Mostra el registre d'ítem simple
Learning the semantics of object-action relations by observation
dc.contributor.author | Aksoy, Eren Erdal |
dc.contributor.author | Abramov, Alexey |
dc.contributor.author | Dörr, Johannes |
dc.contributor.author | Ning, Kejun |
dc.contributor.author | Dellen, Babette |
dc.contributor.author | Wörgötter, Florentin |
dc.contributor.other | Institut de Robòtica i Informàtica Industrial |
dc.date.accessioned | 2011-11-22T16:44:36Z |
dc.date.available | 2011-11-22T16:44:36Z |
dc.date.issued | 2011-10-28 |
dc.identifier.citation | Aksoy, E.E. [et al.]. Learning the semantics of object-action relations by observation. "International journal of robotics research", 28 Octubre 2011, vol. 30, núm. 10, p. 1229-1249. |
dc.identifier.issn | 0278-3649 |
dc.identifier.uri | http://hdl.handle.net/2117/14016 |
dc.description.abstract | Recognizing manipulations performed by a human and the transfer and execution of this by a robot is a difficult problem. We address this in the current study by introducing a novel representation of the relations between objects at decisive time points during a manipulation. Thereby, we encode the essential changes in a visual scenery in a condensed way such that a robot can recognize and learn a manipulation without prior object knowledge. To achieve this we continuously track image segments in the video and construct a dynamic graph sequence. Topological transitions of those graphs occur whenever a spatial relation between some segments has changed in a discontinuous way and these moments are stored in a transition matrix called the semantic event chain (SEC). We demonstrate that these time points are highly descriptive for distinguishing between different manipulations. Employing simple sub-string search algorithms, SECs can be compared and type-similar manipulations can be recognized with high confidence. As the approach is generic, statistical learning can be used to find the archetypal SEC of a given manipulation class. The performance of the algorithm is demonstrated on a set of real videos showing hands manipulating various objects and performing different actions. In experiments with a robotic arm, we show that the SEC can be learned by observing human manipulations, transferred to a new scenario, and then reproduced by the machine. |
dc.format.extent | 21 p. |
dc.language.iso | eng |
dc.rights | Attribution-NonCommercial-NoDerivs 3.0 Spain |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/3.0/es/ |
dc.subject | Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Reconeixement de formes |
dc.subject | Àrees temàtiques de la UPC::Informàtica::Automàtica i control |
dc.subject.lcsh | Pattern recognition systems |
dc.subject.lcsh | Automation |
dc.subject.other | automation pattern recognition |
dc.title | Learning the semantics of object-action relations by observation |
dc.type | Article |
dc.subject.lemac | Reconeixement de formes (Informàtica) |
dc.subject.lemac | Automatització |
dc.contributor.group | Universitat Politècnica de Catalunya. ROBiri - Grup de Robòtica de l'IRI |
dc.identifier.doi | 10.1177/0278364911410459 |
dc.description.peerreviewed | Peer Reviewed |
dc.subject.inspec | Classificació INSPEC::Pattern recognition |
dc.subject.inspec | Classificació INSPEC::Automation |
dc.relation.publisherversion | http://dx.doi.org/10.1177/0278364911410459 |
dc.rights.access | Open Access |
local.identifier.drac | 8560555 |
dc.description.version | Preprint |
dc.relation.projectid | info:eu-repo/grantAgreement/EC/FP7/247947/EU/Gardening with a Cognitive System/GARNICS |
dc.relation.projectid | info:eu-repo/grantAgreement/EC/FP7/247947/EU/Gardening with a Cognitive System/GARNICS |
local.citation.publicationName | International journal of robotics research |
local.citation.volume | 30 |
local.citation.number | 10 |
local.citation.startingPage | 1229 |
local.citation.endingPage | 1249 |
Fitxers d'aquest items
Aquest ítem apareix a les col·leccions següents
-
Articles de revista [163]
-
Articles de revista [376]