Towards Learning Obstacles to Avoid Collisions in Autonomous Robot Navigation

Avoiding obstacles is one of the main tasks in robotic navigation. In this paper, robot navigation using monocular vision is presented. Therefore, an accuracy in the segmentation of obstacles is necessary to avoid collisions by estimating the Time-to-Contact. Our proposal in this research process is...

Full description

Saved in:
Bibliographic Details
Main Authors: Sanchez-Garcia, Angel J., Rios-Figueroa, Homero V., Limon-Riano, Xavier, Sanchez-Garcia, Juan Andres, Cortes-Verdin, Karen
Format: Conference Proceeding
Language:English
Subjects:
Automotive engineering
Avoiding collisions
Mechatronics
robot navigation
Segmentation
YOLOv3
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 27
container_issue
container_start_page 24
container_title
container_volume
creator Sanchez-Garcia, Angel J.
Rios-Figueroa, Homero V.
Limon-Riano, Xavier
Sanchez-Garcia, Juan Andres
Cortes-Verdin, Karen
description Avoiding obstacles is one of the main tasks in robotic navigation. In this paper, robot navigation using monocular vision is presented. Therefore, an accuracy in the segmentation of obstacles is necessary to avoid collisions by estimating the Time-to-Contact. Our proposal in this research process is based on using YOLO so that through a training process, the robot identifies which regions of the image are potentially obstacles. The experimentation was performed in a real environment, with low daylight and without controlling lighting parameters. The first results of this approach are satisfactory although this project will continue with the learning of other obstacles.
doi_str_mv 10.1109/ICMEAE.2019.00012
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_9140167</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9140167</ieee_id><sourcerecordid>9140167</sourcerecordid><originalsourceid>FETCH-LOGICAL-i203t-b3e1028e9e8c95458c7e03dcee36e759e84cfba8baae9fbd9c574f80ba931c5d3</originalsourceid><addsrcrecordid>eNotjNFKwzAYRqMgOOceQLzJC3TmT5omuSyl6qBzIPN6JOnfEekaabqJb29Brw585-MQ8gBsDcDM06ba1mW95gzMmjEG_IrcgeIaCiaUvCYLLpXIxGxuySqlz_nDJQiuiwXZ7uO3HdtEG7TjEIYj3bk0Wd9jolOk5SWGllax70MKcUg0DLQ8T3GIp3hO9D26ONE3ewlHO83-ntx0tk-4-ueSfDzX--o1a3Yvm6psssCZmDInEBjXaFB7I3OpvUImWo8oClRynnPfOaudtWg61xovVd5p5qwR4GUrluTxrxsQ8fA1hpMdfw4GcgaFEr-hU0-J</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Towards Learning Obstacles to Avoid Collisions in Autonomous Robot Navigation</title><source>IEEE Xplore All Conference Series</source><creator>Sanchez-Garcia, Angel J. ; Rios-Figueroa, Homero V. ; Limon-Riano, Xavier ; Sanchez-Garcia, Juan Andres ; Cortes-Verdin, Karen</creator><creatorcontrib>Sanchez-Garcia, Angel J. ; Rios-Figueroa, Homero V. ; Limon-Riano, Xavier ; Sanchez-Garcia, Juan Andres ; Cortes-Verdin, Karen</creatorcontrib><description>Avoiding obstacles is one of the main tasks in robotic navigation. In this paper, robot navigation using monocular vision is presented. Therefore, an accuracy in the segmentation of obstacles is necessary to avoid collisions by estimating the Time-to-Contact. Our proposal in this research process is based on using YOLO so that through a training process, the robot identifies which regions of the image are potentially obstacles. The experimentation was performed in a real environment, with low daylight and without controlling lighting parameters. The first results of this approach are satisfactory although this project will continue with the learning of other obstacles.</description><identifier>EISSN: 2573-3001</identifier><identifier>EISBN: 1728160375</identifier><identifier>EISBN: 9781728160375</identifier><identifier>DOI: 10.1109/ICMEAE.2019.00012</identifier><language>eng</language><publisher>IEEE</publisher><subject>Automotive engineering ; Avoiding collisions ; Mechatronics ; robot navigation ; Segmentation ; YOLOv3</subject><ispartof>2019 International Conference on Mechatronics, Electronics and Automotive Engineering (ICMEAE), 2019, p.24-27</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9140167$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,23930,23931,25140,27925,54555,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9140167$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Sanchez-Garcia, Angel J.</creatorcontrib><creatorcontrib>Rios-Figueroa, Homero V.</creatorcontrib><creatorcontrib>Limon-Riano, Xavier</creatorcontrib><creatorcontrib>Sanchez-Garcia, Juan Andres</creatorcontrib><creatorcontrib>Cortes-Verdin, Karen</creatorcontrib><title>Towards Learning Obstacles to Avoid Collisions in Autonomous Robot Navigation</title><title>2019 International Conference on Mechatronics, Electronics and Automotive Engineering (ICMEAE)</title><addtitle>ICMEAE</addtitle><description>Avoiding obstacles is one of the main tasks in robotic navigation. In this paper, robot navigation using monocular vision is presented. Therefore, an accuracy in the segmentation of obstacles is necessary to avoid collisions by estimating the Time-to-Contact. Our proposal in this research process is based on using YOLO so that through a training process, the robot identifies which regions of the image are potentially obstacles. The experimentation was performed in a real environment, with low daylight and without controlling lighting parameters. The first results of this approach are satisfactory although this project will continue with the learning of other obstacles.