Human Intention Inference Using Expectation-Maximization Algorithm With Online Model Learning

An algorithm called adaptive-neural-intention estimator (ANIE) is presented to infer the intent of a human operator's arm movements based on the observations from a 3-D camera sensor (Microsoft Kinect). Intentions are modeled as the goal locations of reaching motions in 3-D space. Human arm...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on automation science and engineering Vol. 14; no. 2; pp. 855 - 868
Main Authors:	Ravichandar, Harish Chaandar, Dani, Ashwin P.
Format:	Journal Article
Language:	English
Published:	IEEE 01.04.2017
Subjects:	Adaptation models Artificial neural networks Dynamics expectation-maximization Heuristic algorithms Hidden Markov models Human-robot interaction Inference algorithms intention inference neural network modeling Prediction algorithms
ISSN:	1545-5955, 1558-3783
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	An algorithm called adaptive-neural-intention estimator (ANIE) is presented to infer the intent of a human operator's arm movements based on the observations from a 3-D camera sensor (Microsoft Kinect). Intentions are modeled as the goal locations of reaching motions in 3-D space. Human arm's nonlinear motion dynamics are modeled using an unknown nonlinear function with intentions represented as parameters. The unknown model is learned by using a neural network. Based on the learned model, an approximate expectation-maximization algorithm is developed to infer human intentions. Furthermore, an identifier-based online model learning algorithm is developed to adapt to the variations in the arm motion dynamics, the motion trajectory, the goal locations, and the initial conditions of different human subjects. The results of experiments conducted on data obtained from different users performing a variety of reaching motions are presented. The ANIE algorithm is compared with an unsupervised Gaussian mixture model algorithm and an Euclidean distance-based approach by using Cornell's CAD-120 data set and data collected in the Robotics and Controls Laboratoy at UConn. The ANIE algorithm is compared with the inverse LQR and ATCRF algorithms using a labeling task carried out on the CAD-120 data set.
AbstractList	An algorithm called adaptive-neural-intention estimator (ANIE) is presented to infer the intent of a human operator's arm movements based on the observations from a 3-D camera sensor (Microsoft Kinect). Intentions are modeled as the goal locations of reaching motions in 3-D space. Human arm's nonlinear motion dynamics are modeled using an unknown nonlinear function with intentions represented as parameters. The unknown model is learned by using a neural network. Based on the learned model, an approximate expectation-maximization algorithm is developed to infer human intentions. Furthermore, an identifier-based online model learning algorithm is developed to adapt to the variations in the arm motion dynamics, the motion trajectory, the goal locations, and the initial conditions of different human subjects. The results of experiments conducted on data obtained from different users performing a variety of reaching motions are presented. The ANIE algorithm is compared with an unsupervised Gaussian mixture model algorithm and an Euclidean distance-based approach by using Cornell's CAD-120 data set and data collected in the Robotics and Controls Laboratoy at UConn. The ANIE algorithm is compared with the inverse LQR and ATCRF algorithms using a labeling task carried out on the CAD-120 data set.
