2024-03-28T21:32:02Zhttp://buleria.unileon.es/oai/requestoai:buleria.unileon.es:10612/52352023-05-30T11:13:24Zcom_10612_17col_10612_21
Escuela de Ingenierias Industrial, Informática y Aeroespacial
Martín Rico, Francisco
Rodríguez Lera, Francisco Javier
Matellán Olivera, Vicente
Arquitectura y Tecnologia de Computadores
2016-06-04
2016-06-07T08:23:29Z
2016-06-07T08:23:29Z
2016-06-07
XVII Workshop en Agentes Físicos, 16-17 de junio, 2016, Málga
http://hdl.handle.net/10612/5235
Abstract—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@home
eng
Informática
3D Maps
RGBD sensors
Multi-threading
Robótica
Robotics
Multi-thread impact on the performance of Monte Carlo based algorithms for self-localization of robots using RGBD sensors
info:eu-repo/semantics/conferenceObject
info:eu-repo/semantics/lecture
info:eu-repo/semantics/openAccess