Realising Dextrous Manipulation with Structured Manifolds using Unsupervised Kernel Regression with Structural Hints

Steffen JF, Klanke S, Vijayakumar S, Ritter H (2009)
In: ICRA 2009 Workshop: Approaches to Sensorimotor Learning on Humanoid Robots.

Download
Restricted steffen_icra09ws_preprint.pdf
Konferenzbeitrag | Veröffentlicht | Englisch
Volltext vorhanden für diesen Nachweis
Autor
; ; ;
Abstract / Bemerkung
Dextrous manipulation based on techniques for non-linear dimension reduction and manifold learning is an upcoming field of research and offers promising opportunities. Still, many problems remain unsolved and researchers are seeking for new representations that combine efficient learning of examples and robust generalisation to unseen situations. Here, we propose a manifold representation of hand postures, which due to its structural clarity lends itself to simple and robust manipulation control schemes. Focussing on cyclic movements, we describe extensions to the dimensionality reduction algorithm Unsupervised Kernel Regression (UKR) that allow to incorporate structural hints about the training data into the learning yielding task-related structures in the manifold’s latent space. We present the resulting manifold representation and a simplified controller using this representation for manipulation in the example of turning a bottle cap in a physics-based simulation.
Erscheinungsjahr
Titel des Konferenzbandes
ICRA 2009 Workshop: Approaches to Sensorimotor Learning on Humanoid Robots
Konferenz
ICRA 2009
Konferenzort
Kobe, Japan
PUB-ID

Zitieren

Steffen JF, Klanke S, Vijayakumar S, Ritter H. Realising Dextrous Manipulation with Structured Manifolds using Unsupervised Kernel Regression with Structural Hints. In: ICRA 2009 Workshop: Approaches to Sensorimotor Learning on Humanoid Robots. 2009.
Steffen, J. F., Klanke, S., Vijayakumar, S., & Ritter, H. (2009). Realising Dextrous Manipulation with Structured Manifolds using Unsupervised Kernel Regression with Structural Hints. ICRA 2009 Workshop: Approaches to Sensorimotor Learning on Humanoid Robots
Steffen, J. F., Klanke, S., Vijayakumar, S., and Ritter, H. (2009). “Realising Dextrous Manipulation with Structured Manifolds using Unsupervised Kernel Regression with Structural Hints” in ICRA 2009 Workshop: Approaches to Sensorimotor Learning on Humanoid Robots.
Steffen, J.F., et al., 2009. Realising Dextrous Manipulation with Structured Manifolds using Unsupervised Kernel Regression with Structural Hints. In ICRA 2009 Workshop: Approaches to Sensorimotor Learning on Humanoid Robots.
J.F. Steffen, et al., “Realising Dextrous Manipulation with Structured Manifolds using Unsupervised Kernel Regression with Structural Hints”, ICRA 2009 Workshop: Approaches to Sensorimotor Learning on Humanoid Robots, 2009.
Steffen, J.F., Klanke, S., Vijayakumar, S., Ritter, H.: Realising Dextrous Manipulation with Structured Manifolds using Unsupervised Kernel Regression with Structural Hints. ICRA 2009 Workshop: Approaches to Sensorimotor Learning on Humanoid Robots. (2009).
Steffen, Jan Frederik, Klanke, Stefan, Vijayakumar, Sethu, and Ritter, Helge. “Realising Dextrous Manipulation with Structured Manifolds using Unsupervised Kernel Regression with Structural Hints”. ICRA 2009 Workshop: Approaches to Sensorimotor Learning on Humanoid Robots. 2009.
Volltext(e)
Name
steffen_icra09ws_preprint.pdf
Access Level
Restricted Closed Access
Zuletzt Hochgeladen
2012-04-10T07:54:00Z

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar