Edge Intelligence for Autonomous Driving in 6G Wireless System: Design Challenges and Solutions

In a level-5 autonomous driving system, the autonomous driving vehicles (AVs) are expected to sense the surroundings via analyzing a large amount of data captured by a variety of onboard sensors in near-real-time. As a result, enormous computing costs will be introduced to the AVs for processing the...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE wireless communications Jg. 28; H. 2; S. 40 - 47
Hauptverfasser:	Yang, Bo, Cao, Xuelin, Xiong, Kai, Yuen, Chau, Guan, Yong Liang, Leng, Supeng, Qian, Lijun, Han, Zhu
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	New York IEEE 01.04.2021 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	6G mobile communication Artificial neural networks Autonomous vehicles Computational modeling Computing costs Edge computing Inference Intelligence Machine learning Mixed integer Mobile computing Model accuracy Neural networks Nonlinear programming Real time Resource allocation Segmentation Sensor systems Servers Vehicles Wireless communication Wireless sensor networks
ISSN:	1536-1284, 1558-0687
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	In a level-5 autonomous driving system, the autonomous driving vehicles (AVs) are expected to sense the surroundings via analyzing a large amount of data captured by a variety of onboard sensors in near-real-time. As a result, enormous computing costs will be introduced to the AVs for processing the tasks with the deployed machine learning (ML) model, while the inference accuracy may not be guaranteed. In this context, the advent of edge intelligence (EI) and sixth-generation (6G) wireless networking are expected to pave the way to more reliable and safer autonomous driving by providing multi-access edge computing (MEC) together with ML to AVs in close proximity. To realize this goal, we propose a two-tier EI-empowered autonomous driving framework. In the autonomous-vehicles tier, the autonomous vehicles are deployed with the shallow layers by splitting the trained deep neural network model. In the edge-intelligence tier, an edge server is implemented with the remaining layers (also deep layers) and an appropriately trained multi-task learning (MTL) model. In particular, obtaining the optimal offloading strategy (including the binary offloading decision and the computational resources allocation) can be formulated as a mixed-integer nonlinear programming (MINLP) problem, which is solved via MTL in near-real-time with high accuracy. On another note, an edge-vehicle joint inference is proposed through neural network segmentation to achieve efficient online inference with data privacy-preserving and less communication delay. Experiments demonstrate the effectiveness of the proposed framework, and open research topics are finally listed.
AbstractList	In a level-5 autonomous driving system, the autonomous driving vehicles (AVs) are expected to sense the surroundings via analyzing a large amount of data captured by a variety of onboard sensors in near-real-time. As a result, enormous computing costs will be introduced to the AVs for processing the tasks with the deployed machine learning (ML) model, while the inference accuracy may not be guaranteed. In this context, the advent of edge intelligence (EI) and sixth-generation (6G) wireless networking are expected to pave the way to more reliable and safer autonomous driving by providing multi-access edge computing (MEC) together with ML to AVs in close proximity. To realize this goal, we propose a two-tier EI-empowered autonomous driving framework. In the autonomous-vehicles tier, the autonomous vehicles are deployed with the shallow layers by splitting the trained deep neural network model. In the edge-intelligence tier, an edge server is implemented with the remaining layers (also deep layers) and an appropriately trained multi-task learning (MTL) model. In particular, obtaining the optimal offloading strategy (including the binary offloading decision and the computational resources allocation) can be formulated as a mixed-integer nonlinear programming (MINLP) problem, which is solved via MTL in near-real-time with high accuracy. On another note, an edge-vehicle joint inference is proposed through neural network segmentation to achieve efficient online inference with data privacy-preserving and less communication delay. Experiments demonstrate the effectiveness of the proposed framework, and open research topics are finally listed.
