A Tactile-Based Framework for Active Object Learning and Discrimination using Multimodal Robotic Skin

In this letter, we propose a complete probabilistic tactile-based framework to enable robots to autonomously explore unknown workspaces and recognize objects based on their physical properties. Our framework consists of three components: 1) an active pretouch strategy to efficiently explore unknown...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE robotics and automation letters Ročník 2; číslo 4; s. 2143 - 2150
Hlavní autoři:	Kaboli, Mohsen, Di Feng, Kunpeng Yao, Lanillos, Pablo, Cheng, Gordon
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	IEEE 01.10.2017
Témata:	Active tactile learning artificial robotic skin Conductivity force and tactile sensing Robot sensing systems Skin Surface texture tactile object recognition Thermal conductivity Training
ISSN:	2377-3766, 2377-3766
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	In this letter, we propose a complete probabilistic tactile-based framework to enable robots to autonomously explore unknown workspaces and recognize objects based on their physical properties. Our framework consists of three components: 1) an active pretouch strategy to efficiently explore unknown workspaces; 2) an active touch learning method to learn about unknown objects based on their physical properties (surface texture, stiffness, and thermal conductivity) with the least number of training samples; and 3) an active touch algorithm for object discrimination, which selects the most informative exploratory action to apply to the object, so that the robot can efficiently distinguish between objects with a few number of actions. Our proposed framework was experimentally evaluated using a robotic arm equipped with multimodal artificial skin. The robot with the active pretouch method reduced the uncertainty of the workspace up to 30% and 70% compared to uniform and random strategies, respectively. By means of the active touch learning algorithm, the robot used 50% fewer samples to achieve the same learning accuracy than the baseline methods. By taking advantage of the prior knowledge obtained during the learning process, the robot actively discriminated objects with an improvement of 10% recognition accuracy compare to the random action selection approach.
AbstractList	In this letter, we propose a complete probabilistic tactile-based framework to enable robots to autonomously explore unknown workspaces and recognize objects based on their physical properties. Our framework consists of three components: 1) an active pretouch strategy to efficiently explore unknown workspaces; 2) an active touch learning method to learn about unknown objects based on their physical properties (surface texture, stiffness, and thermal conductivity) with the least number of training samples; and 3) an active touch algorithm for object discrimination, which selects the most informative exploratory action to apply to the object, so that the robot can efficiently distinguish between objects with a few number of actions. Our proposed framework was experimentally evaluated using a robotic arm equipped with multimodal artificial skin. The robot with the active pretouch method reduced the uncertainty of the workspace up to 30% and 70% compared to uniform and random strategies, respectively. By means of the active touch learning algorithm, the robot used 50% fewer samples to achieve the same learning accuracy than the baseline methods. By taking advantage of the prior knowledge obtained during the learning process, the robot actively discriminated objects with an improvement of 10% recognition accuracy compare to the random action selection approach.
Author	Cheng, Gordon Di Feng Kunpeng Yao Kaboli, Mohsen Lanillos, Pablo
Author_xml	– sequence: 1 givenname: Mohsen surname: Kaboli fullname: Kaboli, Mohsen email: mohsen.kaboli@tum.de organization: Inst. for Cognitive Syst., Tech. Univ. Munchen, Munich, Germany – sequence: 2 surname: Di Feng fullname: Di Feng email: fengdi1015@gmail.com organization: Inst. for Cognitive Syst., Tech. Univ. Munchen, Munich, Germany – sequence: 3 surname: Kunpeng Yao fullname: Kunpeng Yao email: kunpeng.yao@tum.de organization: Inst. for Cognitive Syst., Tech. Univ. Munchen, Munich, Germany – sequence: 4 givenname: Pablo surname: Lanillos fullname: Lanillos, Pablo email: p.lanillos@tum.de organization: Inst. for Cognitive Syst., Tech. Univ. Munchen, Munich, Germany – sequence: 5 givenname: Gordon surname: Cheng fullname: Cheng, Gordon email: gordon.cheng@ieee.org organization: Inst. for Cognitive Syst., Tech. Univ. Munchen, Munich, Germany
