ethz bachelor thesis

• Press Enter to activate screen reader mode.

Department of Earth and Planetary Sciences

Bachelor's seminar and thesis.

Alongside the Bachelor's thesis students take part in the Bachelor's seminar during the fifth and sixth semester, in which students learn scientific writing and presentation.

• chevron_right Bachelor's seminar I and II
• chevron_right Bachelor's thesis

Bachelor's seminar I and II

In the Bachelor's seminars I and II, students gain an insight into scientific work. Important aspects are efficient scientific research and the processing of scientific findings as well as their oral and written presentation. Special emphasis is placed on scientific ethics and correct scientific work.

In the Bachelor's seminar I, students learn important research skills, such as how to efficiently search scientific literature and present scientific research in orally and in writing.

The Bachelor's seminar I is major specific.

The Bachelor's seminar II is completed by students of both majors alongside the Bachelor's thesis. In the Bachelor's seminar II, students apply what they have learned in writing their Bachelor's proposal and Bachelor's poster. The highlight of the second seminar is the Bachelor's posterfair, where students present their Bachelor's poster. 651-3698-01L Bachelor's seminar II

Bachelor's thesis

The Bachelor's thesis is the final project of the Bachelor's programme. It is carried out in parallel with the Bachelor's seminar II. The Bachelor's thesis consists of:

• Literature study, approximately two weeks
• Practical work, approximately three weeks (laboratory, fieldwork, etc.)
• Written Bachelor's thesis, approximately three weeks

The Bachelor's thesis is written in the area of the chosen major. Students can either propose a topic or choose a project from the list of topics within their major. A clear outline of the project is essential. The Bachelor's thesis can also be carried out in collaboration with industry or a geological office. The students organise the collaboration in industry independently.

Bachelor's Thesis topics

The Bachelor's thesis is supervised by two persons:

• one main supervisor
• one co-examiner

At least one person must be a lecturer of the Department of Earth and Planetary Sciences or the Institute for Atmosphere and Climate. Both supervisors may belong to the same research group.

The supervisors follows the progress of the thesis with regular meetings and supports the student in writing the Bachelor's thesis.

The Bachelor's thesis is carried out independently by the students. The writing of the text is the responsibility of the student. It is important that supervisors and student outline the project in detail at the beginning and that there is a common understanding of the methods and the expected results. The supervisors provides the infrastructure needed such as samples, instruments and/or data series, which must be in place at the beginning of the work. All parties involved are familiar with the scope of work, time and deadline defined in the Bachelor's proposal.

Both Bachelor's seminar II and Bachelor's thesis must be registered in the same semester.

• Provisional registration of the Bachelor's thesis (651-3698-00) in myStudies by mid-March (“project/paper/theses”) incl. indication of the main supervisor and co-examiner.
• The Bachelor's proposal must be uploaded in myStudies by mid-April , the Bachelor's thesis is considered as definitely registered only after the confirmation of the main supervisor in eDoz .

The students write their Bachelor's proposal for the Bachelor's thesis in the Bachelor's seminar II.

• Discuss and correct the Bachelor's proposal together with the main supervisor and the co-examiner.
• Upload the accepted Bachelor's proposal to myStudies as assignment.
• By confirming the registration for the Bachelor's thesis in eDoz the main supervisor accepts the Bachelor's proposal.
• The Bachelor's proposal has to be sent as a PDF to the lecturers of the Bachelor's seminar for grading.

Refer to the guidelines for writing a Bachelor's proposal for more information (only available in German).

The Bachelor's poster is prepared in the Bachelor's seminar II. The students design a scientific poster for their Bachelor's thesis, which is presented and graded at the Bachelor's posterfair (end of spring semester, the exact time is communicated in the Bachelor's seminar II).

Bachelor's poster

In order to design the Bachelor's poster, students can download the ETH scientific poster templates and the D-EAPS logo. Please refer to the ETH logo guidelines if you choose to use another poster template.

• chevron_right ETH templates: scientific poster
• protected page lock D-EAPS logo  (ZIP, 400 KB)

The outline of a Bachelor's thesis consists of the three main parts:

• Introduction

The formatting of the Bachelor's thesis is as follows:

• Length: recommended between 4,500 - 12,000 words (excluding appendices).
• Paper size: A4, min. 80 g/m2
• Font: Times New Roman
• Font size: 11pt or 12pt
• Paragraph justification
• Line spacing: 1.5
• Margins: inside 3 cm, outside 2 cm, top and bottom 3 cm each
• Binding: ring or adhesive binding

For details please refer to the guidelines for writing a Bachelor's thesis (only available in German).

The Bachelor's thesis must be submitted to all supervisors in time (printed or in electronic form as a PDF by arrangement).

Deadline: 30 June Late submission will result in a fail according to the Ordinance on Course Units and Performance Assessments at ETH Zurich Art. 11.

Theses for Bachelor and Master Students

Our group offers projects for ETH students in D-ITET and D-INFK (if you’re in another department, please contact us first). On this page, you will find a non-exhaustive list of currently open, ongoing and past projects. We tend to publish new theses around the beginning and the end of the semesters.

If you are interested in doing a project in our group, you are welcome to contact us at [email protected] .

Note that we receive many more requests than we are able to supervise . To maximize your chances, please contact us early and provide relevant background information for a project, including:

• the topics/areas you are most interested in;
• your current studies status (Bachelor or Master, which semester);
• your grades transcript (check myStudies);
• any past projects and/or industry experience;
• any particular skill or programming experience;
• why you are interested in doing a project in our group, in particular.

From experience, a good alignment between the student’s interests and skills with the project goals goes a long way to make projects successful and enjoyable for everyone. So if you are particularly excited about a specific topic, or even have a project idea of your own to propose, please tell us about it!

To look for networking topics, we encourage you to check out our research areas , recent work , and researchers .

Available Theses

Running theses, completed theses.

Upper Right Menu

Toggle navigation, research collection, bachelor thesis.

Search items of this publication type:

Recent Submissions  

Untrusted predictions for forbidden subgraph problems , a tool for debugging jtag , skewed expectations in the elo rating system: home advantage in football and white advantage in chess , let the best sim win , randomized algorithms to locate the sink in low dimensional unique sink orientations of cubes , comparing geoid-quasigeoid separation calculation methods in the fcc region at cern , local disturbance storm time index for ionospheric forecasting , off-grid trash screen design for a fecal sludge treatment plant in blantyre, malawi , scalable high-frequency function approximation with multi-gpu finite basis physics informed neural networks , development of a monitoring device for improved cookstoves , automated power measurement for network devices: collecting data reliably made simple , generating platform configuration from netlists , hydrogeological gravity anomalies in the bedretto tunnel , the distribution of prime numbers in arithmetic progressions via spectral theory , privat, aber öffentlich: wie urbane grünräume auf privaten grundstücken der öffentlichkeit zur verfügung gestellt werden können , microcontroller based particulate matter monitors utilising the alphasense opc-n3 , wie vergeben gemeinnützige wohnbaugenossenschaften ihre wohnungen , gnss displacement time series modeling and snow detection with machine learning , beitrag des planungsrechtlichen vorkaufsrechts zur förderung des preisgünstigen wohnraums in schweizer städten , prediction of daily grace and grace-fo solutions .

• Press Enter to activate screen reader mode.

Agricultural Economics and Policy

Bachelor’s and master’s theses.

We are looking forward to supervise students for their Bachelor and Master theses. Please find proposals for Bachelor’s or Master’s Theses from our group in the lists below. Do not hesitate to contact us if you require any further information.

Anleitung zum Verfassen wissenschaftliche Arbeiten  Download PDF (PDF, 51 KB)

Please find details on the Declaration of Originality and the Citation Etiquette here

ETH Zürich is using SiROP to publish scientific projects. With your university login you get free access to internships, scientific projects, Bachelor’s and Master’s theses. For more information please visit external page www.sirop.org .

Open Topics

For master theses, also bilateral agreements on thesis topics can be made. please contact prof. dr. robert finger directly for further information (email: eval(unescape('%64%6f%63%75%6d%65%6e%74%2e%77%72%69%74%65%28%27%3c%61%20%63%6c%61%73%73%3d%22%65%74%68%2d%6c%69%6e%6b%22%20%68%72%65%66%3d%22%6d%61%69%6c%74%6f%3a%72%6f%66%69%6e%67%65%72%40%65%74%68%7a%2e%63%68%22%3e%72%6f%66%69%6e%67%65%72%40%65%74%68%7a%2e%63%68%3c%2f%61%3e%27%29')) )., note that we cannot take over the supervision of topics defined with third parties and that have not been discussed with us beforehand.  , master thesis: the use of remote-sensing technologies for optimization of mechanical weed control.

master thesis, remote-sensing, technologies, smart farming, non-chemical weed control, pesticides, herbicides, pesticide-free

Contact Details

Analyse von schweizer agrarmärkten.

Agrarmärkte, Wertschöpfungskette, Marktordnung

Description

Evaluating the performance of swiss crop production.

crop production, pesticides, sustainability, efficiency

Heat Stress and efficiency in Swiss dairy production

Heat Stress, dairy production, climate change, extreme weather events, resilience, sustainability, economics

PLEASE LOG IN TO SEE DESCRIPTION

Review of the state of agricultural insurances in dairy farming.

Dairy production, extreme weather events, climate change, agricultural insurances

Evaluating extreme weather risks in Swiss crop production

weather risks, yield effects, risk management

Spatial correlation of yield losses in Germany

weather risk, spatial correlation, insurance, agricultural risk management

Economic impacts of heat stress in Swiss dairy production

Agricultural economics, dairy cows, heat stress, milk production

Betriebliche Optimierungsmodelle in der Schweizer Landwirtschaft

Optimierung, Schweizer Landwirtschaft, Lineare Programmierung

Analyse der Schweizer AgriFood-Startup-Szene: Relevanz und Umsetzung ökologischer Nachhaltigkeit

AgriFoodTech, Startups, Landwirtschaft, Ernährung, Nachhaltigkeit

• Press Enter to activate screen reader mode.

Department of Computer Science

Bachelor's and master's theses.

Below is a list of the research groups of the department with hyperlinks to their available theses.

Institute for Computing Platforms

• Prof. G. Alonso, Information and Communication Systems Research Group
• Prof. A. Klimovic,  Efficient Architectures and Systems Lab
• Prof. T. Roscoe, Network and Operating Systems

Institute for High Performance Computing Systems

• Prof. T. Hoefler, Scalable Parallel Computing Lab

Institute of Information Security

• Prof. D. Basin, Information Security Group
• Prof. S. Capkun, System Security Group
• Prof. K. Paterson, Applied Cryptography Group
• Prof. A. Perrig, Network Security Group
• Prof. S. Shinde,  Secure & Trustworthy Systems Group
• Prof. F. Tramèr,  external page The Secure and Private AI Lab external page

Institute for Intelligent Interactive Systems

• Prof. S. Coros, Computational Robotics Lab
• Prof. O. Hilliges, Advanced Interactive Technologies Lab
• Prof. C. Holz, external page Sensing, Interaction & Perception Lab
• Prof. A. Wang,  external page Programming, Education, and Computer-Human Interaction Lab

Institute for Machine Learning

• Prof. V. Boeva, Computational Genetics and Epigenetics of Cancer
• Prof. J. Buhmann, Information Science & Engineering
• Prof. N. He,  Optimization and Decision Intelligence Group
• Prof. T. Hofmann, Data Analytics Lab
• Prof. A. Krause, Learning & Adaptive Systems Group
• Prof. G. Rätsch, Biomedical Informatics Group
• Prof. M. Sachan, external page Mrinmaya's Lab
• Prof. J. Vogt, Medical Data Science
• Prof. F. Yang,  Statistical Machine Learning Group

Institute for Programming Languages and Systems

• Prof. R. Jung,  Programming Language Foundations Lab
• Prof. P. Müller, Programming Methodology Group
• Prof. M. Püschel, Advanced Computing Lab
• Prof. Z. Su, Advanced Software Technologies Lab
• Prof. M. Vechev, Secure, Reliable and Intelligent Systems Lab

Institute of Theoretical Computer Science

• Prof. B. Gärtner, Theory of Combinatorial Algorithms
• Prof. D. Hofheinz, Foundations of Cryptography
• Prof. D. Komm,  Algorithms and Didactics Group
• Prof. R. Kyng,  Algorithms and Optimization Group
• Prof. U. Maurer, Information Security and Cryptography
• Prof. A. Steger, Combinatorial Structures and Algorithms
• Prof. D. Steurer, external page Computational Complexity, Optimisation and Estimation

Institute of Visual Computing

• Prof. M. Gross, Computer Graphics Laboratory
• Prof. M. Pollefeys, Computer Vision and Geometry Group
• Prof. O. Sorkine-Hornung, Interactive Geometry Lab
• Prof. R. Sumner, Game Technology Center
• Prof. S. Tang, Computer Vision and Learning Group
• Prof. M. El-​Assady,  external page Interactive,Visualization & Intelligence Augmentation Lab

Computer Engineering and Networks Laboratory

• Prof. R. Wattenhofer,  Distributed Computing Group

Research Centers

• Dr. Fabio Zünd, Game Technology Center
• Dr. Fabio Zünd, Media Technology Center

Swiss Data Science Center

• external page Projects list

Info about Bachelor and Master theses

if anything in this article is outdated or a link does not work, please contact Hopo: hopo ät vis.ethz.ch

Short information

• Regulations: https://inf.ethz.ch/de/studium/dokumente.html
• List of all research groups: https://inf.ethz.ch/studies/semester-and-master-theses.html
• Mailing list: [email protected], subscribe via: https://lists.vis.ethz.ch/sympa/info/thesis (login required)

The Bachelor and Master thesis is part of the Computer Science Bachelor and Master program at ETH. The goal of both theses is to learn independent structured and scientific work methods.