Author	Qian, Lijun Xiong, Kai Leng, Supeng Yang, Bo Guan, Yong Liang Yuen, Chau Han, Zhu Cao, Xuelin
Author_xml	– sequence: 1 givenname: Bo surname: Yang fullname: Yang, Bo email: bo_yang@sutd.edu.sg organization: Singapore University of Technology and Design,Singapore – sequence: 2 givenname: Xuelin surname: Cao fullname: Cao, Xuelin email: xuelin_cao@sutd.edu.sg organization: Singapore University of Technology and Design,Singapore – sequence: 3 givenname: Kai surname: Xiong fullname: Xiong, Kai email: xiongkaipai@163.com organization: University of Electronic Science and Technology of China (UESTC),China – sequence: 4 givenname: Chau surname: Yuen fullname: Yuen, Chau email: yuenchau@sutd.edu.sg organization: Singapore University of Technology and Design,Singapore – sequence: 5 givenname: Yong Liang surname: Guan fullname: Guan, Yong Liang email: eylguan@ntu.edu.sg organization: Nanyang Technological University,Singapore – sequence: 6 givenname: Supeng surname: Leng fullname: Leng, Supeng email: spleng@uestc.edu.cn organization: University of Electronic Science and Technology of China (UESTC),China – sequence: 7 givenname: Lijun surname: Qian fullname: Qian, Lijun email: liqian@pvamu.edu organization: Prairie View A&M University, Texas A&M University System,USA – sequence: 8 givenname: Zhu surname: Han fullname: Han, Zhu email: zhan2@uh.edu organization: University of Houston,USA
BookMark	eNp9kD1PwzAQhi1UJNrCzMBiiTmt49hOzFa1pVQqYiioo5WPS3CV2sVOkPrvSdSKgYHpbnife3XPCA2MNYDQfUgmYUjk9HU3nxASTighhEp6hYYh50lARBIP-j0SQUgTdoNG3u-7YCy4GCK1LCrAa9NAXesKTA64tA7P2sYae7Ctxwunv7WpsDZYrPBOO6jBe7w9-QYOT3gBXlcGzz_TugZTgcepKfDW1m2jrfG36LpMaw93lzlGH8_L9_lLsHlbreezTZDTRDYB5SCZKFgRlzwCzkgWZyRjBU_zWOSZhJQWkmdlnjDCIBOMZnFeAhRJwRgpk2iMHs93j85-teAbtbetM12lopwKKaKQ9anpOZU7672DUh2dPqTupEKieouqs6g6OepisSP4HyLXTdq_1rhU1_9wD2dOA8Bvi2QRkSSOfgAzEYFA
CODEN	IWCEAS
CitedBy_id	crossref_primary_10_1109_JIOT_2023_3348590 crossref_primary_10_1016_j_eng_2025_05_012 crossref_primary_10_1109_TVT_2023_3257048 crossref_primary_10_1016_j_future_2024_07_027 crossref_primary_10_1109_ACCESS_2024_3521579 crossref_primary_10_1109_JIOT_2025_3546701 crossref_primary_10_1109_JIOT_2024_3465553 crossref_primary_10_1109_TVT_2023_3334257 crossref_primary_10_3390_info15090550 crossref_primary_10_1109_ACCESS_2022_3210584 crossref_primary_10_1109_TVT_2023_3306939 crossref_primary_10_1016_j_comnet_2024_111013 crossref_primary_10_1109_MNET_2024_3354209 crossref_primary_10_1364_JOCN_452105 crossref_primary_10_1109_TII_2021_3075444 crossref_primary_10_1061__ASCE_CO_1943_7862_0002187 crossref_primary_10_1360_SSI_2024_0321 crossref_primary_10_1016_j_dcan_2025_07_001 crossref_primary_10_1134_S0361768823100079 crossref_primary_10_1002_ett_4410 crossref_primary_10_1109_ACCESS_2022_3203711 crossref_primary_10_1016_j_comcom_2022_04_006 crossref_primary_10_1109_ACCESS_2024_3429184 crossref_primary_10_1109_JSAC_2022_3143223 crossref_primary_10_3390_s23041963 crossref_primary_10_1016_j_teler_2024_100116 crossref_primary_10_1109_ACCESS_2022_3187745 crossref_primary_10_1109_TITS_2022_3230430 