dc.contributor.author | Kouskouridas, R. | |
dc.contributor.author | Amanatiadis, A. | |
dc.contributor.author | Chatzichristofis, Savvas A. | |
dc.contributor.author | Gasteratos, A. | |
dc.date.accessioned | 2017-10-24T10:43:20Z | |
dc.date.available | 2017-10-24T10:43:20Z | |
dc.date.issued | 2015 | |
dc.identifier.issn | 0957-4174 | |
dc.identifier.uri | http://hdl.handle.net/11728/10142 | |
dc.description.abstract | In this paper we propose a novel method for object grasping that aims to unify robot vision techniques for 24
efficiently accomplishing the demanding task of autonomous object manipulation. Through ontological 25
concepts, we establish three mutually complementary processes that lead to an integrated grasping sys- 26
tem able to answer conjunctive queries such as ‘‘What’’, ‘‘Where’’ and ‘‘How’’? For each query, the appro- 27
priate module provides the necessary output based on ontological formalities. The ‘‘What’’ is handled by a 28
state of the art object recognition framework. A novel 6 DoF object pose estimation technique, which 29
entails a bunch-based architecture and a manifold modeling method, answers the ‘‘Where’’. Last, 30
‘‘How’’ is addressed by an ontology-based semantic categorization enabling the sufficient mapping 31
between visual stimuli and motor commands. | en_UK |
dc.language.iso | en | en_UK |
dc.publisher | Elsevier | en_UK |
dc.relation.ispartofseries | Expert Systems with Applications;Volume 42, Issue 21 | |
dc.rights | © 2015 Published by Elsevier Ltd. | en_UK |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | en_UK |
dc.subject | Object grasping | en_UK |
dc.subject | Object recognition | en_UK |
dc.subject | Pose estimation | en_UK |
dc.subject | Ontology-based semantic categorization | en_UK |
dc.title | What, Where and How? Introducing pose manifolds for industrial object manipulation | en_UK |
dc.type | Article | en_UK |
dc.doi | https://doi.org/10.1016/j.eswa.2015.06.039 | en_UK |