Semantic Segmentation to Develop an Indoor Navigation System for an Autonomous Mobile Robot

In this study, a semantic segmentation network is presented to develop an indoor navigation system for a mobile robot. Semantic segmentation can be applied by adopting different techniques, such as a convolutional neural network (CNN). However, in the present work, a residual neural network is imple...

Descripción completa

Detalles Bibliográficos
Autores: Teso Fernández de Betoño, Daniel, Zulueta Guerrero, Ekaitz, Sánchez Chica, Ander, Fernández Gámiz, Unai, Sáenz Aguirre, Aitor
Tipo de recurso: artículo
Fecha de publicación:2020
País:España
Institución:Universidad del País Vasco
Repositorio:Addi. Archivo Digital para la Docencia y la Investigación
OAI Identifier:oai:addi.ehu.eus:10810/43623
Acceso en línea:http://hdl.handle.net/10810/43623
Access Level:acceso abierto
Palabra clave:indoor navigation
semantic segmentation
fully convolutional networks
obstacle detection
autonomous mobile robot
ResNet
Unet
Segnet
id ES_fbbe7fb75c7fc3fd1a5b58dfe308e010
oai_identifier_str oai:addi.ehu.eus:10810/43623
network_acronym_str ES
network_name_str España
repository_id_str
spelling Semantic Segmentation to Develop an Indoor Navigation System for an Autonomous Mobile RobotTeso Fernández de Betoño, DanielZulueta Guerrero, EkaitzSánchez Chica, AnderFernández Gámiz, UnaiSáenz Aguirre, Aitorindoor navigationsemantic segmentationfully convolutional networksobstacle detectionautonomous mobile robotResNetUnetSegnetIn this study, a semantic segmentation network is presented to develop an indoor navigation system for a mobile robot. Semantic segmentation can be applied by adopting different techniques, such as a convolutional neural network (CNN). However, in the present work, a residual neural network is implemented by engaging in ResNet-18 transfer learning to distinguish between the floor, which is the navigation free space, and the walls, which are the obstacles. After the learning process, the semantic segmentation floor mask is used to implement indoor navigation and motion calculations for the autonomous mobile robot. This motion calculations are based on how much the estimated path differs from the center vertical line. The highest point is used to move the motors toward that direction. In this way, the robot can move in a real scenario by avoiding different obstacles. Finally, the results are collected by analyzing the motor duty cycle and the neural network execution time to review the robot’s performance. Moreover, a different net comparison is made to determine other architectures’ reaction times and accuracy values.This research was financed by the plant of Mercedes-Benz Vitoria through the PIF program to develop an intelligent production. Moreover, The Regional Development Agency of the Basque Country (SPRI) is gratefully acknowledged for their economic support through the research project “Motor de Accionamiento para Robot Guiado Automáticamente”, KK-2019/00099, Programa ELKARTEK.MDPI2020202020202020info:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10810/43623reponame:Addi. Archivo Digital para la Docencia y la Investigacióninstname:Universidad del País VascoIngléshttps://www.mdpi.com/2227-7390/8/5/855/htminfo:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by/3.0/es/2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).oai:addi.ehu.eus:10810/436232026-06-18T09:23:17Z
dc.title.none.fl_str_mv Semantic Segmentation to Develop an Indoor Navigation System for an Autonomous Mobile Robot
title Semantic Segmentation to Develop an Indoor Navigation System for an Autonomous Mobile Robot
spellingShingle Semantic Segmentation to Develop an Indoor Navigation System for an Autonomous Mobile Robot
Teso Fernández de Betoño, Daniel
indoor navigation
semantic segmentation
fully convolutional networks
obstacle detection
autonomous mobile robot
ResNet
Unet
Segnet
title_short Semantic Segmentation to Develop an Indoor Navigation System for an Autonomous Mobile Robot
title_full Semantic Segmentation to Develop an Indoor Navigation System for an Autonomous Mobile Robot
title_fullStr Semantic Segmentation to Develop an Indoor Navigation System for an Autonomous Mobile Robot
title_full_unstemmed Semantic Segmentation to Develop an Indoor Navigation System for an Autonomous Mobile Robot
title_sort Semantic Segmentation to Develop an Indoor Navigation System for an Autonomous Mobile Robot
dc.creator.none.fl_str_mv Teso Fernández de Betoño, Daniel
Zulueta Guerrero, Ekaitz
Sánchez Chica, Ander
Fernández Gámiz, Unai
Sáenz Aguirre, Aitor
author Teso Fernández de Betoño, Daniel
author_facet Teso Fernández de Betoño, Daniel
Zulueta Guerrero, Ekaitz
Sánchez Chica, Ander
Fernández Gámiz, Unai
Sáenz Aguirre, Aitor
author_role author
author2 Zulueta Guerrero, Ekaitz
Sánchez Chica, Ander
Fernández Gámiz, Unai
Sáenz Aguirre, Aitor
author2_role author
author
author
author
dc.subject.none.fl_str_mv indoor navigation
semantic segmentation
fully convolutional networks
obstacle detection
autonomous mobile robot
ResNet
Unet
Segnet
topic indoor navigation
semantic segmentation
fully convolutional networks
obstacle detection
autonomous mobile robot
ResNet
Unet
Segnet
description In this study, a semantic segmentation network is presented to develop an indoor navigation system for a mobile robot. Semantic segmentation can be applied by adopting different techniques, such as a convolutional neural network (CNN). However, in the present work, a residual neural network is implemented by engaging in ResNet-18 transfer learning to distinguish between the floor, which is the navigation free space, and the walls, which are the obstacles. After the learning process, the semantic segmentation floor mask is used to implement indoor navigation and motion calculations for the autonomous mobile robot. This motion calculations are based on how much the estimated path differs from the center vertical line. The highest point is used to move the motors toward that direction. In this way, the robot can move in a real scenario by avoiding different obstacles. Finally, the results are collected by analyzing the motor duty cycle and the neural network execution time to review the robot’s performance. Moreover, a different net comparison is made to determine other architectures’ reaction times and accuracy values.
publishDate 2020
dc.date.none.fl_str_mv 2020
2020
2020
2020
dc.type.none.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv http://hdl.handle.net/10810/43623
url http://hdl.handle.net/10810/43623
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv https://www.mdpi.com/2227-7390/8/5/855/htm
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by/3.0/es/
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by/3.0/es/
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv reponame:Addi. Archivo Digital para la Docencia y la Investigación
instname:Universidad del País Vasco
instname_str Universidad del País Vasco
reponame_str Addi. Archivo Digital para la Docencia y la Investigación
collection Addi. Archivo Digital para la Docencia y la Investigación
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869425358019756032
score 15,300724

Similares en LA Referencia