ICRA 2011 Paper Abstract

Close

Paper ThP112.4

Kopicki, Marek Sewer (University of Birmingham), Zurek, Sebastian (University of Birmingham, UK), Stolkin, Rustam (University of Birmingham), Mörwald, Thomas (Vienna University of Technology), Wyatt, Jeremy (University of Birmingham)

Learning to Predict How Rigid Objects Behave under Simple Manipulation

Scheduled for presentation during the Regular Sessions "Learning and Adaptive Systems III" (ThP112), Thursday, May 12, 2011, 14:25−14:40, Room 5H

2011 IEEE International Conference on Robotics and Automation, May 9-13, 2011, Shanghai International Conference Center, Shanghai, China

This information is tentative and subject to change. Compiled on May 22, 2019

Keywords Learning and Adaptive Systems, Contact Modelling

Abstract

An important problem in robotic manipulation is the ability to predict how objects behave under manipulative actions. This ability is necessary to allow planning of object manipulations. Physics simulators can be used to do this, but they model many kinds of object interaction poorly. An alternative is to learn a motion model for objects by interacting with them. In this paper we address the problem of learning to predict the interactions of rigid bodies in a probabilistic framework, and demonstrate the results in the domain of robotic push manipulation. A robot arm applies random pushes to various objects and observes the resulting motion with a vision system. The relationship between push actions and object motions is learned, and enables the robot to predict the motions that will result from new pushes. The learning does not make explicit use of physics knowledge, or any pre-coded physical constraints, nor is it even restricted to domains which obey any particular rules of physics. We use regression to learn efficiently how to predict the gross motion of a particular object. We further show how different density functions can encode different kinds of information about the behaviour of interacting objects. By combining these as a product of densities, we show how learned predictors can cope with a degree of generalisation to previously unencountered object shapes, subjected to previously unencountered push directions. Performance is evaluated through a combination of virtu

 

 

Technical Content © IEEE Robotics & Automation Society

This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2019 PaperCept, Inc.
Page generated 2019-05-22  23:53:18 PST  Terms of use