Learning sequential force interaction skills

Simon Manschitz, Michael Gienger, Jens Kober, Jan Peters

Research output: Contribution to journalArticleScientificpeer-review

7 Downloads (Pure)


Learning skills from kinesthetic demonstrations is a promising way of minimizing the gap between human manipulation abilities and those of robots. We propose an approach to learn sequential force interaction skills from such demonstrations. The demonstrations are decomposed into a set of movement primitives by inferring the underlying sequential structure of the task. The decomposition is based on a novel probability distribution which we call Directional Normal Distribution. The distribution allows infering the movement primitive's composition, i.e., its coordinate frames, control variables and target coordinates from the demonstrations. In addition, it permits determining an appropriate number of movement primitives for a task via model selection. After finding the task's composition, the system learns to sequence the resulting movement primitives in order to be able to reproduce the task on a real robot. We evaluate the approach on three different tasks, unscrewing a light bulb, box stacking and box flipping. All tasks are kinesthetically demonstrated and then reproduced on a Barrett WAM robot.

Original languageEnglish
Article number45
Number of pages30
Issue number2
Publication statusPublished - 2020


  • Behavioral cloning
  • Human-robot interaction;motor skill learning
  • Learning fromdemonstration

Fingerprint Dive into the research topics of 'Learning sequential force interaction skills'. Together they form a unique fingerprint.

Cite this