The most important information about the Bachelor's and Master's thesis can be found in the study regulations and the information sheets of the respective study program. These documents are listed on the following page of the D-INFK: https://inf.ethz.ch/de/studium/dokumente.html In the following we summarize the most important points.

Both theses take 6 months to complete. The bachelor thesis is worth 10 KP and the master thesis 30 KP. The bachelor thesis can be written over 6 months in a part-time workload or as a full-time workload in a shorter time frame. The master's thesis is written over 6 months in a 100% workload.

Under certain conditions, the Bachelor thesis can also be written in a group (see Bachelor regulations Art 36.6). However, this is not common.

In order to be admitted for the Master thesis, sufficient credit points must have been acquired from some categories: see Master regulations 2020 Art 35.2 and the regulations of 2009 Art 32.2. In order to be admitted for the Bachelor thesis, 5 basic subjects must have been passed, see information sheet Bachelor thesis. If these conditions are fulfilled, you can start the thesis at any time. But note that the submission date is before the end of your study deadline and the start date must also be convenient for your supervisors.

The Bachelor thesis is supervised by one or more professors. From our experience (HoPo-Team) this supervision can vary a lot:

• The supervision can be done directly by the professor or by PhD students or PostDocs of the respective group.
• Supervision can be very time intensive (meetings at least once a week) or only as needed (if questions arise, they are clarified).

Both theses are completed with a written report and a presentation. The form of this presentation (audience, duration) may vary from group to group. The standard of the written work also varies.

The work can also be done externally, i.e. in industry or at another university. However, the work must still be supervised by an ETH professor. This professor also assigns the grade at the end and, depending on the project, also takes over part of the supervision. For the Data Science and Cyber Security Master there are some additional regulations regarding external master theses: See section 3 of the Data Science Master thesis leaflet, section 4 of the Cyber Security leaflet or Data Science study regulations art. 28.2. or Cyber Security study regulations art. 33.4.

For more and detailed information, check out the documents linked above.

How to find a topic:

Take your time to find a topic and a group. You should expect at least one month from your first mail to the start of your work. This process may also take longer. So if you want to start on a fixed date, you should start looking early enough. For some groups, half a year before the start is too early. This varies from group to group.

Subscribe to the mailing list: Once you are looking, you should subscribe to the mailing list to get possible proposals from there ( https://lists.vis.ethz.ch/sympa/info/thesis ). When you have found a thesis, you can unsubscribe.

Find a subject: First of all, you should think about what field you are interested in. Especially for the bachelor thesis, you probably don't have very concrete ideas yet. It can help to think about which lectures you were interested in and which you enjoyed. And then look at the field of the professorship.

Find a group: The department lists all professorships and their research groups at the following link https://inf.ethz.ch/studies/semester-and-master-theses.html . The links sometimes point to the general website of the research group, then you can get an idea of their work, or to a page for writing papers in the respective group. Such pages often contain possible topics or already prepared proposals, requirements to you and email addresses of the contact persons. It is worthwhile to study such pages. It should be noted, however, that the lists of proposals are usually not complete and often not up to date. However, the proposals will give you a good idea of what you can do as work in this group. The new topics will be similar. Even if no concrete proposals are announced, it is worth asking. There is also a new mailing list where topics for papers are advertised. Both from research groups of the department and from externals: https://lists.vis.ethz.ch/sympa/info/thesis

Write to the groups: The above sites often tell you who to contact to find a paper. If you are unsure, write to the professor personally. You can also write to several groups, and then choose the topic that interests you the most. This process can take some time. Professors are very busy and often take 2 days or more to respond. If you don't get an answer within a week, you can ask nicely. Unfortunately, it also happens that emails are ignored completely, then you should look for another group. Even if it sometimes takes a while with the professors; try to write back within 24 hours.

Have a meeting: It's best to set up a meeting where you can talk about possible projects and get to know the potential supervisors. Have them explain the topic and ask questions. Also find out a bit about how the group will supervise you (and if that's right for you) and when you can start working. Additionally, for the bachelor's thesis, clarify whether you will be working on it part-time for 6 months (the normal case) or full-time for a shorter period of time.

Decide: When deciding on a topic, it is certainly important that it interests or even excites you. You have to work intensively on it for 6 months. But it is just as important that the supervision is right for you. Do you prefer intensive collaboration or are infrequent inputs enough for you? Can you imagine working together with the supervisor? Are the expectations realistic? Also, exchange ideas with friends or stop by the VIS office, someone may already know the group you want to learn about.

Finish in time: If you do the Bachelor thesis and an ETH Computer Science Master: The Bachelor thesis grade must be there at the beginning of the Computer Science Master, so that you can still enroll (Friday second week of the first Master semester at the latest). In case of doubt please ask Denise Spicher (or Hopo). Note that your supervisors need time to give you the grade (up to 4 weeks, in rare cases more).

Other useful links:

• Latex template: The CADMO provides the following template: https://www.cadmo.ethz.ch/education/thesis/template.html
• Links from CADMO: On the page of CADMO about master and bachelor theses is a list of useful links: https://www.cadmo.ethz.ch/education/thesis/guidelines.html (at the bottom)

• Press Enter to activate screen reader mode.

Chair of Energy and Public Economics

Guidelines bachelor thesis and semester project.

• Location location_on ZUE E 14
• Phone phone +41 44 633 63 42

Energy and Public Economics Zürichbergstrasse 18 8092 Zürich Switzerland

Goal of Semester project and Bachelor thesis

The objective of a bachelor thesis or semester project is to provide a detailed analysis and discussion of an economic issue using microeconomic theory and empirical methods.

Requirements for Bachelor Thesis

The student should be familiar with the contents of the following courses (or courses with equivalent contents):

• Principles of Microeconomics or Managerial Economics
• Energy Economics and Policy
• One lecture in 'Statistics' (not Stochastics)
• Two other lectures out of the field Environmental / Resource Economics  

Requirements for Semester Project

• Principles of Microeconomics
• One lecture 'Statistics' (not Stochastics) or Operations Research

Semester projects and Bachelor thesis can be written on the following topics:

• Energy economics and policy
• Public economics

Form and outline of the thesis

Semester project.

• Problem description and goal of the thesis
• Detailed microeconomic description of the problem
• Discussion of the relevant literature
• Policy implications

Outline: 15-20 pages (Font: Times New Roman, size 12, line spacing: 1.5, border: double-sided 3 cm)

Bachelor thesis

• Empirical analysis of the problem set

Outline: 30-40 pages (Font: Times New Roman, size 12, line spacing: 1.5, border: double-sided 3 cm)

A) Choice of the topic

The student has the possibility of making a proposal for your thesis (the topic should be in the field of the institute) or to choose a general topic from the topics given by the institute.

B) Preliminary advisement

The student should contact the institute for a preliminary advisement in order to finalize the topic and choose a thesis supervisor from the institute. The assigned person for preliminary advisement is  Dr. Suchita Srinivasan.

C) Proposal

After the preliminary advisement, the student will submit a short proposal. The final decision for the commencement of the thesis is based on this proposal. The proposal should be maximum two pages and must contain the following points:

• A description fo the problem/ research question
• Methodology
• A description of the data to be used (in case of empirical study)
• Bibliography
• Provisional table of contents

D) Start to write

As soon as the proposal has been accepted you can start writing the thesis.

E) Support and workplace

Semester project After the discussion of the proposal there is the possibility of having one meeting with your supervisor. After handing in the final report there will be a final discussion. Bachelor thesis After the discussion of the proposal there is the possibility of having one meeting with your supervisor. Furthermore you can hand in a draft of the final report in order to get a feedback from your supervisor. After handing in the final report there will be a final discussion.

F) Submitting the thesis

Two copies of your thesis must be handed in, duplex print and bound. In addition, the abstract of the thesis including your e-mail address (in pdf format) is needed for the CEPE website.

G) Evaluation

The following points will be assessed:

• Structure: Structure and outline should be consistent and logical.
• Content: The content must be correct and clear.
• Language: Accurate wording and correct grammar is assumed.
• Empirical analysis: The data collection and analysis must be performed in an accurate and transparent way.
• Literature: The relevant literature should be critically discussed and the references should be correctly cited.

• Press Enter to activate screen reader mode.

Department of Environmental Systems Science

Bachelor's thesis.

The Bachelor's thesis is an independently written, scientific work. It is supervised by a lecturer who teaches in the field of Agricultural Sciences. The thesis represents the completion of the Bachelor's degree.

Please note the Download implementation provisions (PDF, 84 KB) for bachelor's thesis (in German). 

Guidance: Lecturers who teach in the field of agricultural sciences are entitled to act as supervisor for a Bachelor's thesis. Supervision: Each Bachelor's thesis is supervised by a co-supervisor. It may happen that the thesis is supervised by a third person (advisor). (Note: only the supervisor and co-supervisor grade the thesis) Subject:  Subjects for Bachelor's theses can be requested directly from the lecturers. The supervisor of the Bachelor's thesis defines the task.

Registration and approval: Students register their Bachelor's thesis with the Study Administration before they begin. The Study Administration submits the applications for admission to the Departmental Conference in accordance with the Study Regulations 2016. The Download registration form (PDF, 694 KB) (PDF, 216 KB) must be filled in and signed by the Registrar's Office. Entering: Students can sign-in for the Bachelor's thesis themselves in myStudies .

Scope: The Bachelor's thesis comprises 14 CP, which corresponds to approximately 420 hours. The start and end date of the written work is scheduled with the supervisor.

The Bachelor's thesis is an independently written work. Students are therefore obliged to sign a Download declaration of originality (PDF, 183 KB) (PDF, 624 KB). The declaration of independence must also be included in the work. Further information on the integrity of research and plagiarism can be found on the Student portal.

There is no layout restriction e.g. order, picture, Logo (not ETH) but the front page must contain the following information:

• Thesis type (Bachelor's thesis)
• Name of the student
• Student ID no.
• Degree Programme Agricultural Sciences
• Title of the Bachelor's thesis
• note: both grade the thesis
• note: only if applicable; doesn't grade the thesis
• Date of submission (dd/mm/yyyy)
• Note "Confidential" *

(*only if asked)  

see Download sample (PDF, 111 KB)

The supervisor and the co-supervisor each grade the thesis. The final grade is calculated as the arithmetic mean of the two grades. The criteria for the assessment of the written paper are shown on the evaluation sheet ( Download in German (PDF, 27 KB) / Download in English (PDF, 26 KB) ).

Study Coordinator

Emma Lindberg

• Phone phone +41 44 632 38 93

Universitätstrasse 2 LFW C 13.1 8092 Zürich

Study Administration

• Phone phone +41 44 632 55 89

• Press Enter to activate screen reader mode.

Dept. of Information Technology and Electrical Engineering

Bachelor's project.

The Bachelor's Thesis is the final part of the programme and is usually carried out in the sixth semester (2018 regulations). During the thesis, students will gain initial experience in the independent solution of a technical-scientific problem by applying the acquired specialist and social skills.

Bachelor's theses are supervised by a professor of the Department (including adjunct professors) or by a Download professor associated with the Department (PDF, 97 KB) . Most theses are carried out under the guidance of, and in close contact with, a PhD student of the supervising professor.

A Bachelor's Thesis should take about half of a student's time during one semester, i.e., about 300-400 hours and usually has a duration of 14 weeks. The thesis includes an oral presentation and a written report, and it is graded. Before starting, the project must be registered in myStudies ("Projects/papers/theses").

