What the Constant Velocity Model Can Teach Us About Pedestrian Motion Prediction

Pedestrian motion prediction is a fundamental task for autonomous robots and vehicles to operate safely. In recent years many complex approaches based on neural networks have been proposed to address this problem. In this work we show that - surprisingly - a simple Constant Velocity Model can outper...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE robotics and automation letters Jg. 5; H. 2; S. 1695 - 1702
Hauptverfasser:	Scholler, Christoph, Aravantinos, Vincent, Lay, Florian, Knoll, Alois
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Piscataway IEEE 01.04.2020 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	deep learning in robotics and automation Gallium nitride History Motion and path planning Neural networks Pedestrians Predictive models Tracking Training Trajectory
ISSN:	2377-3766, 2377-3766
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	Pedestrian motion prediction is a fundamental task for autonomous robots and vehicles to operate safely. In recent years many complex approaches based on neural networks have been proposed to address this problem. In this work we show that - surprisingly - a simple Constant Velocity Model can outperform even state-of-the-art neural models. This indicates that either neural networks are not able to make use of the additional information they are provided with, or that this information is not as relevant as commonly believed. Therefore, we analyze how neural networks process their input and how it impacts their predictions. Our analysis reveals pitfalls in training neural networks for pedestrian motion prediction and clarifies false assumptions about the problem itself. In particular, neural networks implicitly learn environmental priors that negatively impact their generalization capability, the motion history of pedestrians is irrelevant and interactions are too complex to predict. Our work shows how neural networks for pedestrian motion prediction can be thoroughly evaluated and our results indicate which research directions for neural motion prediction are promising in future.
AbstractList	Pedestrian motion prediction is a fundamental task for autonomous robots and vehicles to operate safely. In recent years many complex approaches based on neural networks have been proposed to address this problem. In this work we show that – surprisingly – a simple Constant Velocity Model can outperform even state-of-the-art neural models. This indicates that either neural networks are not able to make use of the additional information they are provided with, or that this information is not as relevant as commonly believed. Therefore, we analyze how neural networks process their input and how it impacts their predictions. Our analysis reveals pitfalls in training neural networks for pedestrian motion prediction and clarifies false assumptions about the problem itself. In particular, neural networks implicitly learn environmental priors that negatively impact their generalization capability, the motion history of pedestrians is irrelevant and interactions are too complex to predict. Our work shows how neural networks for pedestrian motion prediction can be thoroughly evaluated and our results indicate which research directions for neural motion prediction are promising in future.
