KNODE-MPC: A Knowledge-Based Data-Driven Predictive Control Framework for Aerial Robots

In this letter, we consider the problem of deriving and incorporating accurate dynamic models for model predictive control (MPC) with an application to quadrotor control. MPC relies on precise dynamic models to achieve the desired closed-loop performance. However, the presence of uncertainties in co...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE robotics and automation letters Jg. 7; H. 2; S. 2819 - 2826
Hauptverfasser:	Chee, Kong Yao, Jiahao, Tom Z., Hsieh, M. Ani
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Piscataway IEEE 01.04.2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Aerodynamics Complex systems Computational modeling Data models Differential equations Dynamic models First principles Gaussian process Machine learning for robot control Mathematical models model learning for control model predictive control Neural networks Ordinary differential equations Predictive control Predictive models Robot control System dynamics Uncertainty
ISSN:	2377-3766, 2377-3766
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	In this letter, we consider the problem of deriving and incorporating accurate dynamic models for model predictive control (MPC) with an application to quadrotor control. MPC relies on precise dynamic models to achieve the desired closed-loop performance. However, the presence of uncertainties in complex systems and the environments they operate in poses a challenge in obtaining sufficiently accurate representations of the system dynamics. In this letter, we make use of a deep learning tool, knowledge-based neural ordinary differential equations (KNODE), to augment a model obtained from first principles. The resulting hybrid model encompasses both a nominal first-principle model and a neural network learnt from simulated or real-world experimental data. Using a quadrotor, we benchmark our hybrid model against a state-of-the-art Gaussian Process (GP) model and show that the hybrid model provides more accurate predictions of the quadrotor dynamics and is able to generalize beyond the training data. To improve closed-loop performance, the hybrid model is integrated into a novel MPC framework, known as KNODE-MPC. Results show that the integrated framework achieves 60.2% improvement in simulations and more than 21% in physical experiments, in terms of trajectory tracking performance.
AbstractList	In this letter, we consider the problem of deriving and incorporating accurate dynamic models for model predictive control (MPC) with an application to quadrotor control. MPC relies on precise dynamic models to achieve the desired closed-loop performance. However, the presence of uncertainties in complex systems and the environments they operate in poses a challenge in obtaining sufficiently accurate representations of the system dynamics. In this letter, we make use of a deep learning tool, knowledge-based neural ordinary differential equations (KNODE), to augment a model obtained from first principles. The resulting hybrid model encompasses both a nominal first-principle model and a neural network learnt from simulated or real-world experimental data. Using a quadrotor, we benchmark our hybrid model against a state-of-the-art Gaussian Process (GP) model and show that the hybrid model provides more accurate predictions of the quadrotor dynamics and is able to generalize beyond the training data. To improve closed-loop performance, the hybrid model is integrated into a novel MPC framework, known as KNODE-MPC. Results show that the integrated framework achieves 60.2% improvement in simulations and more than 21% in physical experiments, in terms of trajectory tracking performance.
Author	Jiahao, Tom Z. Hsieh, M. Ani Chee, Kong Yao
Author_xml	– sequence: 1 givenname: Kong Yao orcidid: 0000-0002-1808-3807 surname: Chee fullname: Chee, Kong Yao email: ckongyao@seas.upenn.edu organization: GRASP Laboratory, University of Pennsylvania, Philadelphia, PA, USA – sequence: 2 givenname: Tom Z. orcidid: 0000-0001-6645-6068 surname: Jiahao fullname: Jiahao, Tom Z. email: zjh@seas.upenn.edu organization: GRASP Laboratory, University of Pennsylvania, Philadelphia, PA, USA – sequence: 3 givenname: M. Ani orcidid: 0000-0003-2186-9074 surname: Hsieh fullname: Hsieh, M. Ani email: m.hsieh@seas.upenn.edu organization: GRASP Laboratory, University of Pennsylvania, Philadelphia, PA, USA
BookMark	eNp9kE1Lw0AQhhdRsNbeBS8LnlP3K7uJt9gPlVZbiuIxbDYTSU2zdbO1-O9NaRHx4Gnew_vMMM8ZOq5tDQhdUNKnlMTX00XSZ4SxPqdCqEgdoQ7jSgVcSXn8K5-iXtMsCSE0ZIrHYQe9Tp5mw1HwOB_c4ARParutIH-D4FY3kOOh9joYuvITajx3kJfGtxkPbO2drfDY6RVsrXvHhXU4AVfqCi9sZn1zjk4KXTXQO8wuehmPngf3wXR29zBIpoFhMfVBBgXnpogLUJmIlBSh1nmURSZkcURZriRELDSa5kZkIc-NUlqA5JwIrgQB3kVX-71rZz820Ph0aTeubk-mTDKhQhkS1bbkvmWcbRoHRWpKr325-0OXVUpJuvOYth7Tncf04LEFyR9w7cqVdl__IZd7pASAn3osY6pixb8Bsex9mQ
CODEN	IRALC6
CitedBy_id	crossref_primary_10_1016_j_conengprac_2025_106587 crossref_primary_10_1177_09544070221127785 crossref_primary_10_1038_s41598_024_51822_0 crossref_primary_10_1109_LRA_2025_3573624 crossref_primary_10_1007_s13042_023_02095_y crossref_primary_10_1080_0951192X_2022_2128219 crossref_primary_10_1016_j_ast_2025_110045 crossref_primary_10_1109_LRA_2025_3592067 crossref_primary_10_1109_TNNLS_2024_3445976 crossref_primary_10_3390_drones9010071 crossref_primary_10_1016_j_conengprac_2025_106479 crossref_primary_10_1016_j_precisioneng_2024_03_003 crossref_primary_10_1002_oca_3287 crossref_primary_10_1002_rob_22346 crossref_primary_10_1016_j_conengprac_2024_106015 crossref_primary_10_1098_rsta_2024_0228 crossref_primary_10_1109_LRA_2025_3607272 crossref_primary_10_1002_oca_3207 crossref_primary_10_1109_TCST_2024_3521182 crossref_primary_10_1109_TNNLS_2024_3525264 crossref_primary_10_1109_TRO_2024_3381554 crossref_primary_10_1109_LRA_2024_3484182 crossref_primary_10_1109_TCYB_2024_3413072 crossref_primary_10_1109_TRO_2023_3326350 crossref_primary_10_1109_LRA_2023_3337701 crossref_primary_10_1109_TRO_2025_3567491 crossref_primary_10_1109_TCYB_2025_3536606 crossref_primary_10_3390_app12094764 crossref_primary_10_1007_s40435_025_01786_4 crossref_primary_10_1109_LRA_2023_3246839 crossref_primary_10_1109_TITS_2024_3374796 crossref_primary_10_1109_LRA_2024_3350982
Cites_doi	10.1007/s12532-018-0139-4 10.1007/BFb0109870 10.1109/ACC.2014.6858851 10.1109/LRA.2019.2930489 10.1109/IROS.2018.8593995 10.1073/pnas.1906995116 10.1002/rnc.1758 10.1063/1.5133386 10.1016/j.physd.2020.132736 10.1017/9781139061759 10.15607/RSS.2021.XVII.042 10.1063/5.0005541 10.1109/MCS.2016.2602087 10.1109/LRA.2019.2926677 10.1109/LRA.2021.3061307 10.1109/ICRA.2011.5980409 10.1073/pnas.1517384113 10.1098/rspa.2018.0335 10.1063/5.0065617 10.1016/S0967-0661(02)00186-7 10.1109/ICRA.2017.7989202 10.1137/S1064827501380630 10.1109/TASSP.1978.1163055
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
DOI	10.1109/LRA.2022.3144787
