TU Darmstadt / ULB / TUbiblio

Learning movement primitive libraries through probabilistic segmentation

Lioutikov, Rudolf ; Neumann, Gerhard ; Maeda, Guilherme ; Peters, Jan (2022)
Learning movement primitive libraries through probabilistic segmentation.
In: The International Journal of Robotics Research, 36 (8)
doi: 10.26083/tuprints-00020539
Article, Secondary publication, Postprint

Abstract

Movement primitives are a well-established approach for encoding and executing movements. While the primitives themselves have been extensively researched, the concept of movement primitive libraries has not received similar attention. Libraries of movement primitives represent the skill set of an agent. Primitives can be queried and sequenced in order to solve specific tasks. The goal of this work is to segment unlabeled demonstrations into a representative set of primitives. Our proposed method differs from current approaches by taking advantage of the often neglected, mutual dependencies between the segments contained in the demonstrations and the primitives to be encoded. By exploiting this mutual dependency, we show that we can improve both the segmentation and the movement primitive library. Based on probabilistic inference our novel approach segments the demonstrations while learning a probabilistic representation of movement primitives. We demonstrate our method on two real robot applications. First, the robot segments sequences of different letters into a library, explaining the observed trajectories. Second, the robot segments demonstrations of a chair assembly task into a movement primitive library. The library is subsequently used to assemble the chair in an order not present in the demonstrations.

Item Type: Article
Erschienen: 2022
Creators: Lioutikov, Rudolf ; Neumann, Gerhard ; Maeda, Guilherme ; Peters, Jan
Type of entry: Secondary publication
Title: Learning movement primitive libraries through probabilistic segmentation
Language: English
Date: 2022
Place of Publication: Darmstadt
Publisher: SAGE Publications
Journal or Publication Title: The International Journal of Robotics Research
Volume of the journal: 36
Issue Number: 8
DOI: 10.26083/tuprints-00020539
URL / URN: https://tuprints.ulb.tu-darmstadt.de/20539
Corresponding Links:
Origin: Secondary publication service
Abstract:

Movement primitives are a well-established approach for encoding and executing movements. While the primitives themselves have been extensively researched, the concept of movement primitive libraries has not received similar attention. Libraries of movement primitives represent the skill set of an agent. Primitives can be queried and sequenced in order to solve specific tasks. The goal of this work is to segment unlabeled demonstrations into a representative set of primitives. Our proposed method differs from current approaches by taking advantage of the often neglected, mutual dependencies between the segments contained in the demonstrations and the primitives to be encoded. By exploiting this mutual dependency, we show that we can improve both the segmentation and the movement primitive library. Based on probabilistic inference our novel approach segments the demonstrations while learning a probabilistic representation of movement primitives. We demonstrate our method on two real robot applications. First, the robot segments sequences of different letters into a library, explaining the observed trajectories. Second, the robot segments demonstrations of a chair assembly task into a movement primitive library. The library is subsequently used to assemble the chair in an order not present in the demonstrations.

Status: Postprint
URN: urn:nbn:de:tuda-tuprints-205394
Classification DDC: 000 Generalities, computers, information > 004 Computer science
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Intelligent Autonomous Systems
TU-Projects: EC/H2020|640554|SKILLS4ROBOTS
Date Deposited: 18 Nov 2022 13:49
Last Modified: 21 Nov 2022 10:40
PPN:
Corresponding Links:
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details