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
Artikel, Zweitveröffentlichung, Postprint

Kurzbeschreibung (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.

Typ des Eintrags: Artikel
Erschienen: 2022
Autor(en): Lioutikov, Rudolf ; Neumann, Gerhard ; Maeda, Guilherme ; Peters, Jan
Art des Eintrags: Zweitveröffentlichung
Titel: Learning movement primitive libraries through probabilistic segmentation
Sprache: Englisch
Publikationsjahr: 2022
Ort: Darmstadt
Verlag: SAGE Publications
Titel der Zeitschrift, Zeitung oder Schriftenreihe: The International Journal of Robotics Research
Jahrgang/Volume einer Zeitschrift: 36
(Heft-)Nummer: 8
DOI: 10.26083/tuprints-00020539
URL / URN: https://tuprints.ulb.tu-darmstadt.de/20539
Zugehörige Links:
Herkunft: Zweitveröffentlichungsservice
Kurzbeschreibung (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
Sachgruppe der Dewey Dezimalklassifikatin (DDC): 000 Allgemeines, Informatik, Informationswissenschaft > 004 Informatik
Fachbereich(e)/-gebiet(e): 20 Fachbereich Informatik
20 Fachbereich Informatik > Intelligente Autonome Systeme
TU-Projekte: EC/H2020|640554|SKILLS4ROBOTS
Hinterlegungsdatum: 18 Nov 2022 13:49
Letzte Änderung: 21 Nov 2022 10:40
PPN:
Zugehörige Links:
Export:
Suche nach Titel in: TUfind oder in Google
Frage zum Eintrag Frage zum Eintrag

Optionen (nur für Redakteure)
Redaktionelle Details anzeigen Redaktionelle Details anzeigen