Multimodal Deep Generative Models for Trajectory Prediction: A Conditional Variational Autoencoder Approach

Human behavior prediction models enable robots to anticipate how humans may react to their actions, and hence are instrumental to devising safe and proactive robot planning algorithms. However, modeling complex interaction dynamics and capturing the possibility of many possible outcomes in such inte...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE robotics and automation letters Ročník 6; číslo 2; s. 295 - 302
Hlavní autoři: Ivanovic, Boris, Leung, Karen, Schmerling, Edward, Pavone, Marco
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 01.04.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
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 Human behavior prediction models enable robots to anticipate how humans may react to their actions, and hence are instrumental to devising safe and proactive robot planning algorithms. However, modeling complex interaction dynamics and capturing the possibility of many possible outcomes in such interactive settings is very challenging, which has recently prompted the study of several different approaches. In this work, we provide a self-contained tutorial on a conditional variational autoencoder (CVAE) approach to human behavior prediction which, at its core, can produce a multimodal probability distribution over future human trajectories conditioned on past interactions and candidate robot future actions. Specifically, the goals of this tutorial paper are to review and build a taxonomy of state-of-the-art methods in human behavior prediction, from physics-based to purely data-driven methods, provide a rigorous yet easily accessible description of a data-driven, CVAE-based approach, highlight important design characteristics that make this an attractive model to use in the context of model-based planning for human-robot interactions, and provide important design considerations when using this class of models.
AbstractList Human behavior prediction models enable robots to anticipate how humans may react to their actions, and hence are instrumental to devising safe and proactive robot planning algorithms. However, modeling complex interaction dynamics and capturing the possibility of many possible outcomes in such interactive settings is very challenging, which has recently prompted the study of several different approaches. In this work, we provide a self-contained tutorial on a conditional variational autoencoder (CVAE) approach to human behavior prediction which, at its core, can produce a multimodal probability distribution over future human trajectories conditioned on past interactions and candidate robot future actions. Specifically, the goals of this tutorial paper are to review and build a taxonomy of state-of-the-art methods in human behavior prediction, from physics-based to purely data-driven methods, provide a rigorous yet easily accessible description of a data-driven, CVAE-based approach, highlight important design characteristics that make this an attractive model to use in the context of model-based planning for human-robot interactions, and provide important design considerations when using this class of models.
Author Leung, Karen
Schmerling, Edward
Ivanovic, Boris
Pavone, Marco
Author_xml – sequence: 1
