{"id":"https://openalex.org/W4378191572","doi":"https://doi.org/10.1109/icarsc58346.2023.10129591","title":"A Reinforcement Learning Based Online Coverage Path Planning Algorithm","display_name":"A Reinforcement Learning Based Online Coverage Path Planning Algorithm","publication_year":2023,"publication_date":"2023-04-26","ids":{"openalex":"https://openalex.org/W4378191572","doi":"https://doi.org/10.1109/icarsc58346.2023.10129591"},"language":"en","primary_location":{"id":"doi:10.1109/icarsc58346.2023.10129591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarsc58346.2023.10129591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)","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/A5103023775","display_name":"Jos\u00e9 Pedro Carvalho","orcid":"https://orcid.org/0009-0008-3416-5694"},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Jos\u00e9 Pedro Carvalho","raw_affiliation_strings":["Universidade do Porto,Faculdade de Engenharia,SYSTEC-ARISE & ECE Department"],"affiliations":[{"raw_affiliation_string":"Universidade do Porto,Faculdade de Engenharia,SYSTEC-ARISE & ECE Department","institution_ids":["https://openalex.org/I182534213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069883451","display_name":"A. Pedro Aguiar","orcid":"https://orcid.org/0000-0001-7105-0505"},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"A. Pedro Aguiar","raw_affiliation_strings":["Universidade do Porto,Faculdade de Engenharia,SYSTEC-ARISE & ECE Department"],"affiliations":[{"raw_affiliation_string":"Universidade do Porto,Faculdade de Engenharia,SYSTEC-ARISE & ECE Department","institution_ids":["https://openalex.org/I182534213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103023775"],"corresponding_institution_ids":["https://openalex.org/I182534213"],"apc_list":null,"apc_paid":null,"fwci":1.2347,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.81294821,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"81","last_page":"86"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9914000034332275,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9661999940872192,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8649821281433105},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7435451745986938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7383390665054321},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.6224734783172607},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6193121075630188},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5672442317008972},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5433507561683655},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5282387137413025},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.523621141910553},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.52309250831604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5205653309822083},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5002110004425049},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.45861271023750305},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.43495553731918335},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.434654176235199},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.40594425797462463},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3695496916770935},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12861239910125732}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8649821281433105},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7435451745986938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7383390665054321},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.6224734783172607},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6193121075630188},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5672442317008972},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5433507561683655},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5282387137413025},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.523621141910553},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.52309250831604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5205653309822083},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5002110004425049},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.45861271023750305},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.43495553731918335},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.434654176235199},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.40594425797462463},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3695496916770935},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12861239910125732},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icarsc58346.2023.10129591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarsc58346.2023.10129591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1544032329","https://openalex.org/W2019738489","https://openalex.org/W2131600418","https://openalex.org/W2145339207","https://openalex.org/W2168359464","https://openalex.org/W2257979135","https://openalex.org/W2464973370","https://openalex.org/W2596585349","https://openalex.org/W2761873684","https://openalex.org/W2775495931","https://openalex.org/W2789773866","https://openalex.org/W2902907165","https://openalex.org/W3005340481","https://openalex.org/W3093365091","https://openalex.org/W3119335594","https://openalex.org/W3197167612","https://openalex.org/W3206820021","https://openalex.org/W4214717370","https://openalex.org/W4220829754","https://openalex.org/W6677067356","https://openalex.org/W6803126622"],"related_works":["https://openalex.org/W2808418668","https://openalex.org/W2357975469","https://openalex.org/W2101748387","https://openalex.org/W3096874164","https://openalex.org/W2807018115","https://openalex.org/W4388236136","https://openalex.org/W4281812492","https://openalex.org/W3105579180","https://openalex.org/W4200250224","https://openalex.org/W2970347269"],"abstract_inverted_index":{"Coverage":[0],"Path":[1],"Planning":[2],"(CPP)":[3],"is":[4,30,91,113,161,166],"a":[5,81,86,94,106,110,119,195],"common":[6],"task":[7,29,183],"in":[8,12,168],"robotics":[9],"that":[10,16,104,177],"consists":[11],"computing":[13],"collision-free":[14],"paths":[15],"pass":[17],"through":[18],"all":[19],"the":[20,39,57,123,131,136,139,148,155,182],"specified":[21],"points":[22],"from":[23],"an":[24,51,69,101],"area":[25],"of":[26,59,125,138,144,198],"interest.":[27],"This":[28,66],"known":[31],"to":[32,54,121,134],"be":[33],"NP-Hard,":[34],"and":[35,62,100,146,153,163,194],"increasingly":[36],"complex":[37],"when":[38],"agent":[40],"relies":[41],"exclusively":[42],"on":[43,74],"sensor":[44],"information.":[45],"Reinforcement":[46],"Learning":[47,78,174],"methods":[48],"appear":[49],"as":[50,93],"interesting":[52],"solution":[53],"deal":[55],"with":[56,85,109,128,184,188],"complexity":[58],"this":[60],"problem":[61,90],"obtain":[63],"efficient":[64],"solutions.":[65],"paper":[67],"presents":[68],"online":[70],"CPP":[71],"algorithm":[72,133,160],"based":[73],"Tabular":[75],"Temporal":[76,172],"Difference":[77,173],"methods,":[79,175],"for":[80],"generic":[82],"robotic":[83],"platform":[84],"ranging":[87],"sensor.":[88],"The":[89,115,158],"formulated":[92],"Partially":[95],"Observed":[96],"Markov":[97],"Decision":[98],"Process":[99],"RL":[102],"scheme":[103],"includes":[105],"modified":[107],"policy":[108,156],"heuristic":[111],"method":[112],"proposed.":[114],"presented":[116],"approach":[117],"provides":[118],"way":[120],"mix":[122],"concepts":[124],"classical":[126],"algorithms":[127],"RL,":[129],"enabling":[130],"tabular":[132],"overcome":[135],"shortcomings":[137],"inherent":[140],"large":[141],"state":[142],"space":[143],"CPP,":[145],"accelerated":[147],"training":[149],"process":[150],"by":[151],"optimizing":[152],"reducing":[154],"space.":[157],"proposed":[159],"tested":[162],"its":[164],"performance":[165],"compared":[167],"simulation":[169],"using":[170],"different":[171,189],"showing":[176],"it":[178],"can":[179],"efficiently":[180],"complete":[181],"no":[185],"prior":[186],"information,":[187],"map":[190],"sizes,":[191],"starting":[192],"positions,":[193],"random":[196],"number":[197],"obstacles.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}