{"id":"https://openalex.org/W4405785370","doi":"https://doi.org/10.1109/iros58592.2024.10801487","title":"Synergistic Reinforcement and Imitation Learning for Vision-driven Autonomous Flight of UAV Along River","display_name":"Synergistic Reinforcement and Imitation Learning for Vision-driven Autonomous Flight of UAV Along River","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785370","doi":"https://doi.org/10.1109/iros58592.2024.10801487"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10801487","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801487","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092276634","display_name":"Zihan Wang","orcid":"https://orcid.org/0000-0001-7527-5955"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zihan Wang","raw_affiliation_strings":["Purdue University,School of Mechanical Engineering,West Lafayette,IN,USA,47907"],"affiliations":[{"raw_affiliation_string":"Purdue University,School of Mechanical Engineering,West Lafayette,IN,USA,47907","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114860351","display_name":"Jianwen Li","orcid":"https://orcid.org/0000-0003-3519-6405"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianwen Li","raw_affiliation_strings":["Purdue University,School of Mechanical Engineering,West Lafayette,IN,USA,47907"],"affiliations":[{"raw_affiliation_string":"Purdue University,School of Mechanical Engineering,West Lafayette,IN,USA,47907","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063519076","display_name":"Nina Mahmoudian","orcid":"https://orcid.org/0000-0002-3285-8234"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nina Mahmoudian","raw_affiliation_strings":["Purdue University,School of Mechanical Engineering,West Lafayette,IN,USA,47907"],"affiliations":[{"raw_affiliation_string":"Purdue University,School of Mechanical Engineering,West Lafayette,IN,USA,47907","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5092276634"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":1.0878,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.82632516,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"9976","last_page":"9982"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9825999736785889,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9760000109672546,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7545778155326843},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.6432323455810547},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6138414144515991},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4408406615257263},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3819545805454254},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3614858388900757},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09163668751716614}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7545778155326843},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6432323455810547},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6138414144515991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4408406615257263},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3819545805454254},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3614858388900757},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09163668751716614},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10801487","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801487","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1483373940","https://openalex.org/W1483681246","https://openalex.org/W2051228319","https://openalex.org/W2767506186","https://openalex.org/W2998396902","https://openalex.org/W3035624836","https://openalex.org/W3089695338","https://openalex.org/W3090027660","https://openalex.org/W3166974263","https://openalex.org/W3173218700","https://openalex.org/W3189981916","https://openalex.org/W3202883604","https://openalex.org/W4205966136","https://openalex.org/W4214864511","https://openalex.org/W4226257065","https://openalex.org/W4292262865","https://openalex.org/W4319788363","https://openalex.org/W4353056919","https://openalex.org/W4361280481","https://openalex.org/W4362683553","https://openalex.org/W6640174482","https://openalex.org/W6640963894","https://openalex.org/W6741002519","https://openalex.org/W6751285671","https://openalex.org/W6753526802","https://openalex.org/W6768977950","https://openalex.org/W6780559895","https://openalex.org/W6782364735","https://openalex.org/W6804601995","https://openalex.org/W6847056214","https://openalex.org/W6854886429"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Vision-driven":[0],"autonomous":[1],"flight":[2],"and":[3,19,101,152,161,170,192,196],"obstacle":[4],"avoidance":[5],"of":[6,36,149,182,188],"Unmanned":[7],"Aerial":[8],"Vehicles":[9],"(UAVs)":[10],"along":[11],"complex":[12],"riverine":[13,38,63],"environments":[14,198],"for":[15,49],"tasks":[16],"like":[17],"rescue":[18],"surveillance":[20],"requires":[21],"a":[22,59,84,95,157],"robust":[23],"navigation":[24,46,85],"policy,":[25],"which":[26,115],"is":[27,109],"yet":[28],"difficult":[29],"to":[30,33,132,140,142,165],"obtain":[31],"due":[32],"the":[34,44,50,73,118,127,134,147,180,183],"shortage":[35],"trainable":[37,60,197],"environment":[39,65],"simulators.":[40],"To":[41],"easily":[42],"verify":[43],"vision-based":[45],"controller":[47],"performance":[48,163],"river":[51],"following":[52],"task":[53,190],"before":[54],"real-world":[55],"deployment,":[56],"we":[57,71],"developed":[58],"photo-realistic":[61],"dynamics-free":[62],"simulation":[64],"using":[66],"Unity.":[67],"In":[68],"this":[69,88,154],"paper,":[70],"address":[72],"shortcomings":[74],"that":[75,98],"vanilla":[76],"Reinforcement":[77],"Learning":[78,103],"(RL)":[79],"algorithm":[80],"encounters":[81],"in":[82,186],"learning":[83],"policy":[86,120],"within":[87],"partially":[89],"observable,":[90],"non-Markovian":[91],"environment.":[92],"We":[93],"propose":[94],"synergistic":[96],"approach":[97],"integrates":[99],"RL":[100,119,128,151,171],"Imitation":[102],"(IL).":[104],"Initially,":[105],"an":[106],"IL":[107,135,175],"expert":[108],"trained":[110],"on":[111],"manually":[112],"collected":[113],"demonstrations,":[114],"then":[116],"guides":[117],"training":[121],"process.":[122],"Concurrently,":[123],"experiences":[124],"generated":[125],"by":[126],"agent":[129],"are":[130,199],"utilized":[131],"re-train":[133],"expert,":[136],"enhancing":[137],"its":[138],"ability":[139],"generalize":[141],"unseen":[143],"data.":[144],"By":[145],"leveraging":[146],"strengths":[148],"both":[150,189],"IL,":[153,169],"framework":[155],"achieves":[156],"faster":[158],"convergence":[159],"rate":[160],"higher":[162],"compared":[164],"pure":[166,168],"RL,":[167],"combined":[172],"with":[173],"static":[174],"algorithms.":[176],"The":[177,194],"results":[178],"validate":[179],"efficacy":[181],"proposed":[184],"method":[185],"terms":[187],"completion":[191],"efficiency.":[193],"code":[195],"available<sup":[200],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[201],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
