This interdisciplinary block seminar deals with methods of modeling, generating and controlling movements in humans and robot systems. Students gain an insight into this interdisciplinary field and learn the basics of capturing biological motion, biomechanical simulation, robotics, and machine learning. In the introduction, the generation of human movement as effect of muscle contraction is discussed. It is shown how observed movement patterns can be identified and categorized and how these patterns can be reproduced on a humanoid robot. Finally, methods for learning movement primitives from human demonstration are presented and their application to motion generation in humanoid robots are explained.

Competency Goals:

The student knows methods for modeling, processing and analyzing human motions. He/she knows methods for learning motion primitives and mapping human motion to robots with different kinematics and dynamics and can apply these in new contexts.

Institutions: KIT IAR-H²T Prof. T. Asfour, University of Stuttgart, University of Tübingen 

This interdisciplinary block seminar is offered in cooperation with the University of Stuttgart and the University of Tübingen.

Competency certificate: Success is assessed by preparing documentation and a final presentation as a different type of success assessment in accordance with Section 4 (2) No. 3 of the SPO.

Module for Masters in Information Management, Mechanical Engineering, Mechatronics and Information Technology, Electrical Engineering and Information Technology, Sports Science

Workload: 90 h

Recommendations:

Programming skills in C++, Python or Matlab are recommended.
Attendance of the lectures Robotics I – Introduction to Robotics, Robotics II – Humanoid Robotics, Robotics III – Sensors and Perception in Robotics, Mechano-Informatics and Robotics and Wearable Robot Technologies is recommended.