A Survey on Imitation Learning Techniques for End-to-End Autonomous Vehicles
The state-of-the-art decision and planning approaches for autonomous vehicles have moved away from manually designed systems, instead focusing on the utilisation of large-scale datasets of expert demonstration via Imitation Learning (IL). In this paper, we present a comprehensive review of IL approa...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on intelligent transportation systems 2022-09, Vol.23 (9), p.14128-14147 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 14147 |
|---|---|
| container_issue | 9 |
| container_start_page | 14128 |
| container_title | IEEE transactions on intelligent transportation systems |
| container_volume | 23 |
| creator | Le Mero, Luc Yi, Dewei Dianati, Mehrdad Mouzakitis, Alexandros |
| description | The state-of-the-art decision and planning approaches for autonomous vehicles have moved away from manually designed systems, instead focusing on the utilisation of large-scale datasets of expert demonstration via Imitation Learning (IL). In this paper, we present a comprehensive review of IL approaches, primarily for the paradigm of end-to-end based systems in autonomous vehicles. We classify the literature into three distinct categories: 1) Behavioural Cloning (BC), 2) Direct Policy Learning (DPL) and 3) Inverse Reinforcement Learning (IRL). For each of these categories, the current state-of-the-art literature is comprehensively reviewed and summarised, with future directions of research identified to facilitate the development of imitation learning based systems for end-to-end autonomous vehicles. Due to the data-intensive nature of deep learning techniques, currently available datasets and simulators for end-to-end autonomous driving are also reviewed. |
| doi_str_mv | 10.1109/TITS.2022.3144867 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_crossref_primary_10_1109_TITS_2022_3144867</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9700770</ieee_id><sourcerecordid>2714899330</sourcerecordid><originalsourceid>FETCH-LOGICAL-c402t-120ca143a840279d2a4f2ef3787cd7570bc3332a98d2c6515d3fe0d7a4bbc85d3</originalsourceid><addsrcrecordid>eNo9UE1LAzEUDKJgrf4A8RLwnPXlq9k9llK1sOChq9eQZrN2S7upya7Qf2-WFk8z85h57zEIPVLIKIXipVpV64wBYxmnQuQzdYUmVMqcANDZ9ciZIAVIuEV3Me7SVEhKJ6ic4_UQft0J-w6vDm1v-jax0pnQtd03rpzddu3P4CJufMDLria9JwnwfOh95w9-iPjLbVu7d_Ee3TRmH93DBafo83VZLd5J-fG2WsxLYgWwnlAG1lDBTZ6kKmpmRMNcw1WubK2kgo3lnDNT5DWzM0llzRsHtTJis7F5UlP0fN57DH58rdc7P4QundRMUZEXBeeQXPTsssHHGFyjj6E9mHDSFPRYmh5L02Np-lJayjydM61z7t9fKAClgP8Bgx5nbg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2714899330</pqid></control><display><type>article</type><title>A Survey on Imitation Learning Techniques for End-to-End Autonomous Vehicles</title><source>IEEE Electronic Library (IEL)</source><creator>Le Mero, Luc ; Yi, Dewei ; Dianati, Mehrdad ; Mouzakitis, Alexandros</creator><creatorcontrib>Le Mero, Luc ; Yi, Dewei ; Dianati, Mehrdad ; Mouzakitis, Alexandros</creatorcontrib><description>The state-of-the-art decision and planning approaches for autonomous vehicles have moved away from manually designed systems, instead focusing on the utilisation of large-scale datasets of expert demonstration via Imitation Learning (IL). In this paper, we present a comprehensive review of IL approaches, primarily for the paradigm of end-to-end based systems in autonomous vehicles. We classify the literature into three distinct categories: 1) Behavioural Cloning (BC), 2) Direct Policy Learning (DPL) and 3) Inverse Reinforcement Learning (IRL). For each of these categories, the current state-of-the-art literature is comprehensively reviewed and summarised, with future directions of research identified to facilitate the development of imitation learning based systems for end-to-end autonomous vehicles. Due to the data-intensive nature of deep learning techniques, currently available datasets and simulators for end-to-end autonomous driving are also reviewed.