After successful completion of the course, students are able to...
- understand the working principles of the most important machine learning algorithms in robotics
- apply machine learning algorithms in their interested robotic tasks and problems
- be qualified in doing research in robot learning.
The lecture covers robot learning methods and models and potential applications in industrial and service robotics. The lecture contains supervised learning and unsupervised learning approaches of robot learning. The course covers learning from demonstration, reinforcement learning, deep learning, and probabilistic learning approaches, and robot programming including teaching robotic tasks by interacting with human demonstrators.
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 will be based on project work. The students will write an extended abstract and give an oral presentation of their projects with details of methods and qualitative and quantitative results. Oral questions will be followed.
Not necessary
Contents of the lecture " Machine Learning"
