Benutzer: Gast  Login
Titel:

Gaussian Processes for Dynamic Movement Primitives with Application in Knowledge-based Cooperation

Dokumenttyp:
Konferenzbeitrag
Art des Konferenzbeitrags:
Textbeitrag / Aufsatz
Autor(en):
Y. Fanger; J. Umlauft; S. Hirche
Abstract:
Dynamic Movement Primitives (DMPs) represent stable goal-directed or periodic movements, which are learned from observations or demonstrations. They rely on proper function approximators, which are sufficiently flexible to represent arbitrary movements but also ensure goal convergence in pointto- point motions. This work shows that Gaussian Processes (GPs) are suitable as a regressor for learning movements with DMPs ensuring stability. In addition, GPs provide a measure for the uncertainty about...     »
Stichworte:
conhumo
Herausgeber:
IEEE
Kongress- / Buchtitel:
International Conference on Intelligent Robots and Systems (IROS)
Jahr:
2016
Jahr / Monat:
2016-10
Monat:
Oct
Seiten:
7
Reviewed:
ja
Sprache:
en
TUM Einrichtung:
Lehrstuhl für Informationstechnische Regelung (Prof. Hirche)
 BibTeX