</description><subject>Automotive engineering</subject><subject>Avoiding collisions</subject><subject>Mechatronics</subject><subject>robot navigation</subject><subject>Segmentation</subject><subject>YOLOv3</subject><issn>2573-3001</issn><isbn>1728160375</isbn><isbn>9781728160375</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2019</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotjNFKwzAYRqMgOOceQLzJC3TmT5omuSyl6qBzIPN6JOnfEekaabqJb29Brw585-MQ8gBsDcDM06ba1mW95gzMmjEG_IrcgeIaCiaUvCYLLpXIxGxuySqlz_nDJQiuiwXZ7uO3HdtEG7TjEIYj3bk0Wd9jolOk5SWGllax70MKcUg0DLQ8T3GIp3hO9D26ONE3ewlHO83-ntx0tk-4-ueSfDzX--o1a3Yvm6psssCZmDInEBjXaFB7I3OpvUImWo8oClRynnPfOaudtWg61xovVd5p5qwR4GUrluTxrxsQ8fA1hpMdfw4GcgaFEr-hU0-J</recordid><startdate>201911</startdate><enddate>201911</enddate><creator>Sanchez-Garcia, Angel J.</creator><creator>Rios-Figueroa, Homero V.</creator><creator>Limon-Riano, Xavier</creator><creator>Sanchez-Garcia, Juan Andres</creator><creator>Cortes-Verdin, Karen</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201911</creationdate><title>Towards Learning Obstacles to Avoid Collisions in Autonomous Robot Navigation</title><author>Sanchez-Garcia, Angel J. ; Rios-Figueroa, Homero V. ; Limon-Riano, Xavier ; Sanchez-Garcia, Juan Andres ; Cortes-Verdin, Karen</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i203t-b3e1028e9e8c95458c7e03dcee36e759e84cfba8baae9fbd9c574f80ba931c5d3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Automotive engineering</topic><topic>Avoiding collisions</topic><topic>Mechatronics</topic><topic>robot navigation</topic><topic>Segmentation</topic><topic>YOLOv3</topic><toplevel>online_resources</toplevel><creatorcontrib>Sanchez-Garcia, Angel J.</creatorcontrib><creatorcontrib>Rios-Figueroa, Homero V.</creatorcontrib><creatorcontrib>Limon-Riano, Xavier</creatorcontrib><creatorcontrib>Sanchez-Garcia, Juan Andres</creatorcontrib><creatorcontrib>Cortes-Verdin, Karen</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE/IET Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Sanchez-Garcia, Angel J.</au><au>Rios-Figueroa, Homero V.</au><au>Limon-Riano, Xavier</au><au>Sanchez-Garcia, Juan Andres</au><au>Cortes-Verdin, Karen</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Towards Learning Obstacles to Avoid Collisions in Autonomous Robot Navigation</atitle><btitle>2019 International Conference on Mechatronics, Electronics and Automotive Engineering (ICMEAE)</btitle><stitle>ICMEAE</stitle><date>2019-11</date><risdate>2019</risdate><spage>24</spage><epage>27</epage><pages>24-27</pages><eissn>2573-3001</eissn><eisbn>1728160375</eisbn><eisbn>9781728160375</eisbn><abstract>Avoiding obstacles is one of the main tasks in robotic navigation. In this paper, robot navigation using monocular vision is presented. Therefore, an accuracy in the segmentation of obstacles is necessary to avoid collisions by estimating the Time-to-Contact. Our proposal in this research process is based on using YOLO so that through a training process, the robot identifies which regions of the image are potentially obstacles. The experimentation was performed in a real environment, with low daylight and without controlling lighting parameters. The first results of this approach are satisfactory although this project will continue with the learning of other obstacles.</abstract><pub>IEEE</pub><doi>10.1109/ICMEAE.2019.00012</doi><tpages>4</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier EISSN: 2573-3001
ispartof 2019 International Conference on Mechatronics, Electronics and Automotive Engineering (ICMEAE), 2019, p.24-27
issn 2573-3001
language eng
recordid cdi_ieee_primary_9140167
source IEEE Xplore All Conference Series
subjects Automotive engineering
Avoiding collisions
Mechatronics
robot navigation
Segmentation
YOLOv3
title Towards Learning Obstacles to Avoid Collisions in Autonomous Robot Navigation
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T22%3A51%3A11IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Towards%20Learning%20Obstacles%20to%20Avoid%20Collisions%20in%20Autonomous%20Robot%20Navigation&rft.btitle=2019%20International%20Conference%20on%20Mechatronics,%20Electronics%20and%20Automotive%20Engineering%20(ICMEAE)&rft.au=Sanchez-Garcia,%20Angel%20J.&rft.date=2019-11&rft.spage=24&rft.epage=27&rft.pages=24-27&rft.eissn=2573-3001&rft_id=info:doi/10.1109/ICMEAE.2019.00012&rft.eisbn=1728160375&rft.eisbn_list=9781728160375&rft_dat=%3Cieee_CHZPO%3E9140167%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i203t-b3e1028e9e8c95458c7e03dcee36e759e84cfba8baae9fbd9c574f80ba931c5d3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=9140167&rfr_iscdi=true