crossref_primary_10_1109_TVT_2022_3203056 crossref_primary_10_1109_TSIPN_2023_3325963 crossref_primary_10_1080_10584587_2024_2322353 crossref_primary_10_1109_ACCESS_2023_3234761 crossref_primary_10_1016_j_comnet_2025_111300 crossref_primary_10_1109_TII_2023_3257308 crossref_primary_10_1016_j_comnet_2023_109872 crossref_primary_10_3390_ai4030039 crossref_primary_10_1016_j_vehcom_2022_100536 crossref_primary_10_1109_COMST_2024_3482978 crossref_primary_10_1109_OJCOMS_2025_3579240 crossref_primary_10_1109_TDSC_2024_3523561 crossref_primary_10_3390_electronics12020366 crossref_primary_10_1016_j_jksuci_2022_03_019 crossref_primary_10_1109_JSAC_2024_3460078 crossref_primary_10_1109_TMC_2023_3343939 crossref_primary_10_3390_s25165119 crossref_primary_10_1007_s11235_025_01325_8 crossref_primary_10_1049_2024_5802816 crossref_primary_10_3390_electronics12061472 crossref_primary_10_1109_TMLCN_2025_3576727 crossref_primary_10_1109_JIOT_2025_3531910 crossref_primary_10_1002_dac_70102 crossref_primary_10_1109_TITS_2021_3052355 crossref_primary_10_1109_ACCESS_2022_3174548 crossref_primary_10_1109_JIOT_2024_3357861 crossref_primary_10_1109_TVT_2023_3253695 crossref_primary_10_1016_j_eswa_2025_127273 crossref_primary_10_1016_j_vehcom_2023_100623 crossref_primary_10_1109_TITS_2022_3232153 crossref_primary_10_1109_TSC_2023_3340672 crossref_primary_10_1109_JSEN_2022_3228768 crossref_primary_10_1109_TITS_2022_3149860 crossref_primary_10_1109_MWC_014_2300277 crossref_primary_10_1016_j_cose_2023_103278 crossref_primary_10_1109_TITS_2024_3486555 crossref_primary_10_1109_TVT_2023_3264504 crossref_primary_10_1109_JSAC_2022_3227027 crossref_primary_10_1109_JIOT_2024_3353793 crossref_primary_10_1109_TITS_2023_3241251 crossref_primary_10_1109_TMC_2022_3199812 crossref_primary_10_1109_TNSE_2021_3103124 crossref_primary_10_1109_TNSM_2025_3561739 crossref_primary_10_3390_math13091540 crossref_primary_10_1109_MNET_2023_3321519 crossref_primary_10_1016_j_future_2024_107572 crossref_primary_10_1109_TMC_2025_3568248 crossref_primary_10_1007_s11276_024_03889_w crossref_primary_10_1016_j_adhoc_2023_103343 crossref_primary_10_1109_JIOT_2023_3314923 crossref_primary_10_1109_JIOT_2023_3333826 crossref_primary_10_1109_MNET_110_2100301 crossref_primary_10_1109_TVT_2024_3409554 crossref_primary_10_1109_IOTM_001_2200178 crossref_primary_10_1109_TMC_2023_3259394 crossref_primary_10_1109_TIV_2023_3332675 crossref_primary_10_1109_JSAC_2022_3227032 crossref_primary_10_1109_MNET_2024_3468328 crossref_primary_10_1016_j_tcs_2022_06_014 crossref_primary_10_1109_JSTSP_2022_3161786 crossref_primary_10_1109_TMC_2024_3411295 crossref_primary_10_1109_TMC_2024_3438155
Cites_doi	10.1109/TMC.2020.2990630 10.1109/TVT.2020.3029109 10.1109/COMST.2020.2965856 10.1109/TVT.2020.2973651 10.1109/JIOT.2019.2903191 10.1109/TITS.2020.3015210 10.1109/MNET.2019.1800254 10.1109/MWC.2018.1700200 10.1109/TVT.2018.2876804 10.1109/MWC.2019.1800411 10.1109/LWC.2020.2984620 10.1109/COMST.2018.2888904 10.1109/MCOM.001.1900103 10.1109/MCOM.2019.1900271
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 7SP 8FD F28 FR3 L7M
