Lioutikov, Rudolf ; Neumann, Gerhard ; Maeda, Guilherme ; Peters, Jan (2022)
Learning movement primitive libraries through probabilistic segmentation.
In: The International Journal of Robotics Research, 2022, 36 (8)
doi: 10.26083/tuprints-00020539
Artikel, Zweitveröffentlichung, Postprint
 | Es ist eine neuere Version dieses Eintrags verfügbar. |
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 |
| Publikationsdatum der Erstveröffentlichung: | 2022 |
| 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: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
Verfügbare Versionen dieses Eintrags
- Learning movement primitive libraries through probabilistic segmentation. (deposited 18 Nov 2022 13:49) [Gegenwärtig angezeigt]
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum