{"id":"https://openalex.org/W4378191888","doi":"https://doi.org/10.1109/icarsc58346.2023.10129605","title":"Using Deep Reinforcement Learning for Navigation in Simulated Hallways","display_name":"Using Deep Reinforcement Learning for Navigation in Simulated Hallways","publication_year":2023,"publication_date":"2023-04-26","ids":{"openalex":"https://openalex.org/W4378191888","doi":"https://doi.org/10.1109/icarsc58346.2023.10129605"},"language":"en","primary_location":{"id":"doi:10.1109/icarsc58346.2023.10129605","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icarsc58346.2023.10129605","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/A5042705627","display_name":"Gon\u00e7alo Le\u00e3o","orcid":"https://orcid.org/0000-0002-9081-9268"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"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"]},{"id":"https://openalex.org/I4210166615","display_name":"INESC TEC","ror":"https://ror.org/05fa8ka61","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590","https://openalex.org/I4210166615"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Gon\u00e7alo Le\u00e3o","raw_affiliation_strings":["University of Porto,FEUP - Faculty of Engineering,Portugal","FEUP - Faculty of Engineering, University of Porto, Portugal","INESC TEC - INESC Technology and Science, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Porto,FEUP - Faculty of Engineering,Portugal","institution_ids":["https://openalex.org/I182534213"]},{"raw_affiliation_string":"FEUP - Faculty of Engineering, University of Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]},{"raw_affiliation_string":"INESC TEC - INESC Technology and Science, Portugal","institution_ids":["https://openalex.org/I121345201","https://openalex.org/I4210166615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101514397","display_name":"Filipe Almeida","orcid":"https://orcid.org/0009-0000-1129-2916"},"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":"Filipe Almeida","raw_affiliation_strings":["University of Porto,FEUP - Faculty of Engineering,Portugal","FEUP - Faculty of Engineering, University of Porto, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Porto,FEUP - Faculty of Engineering,Portugal","institution_ids":["https://openalex.org/I182534213"]},{"raw_affiliation_string":"FEUP - Faculty of Engineering, University of Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102516217","display_name":"Emanuel Trigo","orcid":null},"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":"Emanuel Trigo","raw_affiliation_strings":["University of Porto,FEUP - Faculty of Engineering,Portugal","FEUP - Faculty of Engineering, University of Porto, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Porto,FEUP - Faculty of Engineering,Portugal","institution_ids":["https://openalex.org/I182534213"]},{"raw_affiliation_string":"FEUP - Faculty of Engineering, University of Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052679687","display_name":"Henrique Ferreira","orcid":"https://orcid.org/0000-0003-3309-2098"},"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":"Henrique Ferreira","raw_affiliation_strings":["University of Porto,FEUP - Faculty of Engineering,Portugal","FEUP - Faculty of Engineering, University of Porto, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Porto,FEUP - Faculty of Engineering,Portugal","institution_ids":["https://openalex.org/I182534213"]},{"raw_affiliation_string":"FEUP - Faculty of Engineering, University of Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057871059","display_name":"Armando Sousa","orcid":"https://orcid.org/0000-0002-0317-4714"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"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"]},{"id":"https://openalex.org/I4210166615","display_name":"INESC TEC","ror":"https://ror.org/05fa8ka61","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590","https://openalex.org/I4210166615"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Armando Sousa","raw_affiliation_strings":["University of Porto,FEUP - Faculty of Engineering,Portugal","FEUP - Faculty of Engineering, University of Porto, Portugal","INESC TEC - INESC Technology and Science, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Porto,FEUP - Faculty of Engineering,Portugal","institution_ids":["https://openalex.org/I182534213"]},{"raw_affiliation_string":"FEUP - Faculty of Engineering, University of Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]},{"raw_affiliation_string":"INESC TEC - INESC Technology and Science, Portugal","institution_ids":["https://openalex.org/I121345201","https://openalex.org/I4210166615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089812166","display_name":"Lu\u00eds Paulo Reis","orcid":"https://orcid.org/0000-0002-4709-1718"},"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":"Lu\u00eds Paulo Reis","raw_affiliation_strings":["University of Porto,FEUP - Faculty of Engineering,Portugal","FEUP - Faculty of Engineering, University of Porto, Portugal","LIACC - Artificial Intelligence and Computer Science Laboratory, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Porto,FEUP - Faculty of