Semester project, bachelor's and master's thesis offers at D-ITET:

If projects are taken, sometimes related projects may be available. Often, labs are willing to customize a project to match the students' interests. Where bachelor's theses are not clearly advertised, it is advisable to search for topics for semester projects and ask about the possibility of working on them as a bachelor's thesis. Many labs welcome students' own ideas for projects.

An overview of the labs that offer bachelor's, semester and Master's theses can be found on the page of the master programme.

• Press Enter to activate screen reader mode.

Environmental Physics

Bachelor and master theses.

We always welcome students who are interested in undertaking their bachelor or master theses with us.  

If you are interested in joining our group for a bachelor, master thesis or an internship please explore our research and contact the corresponding group leader. We are offering theses that span the range of interests in our group, that is theses that tackle questions coming from the physical, through biogeochemical all the way to the classical ecological realms.

Please contact us well ahead of your desired starting date so that we can develop a topic together with you. We are also presenting the currently available thesis topics at the IBP Master thesis fair in the spring semester, and in the IAC master thesis orientation events in the fall semester.

In order to give you an impression of the type of thesis that you can pursue with us, we give you here a list of recently completed theses.

Zhang Siyi: "Biomes Partitioning and Network Analysis of Marine Plankton" (supervised by Meike Vogt, Urs Hofmann Elizondo, and Alexandre Schickele)

Aline Schneuwly: "Impact of the 2023 Marine Heatwave on the North Atlantic Carbon Sink” (supervised by Luke Gregor, Jens Müller, and Nicolas Gruber)

Xinhang Li: "Trends In Marine Plankton Biodiversity over the 21st Century under Different Climate Change Scenarios” (supervised by Meike Vogt, Fabio Benedetti, and Dominik Eriksson)

Danling Ma: "Long-Term Trends and Drivers of Global Ocean Acidification from 1982 to 2020” (supervised by Luke Gregor and Nicolas Gruber)

Andrea von Langen Roson: "Variability Of Water Column Denitrification and its Drivers in the Eastern Tropical Pacific Oxygen Deficient Zones" (supervised by Eike Köhn, Nicolas Gruber, and Jana Harri)

Giacomo Poli: "The potential of machine learning algorithms for mapping microplastic concentrations in the ocean” (supervised by Meike Vogt, Fabio Benedetti, and Dominik Eriksson)

Marcel Scheiwiller: "Compound events of temperature and acidification extremes in the California Current System” (supervised by Flora Desmet and Nicolas Gruber)

Nielja Knecht: "The impact of zooplankton calcifiers on the marine carbon cycle” (supervised by Meike Vogt, Fabio Benedetti, and urs Hofmann Elizondo)

• Press Enter to activate screen reader mode.

Dept. of Civil, Environmental and Geomatic Engineering

Bachelor thesis.

The Bachelor thesis in the 6th semester is intended to promote independent, hands-on problem-solving skills. 10 credits are awarded for submission of a satisfactory Bachelor's thesis (minimum grade 4.0).

Prerequisite

The bachelor thesis can only be started if the first-year examination and examination blocks 1 to 4 have been passed.

Students can repeat an unsatisfactory Bachelor thesis only once. However, they have to write it on a different subject. Students can change professor.

Breaking off the Bachelor Thesis

The Bachelor thesis can only be abandoned in exceptional circumstances. An official written request stating the reasons must be submitted immediately to the Director of Study. There needs to be a compelling reason for abandoning the  thesis from the second half of the allotted processing time onwards, otherwise abandonment is not possible.

Professors announce the topics for the Bachelor theses with enough time. Students are required to register for a specific topic at the end of the 5th semester. Group work is possible on condition that the individual contributions by the students are clearly defined and can be assessed and graded individually.

More information can be found on the Download leaflet (PDF, 110 KB) .

Bachelor Theses at the Institute of Environmental Engineering

• chevron_right Groundwater and Hydromechanics
• chevron_right Hydrology and Water Management
• chevron_right Urban Water Management
• chevron_right Ecological System Design
• chevron_right Earth Observation and Remote Sensing
• chevron_right Industrial Ecology/Air Pollution Control

• Press Enter to activate screen reader mode.

Chair of Cartography

Bachelor thesis.

The Bachelor's thesis is usually written in the 6th semester under the supervision of a D-BAUG professor. It promotes the ability to undertake independent, practice-oriented problem-solving or scientific work. The Bachelor's thesis is completed at the end of the semester with a written report and an oral presentation. 10 credits will be awarded for a satisfactory Bachelor’s thesis. Students can repeat an unsatisfactory Bachelor's thesis only once and they have to write it on a different subject.

• Press Enter to activate screen reader mode.

Institute for Dynamic Systems and Control

Theses & semester projects.

The Institute for Dynamic Systems and Control offers the following projects to ETH students:

• Studies on Mechatronics (SM)
• Bachelor Theses (BT)
• Semester Projects (SP)
• Master Theses (MT)
• You should read the ETH Citation Etiquette and working accordingly.
• For more information, read the ETH information on plagiarism .
• Furthermore, you are urged to use the Download IDSC Thesis Template (ZIP, 55.7 MB) to write your report.

How to apply:

• Please review the available projects below
• Send an email to the project contact.

ETH Zurich uses SiROP to publish and search scientific projects. For more information visit sirop.org call_made .

Open-Source Cubli Project: Research Assistant

We are seeking a highly motivated ETH Zurich student for a paid position to help open-source the Cubli platform, an advanced robotics system. The role involves refining CAD designs, hardware prototyping, and integrating electronics and software. Applicants should demonstrate experience in hardware prototyping and/or software development (C++, Python). You’ll work closely with the technical team at IDSC to document the entire process and make the Cubli easy to rebuild. This is a unique opportunity to contribute to a high-impact project and collaborate with leading experts in the field. Show details add remove

ETH Zurich (ETHZ)

Description

Contact details, more information.

Open this project...  call_made

Published since: 2024-09-06 , Earliest start: 2024-09-01

Organization Research D'Andrea

Hosts Ramachandran Aswin

Topics Information, Computing and Communication Sciences , Engineering and Technology

Learning-based model predictive control for navigating uncertain wind fields

In this Master thesis, you will implement an efficient Gaussian process-based model predictive controller for spatio-temporal wind field modeling of a real-world airborne control system. Show details add remove

model predictive control, mpc, gaussian process, gp, gp-mpc, machine learning, wind forecasting, renewable energy, airborne wind energy

Master Thesis

Published since: 2024-09-02 , Earliest start: 2024-09-09 , Latest end: 2025-05-31

Applications limited to ETH Zurich

Organization Research Zeilinger

Hosts Lahr Amon

Topics Mathematical Sciences , Engineering and Technology

Strategic Interactions of Future Mobility Systems

Mobility is typically self-optimized for a particular region to accommodate internal travel needs. However, as soon as one considers multiple, interacting regions (e.g., urban areas interacting with agglomerations, and agglomerations interacting with rural areas), important coordination issues occur, including scheduling mismatches, fleet allocations, and congestion peaks. In short, a mobility system composed of self-optimized mobility systems seems to often operate suboptimally. In this project, we will investigate the idea of strategic interactions of future mobility stakeholders across heterogeneous regions, such as urban areas, agglomerations, and rural areas, leveraging techniques from network design, optimization, game theory, and policy making. Show details add remove

Optimization, Game theory, Multi-agent interactions, Transportation systems, Robotics

Semester Project , Master Thesis

Published since: 2024-09-02 , Earliest start: 2024-09-02 , Latest end: 2025-07-31

Organization Research Frazzoli

Hosts He Mingjia

Topics Mathematical Sciences , Information, Computing and Communication Sciences , Engineering and Technology

Piston-based Brayton Engine - Design and Control

At etavalve, we are developing a novel category of engines to convert industrial waste heat at 400°C or more into electricity with an anticipated conversion efficiency of 35% to 45% - an outstanding value for waste heat recovery systems. In this thesis, we focus on developing a zero-dimensional model that captures the fast dynamics of a piston engine and the slow thermal inertia of the heat exchanger. The aim is to obtain an accurate yet computationally lean model, which will then be subjected to optimization methods. Show details add remove

Published since: 2024-08-27

Organization Research Onder

Hosts Fieni Giona

Topics Engineering and Technology

The Way of Water: Development of a fleet of water-based drones for live performance

This project focuses on developing autonomous robots for synchronized performances on water. Equipped with kinetic water fountains, RGB lighting, and ultrasonic mist generators, the robots are designed to execute planned choreographies. The system utilizes robotics control, wireless communication, and positioning technologies to coordinate movements, and payload activation, facilitating complex pattern generation and synchronization. The objective is to advance the application of distributed robotic systems in creating structured and cohesive visual displays on water. Show details add remove

Water based rovers, Electronics development, Distributed Robotics, Control Systems, Game design

Semester Project , Bachelor Thesis , Master Thesis

Published since: 2024-08-24

Topics Arts , Information, Computing and Communication Sciences , Engineering and Technology

Optimal racing using MPC with a novel repetitive observer

This project aims at developing and deploying a control algorithm for racing with a minitature race car. The methodology combines model predictive control with a recently investigated periodic estimation/learning procedure. Show details add remove

Model predictive control (MPC), racing, online learning

Published since: 2024-08-14

Hosts Köhler Johannes

Thermal Energy Storage - Design and Control

Energy storage systems become increasingly important to tackle the intermittent nature of renewable energy sources such as photovoltaics and wind turbines. This thesis focuses on a novel energy storage solution where excess electrical energy is converted into heat and back into electricity, using a novel piston-based engine concept that achieves over 70% round-trip efficiency. The aim is to design, optimize, and control this thermal energy storage system and to assess its economic potential in various scenarios. Show details add remove

Energy Storage, Optimal Design, Optimal Control

Published since: 2024-08-08 , Earliest start: 2024-09-02 , Latest end: 2025-04-30

Hosts Auckenthaler Theophil

Electromagnetic Speed Log development for dual axis velocity measurement of watercraft

This project focuses on developing a high-precision electromagnetic (EM) speed log designed to measure watercraft velocity with an accuracy range from 0.005 m/s to 3 m/s. The system will use a set of metal electrodes to generate and detect electromagnetic fields, providing accurate speed measurements based on Faraday’s law of induction. Show details add remove

Published since: 2024-07-30

Teaching a robot to master a board game using Reinforcement Learning

The master thesis aims to create a physics-based simulation with Brax or MuJoCo for a robot to learn board game strategies via reinforcement learning. Utilizing a pre-built 2x 2D gantry robot integrated with ROS2, the project seeks to train the robot to learn the game from scratch and improve its play against both human and robotic opponents. The primary goal is rapid learning and superior performance, with a focus on understanding the factors of victory in games like this between robots trained on the same algorithm. All this will be performed in simulation and on a real robot. Show details add remove

PLEASE LOG IN TO SEE DESCRIPTION

Published since: 2024-07-29 , Earliest start: 2024-08-15

CyberRunner: Pushing the Boundary of Autonomy

CyberRunner is an AI robot whose task is to learn how to play the popular and widely accessible labyrinth marble game. The labyrinth is a game of physical skill whose goal is to steer a marble from a given start point to the end point. In doing so, the player must prevent the ball from falling into any of the holes that are present on the labyrinth board. The movement of the ball can be indirectly controlled by two knobs which change the orientation of the board. While it is a relatively straightforward game, it requires fine motor skills and spatial reasoning abilities, and, from experience, humans require a great amount of practice to become proficient at the game. Using recent advances in model-based reinforcement learning techniques, CyberRunner is able to outperform the previously fastest recorded time, achieved by an extremely skilled human player, by over 6%. Moreover, it does so with only 6 hours of practice. We envision expanding the capabilities of CyberRunner through further research. Students will contribute to advancing the field and establishing CyberRunner as a real-world robotic benchmark. Suitable projects in different areas are available for talented and motivated students. The project topics span model-based control, reinforcement learning, computer vision, and hardware design. Show details add remove

CyberRunner, Reinforcement Learning, Machine Learning, Robotics

Published since: 2024-07-24 , Earliest start: 2024-09-01 , Latest end: 2025-09-01

Hosts Bi Thomas

Multi-agent predictive control barrier functions

In this project, we want to explore possible extensions of predictive control barrier functions to the multi-agent setting. Predictive control barrier functions [1] allow certifying safety of a system in terms of constraint satisfaction and provide stability guarantees with respect to the set of safe states in case of initial feasibility. This allows augmenting any human or learning-based controller with closed-loop guarantees through a so-called safety filter [2] which is agnostic to the primary control objective. As current formulations are restricted to single agents, the goal is to investigate how this formulation can be extended for multi-agent applications and how the interactions between the agents can be exploited in order to reduce computational overhead. Show details add remove

predictive control, multi-agent systems, safety filter, control barrier functions