  givenname: Boris
  orcidid: 0000-0002-8698-202X
  surname: Ivanovic
  fullname: Ivanovic, Boris
  email: borisi@stanford.edu
  organization: Department of Aeronautics and Astronautics, Stanford University, Stanford, CA, USA
– sequence: 2
  givenname: Karen
  orcidid: 0000-0002-3033-8761
  surname: Leung
  fullname: Leung, Karen
  email: karen.ym.leung@gmail.com
  organization: Department of Aeronautics and Astronautics, Stanford University, Stanford, CA, USA
– sequence: 3
  givenname: Edward
  surname: Schmerling
  fullname: Schmerling, Edward
  email: ednerd@gmail.com
  organization: Institute for Computational & Mathematical Engineering, Stanford University, Stanford, CA, USA
– sequence: 4
  givenname: Marco
  orcidid: 0000-0002-0206-4337
  surname: Pavone
  fullname: Pavone, Marco
  email: pavone@stanford.edu
  organization: Department of Aeronautics and Astronautics, Stanford University, Stanford, CA, USA
BookMark eNp9kEFLAzEQhYNUsNbeBS8Bz62TZJvseluqVqFFkep1SZMppm43NZsV-u_d2iLiwdPMwHzvzbxT0ql8hYScMxgyBtnV9DkfcuAwFJAIJsUR6XKh1EAoKTu_-hPSr-sVALARVyIbdcn7rCmjW3urS3qDuKETrDDo6D6RzrzFsqZLH-g86BWa6MOWPgW0zkTnq2ua07GvrNsNLf-qg9OHPm-ix8q0CoHmm03w2rydkeOlLmvsH2qPvNzdzsf3g-nj5GGcTweGZywOtE7AZiyVI52xhVSW4YKnBsFIawRou1QqMwmaxUgxhlokCw0MEmUNoFRG9MjlXre1_WiwjsXKN6G9qi54orhgKSSs3YL9lgm-rgMui01wax22BYNil2rRplrsUi0OqbaI_IMYF78_jkG78j_wYg86RPzxyXgqk5SLL5azh0Q
CODEN IRALC6
CitedBy_id crossref_primary_10_1016_j_neuroimage_2024_120651
crossref_primary_10_3390_sym16010118
crossref_primary_10_1109_TITS_2022_3207347
crossref_primary_10_3390_aerospace10040357
crossref_primary_10_1016_j_inffus_2025_103588
crossref_primary_10_1109_TKDE_2022_3185115
crossref_primary_10_1007_s11768_023_00170_x
crossref_primary_10_1109_TBDATA_2023_3310241
crossref_primary_10_1109_LRA_2022_3156856
crossref_primary_10_1109_ACCESS_2024_3524906
crossref_primary_10_1016_j_rcim_2021_102304
crossref_primary_10_1109_LRA_2023_3312035
crossref_primary_10_1016_j_compbiomed_2022_105403
crossref_primary_10_1080_01691864_2022_2035253
crossref_primary_10_1109_OJITS_2025_3580271
crossref_primary_10_1002_eer2_70006
crossref_primary_10_1016_j_engappai_2024_109225
crossref_primary_10_1016_j_buildenv_2021_108457
crossref_primary_10_2514_1_I011545
crossref_primary_10_1016_j_trc_2021_103114
crossref_primary_10_1109_TITS_2024_3419037
crossref_primary_10_1109_TNNLS_2025_3550350
crossref_primary_10_32604_cmc_2024_056222
crossref_primary_10_1109_TII_2023_3302304
crossref_primary_10_1109_TITS_2022_3205676
crossref_primary_10_1109_ACCESS_2021_3116303
crossref_primary_10_1080_23249935_2024_2407076
crossref_primary_10_1109_TPWRS_2021_3107515
crossref_primary_10_1016_j_eswa_2024_125708
crossref_primary_10_1109_TCSVT_2022_3232112
crossref_primary_10_3390_app142210350
crossref_primary_10_1016_j_trc_2022_103829
crossref_primary_10_1016_j_measurement_2022_111409
crossref_primary_10_1177_0954407021997667
crossref_primary_10_1016_j_ifacol_2025_07_021
crossref_primary_10_1002_aisy_202300359
crossref_primary_10_1109_TSM_2022_3146266
crossref_primary_10_1016_j_commtr_2025_100166
crossref_primary_10_1109_TVT_2024_3349601
crossref_primary_10_1145_3719290
crossref_primary_10_1016_j_sigpro_2023_109165
crossref_primary_10_3390_electronics10212654
crossref_primary_10_18267_j_aip_235
crossref_primary_10_1016_j_chaos_2024_115604
crossref_primary_10_3390_s21124248
