Collision-aware In-hand 6D Object Pose Estimation using Multiple Vision-based Tactile Sensors

In this paper, we address the problem of estimating the in-hand 6D pose of an object in contact with multiple vision-based tactile sensors. We reason on the possible spatial configurations of the sensors along the object surface. Specifically, we filter contact hypotheses using geometric reasoning a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Caddeo, Gabriele M, Piga, Nicola A, Bottarel, Fabrizio, Natale, Lorenzo
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Caddeo, Gabriele M
Piga, Nicola A
Bottarel, Fabrizio
Natale, Lorenzo
description In this paper, we address the problem of estimating the in-hand 6D pose of an object in contact with multiple vision-based tactile sensors. We reason on the possible spatial configurations of the sensors along the object surface. Specifically, we filter contact hypotheses using geometric reasoning and a Convolutional Neural Network (CNN), trained on simulated object-agnostic images, to promote those that better comply with the actual tactile images from the sensors. We use the selected sensors configurations to optimize over the space of 6D poses using a Gradient Descent-based approach. We finally rank the obtained poses by penalizing those that are in collision with the sensors. We carry out experiments in simulation using the DIGIT vision-based sensor with several objects, from the standard YCB model set. The results demonstrate that our approach estimates object poses that are compatible with actual object-sensor contacts in $87.5\%$ of cases while reaching an average positional error in the order of $2$ centimeters. Our analysis also includes qualitative results of experiments with a real DIGIT sensor.
doi_str_mv 10.48550/arxiv.2301.13667
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2301_13667</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2301_13667</sourcerecordid><originalsourceid>FETCH-LOGICAL-a677-d8bb670ba5e8eaae506cece3be4dc3ef48e393e6cd165ca0ded2d41f39a9a9063</originalsourceid><addsrcrecordid>eNotj81OwzAQhH3hgAoPwKl-AQe7jp30iEKBSkVFIuoNRWt7A0bBqWyXn7cntGgOI41mVvsRciV4UdZK8WuI3_6zWEguCiG1rs7JSzMOg09-DAy-ICJdB_YGwVF9S7fmHW2mT2NCukrZf0CeevSQfHilj4ch-_2AdHdaG0joaAs2-yl8xpDGmC7IWQ9Dwst_n5H2btU2D2yzvV83NxsGuqqYq43RFTegsEYAVFxbtCgNls5K7Msa5VKitk5oZYE7dAtXil4uYRLXckbmp7NHvm4fp1fjT_fH2R055S_g9k-H</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Collision-aware In-hand 6D Object Pose Estimation using Multiple Vision-based Tactile Sensors</title><source>arXiv.org</source><creator>Caddeo, Gabriele M ; Piga, Nicola A ; Bottarel, Fabrizio ; Natale, Lorenzo</creator><creatorcontrib>Caddeo, Gabriele M ; Piga, Nicola A ; Bottarel, Fabrizio ; Natale, Lorenzo</creatorcontrib><description>In this paper, we address the problem of estimating the in-hand 6D pose of an object in contact with multiple vision-based tactile sensors. We reason on the possible spatial configurations of the sensors along the object surface. Specifically, we filter contact hypotheses using geometric reasoning and a Convolutional Neural Network (CNN), trained on simulated object-agnostic images, to promote those that better comply with the actual tactile images from the sensors. We use the selected sensors configurations to optimize over the space of 6D poses using a Gradient Descent-based approach. We finally rank the obtained poses by penalizing those that are in collision with the sensors. We carry out experiments in simulation using the DIGIT vision-based sensor with several objects, from the standard YCB model set. The results demonstrate that our approach estimates object poses that are compatible with actual object-sensor contacts in $87.5\%$ of cases while reaching an average positional error in the order of $2$ centimeters. Our analysis also includes qualitative results of experiments with a real DIGIT sensor.</description><identifier>DOI: 10.48550/arxiv.2301.13667</identifier><language>eng</language><subject>Computer Science - Learning ; Computer Science - Robotics</subject><creationdate>2023-01</creationdate><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>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2301.13667$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2301.13667$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Caddeo, Gabriele M</creatorcontrib><creatorcontrib>Piga, Nicola A</creatorcontrib><creatorcontrib>Bottarel, Fabrizio</creatorcontrib><creatorcontrib>Natale, Lorenzo</creatorcontrib><title>Collision-aware In-hand 6D Object Pose Estimation using Multiple Vision-based Tactile Sensors</title><description>In this paper, we address the problem of estimating