Published since: 2024-06-25

Hosts Didier Alexandre

Forecasting Market Trends in Maritime Transportation Systems

Maritime transportation accounts for around 80% of global trade volume. It is deeply entangled with important global supply chains and constitutes a network driven by complex dynamics. One of the major driving forces are market rates which in turn influence the decisions of multiple stakeholders. In this project we aim to forecast future market rate trends by leveraging state-of-the art artificial intelligence/machine learning techniques. More specifically we develop a forecasting pipeline based on relevant real-world historic supply-demand imbalances and from real-world historic market rates data. Show details add remove

Machine Learning, Artificial Intelligence, Data Science, Python, Prediction, Classification

Published since: 2024-06-14

Applications limited to Department of Mathematics , Department of Computer Science , Department of Information Technology and Electrical Engineering , Department of Mechanical and Process Engineering

Hosts Albert Marc

Topics Mathematical Sciences , Information, Computing and Communication Sciences , Engineering and Technology , Economics

A Control Perspective to Language Recommender Systems

The development of Large Language Models (LLMs), like ChatGPT and GPT-4, has influenced the field of Natural Language Processing and Artificial Intelligence with their exceptional proficiency in comprehending and generating language, alongside their notable generalization and reasoning abilities. Consequently, recent research efforts have focused on leveraging the capabilities of LLMs to improve recommender systems. Recommender systems significantly influence human behavior by shaping users’ preferences, decision-making processes, and overall engagement with digital content. This project develops on the interpretation of recommender systems (controller) in feedback interaction with the users (system), [3]. By following a similar approach to [2], we will investigate how a careful integration of a LLM with a Model Predictive Control (MPC) framework can enhance recommender systems by ensuring accurate and adaptable recommendations while considering user preferences and constraints. Understanding the influence of recommender systems over users behaviour and managing it effectively will be enhanced through the MPC framework, which offers a structured and interpretable approach to recommendation optimization. Show details add remove

Large Language Models, MPC, Social Systems

Semester Project , Master Thesis , ETH Zurich (ETHZ)

Published since: 2024-06-11 , Earliest start: 2024-06-11

Organization Automatic Control Laboratory

Hosts De Pasquale Giulia , Amo Carmen

Prioritized and hierarchical reinforcement learning (RL) for gokart racing and urban driving

Abstract Reinforcement learning (RL) has achieved remarkable performance in various domains such as gaming, protein folding, and foundation models. However, efficiently applying RL to real-world applications like go-kart racing and urban driving presents significant challenges due to high-dimensional environments and the lack of structured task decomposition. This thesis proposes addressing these challenges through prioritized rewards and hierarchical task decomposition. By incorporating prioritized experience replay and dynamic reward shaping, the learning process focuses on critical experiences, enhancing efficiency. Hierarchical RL will break down complex tasks into manageable sub-tasks for better strategic planning and execution. The goal is to develop robust and adaptable RL agents capable of high performance in both racing and urban driving scenarios. The student will select a specific application domain, define benchmarks, and potentially conduct real-world testing. The outcomes are expected to contribute significantly to robotics research, with potential publications in top conferences and journals. Pre-requisites include a strong interest in machine learning, RL, optimization, robotics, and proficiency in Python. Prior experience in autonomous vehicles or robotics is a plus. Show details add remove

Published since: 2024-05-28 , Earliest start: 2024-05-28 , Latest end: 2025-02-28

Hosts Zanardi Alessandro, Dr.

Topics Information, Computing and Communication Sciences , Engineering and Technology , Behavioural and Cognitive Sciences

Reinforcement Learning for Go-Kart Racing

Our aim is to create an autonomous racing system capable of swiftly learning optimal racing strategies and navigating tracks more effectively (faster) than traditional methods and human drivers using RL. Show details add remove

robotics, racing, reinforcement learning, autonomy, controls, planning, learning

Published since: 2024-05-08 , Earliest start: 2024-05-03 , Latest end: 2026-07-18

Hosts Di Cicco Maurilio, Dr.

Topics Information, Computing and Communication Sciences

Submodular optimization for scenario sampling in autonomous vehicles safety testing

A key barrier hindering the swift introduction of autonomous vehicles (AVs) in real-world contexts is the challenge in establishing clear safety benchmarks. Specifically, the issue of systematically assessing both performance and safety remains a significant stumbling block within the industry. This challenge is mainly twofold: Firstly, how can we identify an ideal scenario set to evaluate the vehicle's performance within a targeted Operational Design Domain (ODD) and what criteria would be useful in amplifying or paring down this set? Secondly, how do we determine a substantial stopping criteria for the evaluation campaign, and what level of confidence should be attached to the observed performances? Show details add remove

Published since: 2024-04-11 , Earliest start: 2024-04-01

Direct Projects

The projects from Prof. Chris Onder's group are hosted on the student projects page .

The projects from Prof. Melanie Zeilinger's group are hosted on the student projects page .

Custom Projects

From time to time, project supervisors will develop custom student research projects to fit with a student's particular interests or skills. If you are interested in doing a custom student research project, please email the project supervisor of your choice directly. We recommend that you carefully review their area of research before you contact them. Please note that the decision of whether to develop a custom student project is at the full discretion of the project supervisor.

• Press Enter to activate screen reader mode.

Institute for Computing Platforms - Systems Group

Master's and bachelor's theses.

The Systems Group has a variety of projects available, as possible topics for a Masters Thesis, a Semester Projects, or as labs for bachelors or masters students.

• protected page lock Understanding ML Compilers: A Benchmark on Heterogeneous Hardware [MT]  (PDF, 119 KB)
• protected page lock Deploying RoFL at Scale [BT]  (PDF, 92 KB)
• protected page lock End-to-End System Designs for Privacy [MT/BT]  (PDF, 95 KB)
• protected page lock Cryptographic Audits for Secure Machine Learning [MT]  (PDF, 96 KB)
• protected page lock Scheme-Independent FHE Compiler for TensorFlow [MT]  (PDF, 75 KB)
• protected page lock Deploying Secure Computation on Heterogeneous Hardware [MT]  (PDF, 285 KB)
• protected page lock Extend an FPGA Collective Offload Engine [MT]  (PDF, 269 KB)
• protected page lock Code generation for heterogeneous architectures [BT]  (PDF, 165 KB)
• protected page lock Differential Private Data and Query Set Generation for Benchmarking  (PDF, 85 KB)
• protected page lock Answering subjective queries using vector search [Semester Project]  (PDF, 183 KB)
• Download lock Low-Latency 64-Channel Stereo Audio Mixing using FPGA [MT/Semester Project]  (PDF, 177 KB)
• Download lock A New Music Notation for Chinese GuQin [MT/Semester Project]  (PDF, 564 KB)
• protected page lock FPGA-accelerated Database Operators as a Service [MT/SP/BT]  (PDF, 198 KB)
• protected page lock Parquet File Writer for FPGA-accelerated Cloud Storage Layer [MT]  (PDF, 193 KB)
• protected page lock Optimizing Compound AI Systems [MT/Semester Project]  (PDF, 112 KB)
• protected page lock Offloading Garbage Collection to GPUs [BT]  (PDF, 106 KB)
• protected page lock Multi-word Compare and Swap on FPGAs [MT]  (PDF, 101 KB)

There are several thesis projects available within the Enzian and Sockeye projects:

• protected page lock USB Subsystem Support for an OS Course [Practical work]  (PDF, 90 KB)
• protected page lock A BMC orchestration layer in Rust over seL4 [MT/BT]  (PDF, 98 KB)
• protected page lock Complete semantics of the ARMv8.1-A Memory Management Unit [MT]  (PDF, 91 KB)
• protected page lock Runtime Verification with TeSSLa on Enzian [MT]  (PDF, 96 KB)
• protected page lock Integrating ECI and TileLink [MT/Practical work]  (PDF, 65 KB)
• protected page lock Complete semantics of the ARMv8-R Memory Protection Unit [MT]  (PDF, 93 KB)
• protected page lock Hybrid FPGA-Accelerator Encryption [BT/MT] and Compression  (PDF, 89 KB)
• protected page lock Complete semantics of the RISC-V Memory Management Unit [MT]  (PDF, 96 KB)
• protected page lock Specifying the interconnect of the AMD/Xilinx Ultrascale+ MPSoC [MT]  (PDF, 93 KB)
• protected page lock Semantics of the Intel 64 and ia32 Memory Management Unit [MT]  (PDF, 93 KB)

Ongoing Master's Theses

Past theses.

• Press Enter to activate screen reader mode.

ETH AI Center  

Semester and thesis projects.

The ETH AI Center offers a wide range of semester and thesis projects for students at ETH Zurich, as well as other universities. Please see the list below for projects that are currently available.

Are you a student? Check out our Semester and Thesis projects below!

ETH Zurich uses SiROP to publish and search scientific projects. For more information visit sirop.org call_made .

Robust Classification of the Activities of Daily Living using Unobtrusive Sensors and Transfer Learning

This study explores using transfer learning with wearable sensors to improve activity recognition in spinal cord injury patients. Show details add remove

Transfer Learning, Machine Learning, Classification, Artificial Intelligence

Semester Project , Internship , Bachelor Thesis

PLEASE LOG IN TO SEE DESCRIPTION

More information.

Open this project...  call_made

Published since: 2024-09-04 , Earliest start: 2024-10-01 , Latest end: 2025-02-07

Organization ETH Competence Center - ETH AI Center

Hosts Ejtehadi Mehdi

Topics Information, Computing and Communication Sciences , Engineering and Technology

Learn to navigate within scenes by leveraging object representation and interaction.

Biological intelligence excels in adapting to new tasks by reusing prior knowledge, as seen in landmark-based navigation where animals plan routes using spatial relationships. In contrast, machine learning struggles with navigation due to challenges like understanding the effects of actions on perception (equivariance), estimating distances to objects without supervision (localization), and dealing with occlusion. The proposed method addresses these challenges by learning equivariant object representations and composing them into a coherent map, enabling accurate pose estimation and navigation. Successfully tested in a 3D simulation, the goal is to apply this approach to more realistic environments, such as drone navigation, and to demonstrate its utility in various tasks through reinforcement learning. Show details add remove

Reinforcement Learning, Representation learning, Navigation

Course Project

Description

Contact details.

Published since: 2024-08-30 , Earliest start: 2024-08-25 , Latest end: 2025-01-01

Organization Institute of Neuroinformatics

Hosts Taoudi Yassine , Grewe Benjamin , Keurti Hamza

Topics Information, Computing and Communication Sciences

Bridging Imitation- and Reinforcement learning to interact with Articulated Objects

To integrate robots into daily life, they must learn to manipulate diverse environments and objects. Recent advances in imitation learning show promise for teaching visual-motor skills, but require extensive robot-specific data. Reinforcement learning in simulation can learn robust policies in varied settings but struggles with the sim-to-real gap, especially with complex systems and camera observations. This work combines both approaches: using imitation learning to control a five-fingered hand from RGB images and reinforcement learning to control a quadruped's base and arm. Show details add remove

Imitation-Learning, Reinforcement-Learning, Deep-Learning, RL, IL, Deep-Learning, Robotics

Master Thesis

Work Packages

Requirements.

