Abstract
[Japanese | Thesis | Researches in Minoh Lab | Minoh Lab]


Model Parameter Estimation for Deformable Objects from Incremental Observation


This paper discusses modeling real deformable objects for creating a virtual object that reproduces the shapes observed from the reaction of real deformable object under manipulation. For this purpose, models with many parameters are introduced in order to produce the shapes of real deformable objects. Those models can produce realistic shapes of deformable objects when optimal values are set for their parameters.

We aim at estimating these optimal values of model parameters by observing the shapes of real deformable object under manipulation. Although the values of model parameters estimated by this approach depend on the variety of observed shapes,it is unrealistic to assume that all the observed shapes necessary for correct estimating model parameters are given in advance. In this paper, we propose a method of estimating model parameters using Real Coded Genetic Algorithm from the shapes of real object by incremental observation.

String-like objects and clothes are considered as examples of deformable objects. Experimental results show that the model with optimal values of its parameters estimated from our method by incremental observation can reproduce the shapes which were not used for the estimation.


Go back to Thesis Page