Towards semi-supervised learning of semantic spatial concepts for mobile robots
Por favor, use este identificador para citar o enlazar este ítem:
http://hdl.handle.net/10045/16640
Registro completo de metadatos
Campo DC | Valor | Idioma |
---|---|---|
dc.contributor.author | Martínez Gómez, Jesús | - |
dc.contributor.author | Caputo, Barbara | - |
dc.date.accessioned | 2011-03-15T12:37:32Z | - |
dc.date.available | 2011-03-15T12:37:32Z | - |
dc.date.issued | 2010-09 | - |
dc.identifier.citation | MARTÍNEZ GÓMEZ, Jesús; CAPUTO, Barbara. “Towards semi-supervised learning of semantic spatial concepts for mobile robots”. Journal of Physical Agents. Vol. 4, No. 3 (Sept. 2010). ISSN 1888-0258, pp. 19-31 | en |
dc.identifier.issn | 1888-0258 | - |
dc.identifier.uri | http://hdl.handle.net/10045/16640 | - |
dc.identifier.uri | http://dx.doi.org/10.14198/JoPha.2010.4.3.03 | - |
dc.description.abstract | The ability of building robust semantic space representations of environments is crucial for the development of truly autonomous robots. This task, inherently connected with cognition, is traditionally achieved by training the robot with a supervised learning phase. We argue that the design of robust and autonomous systems would greatly benefit from adopting a semi-supervised online learning approach. Indeed, the support of open-ended, lifelong learning is fundamental in order to cope with the dazzling variability of the real world, and online learning provides precisely this kind of ability. Here we focus on the robot place recognition problem, and we present an online place classification algorithm that is able to detect gap in its own knowledge based on a confidence measure. For every incoming new image frame, the method is able to decide if (a) it is a known room with a familiar appearance, (b) it is a known room with a challenging appearance, or (c) it is a new, unknown room. Experiments on ImageCLEF database and a subset of the challenging COLD database show the promise of our approach. | en |
dc.description.sponsorship | This work was supported by the Spanish “Junta de Comunidades de Castilla-La Mancha” under PCI08-0048-8577 and PBI-0210-7127 projects (J. M.-G.) and by the SS2Rob project (B.C.). | en |
dc.language | eng | en |
dc.publisher | Red de Agentes Físicos | en |
dc.subject | Place recognition | en |
dc.subject | Semantic place representation | en |
dc.subject | Online learning | en |
dc.subject | Kernel methods | en |
dc.subject.other | Ciencia de la Computación e Inteligencia Artificial | en |
dc.title | Towards semi-supervised learning of semantic spatial concepts for mobile robots | en |
dc.type | info:eu-repo/semantics/article | en |
dc.peerreviewed | si | en |
dc.identifier.doi | 10.14198/JoPha.2010.4.3.03 | - |
dc.rights.accessRights | info:eu-repo/semantics/openAccess | en |
Aparece en las colecciones: | Journal of Physical Agents - 2010, Vol. 4, No. 3 |
Archivos en este ítem:
Archivo | Descripción | Tamaño | Formato | |
---|---|---|---|---|
JoPha_4_3_03.pdf | 5,21 MB | Adobe PDF | Abrir Vista previa | |
Este ítem está licenciado bajo Licencia Creative Commons