Published since: 2024-08-29 , Earliest start: 2024-08-30

Applications limited to ETH Zurich

Organization Robotic Systems Lab

Hosts Zurbrügg René , Portela Tifanny , Nava Elvis

Topics Information, Computing and Communication Sciences , Engineering and Technology , Behavioural and Cognitive Sciences

Studying Generalization, Compositionality and Sample Efficiency on Reasoning Tasks

Humans excel at breaking down complex scenes and understanding how objects within them relate to each other. In recent years, AI systems designed to test reasoning have made significant progress, with top performers now matching human accuracy on certain tests [1,2]. However, there's still a considerable difference in how efficiently humans and AI learn new tasks. Humans can pick up new skills with remarkably few examples, which is due to the ability to compose and generalize previously acquired knowledge in novel contexts. The ARC Challenge [3] is a remarkable example of a visual reasoning challenge where sample efficiency, compositionality and generalization are of primordial importance, in such a way that SOTA AI systems still significantly lag behind average human performance (46% for SOTA AI vs 100% for humans). In this project, we take the ARC Challenge as an inspiration to study the generalization, compositional and sample efficiency capabilities of different AI model families, using pre-existing datasets. We are also particularly interested in the recently discussed Grokking [4] phenomenon, and eager to exemplify this on visual based tasks. Show details add remove

Artificial Intelligence, Sequence Models, ARC Challenge, Grokking

Semester Project , Master Thesis

Published since: 2024-08-28 , Earliest start: 2024-08-28 , Latest end: 2025-06-30

Hosts Amo Carmen , Taoudi Yassine

Leveraging Human Motion Data from Videos for Humanoid Robot Motion Learning

The advancement in humanoid robotics has reached a stage where mimicking complex human motions with high accuracy is crucial for tasks ranging from entertainment to human-robot interaction in dynamic environments. Traditional approaches in motion learning, particularly for humanoid robots, rely heavily on motion capture (MoCap) data. However, acquiring large amounts of high-quality MoCap data is both expensive and logistically challenging. In contrast, video footage of human activities, such as sports events or dance performances, is widely available and offers an abundant source of motion data. Building on recent advancements in extracting and utilizing human motion from videos, such as the method proposed in WHAM (refer to the paper "Learning Physically Simulated Tennis Skills from Broadcast Videos"), this project aims to develop a system that extracts human motion from videos and applies it to teach a humanoid robot how to perform similar actions. The primary focus will be on extracting dynamic and expressive motions from videos, such as soccer player celebrations, and using these extracted motions as reference data for reinforcement learning (RL) and imitation learning on a humanoid robot. Show details add remove

Published since: 2024-08-27

Applications limited to ETH Zurich , EPFL - Ecole Polytechnique Fédérale de Lausanne

Hosts Li Chenhao , Kaufmann Manuel , Li Chenhao , Li Chenhao , Kaufmann Manuel , Li Chenhao

Topics Engineering and Technology

Periodic Motion Priors for General Quadruped Locomotion Learning

In recent years, advancements in reinforcement learning have achieved remarkable success in quadruped locomotion tasks. Despite their similar structural designs, quadruped robots often require uniquely tailored reward functions for effective motion pattern development, limiting the transferability of learned behaviors across different models. This project proposes to bridge this gap by developing a unified, continuous latent representation of quadruped motions applicable across various robotic platforms. By mapping these motions onto a shared latent space, the project aims to create a versatile foundation that can be adapted to downstream tasks for specific robot configurations. Show details add remove

representation learning, periodic autoencoders, policy modulating trajectory generators

Published since: 2024-08-22

Hosts Li Chenhao , Miki Takahiro

Lifelike Agility on ANYmal by Learning from Animals

The remarkable agility of animals, characterized by their rapid, fluid movements and precise interaction with their environment, serves as an inspiration for advancements in legged robotics. Recent progress in the field has underscored the potential of learning-based methods for robot control. These methods streamline the development process by optimizing control mechanisms directly from sensory inputs to actuator outputs, often employing deep reinforcement learning (RL) algorithms. By training in simulated environments, these algorithms can develop locomotion skills that are subsequently transferred to physical robots. Although this approach has led to significant achievements in achieving robust locomotion, mimicking the wide range of agile capabilities observed in animals remains a significant challenge. Traditionally, manually crafted controllers have succeeded in replicating complex behaviors, but their development is labor-intensive and demands a high level of expertise in each specific skill. Reinforcement learning offers a promising alternative by potentially reducing the manual labor involved in controller development. However, crafting learning objectives that lead to the desired behaviors in robots also requires considerable expertise, specific to each skill. Show details add remove

learning from demonstrations, imitation learning, reinforcement learning

Hosts Li Chenhao , Li Chenhao , Klemm Victor

Pushing the Limit of Quadruped Running Speed with Autonomous Curriculum Learning

The project aims to explore curriculum learning techniques to push the limits of quadruped running speed using reinforcement learning. By systematically designing and implementing curricula that guide the learning process, the project seeks to develop a quadruped controller capable of achieving the fastest possible forward locomotion. This involves not only optimizing the learning process but also ensuring the robustness and adaptability of the learned policies across various running conditions. Show details add remove

curriculum learning, fast locomotion

Hosts Li Chenhao , Bagatella Marco , Li Chenhao , Li Chenhao , Li Chenhao

Learning Real-time Human Motion Tracking on a Humanoid Robot

Humanoid robots, designed to mimic the structure and behavior of humans, have seen significant advancements in kinematics, dynamics, and control systems. Teleoperation of humanoid robots involves complex control strategies to manage bipedal locomotion, balance, and interaction with environments. Research in this area has focused on developing robots that can perform tasks in environments designed for humans, from simple object manipulation to navigating complex terrains. Reinforcement learning has emerged as a powerful method for enabling robots to learn from interactions with their environment, improving their performance over time without explicit programming for every possible scenario. In the context of humanoid robotics and teleoperation, RL can be used to optimize control policies, adapt to new tasks, and improve the efficiency and safety of human-robot interactions. Key challenges include the high dimensionality of the action space, the need for safe exploration, and the transfer of learned skills across different tasks and environments. Integrating human motion tracking with reinforcement learning on humanoid robots represents a cutting-edge area of research. This approach involves using human motion data as input to train RL models, enabling the robot to learn more natural and human-like movements. The goal is to develop systems that can not only replicate human actions in real-time but also adapt and improve their responses over time through learning. Challenges in this area include ensuring real-time performance, dealing with the variability of human motion, and maintaining stability and safety of the humanoid robot. Show details add remove

real-time, humanoid, reinforcement learning, representation learning

Hosts He Junzhe , Li Chenhao , Li Chenhao

Continuous Skill Learning with Fourier Latent Dynamics

In recent years, advancements in reinforcement learning have achieved remarkable success in teaching robots discrete motor skills. However, this process often involves intricate reward structuring and extensive hyperparameter adjustments for each new skill, making it a time-consuming and complex endeavor. This project proposes the development of a skill generator operating within a continuous latent space. This innovative approach contrasts with the discrete skill learning methods currently prevalent in the field. By leveraging a continuous latent space, the skill generator aims to produce a diverse range of skills without the need for individualized reward designs and hyperparameter configurations for each skill. This method not only simplifies the skill generation process but also promises to enhance the adaptability and efficiency of skill learning in robotics. Show details add remove

representation learning, periodic autoencoders, learning from demonstrations, policy modulating trajectory generators

Hosts Li Chenhao , Rudin Nikita

Universal Humanoid Motion Representations for Expressive Learning-based Control

Recent advances in physically simulated humanoids have broadened their application spectrum, including animation, gaming, augmented and virtual reality (AR/VR), and robotics, showcasing significant enhancements in both performance and practicality. With the advent of motion capture (MoCap) technology and reinforcement learning (RL) techniques, these simulated humanoids are capable of replicating extensive human motion datasets, executing complex animations, and following intricate motion patterns using minimal sensor input. Nevertheless, generating such detailed and naturalistic motions requires meticulous motion data curation and the development of new physics-based policies from the ground up—a process that is not only labor-intensive but also fraught with challenges related to reward system design, dataset curation, and the learning algorithm, which can result in unnatural motions. To circumvent these challenges, researchers have explored the use of latent spaces or skill embeddings derived from pre-trained motion controllers, facilitating their application in hierarchical RL frameworks. This method involves training a low-level policy to generate a representation space from tasks like motion imitation or adversarial learning, which a high-level policy can then navigate to produce latent codes that represent specific motor actions. This approach promotes the reuse of learned motor skills and efficient action space sampling. However, the effectiveness of this strategy is often limited by the scope of the latent space, which is traditionally based on specialized and relatively narrow motion datasets, thus limiting the range of achievable behaviors. An alternative strategy involves employing a low-level controller as a motion imitator, using full-body kinematic motions as high-level control signals. This method is particularly prevalent in motion tracking applications, where supervised learning techniques are applied to paired input data, such as video and kinematic data. For generative tasks without paired data, RL becomes necessary, although kinematic motion presents challenges as a sampling space due to its high dimensionality and the absence of physical constraints. This necessitates the use of kinematic motion latent spaces for generative tasks and highlights the limitations of using purely kinematic signals for tasks requiring interaction with the environment or other agents, where understanding of interaction dynamics is crucial. We would like to extend the idea of creating a low-level controller as a motion imitator to full-body motions from real-time expressive kinematic targets. Show details add remove

representation learning, periodic autoencoders

Hosts Li Chenhao , Li Chenhao , Li Chenhao

Humanoid Locomotion Learning and Finetuning from Human Feedback

In the burgeoning field of deep reinforcement learning (RL), agents autonomously develop complex behaviors through a process of trial and error. Yet, the application of RL across various domains faces notable hurdles, particularly in devising appropriate reward functions. Traditional approaches often resort to sparse rewards for simplicity, though these prove inadequate for training efficient agents. Consequently, real-world applications may necessitate elaborate setups, such as employing accelerometers for door interaction detection, thermal imaging for action recognition, or motion capture systems for precise object tracking. Despite these advanced solutions, crafting an ideal reward function remains challenging due to the propensity of RL algorithms to exploit the reward system in unforeseen ways. Agents might fulfill objectives in unexpected manners, highlighting the complexity of encoding desired behaviors, like adherence to social norms, into a reward function. An alternative strategy, imitation learning, circumvents the intricacies of reward engineering by having the agent learn through the emulation of expert behavior. However, acquiring a sufficient number of high-quality demonstrations for this purpose is often impractically costly. Humans, in contrast, learn with remarkable autonomy, benefiting from intermittent guidance from educators who provide tailored feedback based on the learner's progress. This interactive learning model holds promise for artificial agents, offering a customized learning trajectory that mitigates reward exploitation without extensive reward function engineering. The challenge lies in ensuring the feedback process is both manageable for humans and rich enough to be effective. Despite its potential, the implementation of human-in-the-loop (HiL) RL remains limited in practice. Our research endeavors to significantly lessen the human labor involved in HiL learning, leveraging both unsupervised pre-training and preference-based learning to enhance agent development with minimal human intervention. Show details add remove

reinforcement learning from human feedback, preference learning

Hosts Li Chenhao , Li Chenhao , Chen Xin , Li Chenhao

Online Safe Locomotion Learning in the Wild

Reinforcement learning (RL) can potentially solve complex problems in a purely data-driven manner. Still, the state-of-the-art in applying RL in robotics, relies heavily on high-fidelity simulators. While learning in simulation allows to circumvent sample complexity challenges that are common in model-free RL, even slight distribution shift ("sim-to-real gap") between simulation and the real system can cause these algorithms to easily fail. Recent advances in model-based reinforcement learning have led to superior sample efficiency, enabling online learning without a simulator. Nonetheless, learning online cannot cause any damage and should adhere to safety requirements (for obvious reasons). The proposed project aims to demonstrate how existing safe model-based RL methods can be used to solve the foregoing challenges. Show details add remove

safe mode-base RL, online learning, legged robotics

Hosts Li Chenhao , Li Chenhao , Li Chenhao , Li Chenhao

Autonomous Curriculum Learning for Increasingly Challenging Tasks

While the history of machine learning so far largely encompasses a series of problems posed by researchers and algorithms that learn their solutions, an important question is whether the problems themselves can be generated by the algorithm at the same time as they are being solved. Such a process would in effect build its own diverse and expanding curricula, and the solutions to problems at various stages would become stepping stones towards solving even more challenging problems later in the process. Consider the realm of legged locomotion: Training a robot via reinforcement learning to track a velocity command illustrates this concept. Initially, tracking a low velocity is simpler due to algorithm initialization and environmental setup. By manually crafting a curriculum, we can start with low-velocity targets and incrementally increase them as the robot demonstrates competence. This method works well when the difficulty correlates clearly with the target, as with higher velocities or more challenging terrains. However, challenges arise when the relationship between task difficulty and control parameters is unclear. For instance, if a parameter dictates various human dance styles for the robot to mimic, it's not obvious whether jazz is easier than hip-hop. In such scenarios, the difficulty distribution does not align with the control parameter. How, then, can we devise an effective curriculum? In the conventional RSL training setting for locomotion over challenging terrains, there is also a handcrafted learning schedule dictating increasingly hard terrain levels but unified with multiple different types. With a smart autonomous curriculum learning algorithm, are we able to overcome separate terrain types asynchronously and thus achieve overall better performance or higher data efficiency? Show details add remove

curriculum learning, open-ended learning, self-evolution, progressive task solving