DOI	10.1109/MWC.001.2000292
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE All-Society Periodicals Package (ASPP) 1998-Present IEEE Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Technology Research Database ANTE: Abstracts in New Technology & Engineering Engineering Research Database Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Engineering Research Database Technology Research Database Advanced Technologies Database with Aerospace ANTE: Abstracts in New Technology & Engineering Electronics & Communications Abstracts
DatabaseTitleList	Engineering 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	1558-0687
EndPage	47
ExternalDocumentID	10_1109_MWC_001_2000292 9430907
Genre	orig-research
GrantInformation_xml	– fundername: NSF grantid: EARS-1839818,CNS1717454,CNS-1731424,CNS-1702850 funderid: 10.13039/100000001 – fundername: A*STAR grantid: A19D6a0053 funderid: 10.13039/501100001348
GroupedDBID	-~X 0R~ 1OL 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AIBXA AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV AZLTO BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ H~9 IES IFIPE IPLJI JAVBF LAI M43 O9- OCL RIA RIE RNS TN5 AAYXX CITATION 7SP 8FD F28 FR3 L7M
ID	FETCH-LOGICAL-c289t-25e946d4d7f53e540b7b0b4d5ac76cb9ea2d95bfc8404eb642b7cfeed8d440f83
IEDL.DBID	RIE
ISICitedReferencesCount	113
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000672740400008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1536-1284
IngestDate	Mon Jun 30 10:24:03 EDT 2025 Tue Nov 18 20:56:41 EST 2025 Sat Nov 29 03:07:43 EST 2025 Wed Aug 27 02:30:26 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-c289t-25e946d4d7f53e540b7b0b4d5ac76cb9ea2d95bfc8404eb642b7cfeed8d440f83
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
PQID	2526963148
PQPubID	75748
PageCount	8
ParticipantIDs	crossref_primary_10_1109_MWC_001_2000292 ieee_primary_9430907 proquest_journals_2526963148 crossref_citationtrail_10_1109_MWC_001_2000292
PublicationCentury	2000
PublicationDate	2021-April 2021-4-00 20210401
PublicationDateYYYYMMDD	2021-04-01
PublicationDate_xml	– month: 04 year: 2021 text: 2021-April
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE wireless communications
PublicationTitleAbbrev	WC-M
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 zhang (ref14) 2020 ref15 ref11 ref10 ref2 ref1 ref8 ref7 ref9 ref4 ref3 ref6 ref5
References_xml	– ident: ref11 doi: 10.1109/TMC.2020.2990630 – year: 2020 ident: ref14 publication-title: Autonomous unknown-application filtering and labeling for DL-based traffic classifier update – ident: ref15 doi: 10.1109/TVT.2020.3029109 – ident: ref4 doi: 10.1109/COMST.2020.2965856 – ident: ref12 doi: 10.1109/TVT.2020.2973651 – ident: ref7 doi: 10.1109/JIOT.2019.2903191 – ident: ref6 doi: 10.1109/TITS.2020.3015210 – ident: ref8 doi: 10.1109/MNET.2019.1800254 – ident: ref10 doi: 10.1109/MWC.2018.1700200 – ident: ref3 doi: 10.1109/TVT.2018.2876804 – ident: ref9 doi: 10.1109/MWC.2019.1800411 – ident: ref5 doi: 10.1109/LWC.2020.2984620 – ident: ref2 doi: 10.1109/COMST.2018.2888904 – ident: ref13 doi: 10.1109/MCOM.001.1900103 – ident: ref1 doi: 10.1109/MCOM.2019.1900271