BookMark	eNp9kFFLwzAQx4NMcM69C77kC3QmzZK0j3U6FSqDOZ_LNblKtq6VpFP89nZuiPjg0x3873fc_c7JoGkbJOSSswnnLL3Ol9kkZlxPYh2zRIoTMoyF1pHQSg1-9WdkHMKaMcZlrEUqhwQzugLTuRqjGwho6dzDFj9av6FV62nWR-9IF-UaTUdzBN-45pVCY-mtC8a7rWugc21Dd2EfPO3qzm1bCzVdtmXbOUOfN665IKcV1AHHxzoiL_O71ewhyhf3j7Msj4yI0y5KDJRoJHCA2CaqBCunZVolcZqUqKxQwKYJKytbcVYJIxXilKUoNdgEJGNiRNRhr_FtCB6rwrju-77Og6sLzoq9r6L3Vex9FUdfPcj-gG_9b-A__0OuDohDxJ9xnSrOUyG-AHXReTo
CODEN	IRALC6
CitedBy_id	crossref_primary_10_1109_TRO_2020_3003230 crossref_primary_10_1109_TCDS_2018_2819826 crossref_primary_10_1109_TRO_2021_3111786 crossref_primary_10_1109_LRA_2020_3038377 crossref_primary_10_1109_LRA_2020_3013915 crossref_primary_10_1109_LRA_2018_2799743 crossref_primary_10_1002_aisy_202200203 crossref_primary_10_1109_LRA_2019_2901991 crossref_primary_10_1109_JSEN_2024_3471175 crossref_primary_10_3390_s18040948 crossref_primary_10_1007_s43154_020_00005_6 crossref_primary_10_1109_TCYB_2023_3249467 crossref_primary_10_1109_LRA_2022_3193466 crossref_primary_10_1109_TIE_2018_2878157 crossref_primary_10_3390_s18092785 crossref_primary_10_3390_s18020634 crossref_primary_10_1109_JSEN_2021_3140002 crossref_primary_10_1109_TRO_2018_2830364 crossref_primary_10_1177_02783649241301443 crossref_primary_10_3390_s24165172 crossref_primary_10_1002_admt_202000641 crossref_primary_10_1016_j_rcim_2025_103020 crossref_primary_10_1109_LRA_2022_3191408 crossref_primary_10_1007_s10514_018_9707_8 crossref_primary_10_1016_j_engappai_2023_107329 crossref_primary_10_1109_LRA_2022_3150045 crossref_primary_10_1002_aisy_202100122 crossref_primary_10_3390_s20133624 crossref_primary_10_1007_s10514_019_09882_z crossref_primary_10_1016_j_robot_2023_104461 crossref_primary_10_1109_LRA_2024_3483037
Cites_doi	10.1109/IJCNN.2010.5596360 10.1109/ICRA.2013.6630996 10.1109/ICSMC.1998.727512 10.1109/MMUL.2006.69 10.3389/fnbot.2012.00004 10.1109/HUMANOIDS.2016.7803358 10.3390/s140814131 10.1109/ICRA.2016.7487372 10.3390/s140304899 10.1016/j.ins.2014.05.054 10.1109/HAVE.2013.6679606 10.1109/EMBC.2015.7320253 10.1109/TRO.2011.2106330 10.1016/j.robot.2016.09.014 10.1109/HUMANOIDS.2014.7041358 10.1109/TIM.2013.2293812 10.1109/IROS.2014.6942622 10.1109/ICRA.2013.6631000 10.1109/ICRA.2013.6631001 10.1016/j.robot.2013.11.011 10.1109/TRO.2009.2033627 10.1109/LRA.2016.2517213 10.1109/HUMANOIDS.2015.7363508
ContentType	Journal Article
DBID	97E ESBDL RIA RIE AAYXX CITATION
DOI	10.1109/LRA.2017.2720853
DatabaseName	IEEE Xplore (IEEE) IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef
DatabaseTitle	CrossRef
DatabaseTitleList
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	2377-3766
EndPage	2150
ExternalDocumentID	10_1109_LRA_2017_2720853 7961193
Genre	orig-research
GrantInformation_xml	– fundername: European Community's Seventh Framework Programme (FP7/2007-2013) grantid: 609206 funderid: 10.13039/501100004963
GroupedDBID	0R~ 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFS AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD ESBDL IFIPE IPLJI JAVBF KQ8 M43 M~E O9- OCL RIA RIE AAYXX CITATION
ID	FETCH-LOGICAL-c329t-8cabec5a1aa2d86bad54b9f8298be6d36a0480bfdf10f3c56ee409e57ad8a5003
IEDL.DBID	RIE
ISICitedReferencesCount	51
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000413741800041&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2377-3766
IngestDate	Sat Nov 29 06:02:59 EST 2025 Tue Nov 18 22:25:27 EST 2025 Tue Aug 26 16:57:02 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	4
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/OAPA.html
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c329t-8cabec5a1aa2d86bad54b9f8298be6d36a0480bfdf10f3c56ee409e57ad8a5003
OpenAccessLink	https://ieeexplore.ieee.org/document/7961193
PageCount	8
ParticipantIDs	crossref_citationtrail_10_1109_LRA_2017_2720853 crossref_primary_10_1109_LRA_2017_2720853 ieee_primary_7961193
PublicationCentury	2000
PublicationDate	2017-Oct. 2017-10-00
PublicationDateYYYYMMDD	2017-10-01
PublicationDate_xml	– month: 10 year: 2017 text: 2017-Oct.