Hosts Li Chenhao , Li Chenhao , Li Chenhao , Bagatella Marco , Li Chenhao

Humanoid Locomotion Learning with Human Motion Priors

Humanoid robots, designed to replicate human structure and behavior, have made significant strides in kinematics, dynamics, and control systems. Research aims to develop robots capable of performing tasks in human-centric settings, from simple object manipulation to navigating complex terrains. Reinforcement learning (RL) has proven to be a powerful method for enabling robots to learn from their environment, enhancing their performance over time without explicit programming for every possible scenario. In the realm of humanoid robotics, RL is used to optimize control policies, adapt to new tasks, and improve the efficiency and safety of human-robot interactions. However, one of the primary challenges is the high dimensionality of the action space, where handcrafted reward functions fall short of generating natural, lifelike motions. Incorporating motion priors into the learning process of humanoid robots addresses these challenges effectively. Motion priors can significantly reduce the exploration space in RL, leading to faster convergence and reduced training time. They ensure that learned policies prioritize stability and safety, reducing the risk of unpredictable or hazardous actions. Additionally, motion priors guide the learning process towards more natural, human-like movements, improving the robot's ability to perform tasks intuitively and seamlessly in human environments. Therefore, motion priors are crucial for efficient, stable, and realistic humanoid locomotion learning, enabling robots to better navigate and interact with the world around them. Show details add remove

motion priors, humanoid, reinforcement learning, representation learning

Learning World Models for Legged Locomotion

Model-based reinforcement learning learns a world model from which an optimal control policy can be extracted. Understanding and predicting the forward dynamics of legged systems is crucial for effective control and planning. Forward dynamics involve predicting the next state of the robot given its current state and the applied actions. While traditional physics-based models can provide a baseline understanding, they often struggle with the complexities and non-linearities inherent in real-world scenarios, particularly due to the varying contact patterns of the robot's feet with the ground. The project aims to develop and evaluate neural network-based models for predicting the dynamics of legged environments, focusing on accounting for varying contact patterns and non-linearities. This involves collecting and preprocessing data from various simulation environment experiments, designing neural network architectures that incorporate necessary structures, and exploring hybrid models that combine physics-based predictions with neural network corrections. The models will be trained and evaluated on prediction autoregressive accuracy, with an emphasis on robustness and generalization capabilities across different noise perturbations. By the end of the project, the goal is to achieve an accurate, robust, and generalizable predictive model for the forward dynamics of legged systems. Show details add remove

forward dynamics, non-smooth dynamics, neural networks, model-based reinforcement learning

Parametrized Shape Optimization using Surrogate Fluid Models

Fast and efficient structure optimization based on parametrized shapes in surrogate fluid simulation environment. Show details add remove

surrogate modeling, deep learning, fluid simulation, optimization

Semester Project , Bachelor Thesis , Master Thesis

Published since: 2024-07-19 , Earliest start: 2023-09-01 , Latest end: 2024-12-31

Hosts Katzschmann Robert, Prof. Dr. , Michelis Mike

Topics Information, Computing and Communication Sciences , Engineering and Technology , Physics

Master Thesis ETH Zurich / ETH AI Center: Infrastructural Control Algorithm for Fairness in Road Traffic Engineering

Do you want to work on smart control algorithms that control the infrastructure of a road network to optimize vehicle traffic flows? And do you want to try them out in a fully-fledged traffic simulator called SUMO? Then this is thesis project is for you. The goal of this thesis is to develop an infrastructural control algorithm that optimizes efficiency and fairness of road traffic flows. You can choose one from the following control applications: intersection management (control flow at intersection), ramp metering (control flow that enters highways), perimeter control (control flows between cells/regions of an urban network). Optional, if interested: depending on your progress and results, we can also support & guide you with creating a scientific publication for your first steps into academia. Show details add remove

Control, AI, Artificial Intelligence, Machine Learning, Reinforcement Learning, Fairness, Transportation, Traffic Engineering, Infrastructure Control, Roads

Bachelor Thesis , Master Thesis , ETH Zurich (ETHZ)

Published since: 2024-07-15 , Earliest start: 2024-07-15 , Latest end: 2025-06-28

Hosts Riehl Kevin

Topics Mathematical Sciences , Information, Computing and Communication Sciences , Engineering and Technology , Commerce, Management, Tourism and Services , Behavioural and Cognitive Sciences

Development of an Open-Source Tool for Biological Age Prediction Using Wearable Accelerometer Data

an opportunity to create an open-source tool that empowers the scientific community to perform digital biological age estimation with high precision and reproducibility Show details add remove

Digital Health, Digital Biomarkers, R/Python Package; Open-Source Tool; Wearables; Reproducibility; Software Package; Biological Age Estimation; Machine Learning; Artificial Intelligence

Published since: 2024-07-15 , Earliest start: 2024-07-22

Hosts Da Conceição Barata Filipe

Topics Medical and Health Sciences , Mathematical Sciences , Information, Computing and Communication Sciences , Engineering and Technology

Master thesis: Secure machine learning to enhance hospital collaboration

This project aims to evaluate the use of fully homomorphic encryption (FHE) in training machine learning models for antimicrobial resistance prediction using datasets from four different hospitals. The goal is to overcome legal constraints on data sharing and address concerns about model generalizability due to variations between hospitals. The project involves conducting simulations, reproducing existing results, and improving the current machine learning pipeline to incorporate FHE. Show details add remove

machine learning, hospital collaboration, secure training, antimicrobial resistance

Collaboration , Internship , Master Thesis

Published since: 2024-06-26 , Earliest start: 2024-08-01

Hosts Duroux Diane

Topics Medical and Health Sciences , Information, Computing and Communication Sciences

Master Thesis / Student Project in Foundation Models for Robotic Manipulation hosted @ mimic

We host projects on the topic of Foundation Models for Robotic Manipulation. Show details add remove

machine learning, behavior cloning, imitation learning, robotics, manipulation, dexterous manipulation, end-to-end training, transformers, sequence modeling, pre-training, diffusion policy

Semester Project , Bachelor Thesis , Master Thesis , ETH Zurich (ETHZ)

Published since: 2024-06-10 , Earliest start: 2024-08-01 , Latest end: 2025-02-28

Hosts Nava Elvis

• Press Enter to activate screen reader mode.

Sustainable Construction

Bachelor thesis, proposals for the spring semester 2024.

The goal of the projects consists in developing alternative building materials to substitute from the current technologies and get an in depth understanding of the materials' properties. Are you passionate about sustainable buildings materials and circular economy?

Are you interested in saving the world with low cost product but high technology and science?

Are you interested in working in the Lab?

Are you creative?

We need your contribution to develop these topics:

• Big data in LCA: analysing the data from Environmental Product Declarations (EPDs) for construction products
• Perspectives for Carbon Capture, Utilisation and Storage (CCUS) application in the construction value chain
• Biostabilization for earthen materials development
• Comprehend the shrink behaviors of poured and 3D- printed earth materials

Download More Information: Bachelor Thesis Topics Spring Semester 2024 (PDF, 88 KB)

More information on Bachelor's Thesis at D-BAUG

Completed Bachelor's theses can be found here .

• Press Enter to activate screen reader mode.

Micro- and Nanosystems

Bachelor theses.

Independent, structured scientific activity.

Written report and presentation required.

Presentation:

- 20 minutes Powerpoint presentation by the student explaining the work performed

- Q&A at the end of the presentation

Tissue mimicking materials for a realistic sensing environment

In this project, you will develop new tissue mimicking materials to use in ultrasonic experimental characterization, in order to reproduce a realistic sensing environment in-vitro. You will also have the opportunity to learn acoustic characterization techniques applied to MEMS and implantable sensors, while working betwen ETH Zurich and EMPA Dubendorf.

Passive Implantable Passive Sensor: process variation study

The aim of this interdisciplinary project is to develop a new passive implantable sensor based on acoustics interrogation, with the ultimate goal to estimate the early on-set of the disease and improve patients’ life.

Optimization of SWCNT growth for integration into nanodevices

Optimizing conditions for synthesis of single walled carbon nanotubes utilizing CVD systems localized at the Binnig and Rohrer Nanotechnology Center in Rüschlikon/Zürich. Characterization of SWNTs.

Synthesis of SWNTs from ferritin precursors embedded in amorphous carbon film

Optimizing conditions for synthesis of single walled carbon nanotubes from ferritin precursors embedded in amorphous carbon film utilizing CVD systems localized at the Binnig and Rohrer Nanotechnology Center in Rüschlikon/Zürich.

Optical visualization of Single Walled Carbon Nanotubes

Optimization of deposition and evaporation condition of specific material (for example pNBA = p-nitrobenzoic acid) forming submicroscopic particles on as-grown SWNTs. Localization of CNTs by optical microscopy. Electrical characterization of CNFET devices fabricated from SWNTs pre-localized by optical microscopy imaging.

Characterization of individual Single Walled Carbon Nanotubes by Raman spectroscopy

Characterization of SWNTs synthetized by a CVD process on MEMS chips by Raman spectroscopy utilizing multiple laser wavelengths. Determination of presence of DWNTs, bundles and individual SWNTs as well as their characteristics and quality.

Modeling and simulation of advanced carbon nanotube sensors

Development of a toolchain based on COMSOL and Matlab to simulate the modulation of charge transport in carbon nanotube sensors due to mechanical or chemical effects.

Monitoring Single Walled Carbon Nanotubes decoration by Raman spectroscopy and electrical measurements

SWNT decoration by preselected nanoparticle types and determination of the impact of the material onto nanotube characteristics and CNFET performance.

This project is not available anymore!

Characterization of thermal actuators for tuning of cnt nanoresonators.

The thermal actuators have been fabricated already using standard microfabrication technology. The current-strain characteristics need to be calibrated using SEM optical methods as well as numerical methods (COMSOL)

Characterizing the Influence of Cyclic Loading onto the Electrical Resistance of Flex‐Lines

Keywords: Artificial robotic finger, flex‐lines, electrical resistance, long term testing Motivation The overall goal of this project is the development of an artificial robotic skin which integrates tactile sensing capabilities into an artificial finger. More than 100 sensing units, electrically connected by flex‐lines, are distributed in an array over the finger. The sensors as well as the flex‐lines are subject to various mechanical loads throughout thelifetime of the finger.

• Press Enter to activate screen reader mode.

IRIS - Institute of Robotics and Intelligent Systems

Bachelor theses at iris.

ETH Zurich uses SiROP to publish and search scientific projects. For more information visit sirop.org call_made .

System integration and automation of 3D printer for smart materials printing

Stereolithography (SLA) 3D printing technology offers high speed and resolution for printing smart materials that respond to external stimuli such as light, ultrasound, and magnetic fields. We have developed an SLA 3D printer equipped with a control interface implemented in Python within the ROS framework. The student will work on improving the current printer design by integrating a rotation platform to enable a third degree of freedom in printing. Additionally, the student will modify the control interface to achieve full automation of the printing process. The student will also characterize the final printing performance. Demonstrations will be designed to highlight the advantages of this enhanced 3D printer. (Don’t you want to make this cute 2D Pikachu become 3D alive?!) Show details add remove

Hardware integration, Software Integration, ROS, Python, 3D printing.

Semester Project , Bachelor Thesis

Description

Contact details, more information.

