Enhancing Robustness to Extrapolate Synergies Learned from Motion Capture

Matthieu Aubry (1) , Pierre de Loor (1) , Sylvie Gibet (2)

1 LySic
2 VALORIA - Laboratoire de Recherche en Informatique et ses Applications de Vannes et Lorient

Reproducing the characteristics of human movements, is a crucial issue in studying motion. In the context of this work, an explicit model of synergies which can be parametrized is used for reproducing the main features of reaching motions. This paper evaluates the possibility to extrapolate learned parameters from a captured motion to new targets and shows how learning process is a key issue to ensure the robustness of parameters. another target, some parameters displayed poor capacity to extend features of the sample motion. In this article, differences between robust and non robust set of parameters are discussed. The learning process is enhanced to ensure robustness of parameters.

Mots clés: Learning; Synergies; Gesture Modeling

Domaines: Modélisation et simulation

Matthieu Aubry, Pierre de Loor, Sylvie Gibet. Enhancing Robustness to Extrapolate Synergies Learned from Motion Capture. 23rd International Conference on Computer Animation and Social Agents (CASA 2010), May 2010, Saint Malo, France. pp.1-4. ⟨hal-00505188⟩