Generalizing pouring actions between objects using warped parameters
Authors:
- 1 November 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21640572,p. 616-621
Abstract
One of the key challenges for learning manipulation skills is generalizing between different objects. The robot should adapt both its actions and the task constraints to the geometry of the object being manipulated. In this paper, we propose computing geometric parameters of novel objects by warping known objects to match their shape. We refer to the parameters computed in this manner as warped parameters, as they are defined as functions of the warped object's point cloud. The warped parameters form the basis of the features for the motor skill learning process, and they are used to generalize between different objects. The proposed method was successfully evaluated on a pouring task both in simulation and on a real robot.Keywords
This publication has 14 references indexed in Scilit:
- Learning to predict phases of manipulation tasks as hidden states2014
- Force-based robot learning of pouring skills using parametric hidden Markov models2013
- Transferring functional grasps through contact warping and local replanning2012
- Generalization of human grasping for multi-fingered robot hands2012
- Learning of Planning Models for Dexterous Manipulation Based on Human DemonstrationsInternational Journal of Social Robotics, 2012
- A kernel-based approach to direct action perception2012
- Learning to pour with a robot arm combining goal and shape learning for dynamic movement primitivesRobotics and Autonomous Systems, 2011
- Gaussian process implicit surfaces for shape estimation and grasping2011
- Non-parametric 3D Shape Warping2010
- Multiresolution mesh morphing1999