After successful completion of the course, students are able to...
- understand the recent trend in robot learning and a collection of state-of-the-art robot learning algorithms
- apply modern machine learning approaches in their interested robotic tasks.
- be qualified in doing research in robot learning and communicate the research results in form of written and oral presentations.
The lecture deepens the contents on robot learning algorithms, by investigating state-of-the-art robot learning methods. The course covers modern approaches of learning from demonstration, reinforcement learning, deep learning, etc. The lecture will contain research projects, in which a robotic task in service robotics applications will be tackled. It will contain the implementation of robot learning algorithms in simulation and optionally in real robots.
The contents of this lecture are presented with slides and on the blackboard. Discussion will help develop deeper understanding for the matter. To deepen, reinforce, and practically apply the material, short student projects will be conducted with simulations and experiments.
The evaluation is based on a project. A practical project will be evaluated based on the categories like algorithms, analysis of the results, report and presentation.
Not necessary
It is strongly recommended to finish the mandatory course "384.185 Machine Learning". It is recommended to finish the course “384.1895 Robot Learning”