Author	Lay, Florian Scholler, Christoph Knoll, Alois Aravantinos, Vincent
Author_xml	– sequence: 1 givenname: Christoph orcidid: 0000-0001-5644-1604 surname: Scholler fullname: Scholler, Christoph email: schoeller@fortiss.org organization: Fortiss, Research Institute of the Free State of Bavaria, Munich, Germany – sequence: 2 givenname: Vincent surname: Aravantinos fullname: Aravantinos, Vincent email: vincent.aravantinos@gmail.com organization: Fortiss, Research Institute of the Free State of Bavaria, Munich, Germany – sequence: 3 givenname: Florian surname: Lay fullname: Lay, Florian email: florian.lay@tum.de organization: Fortiss, Research Institute of the Free State of Bavaria, Munich, Germany – sequence: 4 givenname: Alois surname: Knoll fullname: Knoll, Alois email: knoll@in.tum.de organization: Technical University of Munich, Munich, Germany
BookMark	eNp9kM1LAzEQxYNUsGrvgpeA561Jtkk2x1L8ghaLtHpcstkJ3bJuapIe-t-bpUXEg6cZmHnz3vwu0aBzHSB0Q8mYUqLu52_TMSOMjJkSSjF-hoYslzLLpRCDX_0FGoWwJYRQzmSu-BAtPzY64rgBPHNdiLqL-B1aZ5p4wAtXQ4tnusMr0GaD1wFPK7ePeAk1hOibNFm42LgOLz3Ujenba3RudRtgdKpXaP34sJo9Z_PXp5fZdJ6ZnMuY0YlQk8KqvKprzgkxhhhpuKxslVtFa9CT3FIrjLSKE1MBFYxDwaAuNFWE51fo7nh3593XPsUpt27vu2RZsuTAKJFEpC1y3DLeheDBljvffGp_KCkpe3RlQlf26MoTuiQRfyQJhu5fi1437X_C26OwAYAfn0JJJlLebydAfEo
CODEN	IRALC6
CitedBy_id	crossref_primary_10_1109_LRA_2022_3221335 crossref_primary_10_1109_TRO_2025_3578234 crossref_primary_10_1007_s10489_021_02997_w crossref_primary_10_3390_app14188339 crossref_primary_10_1016_j_knosys_2023_110775 crossref_primary_10_1177_14727978251321950 crossref_primary_10_1186_s43088_025_00638_6 crossref_primary_10_1016_j_oceaneng_2025_120938 crossref_primary_10_1109_TITS_2022_3156011 crossref_primary_10_1109_TITS_2021_3135136 crossref_primary_10_1016_j_patcog_2020_107800 crossref_primary_10_3390_app14209359 crossref_primary_10_1111_mice_12989 crossref_primary_10_1016_j_trc_2021_103010 crossref_primary_10_1109_TVT_2024_3519178 crossref_primary_10_1109_LRA_2020_3009068 crossref_primary_10_1007_s41315_021_00208_w crossref_primary_10_1109_ACCESS_2021_3116303 crossref_primary_10_1109_TNSE_2022_3140529 crossref_primary_10_3390_machines10030202 crossref_primary_10_1109_LRA_2021_3057326 crossref_primary_10_3390_s23052773 crossref_primary_10_1007_s00371_025_03936_3 crossref_primary_10_1109_ACCESS_2023_3257109 crossref_primary_10_1109_LRA_2022_3231832 crossref_primary_10_1109_TITS_2024_3457569 crossref_primary_10_1016_j_robot_2024_104830 crossref_primary_10_1016_j_robot_2022_104352 crossref_primary_10_1016_j_patcog_2025_111524 crossref_primary_10_1016_j_ress_2024_110463 crossref_primary_10_3390_electronics13050946 crossref_primary_10_1007_s00521_021_05888_w crossref_primary_10_1109_TRO_2020_3031268 crossref_primary_10_1109_TIV_2022_3157126 crossref_primary_10_1515_eng_2021_0103 crossref_primary_10_1016_j_trf_2024_12_024 crossref_primary_10_1109_LRA_2022_3148475 crossref_primary_10_3390_s24092794 crossref_primary_10_1002_msd2_12036 crossref_primary_10_1109_LRA_2022_3193243 crossref_primary_10_3390_s25113480 crossref_primary_10_1016_j_ins_2022_06_073 crossref_primary_10_1109_TCE_2023_3318050 crossref_primary_10_1109_LRA_2020_3004324 crossref_primary_10_1016_j_measurement_2024_114797 crossref_primary_10_1109_ACCESS_2023_3327433 crossref_primary_10_1109_ACCESS_2021_3118224 crossref_primary_10_1007_s13177_024_00393_5 crossref_primary_10_1109_TITS_2024_3465234 crossref_primary_10_1007_s00371_021_02109_2 