Author	Dani, Ashwin P. Ravichandar, Harish Chaandar
Author_xml	– sequence: 1 givenname: Harish Chaandar surname: Ravichandar fullname: Ravichandar, Harish Chaandar email: harish.ravichandar@uconn.edu organization: Dept. of Electr. & Comput. Eng., Univ. of Connecticut, Storrs, CT, USA – sequence: 2 givenname: Ashwin P. surname: Dani fullname: Dani, Ashwin P. email: ashwin.dani@uconn.edu organization: Dept. of Electr. & Comput. Eng. & the Manage. & Eng. for Manuf. Program, Univ. of Connecticut, Storrs, CT, USA
BookMark	eNp9kM9OwkAQxjcGEwF9AONlX6B1d7t_ukdCUEggHIR4Ms2yneKadku2NUGe3laIBw9eZr7JfL_J5Buhga89IHRPSUwp0Y-bycssZoTKmEnGmdJXaEiFSKNEpcmg11xEQgtxg0ZN80EI46kmQ_Q2_6yMxwvfgm9d3asCAngLeNs4v8ez4wFsa_pdtDJHV7nTz4An5b4Orn2v8GtX8dqXzgNe1TmUeAkm-I6-RdeFKRu4u_Qx2j7NNtN5tFw_L6aTZWSZFG1kqRXcKmMVIYkCzcHYPGeQFykYuiNAlSx2xBa8s2ibUkVFzomiO5DEKpmMkTrftaFumgBFZt355zYYV2aUZH1KWZ9S1qeUXVLqSPqHPARXmfD1L_NwZhwA_PqV0koykXwDcCh3Nw
CODEN	ITASC7
CitedBy_id	crossref_primary_10_3389_frobt_2024_1430740 crossref_primary_10_1016_j_ifacol_2023_10_515 crossref_primary_10_1016_j_ins_2019_02_005 crossref_primary_10_1002_cpe_4255 crossref_primary_10_3390_s20072104 crossref_primary_10_3389_frobt_2020_573096 crossref_primary_10_1109_TASE_2018_2874454 crossref_primary_10_1007_s12369_023_00965_7 crossref_primary_10_1007_s13272_024_00763_5 crossref_primary_10_1109_LRA_2018_2865034 crossref_primary_10_1109_JSEN_2024_3386683 crossref_primary_10_1109_TCST_2020_3009031 crossref_primary_10_1109_ACCESS_2023_3239009 crossref_primary_10_1016_j_inffus_2019_11_001 crossref_primary_10_1109_MCS_2020_3019725 crossref_primary_10_1007_s11263_020_01404_0 crossref_primary_10_1016_j_artint_2021_103525 crossref_primary_10_1109_TCYB_2018_2864784 crossref_primary_10_1016_j_ifacol_2019_01_001 crossref_primary_10_1162_neco_a_01764 crossref_primary_10_1016_j_ast_2023_108713 crossref_primary_10_1016_j_sigpro_2021_108453 crossref_primary_10_1016_j_conengprac_2023_105769 crossref_primary_10_1109_TASE_2018_2795241 crossref_primary_10_1109_ACCESS_2024_3400604 crossref_primary_10_3390_s22052040 crossref_primary_10_1007_s41315_018_0051_0 crossref_primary_10_1145_3439720 crossref_primary_10_1049_itr2_12090 crossref_primary_10_1109_TVT_2022_3194862 crossref_primary_10_1016_j_jmsy_2022_05_006
Cites_doi	10.1109/TPAMI.2007.1167 10.1109/TAC.2011.2162890 10.1109/ICRA.2013.6630785 10.1109/HAVE.2009.5356124 10.15607/RSS.2014.X.015 10.1109/TASE.2015.2412256 10.1007/978-3-319-00065-7_28 10.1016/S0921-8890(02)00372-X 10.1109/IROS.2014.6943153 10.1561/1100000005 10.1109/ICRA.2015.7139282 10.1115/1.4025810 10.1076/mcmd.5.3.220.3681 10.1111/j.2517-6161.1977.tb01600.x 10.1177/0278364913478447 10.1145/1349822.1349870 10.1109/TRO.2007.904899 10.1016/j.robot.2014.01.003 10.1109/IROS.2015.7353706 10.1145/2696454.2696455 10.1137/1.9780898717563 10.1109/ROMAN.2012.6343875 10.1007/s10514-007-9054-7 10.1177/0278364913478446 10.1109/IROS.2011.6095118 10.1016/S1364-6613(00)01615-6 10.5898/JHRI.2.1.Strabala 10.1109/TAC.2008.930200 10.1109/TAC.2012.2203452 10.15607/RSS.2013.IX.006 10.1109/CDC.2005.1582183 10.1111/j.2517-6161.1995.tb02037.x 10.15607/RSS.2014.X.003 10.1109/IROS.2000.894685 10.1162/neco.1992.4.3.415 10.1109/MFI.2015.7295812 10.1109/CVPRW.2003.10057 10.1109/IROS.2015.7353614 10.1115/DSCC2015-9870 10.1007/978-3-540-74048-3_4 10.1109/ICRA.2011.5980248