the in-hand 6D pose of an object in contact with multiple vision-based tactile sensors. We reason on the possible spatial configurations of the sensors along the object surface. Specifically, we filter contact hypotheses using geometric reasoning and a Convolutional Neural Network (CNN), trained on simulated object-agnostic images, to promote those that better comply with the actual tactile images from the sensors. We use the selected sensors configurations to optimize over the space of 6D poses using a Gradient Descent-based approach. We finally rank the obtained poses by penalizing those that are in collision with the sensors. We carry out experiments in simulation using the DIGIT vision-based sensor with several objects, from the standard YCB model set. The results demonstrate that our approach estimates object poses that are compatible with actual object-sensor contacts in $87.5\%$ of cases while reaching an average positional error in the order of $2$ centimeters. Our analysis also includes qualitative results of experiments with a real DIGIT sensor.</description><subject>Computer Science - Learning</subject><subject>Computer Science - Robotics</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj81OwzAQhH3hgAoPwKl-AQe7jp30iEKBSkVFIuoNRWt7A0bBqWyXn7cntGgOI41mVvsRciV4UdZK8WuI3_6zWEguCiG1rs7JSzMOg09-DAy-ICJdB_YGwVF9S7fmHW2mT2NCukrZf0CeevSQfHilj4ch-_2AdHdaG0joaAs2-yl8xpDGmC7IWQ9Dwst_n5H2btU2D2yzvV83NxsGuqqYq43RFTegsEYAVFxbtCgNls5K7Msa5VKitk5oZYE7dAtXil4uYRLXckbmp7NHvm4fp1fjT_fH2R055S_g9k-H</recordid><startdate>20230131</startdate><enddate>20230131</enddate><creator>Caddeo, Gabriele M</creator><creator>Piga, Nicola A</creator><creator>Bottarel, Fabrizio</creator><creator>Natale, Lorenzo</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20230131</creationdate><title>Collision-aware In-hand 6D Object Pose Estimation using Multiple Vision-based Tactile Sensors</title><author>Caddeo, Gabriele M ; Piga, Nicola A ; Bottarel, Fabrizio ; Natale, Lorenzo</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a677-d8bb670ba5e8eaae506cece3be4dc3ef48e393e6cd165ca0ded2d41f39a9a9063</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Learning</topic><topic>Computer Science - Robotics</topic><toplevel>online_resources</toplevel><creatorcontrib>Caddeo, Gabriele M</creatorcontrib><creatorcontrib>Piga, Nicola A</creatorcontrib><creatorcontrib>Bottarel, Fabrizio</creatorcontrib><creatorcontrib>Natale, Lorenzo</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Caddeo, Gabriele M</au><au>Piga, Nicola A</au><au>Bottarel, Fabrizio</au><au>Natale, Lorenzo</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Collision-aware In-hand 6D Object Pose Estimation using Multiple Vision-based Tactile Sensors</atitle><date>2023-01-31</date><risdate>2023</risdate><abstract>In this paper, we address the problem of estimating the in-hand 6D pose of an object in contact with multiple vision-based tactile sensors. We reason on the possible spatial configurations of the sensors along the object surface. Specifically, we filter contact hypotheses using geometric reasoning and a Convolutional Neural Network (CNN), trained on simulated object-agnostic images, to promote those that better comply with the actual tactile images from the sensors. We use the selected sensors configurations to optimize over the space of 6D poses using a Gradient Descent-based approach. We finally rank the obtained poses by penalizing those that are in collision with the sensors. We carry out experiments in simulation using the DIGIT vision-based sensor with several objects, from the standard YCB model set. The results demonstrate that our approach estimates object poses that are compatible with actual object-sensor contacts in $87.5\%$ of cases while reaching an average positional error in the order of $2$ centimeters. Our analysis also includes qualitative results of experiments with a real DIGIT sensor.</abstract><doi>10.48550/arxiv.2301.13667</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2301.13667
ispartof
issn
language eng
recordid cdi_arxiv_primary_2301_13667
source arXiv.org
subjects Computer Science - Learning
Computer Science - Robotics
title Collision-aware In-hand 6D Object Pose Estimation using Multiple Vision-based Tactile Sensors
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-29T07%3A14%3A53IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Collision-aware%20In-hand%206D%20Object%20Pose%20Estimation%20using%20Multiple%20Vision-based%20Tactile%20Sensors&rft.au=Caddeo,%20Gabriele%20M&rft.date=2023-01-31&rft_id=info:doi/10.48550/arxiv.2301.13667&rft_dat=%3Carxiv_GOX%3E2301_13667%3C/arxiv_GOX%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