crossref_primary_10_1007_s10489_025_06805_7
crossref_primary_10_1109_LRA_2022_3231531
Cites_doi 10.1109/CVPR.2017.233
10.1038/35035023
10.1103/PhysRevE.62.1805
10.1109/IVS.2015.7225830
10.1109/CVPR42600.2020.01164
10.1145/1015330.1015430
10.1109/IVS.2018.8500493
10.1177/0278364920917446
10.1177/0278364920950795
10.1145/2909824.3020253
10.1109/ICRA40945.2020.9196697
10.1162/neco.1997.9.8.1735
10.1109/HRI.2019.8673256
10.1103/PhysRevE.51.4282
10.15607/RSS.2016.XII.029
10.1007/978-3-642-59751-0_36
10.1109/CVPR.2016.573
10.1109/IROS.2018.8594393
10.1109/ICRA.2018.8460766
10.1111/j.1467-8659.2007.01089.x
10.1109/ICCV.2019.00246
10.1177/0278364915619772
10.15607/RSS.2019.XV.048
10.1109/CVPR.2018.00240
10.1109/CVPR.2016.110
10.1109/ICRA.2019.8794465
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
DBID 97E
RIA
RIE
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
DOI 10.1109/LRA.2020.3043163
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
DatabaseTitleList Technology Research Database

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 302
ExternalDocumentID 10_1109_LRA_2020_3043163
9286482
Genre orig-research
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
IFIPE
IPLJI
JAVBF
KQ8
M43
M~E
O9-
OCL
RIA
RIE
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c291t-aa40d91865a91b67d1eb28ce0c6dc30adf779c4ecb5711ea34ba01047dc0e67c3
IEDL.DBID RIE
ISICitedReferencesCount 87
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000602951000001&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 Mon Jun 30 03:56:42 EDT 2025
Sat Nov 29 06:03:09 EST 2025
Tue Nov 18 22:33:11 EST 2025
Wed Aug 27 02:32:33 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 2
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c291t-aa40d91865a91b67d1eb28ce0c6dc30adf779c4ecb5711ea34ba01047dc0e67c3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-3033-8761
0000-0002-8698-202X
0000-0002-0206-4337
PQID 2472318041
PQPubID 4437225
PageCount 8
ParticipantIDs crossref_primary_10_1109_LRA_2020_3043163
crossref_citationtrail_10_1109_LRA_2020_3043163
proquest_journals_2472318041
ieee_primary_9286482
PublicationCentury 2000
PublicationDate 2021-04-01
PublicationDateYYYYMMDD 2021-04-01
PublicationDate_xml – month: 04
  year: 2021
  text: 2021-04-01
  day: 01
PublicationDecade 2020
PublicationPlace Piscataway
PublicationPlace_xml – name: Piscataway
PublicationTitle IEEE robotics and automation letters
PublicationTitleAbbrev LRA
PublicationYear 2021
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
ref12
narayanan (ref15) 0
ref14
ref31
ref30
ziebart (ref19) 0
ref11
ref10
pellegrini (ref43) 0
salzmann (ref8) 0
ref1
ref39
kosaraju (ref32) 0
ref16
ng (ref17) 0
ref18
salimans (ref33) 0
arjovsky (ref35) 0
sohn (ref2) 0
de haan (ref4) 0
lavalle (ref40) 0
sadeghian (ref42) 0
ref24
ref45
ref23
ref25
itkina (ref46) 0
ref20
ref41
ref22
ref44
ref21
adel (ref38) 0
kingma (ref28) 2013
ref29
ref7
ref9
ref3
ref6
ref5
goodfellow (ref26) 0
mirza (ref27) 2014
arjovsky (ref34) 0
maddison (ref37) 0
jang (ref36) 0
References_xml – ident: ref30
  doi: 10.1109/CVPR.2017.233
– ident: ref11
  doi: 10.1038/35035023
– year: 0
  ident: ref46
  article-title: Evidential sparsification of multimodal latent spaces in conditional variational autoencoders
  publication-title: Proc Conf Neural Inform Process Syst