ContentType	Journal Article
DBID	97E RIA RIE AAYXX CITATION
DOI	10.1109/TASE.2016.2624279
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE All-Society Periodicals Package (ASPP) 1998-Present IEEE Electronic Library (IEL) CrossRef
DatabaseTitle	CrossRef
DatabaseTitleList
Database_xml	– sequence: 1 dbid: RIE name: IEEE/IET Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1558-3783
EndPage	868
ExternalDocumentID	10_1109_TASE_2016_2624279 7797625
Genre	orig-research
GroupedDBID	-~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AIBXA AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ H~9 IFIPE IPLJI JAVBF LAI M43 O9- OCL PQQKQ RIA RIE RNS AAYXX CITATION
ID	FETCH-LOGICAL-c265t-c1c54c7ac70037e94eacdd2edf8ea1b0e176fb0cf4ac79c81715d4071be60c763
IEDL.DBID	RIE
ISICitedReferencesCount	43
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000399347500040&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1545-5955
IngestDate	Sat Nov 29 04:12:45 EST 2025 Tue Nov 18 22:23:12 EST 2025 Tue Aug 26 17:03:04 EDT 2025
IsPeerReviewed	false
IsScholarly	true
Issue	2
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c265t-c1c54c7ac70037e94eacdd2edf8ea1b0e176fb0cf4ac79c81715d4071be60c763
ORCID	0000-0002-7091-5607
PageCount	14
ParticipantIDs	crossref_citationtrail_10_1109_TASE_2016_2624279 crossref_primary_10_1109_TASE_2016_2624279 ieee_primary_7797625
PublicationCentury	2000
PublicationDate	2017-April 2017-4-00
PublicationDateYYYYMMDD	2017-04-01
PublicationDate_xml	– month: 04 year: 2017 text: 2017-April
PublicationDecade	2010
PublicationTitle	IEEE transactions on automation science and engineering
PublicationTitleAbbrev	TASE
PublicationYear	2017
Publisher	IEEE
Publisher_xml	– name: IEEE
References	ref13 ref12 ref14 ref11 ghahramani (ref10) 1999 ref17 ref19 ref18 ref46 ref48 ref47 ref42 ref41 kuli? (ref31) 2003 ref43 lange (ref45) 1995; 57 ref49 ref8 ref7 ref9 ref4 ref3 ref5 simon (ref6) 1982 ref34 ref37 ref36 ref30 ref33 ref32 schrempf (ref35) 2005 ref2 ref1 ref39 ref38 monfort (ref15) 2015 dempster (ref44) 1977; 39 mainprice (ref40) 2014 ref24 ref23 ref26 ref25 matsumoto (ref27) 1999 ref20 ref22 preece (ref16) 1994 ref21 ref28 ref29
References_xml	– ident: ref39 doi: 10.1109/TPAMI.2007.1167 – ident: ref47 doi: 10.1109/TAC.2011.2162890 – ident: ref41 doi: 10.1109/ICRA.2013.6630785 – ident: ref32 doi: 10.1109/HAVE.2009.5356124 – start-page: 299 year: 2014 ident: ref40 article-title: Human-robot collaborative manipulation planning using early prediction of human motion publication-title: Proc Human-Robot Collaboration Ind Manuf Workshop Robot Sci Syst Conf – ident: ref38 doi: 10.15607/RSS.2014.X.015 – ident: ref2 doi: 10.1109/TASE.2015.2412256 – ident: ref18 doi: 10.1007/978-3-319-00065-7_28 – start-page: 810 year: 2003 ident: ref31 article-title: Estimating intent for human-robot