TU Darmstadt / ULB / TUprints

Learning Sequential Force Interaction Skills

Manschitz, Simon ; Gienger, Michael ; Kober, Jens ; Peters, Jan (2024)
Learning Sequential Force Interaction Skills.
In: Robotics, 2020, 9 (2)
doi: 10.26083/tuprints-00016992
Article, Secondary publication, Publisher's Version

Copyright Information: CC BY 4.0 International - Creative Commons, Attribution.

Download (26MB) | Preview
Item Type: Article
Type of entry: Secondary publication
Title: Learning Sequential Force Interaction Skills
Language: English
Date: 15 January 2024
Place of Publication: Darmstadt
Year of primary publication: 2020
Place of primary publication: Basel
Publisher: MDPI
Journal or Publication Title: Robotics
Volume of the journal: 9
Issue Number: 2
Collation: 30 Seiten
DOI: 10.26083/tuprints-00016992
Corresponding Links:
Origin: Secondary publication DeepGreen

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.

Uncontrolled Keywords: human-robot interaction, motor skill learning, learning from demonstration, behavioral cloning
Status: Publisher's Version
URN: urn:nbn:de:tuda-tuprints-169926
Additional Information:

This article belongs to the Special Issue Feature Papers 2020

Classification DDC: 000 Generalities, computers, information > 004 Computer science
600 Technology, medicine, applied sciences > 621.3 Electrical engineering, electronics
Divisions: 20 Department of Computer Science > Intelligent Autonomous Systems
Date Deposited: 15 Jan 2024 14:03
Last Modified: 18 Mar 2024 10:07
SWORD Depositor: Deep Green
URI: https://tuprints.ulb.tu-darmstadt.de/id/eprint/16992
PPN: 516346237
Actions (login required)
View Item View Item