whether a more accurate motion model for the Segway Loomo robot can be learned by using artificial neural networks to improve the local path planning for this robot. For this purpose, different architectures of feedforward networks were tested. The neural networks were trained and evaluated using recorded motion data of the segway robot. The best learned model was validated by using a standard differential drive motion model as a reference. For the validation of the learned model, the accuracy of both motion models was examined on the recorded motion data. On average, the learned model is 59.48 % more accurate in determining the position of the robot at the next time step and 24.61 % more accurate in determining the new orientation of the robot than the differential drive motion model.


Phillip Overlöpper: An exploration scheme based on the state-action novelty in continuos state-action space

Supervisors: Elmar Rückert, Honghu Xue

Finished: 11. November.2019


Exploration in step-based reinforcement learning is a challenging and open problem. If it is applied in a continuous search space, the naive exploration strategy could result in an explored space which is only explored in the neighbourhood of an initial state, leaving a vast amount of entire space unexplored. Visiting states only once leads to poor performance, where the reinforcement learning algorithm gets stuck in a local minimum. This thesis presents a novel exploration scheme for continuous state-action space reinforcement learning, based on the novelty of state-action pairs, where the novelty is measured via the density of the compressed state-action pair. Furthermore, this thesis presents a method to interpolate the action to reach a smooth trajectory in a Markov Decision Process, which can be applied to any robot. The experiment was performed in the CoppeliaSim simulator on a robot with seven degrees of freedom. The results of the new approach show a more effective exploration than the baseline exploration.


Robin Denz: Complete coverage path planning for low cost robots

Supervisors: Elmar Rückert, Nils Rottmann

Finished: 11. November.2019


The demand among the population for household robots continues to rise. These include in particular mobile cleaning and lawn mowing robots. These are usually very expensive and still very inefficient. Especially for lawn mowing robots, it is essential to have visited the entire working space in order to perform their task correctly. However, the current state of the art is still random walk algorithms, which are very unreliable and inefficient. The present bachelor thesis therefore presents a method for intelligent path planning for mobile ”low cost”robots using a lawn mower robot. The robot is only equipped with binary sensors to detect its position in its working space, which is fraught with high uncertainties. By an intelligent representation of the already visited working space as well as the path planning inspired by neural networks, the lawn mower robot manages to achieve a decisive improvement in efficiency compared to the random walk.


Franz Johannes Michael Werner: HIBO: Hierachical Acquisition Functions for Bayesian Optimization

Supervisors: Elmar Rückert, Nils Rottmann

Finished: 17.Juni.2019


Bayesian Optimization is a powerful method to optimize black-box derivative-free functions, with high evaluation costs. For instance, applications can be found in the context of robotics, animation design or molecular design. However, Bayesian Optimization is not able to scale into higher dimensions, equivalent to optimizing more than 20 parameters. This thesis introduces HIBO, a new hierarchical algorithm in the context of high dimensional Bayesian Optimization. The algorithm uses an automatic feature generation. The features are used to condition the parameters, to enable faster optimization. The performance of HIBO is compared to existing high dimensional extensions of Bayesian Optimization on three common benchmark functions. Additionally, an air hockey simulation is used to examine the capability in a task-oriented setting. The conducted experiments show that HIBO performs similar to the basic Bayesian Optimization algorithm, independent from the dimensionality of the given problem. Hence, the proposed HIBO algorithm does not scale Bayesian Optimization to higher dimensions.



Viktor Daibert: Automated Real-time 3D Reconstruction on Mobile Devices

Supervisors: Elmar Rückert

Finished: 5. November.2019


In this master thesis, a prototype is being developed that uses existing frameworks to make a Smartphone to a pocket 3D scanner. The resulting prototype consists of a smartphone-, server-application, and a database in between. On the server application, point clouds from photos are created in real time. The point clouds and user support, should be used to assist during the photo creation and reconstruction of 3D-models from photos. After an introductory consideration of the theoretical background, common algorithms of 3D reconstruction are examined for their advantages and disadvantages with regard to the computing time and efficiency with the target platform. Based on the results, a combination of MeshLab, OpenMVG, OpenMVE, and SMVS is used to construct the 3D models. On the basis of fault tolerance with unsorted images, AKAZE and DAISY have been selected, which is why they are being supplemented in the OpenMVG application in this work. This work answers the question of How a technological can be implemente.


Alexander Walter: Machine Learning for plant classification based on chlorophyll detection

Supervisors: Elmar Rückert, Nils Rottmann

Finished: 17.Juni.2019


Based on the intention to build an autonomous lawn mower robot, this work examines the viability of a sensor and microprocessor for onboard plant classification using machine learning. Usually, some sort of fencing is required to keep the robot in its intended processing area, so such a sensor would allow the robot to differentiate between grass and e.g. flowers. Also, the drive and blade speed can be adjusted for certain species or plant densities, etc.
For this, a data set was collected utilizing a specific method called chlorophyll fluorescence induction. A series of narrowband LEDs are used to drive this process, while a spectrometer measures the spectral intensity. The plant will fluoresce in specific wavelengths when sufficiantly illuminated. With this data, machine learning algorithms are trained to explore if they are capable to classify these plants without further information.
With accuracies up to 98% for three plants commonly present on a lawn and up to 86% for eight plants, the results show that chlorophyll fluorescence is a viable method for classification, even under sunlight using the random forest machine learning algorithm