Engineering,Portugal","institution_ids":["https://openalex.org/I182534213"]},{"raw_affiliation_string":"FEUP - Faculty of Engineering, University of Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]},{"raw_affiliation_string":"LIACC - Artificial Intelligence and Computer Science Laboratory, Portugal","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4895,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69615729,"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":"207","last_page":"213"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9998000264167786,"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/T12288","display_name":"Optimization and Search Problems","score":0.9965999722480774,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9038391709327698},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.708859920501709},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6937124729156494},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6609624624252319},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6391632556915283},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.48451942205429077},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4541262686252594},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4351939260959625},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4229668378829956},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4154525101184845},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35970258712768555},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.130240797996521},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.09415650367736816},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05679848790168762}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9038391709327698},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.708859920501709},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6937124729156494},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6609624624252319},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6391632556915283},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.48451942205429077},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4541262686252594},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4351939260959625},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4229668378829956},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4154525101184845},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35970258712768555},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.130240797996521},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.09415650367736816},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05679848790168762},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icarsc58346.2023.10129605","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icarsc58346.2023.10129605","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W123646622","https://openalex.org/W2145339207","https://openalex.org/W2148349146","https://openalex.org/W2781786131","https://openalex.org/W2963428623","https://openalex.org/W2973744167","https://openalex.org/W3100789280","https://openalex.org/W3196776285","https://openalex.org/W4205257762","https://openalex.org/W4224288782","https://openalex.org/W4229066299","https://openalex.org/W4282598608","https://openalex.org/W4309298539","https://openalex.org/W4309489570","https://openalex.org/W6682213442","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W3213722473","https://openalex.org/W2110944602","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W3009457412","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"Reinforcement":[0,29],"Learning":[1,30],"(RL)":[2],"is":[3,85],"a":[4,34,60],"well-suited":[5],"paradigm":[6],"to":[7,20,32,36,87],"train":[8,21,33],"robots":[9],"since":[10],"it":[11],"does":[12],"not":[13],"require":[14],"any":[15],"previous":[16],"information":[17],"or":[18],"database":[19],"an":[22],"agent.":[23],"This":[24],"paper":[25],"explores":[26],"using":[27,54,114],"Deep":[28,61],"(DRL)":[31],"robot":[35,84],"navigate":[37,88],"in":[38,89],"maps":[39,71,90],"containing":[40],"different":[41],"sorts":[42],"of":[43,70,120,130],"obstacles":[44],"and":[45,50,59,76,105,124],"which":[46],"emulate":[47],"hallways.":[48],"Training":[49],"testing":[51],"were":[52,72],"performed":[53],"the":[55,83,93,107,117,121,131],"Flatland":[56],"2D":[57],"simulator":[58],"Q-Network":[62],"(DQN)":[63],"provided":[64],"by":[65,98],"OpenAI":[66],"gym.":[67],"Different":[68],"sets":[69],"used":[73,95],"for":[74,96],"training":[75,97],"testing.":[77],"The":[78],"experiments":[79],"illustrate":[80],"how":[81],"well":[82,128],"able":[86],"distinct":[91],"from":[92],"ones":[94],"learning":[99],"new":[100],"behaviours":[101],"(namely":[102],"following":[103],"walls)":[104],"highlight":[106],"key":[108],"challenges":[109],"when":[110],"solving":[111],"this":[112],"task":[113],"DRL,":[115],"including":[116],"appropriate":[118],"definition":[119],"state":[122],"space":[123],"reward":[125],"function,":[126],"as":[127,129],"stopping":[132],"criteria":[133],"during":[134],"training.":[135]},"counts_by_year":[{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
