Effective Map Merging for Long-Term Autonomous Navigation

Effective Map Merging for Long-Term Autonomous Navigation

An algorithm is presented that intelligently merges multiple 3D point clouds used for localization based on when the point cloud was recorded to create an updated map that is more similar to the current environment. The algorithm was implemented on a Boston Dynamics Spot robot and was used to upgrad...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:ASME journal of autonomous vehicles and systems (Print) 2024-10, Vol.4 (4)
Hauptverfasser: Baird, Christopher, Nokleby, Scott
Format: Artikel
Sprache:eng
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue 4
container_start_page
container_title ASME journal of autonomous vehicles and systems (Print)
container_volume 4
creator Baird, Christopher
Nokleby, Scott
description An algorithm is presented that intelligently merges multiple 3D point clouds used for localization based on when the point cloud was recorded to create an updated map that is more similar to the current environment. The algorithm was implemented on a Boston Dynamics Spot robot and was used to upgrade Spot’s autonomous navigation algorithm called Autowalk by adding the capability for long-term navigation in semi-static environments. The proposed algorithm was validated by having Spot navigate both indoor and outdoor environments over multiple months traveling over 43 km autonomously without losing localization. The proposed method extends the life of programmed autonomous missions to ensure a robot can be used over extended periods of time without the need to re-teach these autonomous missions due to changes in the environment.
doi_str_mv 10.1115/1.4066517
format Article
fullrecord <record><control><sourceid>asme_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1115_1_4066517</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1206152</sourcerecordid><originalsourceid>FETCH-LOGICAL-a557-8e9686bd0e2daaab05f258cd093073129c5d0b77c4f7e7073c63e1aab0f965fd3</originalsourceid><addsrcrecordid>eNo9jz1rwzAYhEVpoSHN0L2D1w5O31eKJGsMIf0Ap108dBOyLBmH2gpSHOi_r0NCpzuOh-OOkEeEJSLyF1yuQAiO8obMqFCQS2DF7b-n3_dkkdIeAChHxlDOiNp67-yxO7lsZw7ZzsW2G9rMh5iVYWjzysU-W4_HMIQ-jCn7NKeuNccuDA_kzpuf5BZXnZPqdVtt3vPy6-1jsy5zw7nMC6dEIeoGHG2MMTVwT3lhG1AMJEOqLG-gltKuvHRyiqxgDs-gV4L7hs3J86XWxpBSdF4fYteb-KsR9Pm1Rn19PbFPF9ak3ul9GOMwLdNIQSCn7A8j_VHB</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Effective Map Merging for Long-Term Autonomous Navigation</title><source>ASME Transactions Journals</source><creator>Baird, Christopher ; Nokleby, Scott</creator><creatorcontrib>Baird, Christopher ; Nokleby, Scott</creatorcontrib><description>An algorithm is presented that intelligently merges multiple 3D point clouds used for localization based on when the point cloud was recorded to create an updated map that is more similar to the current environment. The algorithm was implemented on a Boston Dynamics Spot robot and was used to upgrade Spot’s autonomous navigation algorithm called Autowalk by adding the capability for long-term navigation in semi-static environments. The proposed algorithm was validated by having Spot navigate both indoor and outdoor environments over multiple months traveling over 43 km autonomously without losing localization. The proposed method extends the life of programmed autonomous missions to ensure a robot can be used over extended periods of time without the need to re-teach these autonomous missions due to changes in the environment.</description><identifier>ISSN: 2690-702X</identifier><identifier>EISSN: 2690-7038</identifier><identifier>DOI: 10.1115/1.4066517</identifier><language>eng</language><publisher>ASME</publisher><ispartof>ASME journal of autonomous vehicles and systems (Print), 2024-10, Vol.4 (4)</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-a557-8e9686bd0e2daaab05f258cd093073129c5d0b77c4f7e7073c63e1aab0f965fd3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27915,27916,38511</link.rule.ids></links><search><creatorcontrib>Baird, Christopher</creatorcontrib><creatorcontrib>Nokleby, Scott</creatorcontrib><title>Effective Map Merging for Long-Term Autonomous Navigation</title><title>ASME journal of autonomous vehicles and systems (Print)</title><addtitle>J. Auton. Veh. Sys</addtitle><description>An algorithm is presented that intelligently merges multiple 3D point clouds used for localization based on when the point cloud was recorded to create an updated map that is more similar to the current environment. The algorithm was implemented on a Boston Dynamics Spot robot and was used to upgrade Spot’s autonomous navigation algorithm called Autowalk by adding the capability for long-term navigation in semi-static environments. The proposed algorithm was validated by having Spot navigate both indoor and outdoor environments over multiple months traveling over 43 km autonomously without losing localization. The proposed method extends the life of programmed autonomous missions to ensure a robot can be used over extended periods of time without the need to re-teach these autonomous missions due to changes in the environment.</description><issn>2690-702X</issn><issn>2690-7038</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNo9jz1rwzAYhEVpoSHN0L2D1w5O31eKJGsMIf0Ap108dBOyLBmH2gpSHOi_r0NCpzuOh-OOkEeEJSLyF1yuQAiO8obMqFCQS2DF7b-n3_dkkdIeAChHxlDOiNp67-yxO7lsZw7ZzsW2G9rMh5iVYWjzysU-W4_HMIQ-jCn7NKeuNccuDA_kzpuf5BZXnZPqdVtt3vPy6-1jsy5zw7nMC6dEIeoGHG2MMTVwT3lhG1AMJEOqLG-gltKuvHRyiqxgDs-gV4L7hs3J86XWxpBSdF4fYteb-KsR9Pm1Rn19PbFPF9ak3ul9GOMwLdNIQSCn7A8j_VHB</recordid><startdate>20241001</startdate><enddate>20241001</enddate><creator>Baird, Christopher</creator><creator>Nokleby, Scott</creator><general>ASME</general><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20241001</creationdate><title>Effective Map Merging for Long-Term Autonomous Navigation</title><author>Baird, Christopher ; Nokleby, Scott</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a557-8e9686bd0e2daaab05f258cd093073129c5d0b77c4f7e7073c63e1aab0f965fd3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Baird, Christopher</creatorcontrib><creatorcontrib>Nokleby, Scott</creatorcontrib><collection>CrossRef</collection><jtitle>ASME journal of autonomous vehicles and systems (Print)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Baird, Christopher</au><au>Nokleby, Scott</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Effective Map Merging for Long-Term Autonomous Navigation</atitle><jtitle>ASME journal of autonomous vehicles and systems (Print)</jtitle><stitle>J. Auton. Veh. Sys</stitle><date>2024-10-01</date><risdate>2024</risdate><volume>4</volume><issue>4</issue><issn>2690-702X</issn><eissn>2690-7038</eissn><abstract>An algorithm is presented that intelligently merges multiple 3D point clouds used for localization based on when the point cloud was recorded to create an updated map that is more similar to the current environment. The algorithm was implemented on a Boston Dynamics Spot robot and was used to upgrade Spot’s autonomous navigation algorithm called Autowalk by adding the capability for long-term navigation in semi-static environments. The proposed algorithm was validated by having Spot navigate both indoor and outdoor environments over multiple months traveling over 43 km autonomously without losing localization. The proposed method extends the life of programmed autonomous missions to ensure a robot can be used over extended periods of time without the need to re-teach these autonomous missions due to changes in the environment.</abstract><pub>ASME</pub><doi>10.1115/1.4066517</doi></addata></record>
fulltext fulltext
identifier ISSN: 2690-702X
ispartof ASME journal of autonomous vehicles and systems (Print), 2024-10, Vol.4 (4)
issn 2690-702X
2690-7038
language eng
recordid cdi_crossref_primary_10_1115_1_4066517
source ASME Transactions Journals
title Effective Map Merging for Long-Term Autonomous Navigation
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T18%3A42%3A40IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-asme_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Effective%20Map%20Merging%20for%20Long-Term%20Autonomous%20Navigation&rft.jtitle=ASME%20journal%20of%20autonomous%20vehicles%20and%20systems%20(Print)&rft.au=Baird,%20Christopher&rft.date=2024-10-01&rft.volume=4&rft.issue=4&rft.issn=2690-702X&rft.eissn=2690-7038&rft_id=info:doi/10.1115/1.4066517&rft_dat=%3Casme_cross%3E1206152%3C/asme_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true