Learning-Based Model Predictive Control for a Gyro-Robot

Institute

Lehrstuhl für Angewandte Mechanik

Type

Bachelor's Thesis / Semester Thesis / Master's Thesis /

Content

experimental / theoretical /  

Description

Topic:

Recent work has examined a wide range of learning-enabled control techniques in simulation, including neural network–based system identification, supervised model learning, adaptive dynamics models, imitation-augmented MPC, hybrid RL–MPC schemes, and uncertainty-aware prediction models. These methods were benchmarked against classical MPC and RL across several simulated mechanical systems to identify the strengths and shortcomings. The proposed thesis advances this line of research by transferring these ideas from virtual testbeds to physical platforms, with a focus on the mini-wheelbot and a configurable cart-pole system.

The proposed thesis extends this research to physical platforms, focusing on the mini-wheelbot and a configurable cart-pole system. Your goal is to adapt and implement selected algorithms so they function robustly with real sensor data, real-time processing demands, and the constraints of embedded hardware. This involves assessing how learned models and learning-based controllers must be modified to cope with noise, latency, calibration drift, and other practical effects. The adjustable cart-pole provides a controlled environment for testing different modelling strategies, while the mini-wheelbot offers a more challenging, mobile platform for evaluating closed-loop performance and robustness. (See the attached pdf for more infor on the mini-wheelbot)

 

As with all my theses, the proposed topic is just a starting point. It is flexible and can be adjusted to what interests you and what direction the research leads. The expectations regarding results, prerequisits and work-ethic will be modulated based on whether a MA/SA or BA is written.

 

This topic ties into active research that I aim to publish. Depending on the strength of your thesis contributions, you may be invited to join as a co-author.

 

Application:

Please send all previous transcripts of records and your full CV to tomas.slimak@tum.de with the subject Application MA/SA/BA "name of thesis". Write a few sentences about what motivates you to apply for this thesis and why you would fit the topic. Please be specific in citing the experience/expertise that you have which would be relevant to this topic.

 

After submitting your application, it will be reviewed and if you are deemed suitable for the topic, you will be invited for an interview. Please be aware that part of this interview will be an oral evaluation of your background and understanding of concepts relevant to the thesis. The more preparation, creativity and initiative you are able to show, the better. It should be noted that given the iteresting but very advanced nature of this topic, only correspondingly strong students will be selected.

 

If you are interested in multiple theses that I am offering, do not send multiple applications, just name all the titles in a single mail. Applications and theses can be submitted in English or German as well.

Possible start

sofort

Contact

Tomas Slimak, M.Sc.
Room: 3104
Phone: +49 (89) 289 - 15226
tomas.slimaktum.de

Announcement