Warped Gaussian Processes Occupancy Mapping with Uncertain Inputs

In this paper, we study extensions to the Gaussian Processes (GPs) continuous occupancy mapping problem. There are two classes of occupancy mapping problems that we particularly investigate. The first problem is related to mapping under pose uncertainty and how to propagate pose estimation uncertain...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2017-01
Hauptverfasser: Maani Ghaffari Jadidi, Jaime Valls Miro, Dissanayake, Gamini
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Maani Ghaffari Jadidi
Jaime Valls Miro
Dissanayake, Gamini
description In this paper, we study extensions to the Gaussian Processes (GPs) continuous occupancy mapping problem. There are two classes of occupancy mapping problems that we particularly investigate. The first problem is related to mapping under pose uncertainty and how to propagate pose estimation uncertainty into the map inference. We develop expected kernel and expected sub-map notions to deal with uncertain inputs. In the second problem, we account for the complication of the robot's perception noise using Warped Gaussian Processes (WGPs). This approach allows for non-Gaussian noise in the observation space and captures the possible nonlinearity in that space better than standard GPs. The developed techniques can be applied separately or concurrently to a standard GP occupancy mapping problem. According to our experimental results, although taking into account pose uncertainty leads, as expected, to more uncertain maps, by modeling the nonlinearities present in the observation space WGPs improve the map quality.
doi_str_mv 10.48550/arxiv.1701.00925
format Article
fullrecord <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_1701_00925</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2076113745</sourcerecordid><originalsourceid>FETCH-LOGICAL-a525-32bd7745f8f26e1968f040ad0f9f9815f577a0a4425652de7150506832bbb19d3</originalsourceid><addsrcrecordid>eNotj71OwzAUhS0kJKrSB2DCEnPKtZ0bJ2NVQalUVIYixugmsSEVOMZOgL49oWU6y_n7GLsSME9zRLil8NN-zYUGMQcoJJ6xiVRKJHkq5QWbxbgHAJlpiagmbPFCwZuGr2iIsSXHn0JXmxhN5Nu6Hjy5-sAfyfvWvfLvtn_jz642oafW8bXzQx8v2bml92hm_zplu_u73fIh2WxX6-VikxBKTJSsGq1TtLmVmRFFlltIgRqwhS1ygRa1JqA0lZihbIwWCAhZPuaqShSNmrLrU-2Rr_Sh_aBwKP84yyPn6Lg5OXzoPgcT-3LfDcGNn0oJOhNCjfvqFw4-VD8</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2076113745</pqid></control><display><type>article</type><title>Warped Gaussian Processes Occupancy Mapping with Uncertain Inputs</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Maani Ghaffari Jadidi ; Jaime Valls Miro ; Dissanayake, Gamini</creator><creatorcontrib>Maani Ghaffari Jadidi ; Jaime Valls Miro ; Dissanayake, Gamini</creatorcontrib><description>In this paper, we study extensions to the Gaussian Processes (GPs) continuous occupancy mapping problem. There are two classes of occupancy mapping problems that we particularly investigate. The first problem is related to mapping under pose uncertainty and how to propagate pose estimation uncertainty into the map inference. We develop expected kernel and expected sub-map notions to deal with uncertain inputs. In the second problem, we account for the complication of the robot's perception noise using Warped Gaussian Processes (WGPs). This approach allows for non-Gaussian noise in the observation space and captures the possible nonlinearity in that space better than standard GPs. The developed techniques can be applied separately or concurrently to a standard GP occupancy mapping problem. According to our experimental results, although taking into account pose uncertainty leads, as expected, to more uncertain maps, by modeling the nonlinearities present in the observation space WGPs improve the map quality.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.1701.00925</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Computer Science - Robotics ; Gaussian process ; Mapping ; Occupancy ; Random noise ; Uncertainty</subject><ispartof>arXiv.org, 2017-01</ispartof><rights>2017. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,780,881,27904</link.rule.ids><backlink>$$Uhttps://doi.org/10.1109/LRA.2017.2651154$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.48550/arXiv.1701.00925$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Maani Ghaffari Jadidi</creatorcontrib><creatorcontrib>Jaime Valls Miro</creatorcontrib><creatorcontrib>Dissanayake, Gamini</creatorcontrib><title>Warped Gaussian Processes Occupancy Mapping with Uncertain Inputs</title><title>arXiv.org</title><description>In this paper, we study extensions to the Gaussian Processes (GPs) continuous occupancy mapping problem. There are two classes of occupancy mapping problems that we particularly investigate. The first problem is related to mapping under pose uncertainty and how to propagate pose estimation uncertainty into the map inference. We develop expected kernel and expected sub-map notions to deal with uncertain inputs. In the second problem, we account for the complication of the robot's perception noise using Warped Gaussian Processes (WGPs). This approach allows for non-Gaussian noise in the observation space and captures the possible nonlinearity in that space better than standard GPs. The developed techniques can be applied separately or concurrently to a standard GP occupancy mapping problem. According to our experimental results, although taking into account pose uncertainty leads, as expected, to more uncertain maps, by modeling the nonlinearities present in the observation space WGPs improve the map quality.</description><subject>Computer Science - Robotics</subject><subject>Gaussian process</subject><subject>Mapping</subject><subject>Occupancy</subject><subject>Random noise</subject><subject>Uncertainty</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GOX</sourceid><recordid>eNotj71OwzAUhS0kJKrSB2DCEnPKtZ0bJ2NVQalUVIYixugmsSEVOMZOgL49oWU6y_n7GLsSME9zRLil8NN-zYUGMQcoJJ6xiVRKJHkq5QWbxbgHAJlpiagmbPFCwZuGr2iIsSXHn0JXmxhN5Nu6Hjy5-sAfyfvWvfLvtn_jz642oafW8bXzQx8v2bml92hm_zplu_u73fIh2WxX6-VikxBKTJSsGq1TtLmVmRFFlltIgRqwhS1ygRa1JqA0lZihbIwWCAhZPuaqShSNmrLrU-2Rr_Sh_aBwKP84yyPn6Lg5OXzoPgcT-3LfDcGNn0oJOhNCjfvqFw4-VD8</recordid><startdate>20170104</startdate><enddate>20170104</enddate><creator>Maani Ghaffari Jadidi</creator><creator>Jaime Valls Miro</creator><creator>Dissanayake, Gamini</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20170104</creationdate><title>Warped Gaussian Processes Occupancy Mapping with Uncertain Inputs</title><author>Maani Ghaffari Jadidi ; Jaime Valls Miro ; Dissanayake, Gamini</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a525-32bd7745f8f26e1968f040ad0f9f9815f577a0a4425652de7150506832bbb19d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Computer Science - Robotics</topic><topic>Gaussian process</topic><topic>Mapping</topic><topic>Occupancy</topic><topic>Random noise</topic><topic>Uncertainty</topic><toplevel>online_resources</toplevel><creatorcontrib>Maani Ghaffari Jadidi</creatorcontrib><creatorcontrib>Jaime Valls Miro</creatorcontrib><creatorcontrib>Dissanayake, Gamini</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection (ProQuest)</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>arXiv Computer Science</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Maani Ghaffari Jadidi</au><au>Jaime Valls Miro</au><au>Dissanayake, Gamini</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Warped Gaussian Processes Occupancy Mapping with Uncertain Inputs</atitle><jtitle>arXiv.org</jtitle><date>2017-01-04</date><risdate>2017</risdate><eissn>2331-8422</eissn><abstract>In this paper, we study extensions to the Gaussian Processes (GPs) continuous occupancy mapping problem. There are two classes of occupancy mapping problems that we particularly investigate. The first problem is related to mapping under pose uncertainty and how to propagate pose estimation uncertainty into the map inference. We develop expected kernel and expected sub-map notions to deal with uncertain inputs. In the second problem, we account for the complication of the robot's perception noise using Warped Gaussian Processes (WGPs). This approach allows for non-Gaussian noise in the observation space and captures the possible nonlinearity in that space better than standard GPs. The developed techniques can be applied separately or concurrently to a standard GP occupancy mapping problem. According to our experimental results, although taking into account pose uncertainty leads, as expected, to more uncertain maps, by modeling the nonlinearities present in the observation space WGPs improve the map quality.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.1701.00925</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2017-01
issn 2331-8422
language eng
recordid cdi_arxiv_primary_1701_00925
source arXiv.org; Free E- Journals
subjects Computer Science - Robotics
Gaussian process
Mapping
Occupancy
Random noise
Uncertainty
title Warped Gaussian Processes Occupancy Mapping with Uncertain Inputs
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-24T08%3A36%3A28IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Warped%20Gaussian%20Processes%20Occupancy%20Mapping%20with%20Uncertain%20Inputs&rft.jtitle=arXiv.org&rft.au=Maani%20Ghaffari%20Jadidi&rft.date=2017-01-04&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.1701.00925&rft_dat=%3Cproquest_arxiv%3E2076113745%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2076113745&rft_id=info:pmid/&rfr_iscdi=true