</description><identifier>ISSN: 1524-9050</identifier><identifier>EISSN: 1558-0016</identifier><identifier>DOI: 10.1109/TITS.2022.3144867</identifier><identifier>CODEN: ITISFG</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>autonomous systems ; Autonomous vehicles ; Cameras ; Cloning ; Datasets ; Deep learning ; Intelligent vehicles ; learning ; machine learning ; neural networks ; Simulators ; State-of-the-art reviews ; Task analysis ; Training ; Uncertainty ; Vehicles</subject><ispartof>IEEE transactions on intelligent transportation systems, 2022-09, Vol.23 (9), p.14128-14147</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c402t-120ca143a840279d2a4f2ef3787cd7570bc3332a98d2c6515d3fe0d7a4bbc85d3</citedby><cites>FETCH-LOGICAL-c402t-120ca143a840279d2a4f2ef3787cd7570bc3332a98d2c6515d3fe0d7a4bbc85d3</cites><orcidid>0000-0001-5119-4499 ; 0000-0003-1702-9136 ; 0000-0002-6882-0166</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9700770$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,778,782,794,27911,27912,54745</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9700770$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Le Mero, Luc</creatorcontrib><creatorcontrib>Yi, Dewei</creatorcontrib><creatorcontrib>Dianati, Mehrdad</creatorcontrib><creatorcontrib>Mouzakitis, Alexandros</creatorcontrib><title>A Survey on Imitation Learning Techniques for End-to-End Autonomous Vehicles</title><title>IEEE transactions on intelligent transportation systems</title><addtitle>TITS</addtitle><description>The state-of-the-art decision and planning approaches for autonomous vehicles have moved away from manually designed systems, instead focusing on the utilisation of large-scale datasets of expert demonstration via Imitation Learning (IL). In this paper, we present a comprehensive review of IL approaches, primarily for the paradigm of end-to-end based systems in autonomous vehicles. We classify the literature into three distinct categories: 1) Behavioural Cloning (BC), 2) Direct Policy Learning (DPL) and 3) Inverse Reinforcement Learning (IRL). For each of these categories, the current state-of-the-art literature is comprehensively reviewed and summarised, with future directions of research identified to facilitate the development of imitation learning based systems for end-to-end autonomous vehicles. Due to the data-intensive nature of deep learning techniques, currently available datasets and simulators for end-to-end autonomous driving are also reviewed.</description><subject>autonomous systems</subject><subject>Autonomous vehicles</subject><subject>Cameras</subject><subject>Cloning</subject><subject>Datasets</subject><subject>Deep learning</subject><subject>Intelligent vehicles</subject><subject>learning</subject><subject>machine learning</subject><subject>neural networks</subject><subject>Simulators</subject><subject>State-of-the-art reviews</subject><subject>Task analysis</subject><subject>Training</subject><subject>Uncertainty</subject><subject>Vehicles</subject><issn>1524-9050</issn><issn>1558-0016</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9UE1LAzEUDKJgrf4A8RLwnPXlq9k9llK1sOChq9eQZrN2S7upya7Qf2-WFk8z85h57zEIPVLIKIXipVpV64wBYxmnQuQzdYUmVMqcANDZ9ciZIAVIuEV3Me7SVEhKJ6ic4_UQft0J-w6vDm1v-jax0pnQtd03rpzddu3P4CJufMDLria9JwnwfOh95w9-iPjLbVu7d_Ee3TRmH93DBafo83VZLd5J-fG2WsxLYgWwnlAG1lDBTZ6kKmpmRMNcw1WubK2kgo3lnDNT5DWzM0llzRsHtTJis7F5UlP0fN57DH58rdc7P4QundRMUZEXBeeQXPTsssHHGFyjj6E9mHDSFPRYmh5L02Np-lJayjydM61z7t9fKAClgP8Bgx5nbg</recordid><startdate>20220901</startdate><enddate>20220901</enddate><creator>Le Mero, Luc</creator><creator>Yi, Dewei</creator><creator>Dianati, Mehrdad</creator><creator>Mouzakitis, Alexandros</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>FR3</scope><scope>JQ2</scope><scope>KR7</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0001-5119-4499</orcidid><orcidid>https://orcid.org/0000-0003-1702-9136</orcidid><orcidid>https://orcid.org/0000-0002-6882-0166</orcidid></search><sort><creationdate>20220901</creationdate><title>A Survey on Imitation Learning Techniques for End-to-End Autonomous Vehicles</title><author>Le Mero, Luc ; Yi, Dewei ; Dianati, Mehrdad ; Mouzakitis, Alexandros</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c402t-120ca143a840279d2a4f2ef3787cd7570bc3332a98d2c6515d3fe0d7a4bbc85d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>autonomous systems</topic><topic>Autonomous vehicles</topic><topic>Cameras</topic><topic>Cloning</topic><topic>Datasets</topic><topic>Deep learning</topic><topic>Intelligent vehicles</topic><topic>learning</topic><topic>machine learning</topic><topic>neural networks</topic><topic>Simulators</topic><topic>State-of-the-art reviews</topic><topic>Task analysis</topic><topic>Training</topic><topic>Uncertainty</topic><topic>Vehicles</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Le Mero, Luc</creatorcontrib><creatorcontrib>Yi, Dewei</creatorcontrib><creatorcontrib>Dianati, Mehrdad</creatorcontrib><creatorcontrib>Mouzakitis, Alexandros</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Civil Engineering Abstracts</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE transactions on intelligent transportation systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Le Mero, Luc</au><au>Yi, Dewei</au><au>Dianati, Mehrdad</au><au>Mouzakitis, Alexandros</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Survey on Imitation Learning Techniques for End-to-End Autonomous Vehicles</atitle><jtitle>IEEE transactions on intelligent transportation systems</jtitle><stitle>TITS</stitle><date>2022-09-01</date><risdate>2022</risdate><volume>23</volume><issue>9</issue><spage>14128</spage><epage>14147</epage><pages>14128-14147</pages><issn>1524-9050</issn><eissn>1558-0016</eissn><coden>ITISFG</coden><abstract>The state-of-the-art decision and planning approaches for autonomous vehicles have moved away from manually designed systems, instead focusing on the utilisation of large-scale datasets of expert demonstration via Imitation Learning (IL). In this paper, we present a comprehensive review of IL approaches, primarily for the paradigm of end-to-end based systems in autonomous vehicles. We classify the literature into three distinct categories: 1) Behavioural Cloning (BC), 2) Direct Policy Learning (DPL) and 3) Inverse Reinforcement Learning (IRL). For each of these categories, the current state-of-the-art literature is comprehensively reviewed and summarised, with future directions of research identified to facilitate the development of imitation learning based systems for end-to-end autonomous vehicles. Due to the data-intensive nature of deep learning techniques, currently available datasets and simulators for end-to-end autonomous driving are also reviewed.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TITS.2022.3144867</doi><tpages>20</tpages><orcidid>https://orcid.org/0000-0001-5119-4499</orcidid><orcidid>https://orcid.org/0000-0003-1702-9136</orcidid><orcidid>https://orcid.org/0000-0002-6882-0166</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1524-9050 |
| ispartof | IEEE transactions on intelligent transportation systems, 2022-09, Vol.23 (9), p.14128-14147 |
| issn | 1524-9050 1558-0016 |
| language | eng |
| recordid | cdi_crossref_primary_10_1109_TITS_2022_3144867 |
| source | IEEE Electronic Library (IEL) |
| subjects | autonomous systems Autonomous vehicles Cameras Cloning Datasets Deep learning Intelligent vehicles learning machine learning neural networks Simulators State-of-the-art reviews Task analysis Training Uncertainty Vehicles |
| title | A Survey on Imitation Learning Techniques for End-to-End Autonomous Vehicles |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-16T04%3A20%3A30IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Survey%20on%20Imitation%20Learning%20Techniques%20for%20End-to-End%20Autonomous%20Vehicles&rft.jtitle=IEEE%20transactions%20on%20intelligent%20transportation%20systems&rft.au=Le%20Mero,%20Luc&rft.date=2022-09-01&rft.volume=23&rft.issue=9&rft.spage=14128&rft.epage=14147&rft.pages=14128-14147&rft.issn=1524-9050&rft.eissn=1558-0016&rft.coden=ITISFG&rft_id=info:doi/10.1109/TITS.2022.3144867&rft_dat=%3Cproquest_RIE%3E2714899330%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2714899330&rft_id=info:pmid/&rft_ieee_id=9700770&rfr_iscdi=true |