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library (IEL) (UW System Shared) 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/IET Electronic Library (IEL) (UW System Shared) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	2377-3766
EndPage	2826
ExternalDocumentID	10_1109_LRA_2022_3144787 9691797
Genre	orig-research
GrantInformation_xml	– fundername: NSF IIS grantid: 1910308 – fundername: DSO National Laboratories
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-bef33cf9fe7b487645aad8b8c529812d76e825ca1dc4b53dc77a4e633043740e3
IEDL.DBID	RIE
ISICitedReferencesCount	56
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000750158000030&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 09 07:56:13 EST 2025 Tue Nov 18 19:37:57 EST 2025 Sat Nov 29 06:03:14 EST 2025 Wed Aug 27 03:00:18 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-bef33cf9fe7b487645aad8b8c529812d76e825ca1dc4b53dc77a4e633043740e3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0001-6645-6068 0000-0002-1808-3807 0000-0003-2186-9074
PQID	2624756507
PQPubID	4437225
PageCount	8
ParticipantIDs	crossref_citationtrail_10_1109_LRA_2022_3144787 ieee_primary_9691797 crossref_primary_10_1109_LRA_2022_3144787 proquest_journals_2624756507
PublicationCentury	2000
PublicationDate	2022-04-01
PublicationDateYYYYMMDD	2022-04-01
PublicationDate_xml	– month: 04 year: 2022 text: 2022-04-01 day: 01
PublicationDecade	2020
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE robotics and automation letters
PublicationTitleAbbrev	LRA
PublicationYear	2022
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 ref15 ref14 ref11 Kingma (ref22) 2015 ref10 ref2 ref1 ref17 ref16 ref19 ref18 Pedregosa (ref28) 2011; 12 Chen (ref12) 2018 Pfrommer (ref9) 2020; 155 Tavenard (ref25) 2020; 21 ref24 ref23 Hnig (ref30) 2017 ref26 ref20 ref21 Bitcraze (ref29) ref27 ref8 ref7 ref4 ref3 ref6 ref5
References_xml	– ident: ref26 doi: 10.1007/s12532-018-0139-4 – ident: ref18 doi: 10.1007/BFb0109870 – ident: ref21 doi: 10.1109/ACC.2014.6858851 – volume: 12 start-page: 2825 year: 2011 ident: ref28 article-title: Scikit-learn: Machine learning in python publication-title: J. Mach. Learn. Res. – ident: ref16 doi: 10.1109/LRA.2019.2930489 – ident: ref8 doi: 10.1109/IROS.2018.8593995 – ident: ref6 doi: 10.1073/pnas.1906995116 – ident: ref19 doi: 10.1002/rnc.1758 – ident: ref5 doi: 10.1063/1.5133386 – ident: ref10 doi: 10.1016/j.physd.2020.132736 – ident: ref2 doi: 10.1017/9781139061759 – ident: ref29 article-title: Crazyflie 2.1 – ident: ref27 doi: 10.15607/RSS.2021.XVII.042 – ident: ref11 doi: 10.1063/5.0005541 – ident: ref20 doi: 10.1109/MCS.2016.2602087 – start-page: 6571 volume-title: Adv. Neural Inf. Process. Syst year: 2018 ident: ref12 article-title: Neural ordinary differential equations – ident: ref13 doi: 10.1109/LRA.2019.2926677 – volume: 21 start-page: 1 issue: 118 volume-title: J. Mach. Learn. Res. year: 2020 ident: ref25 article-title: Tslearn, a machine learning toolkit for time series data – ident: ref14 doi: 10.1109/LRA.2021.3061307 – ident: ref17 doi: 10.1109/ICRA.2011.5980409 – ident: ref4 doi: 10.1073/pnas.1517384113 – ident: ref7 doi: 10.1098/rspa.2018.0335 – start-page: 83 volume-title: Flying Multiple UAVs Using ROS year: 2017 ident: ref30 – ident: ref3 