– ident: ref12
  doi: 10.1103/PhysRevE.62.1805
– ident: ref39
  doi: 10.1109/IVS.2015.7225830
– year: 2014
  ident: ref27
– ident: ref45
  doi: 10.1109/CVPR42600.2020.01164
– start-page: 261-268
  year: 0
  ident: ref43
  article-title: You'll never walk alone: Modeling social behavior for multi-target tracking
  publication-title: IEEE Int Conf Comput Vis
– ident: ref18
  doi: 10.1145/1015330.1015430
– ident: ref31
  doi: 10.1109/IVS.2018.8500493
– ident: ref1
  doi: 10.1177/0278364920917446
– start-page: 11698
  year: 0
  ident: ref4
  article-title: Causal confusion in imitation learning
  publication-title: Proc Conf Neural Inform Process Syst
– ident: ref5
  doi: 10.1177/0278364920950795
– ident: ref13
  doi: 10.1145/2909824.3020253
– ident: ref41
  doi: 10.1109/ICRA40945.2020.9196697
– start-page: 3483
  year: 0
  ident: ref2
  article-title: Learning structured output representation using deep conditional generative models
  publication-title: Proc Conf Neural Inform Process Syst
– ident: ref25
  doi: 10.1162/neco.1997.9.8.1735
– ident: ref22
  doi: 10.1109/HRI.2019.8673256
– ident: ref9
  doi: 10.1103/PhysRevE.51.4282
– ident: ref20
  doi: 10.15607/RSS.2016.XII.029
– start-page: 2234
  year: 0
  ident: ref33
  article-title: Improved techniques for training GANs
  publication-title: Proc Conf Neural Inform Process Syst
– ident: ref10
  doi: 10.1007/978-3-642-59751-0_36
– ident: ref24
  doi: 10.1109/CVPR.2016.573
– year: 0
  ident: ref37
  article-title: The concrete distribution: A continuous relaxation of discrete random variables
  publication-title: Proc Int Conf Learn Representations
– start-page: 214
  year: 0
  ident: ref35
  article-title: Wasserstein generative adversarial networks
  publication-title: Proc Int Conf Mach Learn
– year: 0
  ident: ref36
  article-title: Categorial reparameterization with gumbel-softmax
  publication-title: Proc Int Conf Learn Representations
– start-page: 137
  year: 0
  ident: ref32
  article-title: Social-BiGAT: Multimodal trajectory forecasting using bicycle-GAN and graph attention networks
  publication-title: Proc Conf Neural Inform Process Syst
– year: 0
  ident: ref15
  article-title: ProxEmo: Gait-based emotion learning and multi-view proxemic fusion for socially-aware robot navigation
  publication-title: Proc IEEE/RSJ Int Conf Intell Robots Syst
– year: 0
  ident: ref42
  article-title: CAR-Net: Clairvoyant attentive recurrent network
  publication-title: Proc Eur Conf Comput Vis
– ident: ref6
  doi: 10.1109/IROS.2018.8594393
– ident: ref3
  doi: 10.1109/ICRA.2018.8460766
– ident: ref44
  doi: 10.1111/j.1467-8659.2007.01089.x
– ident: ref7
  doi: 10.1109/ICCV.2019.00246
– ident: ref21
  doi: 10.1177/0278364915619772
– start-page: 663
  year: 0
  ident: ref17
  article-title: Algorithms for inverse reinforcement learning
  publication-title: Proc Int Conf Mach Learn
– start-page: 683
  year: 0
  ident: ref8
  article-title: Trajectron++: Dynamically-feasible trajectory forecasting with heterogeneous data
  publication-title: Proc Eur Conf Comput Vis
– start-page: 2672
  year: 0
  ident: ref26
  article-title: Generative adversarial nets
  publication-title: Proc Conf Neural Inform Process Syst
– ident: ref14
  doi: 10.15607/RSS.2019.XV.048
– ident: ref29
  doi: 10.1109/CVPR.2018.00240
– year: 0
  ident: ref19