Open this project...  call_made

Published since: 2024-09-05 , Earliest start: 2024-09-09 , Latest end: 2025-02-28

Organization Multiscale Robotics Lab

Hosts Chen Huimin

Topics Engineering and Technology

Design and Development of Multi-material Microscale 3D Printing System

This project's main focus is to design and develop parts for a novel multi-material microscale 3D printing system. Show details add remove

Design, Development, Microscale, 3D Printing, (Bio-)printing, CAD, Multi-material

Bachelor Thesis , Master Thesis

Published since: 2024-09-03 , Earliest start: 2024-09-09 , Latest end: 2025-03-31

Organization Acoustic Robotics for Life Sciences and Healthcare (ARSL)

Hosts Agrawal Prajwal

Algorithms Implementation for 3D Microscale Fabrication

This project focuses on the incorporation of novel algorithms to control a 3D microscale fabrication system. Show details add remove

Algorithms, Programming, Software, (Bio-)printing, 3D Printing, Control System

Topics Information, Computing and Communication Sciences , Engineering and Technology

Optical Setup Design and Simulation for Advanced Microscale Manufacturing

This project focuses on the design and simulation of an optical setup for advanced microscale manufacturing. Show details add remove

Additive Manufacturing, Microscale, 3D printing, Design, Development, Simulation

Topics Information, Computing and Communication Sciences , Engineering and Technology , Physics

New process for conductive metallic traces for e-textile applications

The goal of the project is to develop simple procedures to deposit metals onto everyday fabrics, for use in e-textiles Show details add remove

e-textiles, wearable electronics, metal, chemistry, plating, 3D printing, additive manufacturing

Published since: 2024-09-02 , Earliest start: 2024-09-15 , Latest end: 2025-02-15

Organization Biomedical and Mobile Health Technology Lab

Hosts Li Yuanlong

Conduct human gait study with optical motion capture to assess smart clothing for movement monitoring

We aim to conduct a study with human participants to assess the function of our textile-based wearable technology for movement monitoring in clinical and fitness scenarios. Show details add remove

smart clothing, wearable technology, textile sensor, fitness tracking, sports medicine, rehabilitation, human study, motion capture, computer science

Semester Project , Internship , Bachelor Thesis , Master Thesis

Published since: 2024-08-29 , Earliest start: 2024-12-01 , Latest end: 2025-09-30

Hosts Ahmadizadeh Chakaveh

Topics Medical and Health Sciences , Information, Computing and Communication Sciences , Engineering and Technology

Breathable hydrogel fabric electrodes for bioelectrical signal detection

The goal of this project is to construct a breathable hydrogel electrode on an everyday fabric substrate for bioelectrical signal detection at the skin interface. Show details add remove

textile, wearable, hydrogel, electrode, electromyography

Published since: 2024-08-28 , Earliest start: 2024-09-01 , Latest end: 2025-03-01

Hosts Yang Weifeng

Topics Medical and Health Sciences , Engineering and Technology

Development of a sensorized device for hand rehabilitation

Accident-related injuries or neurological conditions such as stroke can lead to upper limb deficits. Hand rehabilitation is critical for people to restore or improve hand functionality after such an event. For rehabilitation to be successful, people need to perform significant doses of therapy in clinic, which is resource intensive. This project aims to develop a sensorized device that integrates with hand rehabilitation games, designed to engage patients and increase the amount of therapy they can perform at home. By leveraging real-time data and interactive games, the goal is to create a device that can be used outside the clinic to increase the therapy dose. Show details add remove

Mechanical Design, Engineering, Product Development, Hand Rehabilitation, Sensorized Device, Gamification, Rehabilitation Technology

Semester Project , Internship , Bachelor Thesis , Master Thesis , ETH Zurich (ETHZ)

PLEASE LOG IN TO SEE DESCRIPTION

Published since: 2024-08-27 , Earliest start: 2024-09-15 , Latest end: 2025-05-01

Organization Rehabilitation Engineering Lab

Hosts Retevoi Alexandra

Ultra-flexible catheter for thrombi elimination based on surface acoustic wave

Medical thrombus elimination catheters play a crucial role in modern medicine, especially in the treatment of thrombotic diseases. Conventional catheterization techniques mostly rely on mechanical control, which not only limits operational flexibility, but also requires a high level of skill and long hours of operation. In addition, the safety of rigid materials is an important issue. To address these issues, we propose a thrombus-elimination catheter technology based on a flexible acoustic surface wave device. This technology utilizes acoustic surface waves to drive the flexible components of the catheter. Compared to conventional catheters, acoustic surface wave-driven catheters do not require metal wires or other rigid materials, making them safer and easier to operate. This catheter technology enables precise thrombus elimination with excellent biocompatibility and penetration. We designed, fabricated, and tested SAW-driven catheters with different electrode morphologies and explored their effectiveness in thrombus elimination. The experimental results demonstrate the efficiency and safety of SAW-driven catheters in thrombus elimination, laying the foundation for future broad applications in this field. Show details add remove

Soft and reconfigurable catheter; Surface acoustic waves; Biocompatibility and penetration; hrombus-elimination technology

Bachelor Thesis , Master Thesis , ETH Zurich (ETHZ)

Published since: 2024-08-19 , Earliest start: 2024-08-21 , Latest end: 2025-03-01

Hosts Ahmed Daniel, Prof.

Topics Engineering and Technology , Physics

Solvothermal synthesis of high-performance metal ferrite nanoparticle for biomedical application

Metal ferrite nanoparticle are gathering increasing attention for usage in biomedical applications such as for drug delivery or diagnostics. Their large versatility is thereby enabled by adjusting various of their properties, such as magnetic response or surface design. Precise tuning of the nanoparticles magnetic properties and their reliable reproducibility, however, still remains a challenge by this day. In this project we aim to systematically investigate varying synthesis parameters in the solvothermal synthesis of different metal ferrite nanoparticles. We aim to establish a reliable protocol for large scale production of particles displaying exceptionally strong magnetic response while also enabling precise control over their displayed magnetic hysteresis. Show details add remove

Nanoparticles, Iron Oxide, Microrobotics, Nanomagnetism.

Semester Project , Bachelor Thesis , Master Thesis

Published since: 2024-08-19 , Earliest start: 2024-09-02

Applications limited to ETH Zurich

Hosts Pustovalov Vitaly

Topics Engineering and Technology , Chemistry , Physics

Development and Testing of Electrical Systems for a SmartVNS Docking Station with Focus on Wireless Data Management

We are looking for an enthusiastic electrical/firmware engineer to design and implement the electrical and firmware aspects of a docking station for the SmartVNS device. The station will charge the device components (pulse generator and wrist motion tracker) and pull data from the pulse generator and motion tracker, uploading it to an online server via Wi-Fi. This project will also involve testing the reliability of data transfer and power systems under real-world conditions, providing valuable insights into the practical application of this technology. Show details add remove

Electrical, embedded, electronic, engineering, biomedical

Internship , Bachelor Thesis , Master Thesis

Published since: 2024-08-15 , Earliest start: 2024-08-18 , Latest end: 2025-10-01

Hosts Viskaitis Paulius

Design and Development of a SmartVNS Docking Station with Integrated Usability Testing

Join our team in developing a mechanical docking station for the SmartVNS device, a cutting-edge neurorehabilitation system designed to enhance stroke recovery. The docking station will securely hold and charge the SmartVNS components: the earpiece electrode, over-the-neck pulse generator, cable, and wrist motion tracker. Your task will involve designing a station that is both user-friendly and practical, ensuring all components are comfortably stored and easily accessible. Additionally, you will conduct usability testing to assess how well the docking station meets the needs of patients and clinicians, and make iterative improvements based on feedback. Show details add remove

Mechanical, usability, design, rehabilitation, stroke, neuroscience

Published since: 2024-08-15 , Earliest start: 2024-09-01 , Latest end: 2025-09-30

Bioinspired Ultrasound Microrobots

Inspired by naturally-occurring microswimmers such as spermatozoa that exploit the nonslip boundary conditions of a wall, we propose here a microrobot design (a “sperm-bot”) that can execute upstream motility triggered by ultrasound. Show details add remove

Robotics, micro and nanorobots, microrobotics, soft robotics ultrasound, bioinspired

Semester Project , Bachelor Thesis , Master Thesis , Summer School

Published since: 2024-08-14 , Earliest start: 2024-10-01 , Latest end: 2024-12-19

Resonant Acoustic Microrobots

The newly designed microrobot consists of a cavity at the center of its body within the polymer matrix. The microcavity supports an air-bubble trap, which enables propulsion in an acoustic field. Show details add remove

Keywords: microrobotics, soft swimmers, acoustics, ultrasound, biomedical applications

Published since: 2024-08-14 , Earliest start: 2024-02-15 , Latest end: 2024-12-19

Optimization and Automation of Dual-Balloon Catheter Fabrication for Preclinical Neurovascular Applications

Join our cutting-edge research team in pioneering the next generation of neurovascular treatment technologies. This thesis will focus on optimizing and automating the fabrication of an innovative dual-balloon catheter system designed for precise drug delivery in the treatment of intracranial arteriosclerotic disease (ICAD). You will work closely with a multidisciplinary team, including medical experts in neurology, to conduct preclinical trials using pig models. This role offers a unique opportunity to contribute to groundbreaking research that bridges the gap between advanced medical technology and clinical application, with significant potential for real-world impact. Show details add remove

Catheter Fabrication; Drug Delivery System; Neurovascular Intervention; Medical Robotics; Preclinical Trials

Published since: 2024-08-13 , Earliest start: 2024-09-01 , Latest end: 2025-09-01

Hosts Franco Carlos

Conductive polymer pattern deposition for smart textile applications

The goal of the project is to develop a simple and versatile method for production of robust conductive patterns on textile via deposition of conductive polymers. This technology will allow further development of wearable electronics for biomedical applications. Show details add remove

wearable, smart textile, conducting polymer, polymerization, capacitance, conductivity

Published since: 2024-08-06 , Earliest start: 2024-08-01 , Latest end: 2025-08-01

Hosts Shokurov Aleksandr

Topics Medical and Health Sciences , Engineering and Technology , Chemistry

iMove: instrumented Movements (mobile & low budget)

Neurological patients frequently experience upper limb sensorimotor impairment, necessitating effective rehabilitation strategies to restore functionality. Accurate assessments of patient movements are integral to these strategies, requiring precise measurement tools. The rapid advancements in AI pose estimation and biomechanical modeling offer a promising solution: a low-budget, user-friendly tool for accurately measuring patient movements in diverse settings. We are developing such a tool, iMove, which leverages video-based AI technology to provide clinical-grade precision.Your role will involve improving iMove's graphical user interface (GUI) and algorithms, as well as testing its performance and usability in collaboration with researchers, clinicians, and potentially patients. Show details add remove

neurorhebilitation, computervision, biomechnical modelling, frontend, backend, ai, usability, GUI, webcams, cameras, stroke, assessments

Semester Project , Course Project , Collaboration , Internship , Lab Practice , Bachelor Thesis , Master Thesis

Your Profile

Published since: 2024-08-06 , Earliest start: 2024-08-12

Hosts Unger Tim

Design and fabrication of sample fixtures for the micromechanical testing of nanometric thin films

Freestanding ceramic oxide thin films have significant potential in medical applications, such as implantable electronics (Fig. a) and functional microrobots. They exhibit distinguished mechanical properties compared to their bulk counterpart, such as superior flexibility and elasticity. This project aims to understand the mechanisms behind these exceptional mechanical properties, and their correlation with other functional properties (magnetism, etc.). The student will design, fabricate, and implement sample fixtures that can be equipped with material property characterization devices (as illustrated in Fig. b) to apply strain to thin films. Show details add remove

Mechanical engineering; Microrobotics; Thin films

Published since: 2024-08-05 , Earliest start: 2024-08-11 , Latest end: 2025-09-01

Hosts Mirjolet Mathieu

Feedback Optimization of Acoustic Patterning in Real Time for Bioprinter

Our project aims to enhance the ultrasound-assisted bioprinting process using real-time feedback and image processing. We have developed a transparent nozzle equipped with multiple cameras for real-time monitoring. The next steps involve integrating advanced image processing techniques, such as template matching, and implementing a feedback system to optimize the printing process. The system will be fully automated, featuring a function generator for wave creation and cooling elements. By analyzing the printing process and acoustic cell patterning with computer vision and leveraging real-time sensor feedback, we aim to dynamically optimize parameters such as frequency and amplitude for accurate and consistent pattern formation, crucial for bio applications. Show details add remove

Machine learning, control and automation, 3D Printing, Ultrasound

Published since: 2024-08-02 , Earliest start: 2024-08-10 , Latest end: 2025-05-30

Hosts Agrawal Prajwal , Medany Mahmoud

Topics Medical and Health Sciences , Information, Computing and Communication Sciences , Engineering and Technology , Behavioural and Cognitive Sciences

Develop Python Software to Automate 5D Printing with Robotic Arm and Stress Curve Slicing Mechanism

Our project aims to develop a Python-based software to automate the generation of G-code for 5D printing with a robotic arm, emphasizing slicing along stress curves. The program will interpret Standard Triangle Language (STL) files and integrate user-defined stress parameters to perform stress point analysis. This analysis will inform the slicing paths, optimizing material distribution and enhancing structural integrity. The software will also feature a graphical user interface (GUI) for visualizing parameters, including acoustic pattern analysis. Additionally, it will accommodate the robotic arm's restrictive movements to ensure precise path planning and execution. An integrated feedback mechanism will automate the printing process, improving control and efficiency. Show details add remove

Software, Python, Machine learning, control and automation, 3D Printing, robotic arm.