SSID	ssj0017656
Score	2.6629183
Snippet	In a level-5 autonomous driving system, the autonomous driving vehicles (AVs) are expected to sense the surroundings via analyzing a large amount of data...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	40
SubjectTerms	6G mobile communication Artificial neural networks Autonomous vehicles Computational modeling Computing costs Edge computing Inference Intelligence Machine learning Mixed integer Mobile computing Model accuracy Neural networks Nonlinear programming Real time Resource allocation Segmentation Sensor systems Servers Vehicles Wireless communication Wireless sensor networks
Title	Edge Intelligence for Autonomous Driving in 6G Wireless System: Design Challenges and Solutions
URI	https://ieeexplore.ieee.org/document/9430907 https://www.proquest.com/docview/2526963148
Volume	28
WOSCitedRecordID	wos000672740400008&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: 1558-0687 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017656 issn: 1536-1284 databaseCode: RIE dateStart: 20020101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwED6VigEGXgVRKMgDAwNp08SJY7aqD0CCigFEtyh-BFWqUtSm_H58ThoVAQNbBluyfLHvvvPd9wFcRSpIgkC5Dg27BqDwRDrC4BAn8SVHhyl4YlVLHtl4HE0m_LkGN1UvjNbaFp_pNn7at3w1lytMlXWQKpxj6_gWY2HRq1W9GLDQKrWaA4y6MhEtaXy6Lu88vfXxwcF2pXjc--aBrKTKj3vYOpfR_v-WdQB7ZRBJeoXVD6GmsyPY3aAWbEA8VO-aPGwQbhITnpLeKscuBgP3yWAxxWQCmWYkvCNYBTsztx4pKMxvycCWdpD-WmxlSZJMkSqLdgyvo-FL_94pxRQcaTBV7niB5jRUVLE08LWJ0wQTrqDGVJKFUnCdeIoHIpUG8VEtDCwRTKbGg0aKUjeN_BOoZ_NMnwJh1ER1Siq_qwSNXI0sj8ynqaJSeB4LmtBeb3AsS6ZxFLyYxRZxuDw2FsFiuri0SBOuqwkfBcnG30MbaIBqWLn3TWitLRiXh3AZe6ieHvoG8J39PuscdjwsUbGFOC2o54uVvoBt-ZlPl4tL-399AXtFzZQ
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwED5VBQkYeBVEoYAHBgbSpo4Tx2xVH7SirRiK6BbFj6BKVYr64Pdju2lUBAxsGWzJ8sW--8533wdwF0o_9n3pOiSoa4DCYuFwjUOc2BPMOEzOYqta0qfDYTges5cCPOS9MEopW3ymqubTvuXLmViZVFnNUIUz0zq-4xOC3XW3Vv5mQAOr1aqPsFGWCUlG5FN3WW3w1jRPDrYvBTP8zQdZUZUfN7F1L52j_y3sGA6zMBI11nY_gYJKT-Fgi1ywBFFbvivU26LcRDpARY3V0vQxaMCPWvOJSSegSYqCJ2TqYKf63kNrEvNH1LLFHai5kVtZoDiVKM-jncFrpz1qdp1MTsERGlUtHewrRgJJJE18T-lIjVPucqKNJWggOFMxlsznidCYjyiugQmnItE-NJSEuEnonUMxnaXqAhAlOq6TQnp1yUnoKsPzSD2SSCI4xtQvQ3WzwZHIuMaN5MU0spjDZZG2iCmnizKLlOE-n_Cxptn4e2jJGCAflu19GSobC0bZMVxE2OinB56GfJe_z7qFve5o0I_6veHzFexjU7Biy3IqUFzOV-oadsXncrKY39h_7QtVUtDb
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=Edge+Intelligence+for+Autonomous+Driving+in+6G+Wireless+System%3A+Design+Challenges+and+Solutions&rft.jtitle=IEEE+wireless+communications&rft.au=Cao%2C+Xuelin&rft.au=Xiong%2C+Kai&rft.au=Chau+Yuen&rft.au=Yong+Liang+Guan&rft.date=2021-04-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=1536-1284&rft.eissn=1558-0687&rft.volume=28&rft.issue=2&rft.spage=40&rft_id=info:doi/10.1109%2FMWC.001.2000292&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1536-1284&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1536-1284&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1536-1284&client=summon