Master Thesis/Student Assistent: learning roboti data


Light-weight robotic arms become increasingly popular and important for cheap manufacturing as well as household tasks.  The decreasing costs of these systems increases the effort of control.  In this, we are looking for someone who is interested in working with real-world systems but has a background in machine learning.

Your task

You get to work with a new robotic arm, understanding its accuracy and motor control data.  Using novel machine-learning techniques (GPs, NNs, or whatever is applicable in for this task) you will model the data and improve system accuracy.

In your thesis, you will have to do both practical work (i.e., work with an existing test setup) and programming (i.e., develop the algorithms for data analysis). Knowledge of machine learning methods, e.g. from following our ML1 course, are required. Programming experience in Python and Matlab expected.

application procedure

To apply, please email us with the following information:

  • a letter of interest, including your prospective period of stay (note we normally do not accept students for less than 5 months)
  • a CV
  • a list of courses followed and grades
  • names of references, where applicable
  • reprints of articles or theses, where applicable

Please email all files as PDF to:


Picture of  Patrick van der Smagt

Patrick van der Smagt

current: Head of AI Research, data lab, VW Group

Previous: Director of BRML labs
fortiss, An-Institut der Technischen Universit√§t M√ľnchen
Professor for Biomimetic Robotics and Machine Learning, TUM

Chairman of Assistenzrobotik e.V.

We have somewhat different guidelines as to what a Master's thesis at BRML should look like. Please look at this piece of advise.