Published since: 2024-08-02 , Earliest start: 2024-09-01 , Latest end: 2025-03-31

Hosts Medany Mahmoud , Agrawal Prajwal

Development of an Integrated Control System for Electronics and Automation of Sensors and Actuators in a Robotic Arm-Based Bioprinter

This project aims to develop an integrated control system for a robotic arm-based bioprinter, focusing on enhancing precision and reliability in tissue engineering. The system will control various sensors and actuators, including temperature, humidity, gas sensors, UV lights, pneumatic pumps, HEPA filters, and heating and cooling chambers. Specifically, the control system will ensure environmental conditions are optimal for bioink viability and structural integrity during the printing process. The robotic arm and end effectors will be calibrated to achieve a printing resolution of 200 microns. This initiative will rigorously test the integrated controls to confirm their efficacy in maintaining precise operational parameters, thereby advancing bioprinting technology. Show details add remove

Control systems, GCODE, automation, 5D bioprinting, bioengineering, mechatronics, robotics, sensors, actuators, robotic arm

Drug Screening with 3D Bioprinted Tissue Constructs

In this thesis, we aim to harness the latest advancements in 3D bioprinting of tissue constructs for drug screening applications. Our focus is on evaluating drug efficacy in custom-built bioprinted tissue constructs, and comparing these with microfluidics, organoids, and spheroid-based drug screening methods. By integrating state-of-the-art bioprinting technologies and novel bioinks, this project aims to create biomimetic tissues that can better mimic human tissue thus significantly enhancing drug screening processes. The research will involve the design of drug screening constructs, the testing of various drugs, and the analysis and comparison to traditional methods. Furthermore, we will explore possibilities to improve the construct design to produce more human-mimetic tissues, thereby enhancing human relevance and optimizing outputs. This will offer a more accurate and efficient platform for pharmacological testing and toxicity analysis. Show details add remove

3D bioprinting, drug screening, tissue constructs, pharmacological testing, biomimetics, tissue engineering, biomimetic design.

Published since: 2024-08-01 , Earliest start: 2024-09-01 , Latest end: 2025-03-31

Topics Medical and Health Sciences , Biology

Automation of Robotic arm-based Bioprinter for printing complex geometries

This project mainly focuses on automating the robotic arm-assisted bioprinter by integrating sensors and actuators and optimizing the printing process for fine-tuning. This will also involve automating the robotic arm with the print head control for better complex 3D prints at high resolution and accuracy of the print path. The robotic arm utilized here is the MECA 500 robotic arm with 5-micrometer repeatability, increasing the precision of the printing process. This printer will be used for bioprinting applications. Show details add remove

5D bioprinter, Robotics, Acoustics, additive manufacturing, tissue engineering, control system, robotic arm, automation, artificial intelligence, sensors, actuators.

Published since: 2024-08-01 , Earliest start: 2024-08-01 , Latest end: 2025-03-01

Assessing the feasibility of plantar pressure measurement devices for monitoring the diabetic population

The goal of the project is to assess the feasibility of using commercially available plantar pressure monitoring devices (so called smart insoles) on the diabetic population. Pressure ulcers are a common complication of the diabetic foot, and monitoring plantar pressure continuously is a potential measure of prevention. Diabetic patients are often prescribed personalized footwear (e.g., curved insoles that accommodate any deformity in the feet). This project aims at assessing the potential of the smart insoles available on the market to monitor plantar pressure in diabetic patients with such custom footwear. Show details add remove

wearables, mobile health, prevention, plantar pressure monitoring, diabetic foot

Published since: 2024-07-23 , Earliest start: 2024-04-08 , Latest end: 2024-09-02

Hosts Galli Valeria

Automation of DLP Printer with feedback system

This project mainly focuses on the incorporation of automation control in DLP Printer and manipulate particles using external energy incorporated within a feedback-loop system. Show details add remove

bioprinting, automation, microparticles manipulation, 3D printing, control system

Published since: 2024-07-22 , Earliest start: 2024-09-01 , Latest end: 2025-03-31

Activity and fatigue detection using machine learning based on real-world data from smart clothing

The aim of this project is to use machine learning methods to extract useful information such as activity type and fatigue level from real-world data acquired from our textile-based wearable technology during sport activities. Show details add remove

smart clothing, wearable technology, textile sensor, fitness tracking, sports medicine, fatigue, machine learning, artificial intelligence, computer science

Published since: 2024-07-15 , Earliest start: 2023-09-15 , Latest end: 2024-05-31

Internships (Industrial or Research) on Body Modelling and Sensing Technology for Health Care in SCI

This hands-on work (internship or semester project) within a clinical setting will bring you close to intelligent health management while exploring multiple data systems. You will experience multimodal data of robotics rehabilitation, general clinical practice, and detailed clinical studies applied in classification and dimensionality reduction. Show details add remove

Machine learning, time-series, HR, ECG, BP, wearables, nearables, Medical and health science, healthcare, Android studio, App development

Semester Project , Internship , Lab Practice , Bachelor Thesis , Master Thesis , Other specific labels , ETH Zurich (ETHZ)

Project Background

Your benefits.

Published since: 2024-07-05 , Earliest start: 2024-08-19 , Latest end: 2025-08-31

Applications limited to ETH Zurich , EPFL - Ecole Polytechnique Fédérale de Lausanne , Empa , Eawag , Zurich University of the Arts , Zurich University of Applied Sciences , Wyss Translational Center Zurich , University of Zurich , University of St. Gallen , University of Lucerne , University of Lausanne , University of Geneva , University of Fribourg , University of Berne , University of Basel , Lucerne University of Applied Sciences and Arts , Institute for Research in Biomedicine , IBM Research Zurich Lab , Swiss Institute of Bioinformatics , CSEM - Centre Suisse d'Electronique et Microtechnique , Corporates Switzerland , CERN , Hochschulmedizin Zürich , Université de Neuchâtel , Università della Svizzera italiana , Swiss National Science Foundation , University of Konstanz , University of Hamburg , University of Erlangen-Nuremberg , University of Cologne , Universität zu Lübeck , Universität Ulm , Universität der Bundeswehr München , TU Dresden , TU Darmstadt , TU Berlin , Technische Universität Hamburg , Max Planck Society , Otto Von Guericke Universitat, Magdeburg , RWTH Aachen University , Ludwig Maximilians Universiy Munich , Humboldt-Universität zu Berlin , European Molecular Biology Laboratory (EMBL) , Eberhard Karls Universität Tübingen , Max Delbruck Center for Molecular Medicine (MDC) , Technische Universität München , Imperial College London , National Institute for Medical Research , Royal College of Art , UCL - University College London , University of Aberdeen , University of Cambridge , University of Manchester , University of Nottingham , University of Oxford , University of Leeds , Delft University of Technology , Maastricht Science Programme , Radboud University Nijmegen , Utrecht University

Organization Sensory-Motor Systems Lab

Hosts Paez Diego, Dr. , Paez Diego, Dr. , Paez Diego, Dr.

Master Thesis / Internship / Semester Project: Digitization of large 12-lead ECG Image database

12-lead electrocardiograms (ECGs) are still solely documented on paper in many hospitals, especially in the Global South. These physical paper records provide a multitude of conditions recorded in many different countries. Our lab has access to a dataset with more than 8000 patient’s ECG photos / scans of 12-lead signals printed onto physical paper sheets. The dataset comprises 12-lead ECG image records from more than 35 hospital sites across Europe. The primary objective of this project is to develop an automated digitization pipeline from raw image scan in .png format towards 12 vectorized ECG time series in WFDB format. Show details add remove

Spinal Cord Injury, Computer Vision, CV, Machine Learning, Deep Learning, AI, Signal Processing, ECG, Medical Data, Healthcare

Published since: 2024-07-05 , Earliest start: 2024-09-01 , Latest end: 2025-06-30

Organization Spinal Cord Injury & Artificial Intelligence Lab

Hosts Paez Diego, Dr.

Develop software for wearable technologies

The aim of this project is to develop mobile software to communicate with our already developed textile-based wearable technology and process sensor data for movement monitoring. Show details add remove

smart clothing, wearable technology, software development, fitness tracking, sports medicine, mobile application, computer science

Published since: 2024-07-01 , Earliest start: 2024-07-22 , Latest end: 2025-08-31

Design data acquisition solution for smart clothing

The aim of this project is to develop and improve wearable electronics solutions for data acquisition from textile-based sensors used in our smart clothing. Show details add remove

smart clothing, wearable technology, textile sensor, fitness tracking, sports medicine, PCB, electronics, computer science

Published since: 2024-07-01 , Earliest start: 2023-09-15 , Latest end: 2025-08-31

Development of an Electro-adhesion Skin for a Humanoid Robotic Hand

Incorporating electro-adhesion pads on the artificial soft skin of a humanoid robotic hand to enhance its grasping ability in various scenarios. Show details add remove

Electro-adhesion, Humanoid Robotic Hands, Soft Robotics, Mechatronic Design

Work Packages

Requirements.

Published since: 2024-06-27 , Earliest start: 2024-08-01 , Latest end: 2025-02-01

Organization Soft Robotics Lab

Hosts Gravert Stephan-Daniel , Hinchet Ronan , Katzschmann Robert, Prof. Dr.

GPU Acceleration of Soft Body Modeling: Enhancing Performance with CUDA

The Soft Robotics Lab is developing a GPU-accelerated soft body modeling framework using the Finite Element Method (FEM). This enhancement aims to improve computational efficiency and enable more complex, real-time simulations. By leveraging GPUs' parallel processing power, simulations will be significantly faster. The project seeks to advance soft robotics research and enable innovative applications. Show details add remove

Soft Body Simulation, high-performance computing, GPU programming, Parallel Computing, Finite Element Method (FEM), Multiphysics Simulation

Published since: 2024-06-24 , Earliest start: 2024-08-01

Hosts Mekkattu Manuel , Katzschmann Robert, Prof. Dr.

Design and Fabrication of Dexterous, Humanoid Robotic Hand

Design and build dexterous human-like robotic hands with us at the Soft Robotics Lab and the spin-off mimic. We will explore different possibilities of developing design features such as tendon-driven mechanisms, lightweight structures, and complex mechanical joints of the hand. The developed features shall be integrated into a fully functional robotic hand and applied to solve practical manipulation challenges. Show details add remove

humanoid, robotics, hand, dexterity, soft robotics, actuation, prototyping, modeling and control, mechatronics, biomimetic, design, 3D printing, silicone casting

Published since: 2024-06-22 , Earliest start: 2024-09-01 , Latest end: 2025-07-24

Hosts Weirich Stefan

Explore Neural Activity during Walking

Gait-related symptoms in Parkinson's disease are challenging to treat and not all patients get the same benefits from different treatments. To identify neural biomarkers specific to Parkinsonian gait, a study combines neural activity recordings with gait kinematics in Parkinson's patients and a healthy control group. The aim of the study is to get new insights into neural activity during gait and inform future treatment approaches. Show details add remove

gait; EEG; DBS; neuroscience; rehabilitation; neurofeedback

Semester Project , Internship , Lab Practice , Bachelor Thesis , Master Thesis

Published since: 2024-06-10 , Earliest start: 2024-06-10 , Latest end: 2024-12-31

Hosts Salzmann Lena, MSc

Computational Modeling of Artificial Muscle Cells for Biohybrid Robots

This research aims to advance biohybrid robotics by integrating living biological components with artificial materials. The focus is on developing computational models for artificial muscle cells, a critical element in creating biohybrid robots. Challenges include modeling the complex and nonlinear nature of biological muscles, considering factors like elasticity and muscle fatigue, as well as accounting for fluid-structure interaction in the artificial muscle's environment. The research combines first principle soft body simulation methods and machine learning to improve understanding and control of biohybrid systems. Show details add remove

Biohybrid Robotics, Computational Models, Soft Body Simulation, Machine Learning, Surrogate Models, Finite Element Method (FEM)

Published since: 2024-06-09 , Earliest start: 2024-08-01

Hosts Katzschmann Robert, Prof. Dr. , Mekkattu Manuel

Topics Information, Computing and Communication Sciences , Engineering and Technology , Biology , Physics

Reliability and Validity testing of an Individuation device for a clinical use

After a neurological injury (such as stroke), many patients suffer from impairment of the hand and finger function. Clinical assessments aim to measure and quantify those impairments for a better understanding and to specifically target those deficits in rehabilitation. One aspect of hand function, that is not truly understood yet is finger individuation: the ability to move one finger independently of the others. In a previously developed assessment device, we use force sensors attached to a hand module to measure this dexterous skill. This individuation device will be used in a clinical setting to measure neurological patients. But before it can routinely be put into practice, its reliability (in a test-retest setting) and validity must be proven. Show details add remove

Rehabilitation engineering, reliability, validity, neurology, finger individuation, clinic, patients, assessment testing

Published since: 2024-05-01 , Earliest start: 2024-06-24 , Latest end: 2025-01-31

Hosts Knill Anna

• Press Enter to activate screen reader mode.

Department of Health Sciences and Technology

Student / Programme Doctorate at D-HEST

Proteomics Plattform D-HEST

HPM F 46

Otto-Stern-Weg 3

Switzerland

• contacts V-Card (vcf, 1kb)