  article-title: Maximum entropy inverse reinforcement learning
  publication-title: Proc AAAI Conf Artif Intell
– year: 2013
  ident: ref28
– ident: ref23
  doi: 10.1109/CVPR.2016.110
– start-page: 50
  year: 0
  ident: ref38
  article-title: Discovering interpretable representations for both deep generative and discriminative models
  publication-title: Proc Int Conf Mach Learn
– year: 0
  ident: ref34
  article-title: Towards principled methods for training generative adversarial networks
  publication-title: Proc Int Conf Learn Representations
– start-page: 743
  year: 0
  ident: ref40
  article-title: Better unicycle models
  publication-title: Planning Algorithms
– ident: ref16
  doi: 10.1109/ICRA.2019.8794465
SSID ssj0001527395
Score 2.53962
Snippet Human behavior prediction models enable robots to anticipate how humans may react to their actions, and hence are instrumental to devising safe and proactive...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 295
SubjectTerms Algorithms
Autonomous vehicle navigation
Context modeling
Data models
deep learning methods
Human behavior
Mathematical model
Planning
Prediction models
Predictive models
Robots
social HRI
Taxonomy
Trajectory
Title Multimodal Deep Generative Models for Trajectory Prediction: A Conditional Variational Autoencoder Approach
URI https://ieeexplore.ieee.org/document/9286482
https://www.proquest.com/docview/2472318041
Volume 6
WOSCitedRecordID wos000602951000001&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/eLvHCXMwlV3NS8MwFH-44UEPfk1xOiUHL4J1_ciSxluZGx50DFHxVtLkCepcx9YJXvzbTbJuKorgLYcXKP217_v9HsBRRmOjGrnvSRNdeDRS5hRl0pOBVMgChg-hdMsmeK8X39-L_hKcLGZhENE1n-GpPbpavs7V1KbKmiKMGY2Nwq1wzmazWp_5FMskJlrzSqQvmpfXiYn_QhOWWgIZFn2zPG6Vyg_964xKd_1_j7MBa6XzSJIZ2puwhMMtWP1CKViDZzdR-5JrI3eOOCIzXmmr1IjdezaYEOOmEmOinly-_o30x7ZWY_E5Iwlp57aG7fKD5M7E0WWukCTTIreclxrHJCl5yLfhttu5aV945UIFT4UiKDwpqa9FELOWFEHGuA5MXB0r9BXTKvKlfuBcKIoqa_EgQBnRTDr-Hq18ZFxFO1Ad5kPcBSK5oixmxpaFgpqLmeA6i5BriS1hfLA6NOcvO1Ul27hdejFIXdThi9TAk1p40hKeOhwvboxmTBt_yNYsHAu5Eok6NOZ4puWvOElDyo0Pa2mW9n6_tQ8roW1Uce04DagW4ykewLJ6LR4n40OoXL13Dt239gG1g9OH
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1JSwMxFH6ICurBXaxWzcGL4NhZ0mTibXChYi1FVLwNmeQJbp3SRfDfm6RpVRTBWw4vMMw38_b3PYD9gqZGNfIwkCa6CGiizCkpZCAjqZBFDB9i6ZZN8FYrvb8X7Sk4nMzCIKJrPsMje3S1fF2qoU2V1UScMpoahTtjN2f5aa3PjIrlEhP1cS0yFLXmdWYiwNgEppZChiXfbI9bpvJDAzuzcr70vwdahkXvPpJshPcKTGFnFRa-kAquwbObqX0ttZE7ReySEbO0VWvEbj576RPjqBJjpJ5cxv6dtHu2WmMROiYZOSltFdtlCMmdiaR9tpBkw0FpWS819kjmmcjX4fb87OakEfiVCoGKRTQIpKShFlHK6lJEBeM6MpF1qjBUTKsklPqBc6EoqqLOowhlQgvpGHy0CpFxlWzAdKfs4CYQyRVlKTPWLBbUXCwE10WCXEusC-OFVaA2ftm58nzjdu3FS-7ijlDkBp7cwpN7eCpwMLnRHXFt_CG7ZuGYyHkkKlAd45n7n7Gfx5QbL9YSLW39fmsP5ho3V828edG63Ib52LatuOacKkwPekPcgVn1Nnjs93bdF_cB3lrVnw
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=Multimodal+Deep+Generative+Models+for+Trajectory+Prediction%3A+A+Conditional+Variational+Autoencoder+Approach&rft.jtitle=IEEE+robotics+and+automation+letters&rft.au=Ivanovic%2C+Boris&rft.au=Leung%2C+Karen&rft.au=Schmerling%2C+Edward&rft.au=Pavone%2C+Marco&rft.date=2021-04-01&rft.issn=2377-3766&rft.eissn=2377-3766&rft.volume=6&rft.issue=2&rft.spage=295&rft.epage=302&rft_id=info:doi/10.1109%2FLRA.2020.3043163&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_LRA_2020_3043163
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