interaction publication-title: Proc IEEE Int Conf Adv Robot – ident: ref29 doi: 10.1016/S0921-8890(02)00372-X – ident: ref1 doi: 10.1109/IROS.2014.6943153 – ident: ref17 doi: 10.1561/1100000005 – ident: ref23 doi: 10.1109/ICRA.2015.7139282 – ident: ref43 doi: 10.1115/1.4025810 – ident: ref11 doi: 10.1076/mcmd.5.3.220.3681 – volume: 39 start-page: 1 year: 1977 ident: ref44 article-title: Maximum likelihood from incomplete data via the EM algorithm publication-title: J Roy Statist Soc Series B (Methodol ) doi: 10.1111/j.2517-6161.1977.tb01600.x – ident: ref24 doi: 10.1177/0278364913478447 – ident: ref22 doi: 10.1145/1349822.1349870 – ident: ref20 doi: 10.1109/TRO.2007.904899 – start-page: 251 year: 2005 ident: ref35 article-title: A generic model for estimating user-intentions in human-robot cooperation publication-title: Proc Int Conf Inform Control Autom Robot – ident: ref36 doi: 10.1016/j.robot.2014.01.003 – ident: ref13 doi: 10.1109/IROS.2015.7353706 – ident: ref4 doi: 10.1145/2696454.2696455 – ident: ref49 doi: 10.1137/1.9780898717563 – ident: ref25 doi: 10.1109/ROMAN.2012.6343875 – ident: ref30 doi: 10.1007/s10514-007-9054-7 – ident: ref14 doi: 10.1177/0278364913478446 – ident: ref34 doi: 10.1109/IROS.2011.6095118 – start-page: 431 year: 1999 ident: ref10 article-title: Learning nonlinear dynamical systems using an EM algorithm publication-title: Proc Adv Neural Inf Process Syst – ident: ref5 doi: 10.1016/S1364-6613(00)01615-6 – start-page: 43 year: 1999 ident: ref27 article-title: The essential components of human-friendly robot systems publication-title: Proc Int Conf Field Service Robot – ident: ref26 doi: 10.5898/JHRI.2.1.Strabala – start-page: 3672 year: 2015 ident: ref15 article-title: Intent prediction and trajectory forecasting via predictive inverse linear-quadratic regulation publication-title: Proc AAAI Conf Artif Intell – ident: ref46 doi: 10.1109/TAC.2008.930200 – ident: ref12 doi: 10.1109/TAC.2012.2203452 – ident: ref21 doi: 10.15607/RSS.2013.IX.006 – ident: ref9 doi: 10.1109/CDC.2005.1582183 – volume: 57 start-page: 425 year: 1995 ident: ref45 article-title: A gradient algorithm locally equivalent to the EM algorithm publication-title: J Roy Statist Soc Series B (Methodol ) doi: 10.1111/j.2517-6161.1995.tb02037.x – ident: ref37 doi: 10.15607/RSS.2014.X.003 – ident: ref28 doi: 10.1109/IROS.2000.894685 – year: 1994 ident: ref16 publication-title: Human-Computer Interaction – ident: ref42 doi: 10.1162/neco.1992.4.3.415 – ident: ref3 doi: 10.1109/MFI.2015.7295812 – ident: ref19 doi: 10.1109/CVPRW.2003.10057 – ident: ref7 doi: 10.1109/IROS.2015.7353614 – ident: ref8 doi: 10.1115/DSCC2015-9870 – ident: ref48 doi: 10.1007/978-3-540-74048-3_4 – year: 1982 ident: ref6 publication-title: Understanding human action Social explanation and the vision of social science – ident: ref33 doi: 10.1109/ICRA.2011.5980248
SSID	ssj0024890
Score	2.3325555
Snippet	An algorithm called adaptive-neural-intention estimator (ANIE) is presented to infer the intent of a human operator's arm movements based on the observations...
