IIIT Hyderabad Publications |
|||||||||
|
Learning Support Order for Manipulation in ClutterAuthors: Swagatika Panda,Abdul Hafeez, C V Jawahar Conference: IROS 2013 Date: 2013-11-03 Report no: IIIT/TR/2013/124 AbstractUnderstanding positional semantics of the envi- ronment plays an important role in manipulating an object in clutter. The interaction with surrounding objects in the environment must be considered in order to perform the task without causing the objects fall or get damaged. In this paper, we learn the semantics in terms of support relationsh ip among different objects in a cluttered environment by utili zing various photometric and geometric properties of the scene. To manipulate an object of interest, we use the inferred suppor t relationship to derive a sequence in which its surrounding objects should be removed while causing minimal damage to the environment. We believe, this work can push the boundary of robotic applications in grasping, object manipulation a nd picking-from-bin, towards objects of generic shape and siz e and scenarios with physical contact and overlap. We have created an RGBD dataset that consists of various objects use d in day-to-day life present in clutter. We explore many diffe rent settings involving different kind of object-object intera ction. We successfully learn support relationships and predict su pport order in these settings. Full paper: pdf Centre for Visual Information Technology |
||||||||
Copyright © 2009 - IIIT Hyderabad. All Rights Reserved. |