PublicationDecade	2010
PublicationTitle	IEEE robotics and automation letters
PublicationTitleAbbrev	LRA
PublicationYear	2017
Publisher	IEEE
Publisher_xml	– name: IEEE
References	ref13 rasmussen (ref26) 2005 ref12 ref15 ref14 kaboli (ref25) 2017; 33 ref11 saal (ref17) 0 ref10 ref2 fishel (ref27) 2011; 6 ref1 ref16 ref19 ref18 ref24 ref23 ref20 ref22 ref21 ref8 ref7 ref9 ref4 ref3 ref6 ref5
References_xml	– volume: 33 start-page: 5 year: 2017 ident: ref25 article-title: Robust tactile descriptors for discriminating objects from textural properties via artificial robotic skin publication-title: IEEE Trans Robotics – ident: ref11 doi: 10.1109/IJCNN.2010.5596360 – ident: ref16 doi: 10.1109/ICRA.2013.6630996 – ident: ref9 doi: 10.1109/ICSMC.1998.727512 – ident: ref1 doi: 10.1109/MMUL.2006.69 – ident: ref18 doi: 10.3389/fnbot.2012.00004 – ident: ref5 doi: 10.1109/HUMANOIDS.2016.7803358 – ident: ref22 doi: 10.3390/s140814131 – ident: ref12 doi: 10.1109/ICRA.2016.7487372 – ident: ref8 doi: 10.3390/s140304899 – ident: ref23 doi: 10.1016/j.ins.2014.05.054 – ident: ref4 doi: 10.1109/HAVE.2013.6679606 – start-page: 677 year: 0 ident: ref17 article-title: Active sequential learning with tactile feedback publication-title: Proc 13th Int Conf Artif Intell Statist – ident: ref14 doi: 10.1109/EMBC.2015.7320253 – ident: ref21 doi: 10.1109/TRO.2011.2106330 – volume: 6 start-page: 4 year: 2011 ident: ref27 article-title: Bayesian exploration for intelligent identification of textures publication-title: Front Neurorobot – ident: ref20 doi: 10.1016/j.robot.2016.09.014 – ident: ref13 doi: 10.1109/HUMANOIDS.2014.7041358 – ident: ref7 doi: 10.1109/TIM.2013.2293812 – ident: ref19 doi: 10.1109/IROS.2014.6942622 – year: 2005 ident: ref26 publication-title: Gaussian Processes for Machine Learning – ident: ref6 doi: 10.1109/ICRA.2013.6631000 – ident: ref15 doi: 10.1109/ICRA.2013.6631001 – ident: ref3 doi: 10.1016/j.robot.2013.11.011 – ident: ref2 doi: 10.1109/TRO.2009.2033627 – ident: ref10 doi: 10.1109/LRA.2016.2517213 – ident: ref24 doi: 10.1109/HUMANOIDS.2015.7363508
SSID	ssj0001527395
Score	2.3230648
Snippet	In this letter, we propose a complete probabilistic tactile-based framework to enable robots to autonomously explore unknown workspaces and recognize objects...
