A Deep Learning Based Behavioral Approach to Indoor Autonomous Navigation

Simple item page
dc.contributor.authorSepulveda Villalobos, Gabriel Andres
dc.contributor.authorNiebles, Juan Carlos
dc.contributor.authorSoto Arriaza, Álvaro Marcelo
dc.date.accessioned2022-05-16T13:00:33Z
dc.date.available2022-05-16T13:00:33Z
dc.date.issued2018
dc.description.abstractWe present a semantically rich graph representation for indoor robotic navigation. Our graph representation encodes: semantic locations such as offices or corridors as nodes, and navigational behaviors such as enter office or cross a corridor as edges. In particular, our navigational behaviors operate directly from visual inputs to produce motor controls and are implemented with deep learning architectures. This enables the robot to avoid explicit computation of its precise location or the geometry of the environment, and enables navigation at a higher level of semantic abstraction. We evaluate the effectiveness of our representation by simulating navigation tasks in a large number of virtual environments. Our results show that using a simple sets of perceptual and navigational behaviors, the proposed approach can successfully guide the way of the robot as it completes navigational missions such as going to a specific office. Furthermore, our implementation shows to be effective to control the selection and switching of behaviors.
dc.fuente.origenIEEE
dc.identifier.doi10.1109/ICRA.2018.8460646
dc.identifier.eisbn9781538630815
dc.identifier.isbn9781538630822
dc.identifier.issn2577-087X
dc.identifier.urihttps://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8460646
dc.identifier.urihttps://doi.org/10.1109/ICRA.2018.8460646
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/63950
dc.information.autorucEscuela de ingeniería ; Sepulveda Villalobos, Gabriel Andres ; S/I ; 1030561
dc.information.autorucEscuela de ingeniería ; Soto Arriaza, Álvaro Marcelo ; S/I ; 73678
dc.language.isoen
dc.nota.accesoContenido parcial
dc.pagina.final4653
dc.pagina.inicio4646
dc.publisherIEEE
dc.relation.ispartofIEEE International Conference on Robotics and Automation (ICRA) (2018 : Brisbane, Australia)
dc.rightsacceso restringido
dc.subjectNavigation
dc.subjectSemantics
dc.subjectVisualization
dc.subjectSimultaneous localization and mapping
dc.subjectRobustness
dc.subjectMeasurement
dc.titleA Deep Learning Based Behavioral Approach to Indoor Autonomous Navigationes_ES
dc.typecomunicación de congreso
sipa.codpersvinculados1030561
sipa.codpersvinculados73678
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
A Deep Learning Based Behavioral Approach to Indoor Autonomous Navigation.pdf
Size:
2.75 KB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Artículos de conferencia