Show simple item record

dc.contributorEscuela de Ingenierias Industrial e Informaticaes_ES
dc.contributor.authorMartín Rico, Francisco
dc.contributor.authorRodríguez Lera, Francisco Javier 
dc.contributor.authorMatellán Olivera, Vicente 
dc.contributor.otherArquitectura y Tecnologia de Computadoreses_ES
dc.date2016-06-04
dc.date.accessioned2016-06-07T08:23:29Z
dc.date.available2016-06-07T08:23:29Z
dc.date.issued2016-06-07
dc.identifier.citationXVII Workshop en Agentes Físicos, 16-17 de junio, 2016, Málgaes_ES
dc.identifier.urihttp://hdl.handle.net/10612/5235
dc.description.abstractAbstract—Using information from RGBD sensors requires huge amount of processing. To use these sensors improves the robustness of algorithms for object perception, self-localization and, in general, all the capabilities to be performed by a robot to improve its autonomy. In most cases, these algorithms are not computationally feasible using single-thread implementations. This paper describes two multi thread strategies proposed for self localize a mobile robot in a known environment using information from a RGBD sensor. The experiments will show the benefits obtained when different numbers of threads are compared, using different approaches: a pool of threads and creation/destruction scheme. The work has been carried out on a Kobuki mobile robot in the environment of the RoCKiN competition, similar to RoboCup@homees_ES
dc.languageenges_ES
dc.subjectInformáticaes_ES
dc.subject.other3D Mapses_ES
dc.subject.otherRGBD sensorses_ES
dc.subject.otherMulti-threadinges_ES
dc.subject.otherRobóticaes_ES
dc.subject.otherRoboticses_ES
dc.titleMulti-thread impact on the performance of Monte Carlo based algorithms for self-localization of robots using RGBD sensorses_ES
dc.typeinfo:eu-repo/semantics/conferenceObjectes_ES
dc.type.otherinfo:eu-repo/semantics/lecturees_ES
dc.rights.accessRightsinfo:eu-repo/semantics/openAccesses_ES


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record