SourceID	crossref ieee
SourceType	Enrichment Source Index Database Publisher
StartPage	2143
SubjectTerms	Active tactile learning artificial robotic skin Conductivity force and tactile sensing Robot sensing systems Skin Surface texture tactile object recognition Thermal conductivity Training
Title	A Tactile-Based Framework for Active Object Learning and Discrimination using Multimodal Robotic Skin
URI	https://ieeexplore.ieee.org/document/7961193
Volume	2
WOSCitedRecordID	wos000413741800041&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 2377-3766 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001527395 issn: 2377-3766 databaseCode: RIE dateStart: 20160101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2377-3766 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001527395 issn: 2377-3766 databaseCode: M~E dateStart: 20160101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEB7a4kEPvqpYX-zBi2Bskk32cayP4kGrlAq9hc3uRgo1kdp69Le7k6a1ggjeQtjNhnxhZ3bmm_kAzqgNfF_JyIuFr7yIZ9RLmQ48RpmONeXGSF2KTfBeTwyH8qkGF8taGGttST6zl3hZ5vJNoWcYKmtzyQLncNShzjmb12p9x1Owk5iMF5lIX7bv-x2kbvFLTDWKmP6wPCtSKqUl6W797x22YbPyGElnDvEO1Gy-CxsrfQSbYDtkgAUKY-tdOatkSHdBuSLOJyWdck8jjynGXEjVUfWFqNyQmxFuG0iHQYAIsuBfSFmU-1oYt2q_SAu3LkGNrj147t4Oru-8Sj_B0zSUU09o5RCKVaBUaARLlYmjVGYilCK1zFCmsKA8zUwW-BnVMbPWnfZszJURKJRA96GRF7k9ABL6TGtqqHb2PjLGPTgTKrTOPeFBlEnegvbi2ya6ai6OGhfjpDxk-DJxaCSIRlKh0YLz5Yy3eWONP8Y2EYjluAqDw99vH8E6Tp4z7o6hMZ3M7Ams6Y_p6H1yCvWHz9vT8t_5ApEew3g
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dS8MwED_mFNQHv6Y4P_Pgi2C3tmnT5HF-jIlzypiwt5Im6RjMVebm32-u66aCCL6Vkialv5K73P3ufgAX1HiuK0XghNyVThCl1EmY8hxGmQoVjbQWKhebiDod3u-L5xJcLWthjDE5-czU8DLP5etMzTBUVo8E86zDsQKrqJzlzqu1viIq2EtMhItcpCvq7W4DyVtRDZONPKQ_bM83MZXcljS3__cWO7BV-IykMQd5F0pmvAeb3zoJVsA0SA9LFEbGubZ2SZPmgnRFrFdKGvmuRp4SjLqQoqfqgMixJrdD3DiQEIMQEeTBD0helvuaabtqN0syuy5Bla59eGne9W5aTqGg4Cjqi6nDlbQYhdKT0tecJVKHQSJS7gueGKYpk1hSnqQ69dyUqpAZY897Joyk5iiVQA-gPM7G5hCI7zKlqKbKWvxAaztxyqVvrIMSeUEqoirUF982VkV7cVS5GMX5McMVsUUjRjTiAo0qXC6feJu31vhjbAWBWI4rMDj6_fY5rLd6j-24fd95OIYNnGjOvzuB8nQyM6ewpj6mw_fJWf4HfQJAWsWN
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+Tactile-Based+Framework+for+Active+Object+Learning+and+Discrimination+using+Multimodal+Robotic+Skin&rft.jtitle=IEEE+robotics+and+automation+letters&rft.au=Kaboli%2C+Mohsen&rft.au=Di+Feng&rft.au=Kunpeng+Yao&rft.au=Lanillos%2C+Pablo&rft.date=2017-10-01&rft.pub=IEEE&rft.eissn=2377-3766&rft.volume=2&rft.issue=4&rft.spage=2143&rft.epage=2150&rft_id=info:doi/10.1109%2FLRA.2017.2720853&rft.externalDocID=7961193
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2377-3766&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2377-3766&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2377-3766&client=summon