Learning Movement Primitives

Schaal, S; Peters, J; Nakanishi, J; Ijspeert, A

doi:10.1007/11008941_60

Lokale TagsFreigabegeschichteDetailsÜbersicht

Learning Movement Primitives

Schaal, S., Peters, J., Nakanishi, J., & Ijspeert, A. (2005). Learning Movement Primitives. In P. Dario, & R. Chatila (Eds.), Robotics Research: The Eleventh International Symposium (pp. 561-572). Berlin, Germany: Springer.

Item is Freigegeben

einblenden: alle

Basisdaten

ausblenden:

Datensatz-Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-D4BD-2 Versions-Permalink: https://hdl.handle.net/21.11116/0000-0005-0E20-8

Genre: Konferenzbeitrag

Dateien

einblenden: Dateien

Externe Referenzen

ausblenden:

externe Referenz:
https://link.springer.com/content/pdf/10.1007%2F11008941_60.pdf (Verlagsversion) Open Access Status unbekannt

Beschreibung:
-

OA-Status:

Urheber

ausblenden:

Urheber:
Schaal, S¹, Autor
Peters, J¹, Autor
Nakanishi, J, Autor
Ijspeert, A, Autor

Affiliations:
1External Organizations, ou_persistent22

Inhalt

ausblenden:

Schlagwörter: -

Zusammenfassung: This paper discusses a comprehensive framework for modular motor control based on a recently developed theory of dynamic movement primitives (DMP). DMPs are a formulation of movement primitives with autonomous nonlinear differential equations, whose time evolution creates smooth kinematic control policies. Model-based control theory is used to convert the outputs of these policies into motor commands. By means of coupling terms, on-line modifications can be incorporated into the time evolution of the differential equations, thus providing a rather flexible and reactive framework for motor planning and execution. The linear parameterization of DMPs lends itself naturally to supervised learning from demonstration. Moreover, the temporal, scale, and translation invariance of the differential equations with respect to these parameters provides a useful means for movement recognition. A novel reinforcement learning technique based on natural stochastic policy gradients allows a general approach of improving DMPs b
y trial and error learning with respect to almost arbitrary optimization criteria. We demonstrate the different ingredients of the DMP approach in various examples, involving skill learning from demonstration on the humanoid robot DB, and learning biped walking from demonstration in simulation, including self-improvement of the movement patterns towards energy efficiency through resonance tuning.

Details

ausblenden:

Sprache(n):

Datum: Erschienen: 2005-08

Publikationsstatus: Erschienen

Seiten: -

Ort, Verlag, Ausgabe: -

Inhaltsverzeichnis: -

Art der Begutachtung: -

Identifikatoren: DOI: 10.1007/11008941_60
BibTex Citekey: 5055

Art des Abschluß: -

Veranstaltung

ausblenden:

Titel: 11th International Symposium on Robotics Research (ISRR 2003)

Veranstaltungsort: Siena, Italy

Start-/Enddatum: 2003-10-19 - 2003-10-22

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

ausblenden:

Titel: Robotics Research: The Eleventh International Symposium

Genre der Quelle: Konferenzband

Urheber:
Dario, P, Herausgeber
Chatila, R, Herausgeber

Affiliations:
-

Ort, Verlag, Ausgabe: Berlin, Germany : Springer

Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 561 - 572 Identifikator: ISBN: 3-540-23214-1

Quelle 2

ausblenden:

Titel: Springer Tracts in Advanced Robotics

Genre der Quelle: Reihe

Urheber:

Affiliations:

Ort, Verlag, Ausgabe: -

Seiten: - Band / Heft: 15 Artikelnummer: - Start- / Endseite: - Identifikator: -