crossref_primary_10_1049_itr2_12501 crossref_primary_10_1109_TITS_2024_3386195 crossref_primary_10_1016_j_engappai_2024_108323 crossref_primary_10_1109_ACCESS_2021_3138614 crossref_primary_10_1109_LRA_2021_3061073 crossref_primary_10_1109_LRA_2020_3005369 crossref_primary_10_26599_JICV_2023_9210036 crossref_primary_10_3390_jmse9091037 crossref_primary_10_1109_LRA_2020_3043169 crossref_primary_10_3390_app132312580 crossref_primary_10_1016_j_engappai_2022_105236 crossref_primary_10_1109_TIE_2023_3239775 crossref_primary_10_1109_TNNLS_2021_3084143 crossref_primary_10_3390_rs15092425 crossref_primary_10_1007_s11370_022_00422_w crossref_primary_10_1109_LRA_2023_3262420 crossref_primary_10_1109_TITS_2023_3281393 crossref_primary_10_7717_peerj_cs_2842 crossref_primary_10_1109_LRA_2024_3355641 crossref_primary_10_1016_j_jestch_2025_102008 crossref_primary_10_1016_j_robot_2023_104450 crossref_primary_10_1109_LRA_2023_3280809 crossref_primary_10_1016_j_aap_2024_107906 crossref_primary_10_1088_1742_6596_2303_1_012034 crossref_primary_10_1016_j_isatra_2022_07_004 crossref_primary_10_1109_TITS_2022_3205676 crossref_primary_10_1109_TITS_2022_3233906 crossref_primary_10_1109_TII_2022_3165886 crossref_primary_10_1109_LRA_2025_3566610 crossref_primary_10_1109_LRA_2022_3223024 crossref_primary_10_33769_aupse_1292652 crossref_primary_10_3390_app13052999 crossref_primary_10_1002_aaai_12192 crossref_primary_10_1007_s00521_024_09784_x crossref_primary_10_1016_j_neucom_2025_130649 crossref_primary_10_1109_TPAMI_2021_3107958 crossref_primary_10_1016_j_aei_2021_101450 crossref_primary_10_1016_j_robot_2021_103931 crossref_primary_10_1109_TITS_2023_3337104 crossref_primary_10_1109_TII_2024_3477549 crossref_primary_10_1109_ACCESS_2021_3093471 crossref_primary_10_1109_TASE_2023_3263228 crossref_primary_10_1007_s13042_023_01889_4 crossref_primary_10_1002_rnc_7302 crossref_primary_10_1109_TNNLS_2025_3550350 crossref_primary_10_1109_TITS_2021_3069362 crossref_primary_10_3390_electronics13020331 crossref_primary_10_1016_j_eswa_2025_126557 crossref_primary_10_1109_TASE_2021_3125367 crossref_primary_10_1016_j_aei_2025_103242 crossref_primary_10_1007_s11263_023_01788_9 crossref_primary_10_1109_LRA_2025_3575969 crossref_primary_10_1016_j_aap_2025_108002 crossref_primary_10_1109_TAES_2025_3536436 crossref_primary_10_1016_j_ins_2024_120433 crossref_primary_10_1109_TVT_2021_3115018 crossref_primary_10_1177_02783649241302342
Cites_doi	10.1177/0278364910365417 10.1007/978-3-319-46448-0_42 10.1109/LSP.2014.2364458 10.1103/PhysRevE.51.4282 10.1109/ITSC.2018.8569434 10.1109/IROS.2009.5354147 10.1109/CVPR.2019.00144 10.1109/CVPR.2016.110 10.1162/neco.1989.1.2.270 10.1007/978-3-030-11015-4_13 10.1109/CVPR.2017.233 10.1109/ICRA.2015.7139259 10.1609/aaai.v33i01.33016120 10.1109/CVPR.2011.5995468 10.1111/j.1467-8659.2007.01089.x 10.1109/CVPR.2018.00553 10.1109/ICRA.2018.8461157 10.1109/ROBOT.2010.5509779 10.1109/CVPR.2018.00240 10.1007/978-0-85729-997-0_24 10.1109/ICPR.2018.8545447 10.1007/s11263-018-1104-4 10.1109/ICCVW.2011.6130233 10.1109/ICRA.2018.8460504 10.1109/CVPR.2019.01236 10.1162/neco.1997.9.8.1735
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
DOI	10.1109/LRA.2020.2969925
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present 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	1702
ExternalDocumentID	10_1109_LRA_2020_2969925 8972605
Genre	orig-research