SourceID	crossref ieee
SourceType	Enrichment Source Index Database Publisher
StartPage	855
SubjectTerms	Adaptation models Artificial neural networks Dynamics expectation-maximization Heuristic algorithms Hidden Markov models Human-robot interaction Inference algorithms intention inference neural network modeling Prediction algorithms
Title	Human Intention Inference Using Expectation-Maximization Algorithm With Online Model Learning
URI	https://ieeexplore.ieee.org/document/7797625
Volume	14
WOSCitedRecordID	wos000399347500040&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/IET Electronic Library (IEL) customDbUrl: eissn: 1558-3783 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0024890 issn: 1545-5955 databaseCode: RIE dateStart: 20040101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEB7a4kEPvqpYX-zBk7htNs1mk2ORFi8WwYq9SNjsbmqhD6mt-PPd2ay1BxG8hCVMIMxsMjsz33wDcIVZBcOVom0lUxpJzqjUvE1zoUWoQ2G_9dwNmxD9fjIcpg8VuFn3whhjHPjMNHHpavl6rlaYKmsJYZ1nyKtQFUKUvVo_vHqJy6fgiYDylHNfwWRB2hp0HrsI4oqbIXZDIGprwwdtDFVxPqW397-32Yddf3YkndLYB1Axs0PY2WAUrMOLS8oTB0xHlduVb-gjDhxAkNpYleV3ei8_x1Pfh0k6k9F8MV6-TsmzvZKSgpTgqLQJ8SSsoyN46nUHt3fUT1CgKoz5kiqmeKSEVAJ5ZkwaWdVrHRpdJEayPDBMxEUeqCKyIqlKmGBcY4iXmzhQ9tdzDLXZfGZOgOSyKIR1XTa8kVES2xhcy8iGh2licsli3YDgW6eZ8vTiOOVikrkwI0gzNEOGZsi8GRpwvX7kreTW-Eu4jiZYC3rtn_5--wy2Q_S_DmJzDrXlYmUuYEt9LMfvi0u3c74AXGbDDQ
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dS8MwED90CuqDX1Ocn3nwScxsatO0j0M2JuoQnOiLlDRJdTA3mZv455tL49yDCL6UUK5Q7tJe7u53vwM4xqyC4UrRcyVTGknOqNT8nOZCi1CHwn7ruRs2ITqd5PExvZ2D02kvjDHGgc9MHZeulq-HaoKpsjMhrPMM-Tws8CgKWdmt9cOsl7iMCp4JKE859zVMFqRn3cZdE2FccT3EfgjEbc14oZmxKs6rtNb-9z7rsOpPj6RRmnsD5sxgE1ZmOAWr8OTS8sRB01HpduVb-oiDBxAkN1ZlAZ7eyM_eq-_EJI3-83DUG7-8kgd7JSUJKcFhaX3iaVift-C-1exetKmfoUBVGPMxVUzxSAmpBDLNmDSyytc6NLpIjGR5YJiIizxQRWRFUpUwwbjGIC83caDsz2cbKoPhwOwAyWVRCOu8bIAjoyS2UbiWkQ0Q08TkksW6BsG3TjPlCcZxzkU_c4FGkGZohgzNkHkz1OBk-shbya7xl3AVTTAV9Nrf_f32ESy1uzfX2fVl52oPlkP0xg5wsw-V8WhiDmBRfYx776NDt4u-AKvmxlQ
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=Human+Intention+Inference+Using+Expectation-Maximization+Algorithm+With+Online+Model+Learning&rft.jtitle=IEEE+transactions+on+automation+science+and+engineering&rft.au=Ravichandar%2C+Harish+Chaandar&rft.au=Dani%2C+Ashwin+P.&rft.date=2017-04-01&rft.pub=IEEE&rft.issn=1545-5955&rft.volume=14&rft.issue=2&rft.spage=855&rft.epage=868&rft_id=info:doi/10.1109%2FTASE.2016.2624279&rft.externalDocID=7797625
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1545-5955&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1545-5955&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1545-5955&client=summon