doi: 10.1063/5.0065617 – volume-title: Int. Conf. Learning Representations year: 2015 ident: ref22 article-title: Adam: A method for stochastic optimization – ident: ref1 doi: 10.1016/S0967-0661(02)00186-7 – ident: ref15 doi: 10.1109/ICRA.2017.7989202 – ident: ref23 doi: 10.1137/S1064827501380630 – ident: ref24 doi: 10.1109/TASSP.1978.1163055 – volume: 155 start-page: 2279 volume-title: Conf. Robot Learning year: 2020 ident: ref9 article-title: ContactNets: Learning discontinuous contact dynamics with smooth, implicit representations
SSID	ssj0001527395
Score	2.5071404
Snippet	In this letter, we consider the problem of deriving and incorporating accurate dynamic models for model predictive control (MPC) with an application to...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	2819
SubjectTerms	Aerodynamics Complex systems Computational modeling Data models Differential equations Dynamic models First principles Gaussian process Machine learning for robot control Mathematical models model learning for control model predictive control Neural networks Ordinary differential equations Predictive control Predictive models Robot control System dynamics Uncertainty
Title	KNODE-MPC: A Knowledge-Based Data-Driven Predictive Control Framework for Aerial Robots
URI	https://ieeexplore.ieee.org/document/9691797 https://www.proquest.com/docview/2624756507
Volume	7
WOSCitedRecordID	wos000750158000030&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) (UW System Shared) 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/eLvHCXMwlV1LSwMxEB6seNCDryrWR8nBi2DsusluNt5qHwhqLUWxt2WTzIIgrbSrR3-7yT6qogjeckhCmElm5puZzAAcpwyVikJDtQqQcsGlfVIpp6lVVkyqFJmK8mYTYjCIxmM5XILTxV8YRMyTz_DMDfNYvpnqV-cqa8nQggspalATQhR_tT79Ka6SmAyqSKQnWzejtsV_vm9hKXclaL5pnryVyg_5myuV_sb_jrMJ66XxSNoFt7dgCSfbsPalpGAdHq8Hd90evR12LkibXFceM3pptZUh3SRLaHfmJBwZzlyMxkk70iny1Um_ytQi1pQl7fxyktFUTbP5Djz0e_edK1o2T6Dal-cZVZgyplOZolAWlIQ8SBITqUgHvrRK3YgQLTjUybnRXAXMaCESjqFzbzDBPWS7sDyZTnAPiNERCqYFeopxplAyDJJIedoae0Zp04BWRdhYl5XFXYOL5zhHGJ6MLStix4q4ZEUDThYrXoqqGn_MrTvSL-aVVG_AYcW7uHx289gPfS6sieqJ_d9XHcCq27tIvTmE5Wz2ikewot-yp_msCbXb914zv1cfe5_LBw
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB58gXrwLdZnDl4EY7eb7GbjrbYWpbUWUfS2bJJZEKSVdvX3m-yjKorgLYeEhJlkZr6ZyQzAccpQqSg0VKsAKRdc2ieVcppaZcWkSpGpKG82Ifr96OlJDmbgdPoXBhHz5DM8c8M8lm9G-s25yuoytOBCilmYDzj3G8VvrU-PiqslJoMqFunJeu-uaRGg71tgyl0Rmm-6J2-m8kMC52qls_q_A63BSmk-kmbB73WYweEGLH8pKrgJj93-bfuS3gxa56RJupXPjF5YfWVIO8kS2h47GUcGYxelcfKOtIqMddKpcrWINWZJM7-e5G6kRtlkCx46l_etK1q2T6Dal42MKkwZ06lMUSgLS0IeJImJVKQDX1q1bkSIFh7qpGE0VwEzWoiEY-gcHExwD9k2zA1HQ9wBYnSEgmmBnmKcKZQMgyRSnrbmnlHa1KBeETbWZW1x1-LiJc4xhidjy4rYsSIuWVGDk-mK16Kuxh9zNx3pp_NKqtdgv-JdXD68SeyHPhfWSPXE7u-rjmDx6v6mF_eu-909WHL7FIk4-zCXjd_wABb0e_Y8GR_mt-sDZhvNHQ
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=KNODE-MPC%3A+A+Knowledge-Based+Data-Driven+Predictive+Control+Framework+for+Aerial+Robots&rft.jtitle=IEEE+robotics+and+automation+letters&rft.au=Kong%2C+Yao+Chee&rft.au=Jiahao%2C+Tom+Z&rft.au=M+Ani+Hsieh&rft.date=2022-04-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.eissn=2377-3766&rft.volume=7&rft.issue=2&rft.spage=2819&rft_id=info:doi/10.1109%2FLRA.2022.3144787&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