GrantInformation_xml	– fundername: German Federal Ministry of Transport and Digital Infrastructure
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-c357t-146948f93bdd5500cc0c7c57bfb3f91dea43f1f6c7f950cbe1625e82ed8a19053
IEDL.DBID	RIE
ISICitedReferencesCount	177
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000526520500004&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	Sun Nov 30 05:18:40 EST 2025 Sat Nov 29 06:03:06 EST 2025 Tue Nov 18 22:23:56 EST 2025 Wed Aug 27 02:35:30 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-c357t-146948f93bdd5500cc0c7c57bfb3f91dea43f1f6c7f950cbe1625e82ed8a19053
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0001-5644-1604
PQID	2357210706
PQPubID	4437225
PageCount	8
ParticipantIDs	crossref_primary_10_1109_LRA_2020_2969925 ieee_primary_8972605 proquest_journals_2357210706 crossref_citationtrail_10_1109_LRA_2020_2969925
PublicationCentury	2000
PublicationDate	2020-04-01
PublicationDateYYYYMMDD	2020-04-01
PublicationDate_xml	– month: 04 year: 2020 text: 2020-04-01 day: 01
PublicationDecade	2020
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE robotics and automation letters
PublicationTitleAbbrev	LRA
PublicationYear	2020
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 ref15 ref14 ref31 ref30 ref33 ref11 lipton (ref34) 0 ref10 jaipuria (ref23) 2018 ref2 ref1 ref17 ref16 kingma (ref32) 0 ref19 ref18 brendel (ref35) 0 ref24 goodfellow (ref20) 0 ref26 pellegrini (ref6) 0 ref22 ref28 ref27 ref8 habibi (ref29) 2018 ref7 ref9 ref4 ref3 ref5 devlin (ref36) 2015 amirian (ref21) 0 kingma (ref25) 0
References_xml	– year: 2015 ident: ref36 article-title: Exploring nearest neighbor approaches for image captioning publication-title: arXiv 1505 04467 – ident: ref10 doi: 10.1177/0278364910365417 – ident: ref22 doi: 10.1007/978-3-319-46448-0_42 – ident: ref8 doi: 10.1109/LSP.2014.2364458 – year: 0 ident: ref21 article-title: Social ways: Learning multi-modal distributions of pedestrian trajectories with gans publication-title: Proc Conf Comput Vision Pattern Recognit Workshops (CVPR Workshops) – start-page: 45 year: 0 ident: ref34 article-title: Troubling trends in machine learning scholarship publication-title: Proc Int Conf Mach Learn Debates – ident: ref15 doi: 10.1103/PhysRevE.51.4282 – ident: ref28 doi: 10.1109/ITSC.2018.8569434 – ident: ref30 doi: 10.1109/IROS.2009.5354147 – ident: ref2 doi: 10.1109/CVPR.2019.00144 – ident: ref4 doi: 10.1109/CVPR.2016.110 – ident: ref33 doi: 10.1162/neco.1989.1.2.270 – ident: ref14 doi: 10.1007/978-3-030-11015-4_13 – ident: ref24 doi: 10.1109/CVPR.2017.233 – ident: ref11 doi: 10.1109/ICRA.2015.7139259 – ident: ref19 doi: 10.1609/aaai.v33i01.33016120 – ident: ref13 doi: 10.1109/CVPR.2011.5995468 – start-page: 261 year: 0 ident: ref6 article-title: You'll never walk alone: Modeling social behavior for multi-target tracking publication-title: Proc Int Conf Comput Vision – ident: ref31 doi: 10.1111/j.1467-8659.2007.01089.x – year: 0 ident: ref32 article-title: Adam: A method for stochastic optimization publication-title: Proc Int Conf Learn Representations – start-page: 2672 year: 0 ident: ref20 article-title: Generative adversarial nets publication-title: Proc Conf Neural Inf Process Syst – ident: ref18 doi: 10.1109/CVPR.2018.00553 – ident: ref27 doi: 10.1109/ICRA.2018.8461157 – ident: ref16 doi: 10.1109/ROBOT.2010.5509779 – ident: ref3 doi: 10.1109/CVPR.2018.00240 – ident: ref7 doi: 10.1007/978-0-85729-997-0_24 – year: 0 ident: ref25 article-title: Auto-encoding variational bayes publication-title: Proc Int Conf Learn Representations – year: 0 ident: ref35 article-title: Approximating CNNs with bag-of-local-features models works surprisingly well on imagenet publication-title: Proc Int Conf Learn Representations – ident: ref26 doi: 10.1109/ICPR.2018.8545447 – ident: ref9 doi: 10.1007/s11263-018-1104-4 – year: 2018 ident: ref29 article-title: Context-aware pedestrian motion prediction in urban intersections publication-title: arxiv 1806 09453 – ident: ref12 doi: 10.1109/ICCVW.2011.6130233 – ident: ref5 doi: 10.1109/ICRA.2018.8460504 – ident: ref1 doi: 10.1109/CVPR.2019.01236 – ident: ref17 doi: 10.1162/neco.1997.9.8.1735 – year: 2018 ident: ref23 article-title: A transferable pedestrian motion prediction model for intersections with different geometries publication-title: arXiv 1806 09444
SSID	ssj0001527395
Score	2.5805788
Snippet	Pedestrian motion prediction is a fundamental task for autonomous robots and vehicles to operate safely. In recent years many complex approaches based on...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	1695
SubjectTerms	deep learning in robotics and automation Gallium nitride History Motion and path planning Neural networks Pedestrians Predictive models Tracking Training Trajectory
Title	What the Constant Velocity Model Can Teach Us About Pedestrian Motion Prediction
URI	https://ieeexplore.ieee.org/document/8972605 https://www.proquest.com/docview/2357210706
Volume	5
WOSCitedRecordID	wos000526520500004&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/eLvHCXMwlV3PS8MwFH448aAHf4vTOXLwItgt6680xzE2PKgUceKtNGkCwuhkqx79230v7aagCN5ySEp5X5t8X17yPYDLAc_jpEAEpOYGBYpKPCUL5dkoyPMgDGKt3EXhW3F_nzw_y3QDrtd3YYwx7vCZ6VHT5fKLuX6jrbJ-IgXR7xa0hBD1Xa2v_RRyEpPRKhPJZf_2YYj6z-c9X8ZSUi3sbyuPK6XyY_51i8pk73-vsw-7DXlkwxrtA9gw5SHsfLMUPIKUvLgZsjo2qplfxZ4MLlhIthnVPZuxUV4y5-PMpktGWZ-KpaYwrn5HiX0IKZYuKIFDzWOYTsaPoxuvqZrg6SASlYdTnwwTKwNVFCg_uNZcCx0JZVVg5aAweRjYgY21sDLiCMUAJZBJfFMkObKDKDiBzXJemlNgFsNqZOwj0GFoDZnP20SJHDmjQinpt6G_imimG0txqmwxy5y04DJDDDLCIGswaMPVesRrbafxR98jivm6XxPuNnRWoGXN_7bMyLQHxavg8dnvo85hm55dn7npwGa1eDMXsKXfq5flogutu49x131Qn-veyKI
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1dS8MwFL3oFNQHv8Xp1Dz4IliXfjePMhyKdQxR8a00aQLC6GTr_P3em3ZTUATf8pDQck-bnJObnAtw7vI8SgpEQCiuUaDIxJGikI4J_Tz3Az9S0l4UTuPBIHl9FcMluFzchdFa28Nn-oqaNpdfjNWMtsq6iYiJfi_DShgEnlvf1vraUSEvMRHOc5FcdNPHa1SAHr_yRCQEVcP-tvbYYio_ZmC7rPS3_vdC27DZ0Ed2XeO9A0u63IWNb6aCezAkN26GvI71au5XsReNSxbSbUaVz0asl5fMOjmz5ymjvE_FhrrQtoJHiX0IKzacUAqHmvvw3L956t06Td0ER_lhXDk4-YkgMcKXRYEChCvFVazCWBrpG-EWOg9845pIxUaEHMFwUQTpxNNFkiM_CP0DaJXjUh8CMxhWLSIPoQ4Co8l-3iQyzpE1ShSTXhu684hmqjEVp9oWo8yKCy4yxCAjDLIGgzZcLEa814Yaf_Tdo5gv-jXhbkNnDlrW_HHTjGx7UL7GPDr6fdQZrN0-PaRZeje4P4Z1ek59AqcDrWoy0yewqj6qt-nk1H5Wn8VJyrg
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=What+the+Constant+Velocity+Model+Can+Teach+Us+About+Pedestrian+Motion+Prediction&rft.jtitle=IEEE+robotics+and+automation+letters&rft.au=Scholler%2C+Christoph&rft.au=Aravantinos%2C+Vincent&rft.au=Lay%2C+Florian&rft.au=Knoll%2C+Alois&rft.date=2020-04-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.eissn=2377-3766&rft.volume=5&rft.issue=2&rft.spage=1696&rft_id=info:doi/10.1109%2FLRA.2020.2969925&rft.externalDBID=NO_FULL_TEXT
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