{"id":"https://openalex.org/W2909564046","doi":"https://doi.org/10.1109/iros.2018.8593410","title":"Composite Reinforcement Learning for Social Robot Navigation","display_name":"Composite Reinforcement Learning for Social Robot Navigation","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2909564046","doi":"https://doi.org/10.1109/iros.2018.8593410","mag":"2909564046"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2018.8593410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8593410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5017871472","display_name":"Pei-Huai Ciou","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Pei-Huai Ciou","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science and Information Engineering, National Taiwan University, 106 Taipei City, Da'an District, Taiwan (R.O.C.)"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science and Information Engineering, National Taiwan University, 106 Taipei City, Da'an District, Taiwan (R.O.C.)","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058704261","display_name":"Yu\u2010Ting Hsiao","orcid":"https://orcid.org/0000-0001-5739-7967"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Ting Hsiao","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science and Information Engineering, National Taiwan University, 106 Taipei City, Da'an District, Taiwan (R.O.C.)"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science and Information Engineering, National Taiwan University, 106 Taipei City, Da'an District, Taiwan (R.O.C.)","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009003857","display_name":"Zong-Ze Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Zong-Ze Wu","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science and Information Engineering, National Taiwan University, 106 Taipei City, Da'an District, Taiwan (R.O.C.)"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science and Information Engineering, National Taiwan University, 106 Taipei City, Da'an District, Taiwan (R.O.C.)","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044278469","display_name":"Shih-Huan Tseng","orcid":"https://orcid.org/0000-0003-3572-5274"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shih-Huan Tseng","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science and Information Engineering, National Taiwan University, 106 Taipei City, Da'an District, Taiwan (R.O.C.)"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science and Information Engineering, National Taiwan University, 106 Taipei City, Da'an District, Taiwan (R.O.C.)","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101925654","display_name":"Li\u2010Chen Fu","orcid":"https://orcid.org/0000-0002-6947-7646"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Li-Chen Fu","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science and Information Engineering, National Taiwan University, 106 Taipei City, Da'an District, Taiwan (R.O.C.)"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science and Information Engineering, National Taiwan University, 106 Taipei City, Da'an District, Taiwan (R.O.C.)","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5017871472"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":2.7055,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.89968181,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2553","last_page":"2558"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11500","display_name":"Evacuation and Crowd Dynamics","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.994700014591217,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7805014848709106},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.6896010637283325},{"id":"https://openalex.org/keywords/social-robot","display_name":"Social robot","score":0.6693990230560303},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6675134897232056},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5976727604866028},{"id":"https://openalex.org/keywords/mobile-robot-navigation","display_name":"Mobile robot navigation","score":0.5968685150146484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5748047828674316},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5056533813476562},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4986114501953125},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4891681969165802},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.46186524629592896},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4568721354007721},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.44386008381843567},{"id":"https://openalex.org/keywords/navigation-system","display_name":"Navigation system","score":0.43648388981819153},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4142058789730072},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.2837779223918915},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08909180760383606}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7805014848709106},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.6896010637283325},{"id":"https://openalex.org/C162947575","wikidata":"https://www.wikidata.org/wiki/Q2005645","display_name":"Social robot","level":5,"score":0.6693990230560303},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6675134897232056},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5976727604866028},{"id":"https://openalex.org/C26990112","wikidata":"https://www.wikidata.org/wiki/Q6887224","display_name":"Mobile robot navigation","level":5,"score":0.5968685150146484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5748047828674316},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5056533813476562},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4986114501953125},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4891681969165802},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.46186524629592896},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4568721354007721},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.44386008381843567},{"id":"https://openalex.org/C2777891301","wikidata":"https://www.wikidata.org/wiki/Q3475123","display_name":"Navigation system","level":2,"score":0.43648388981819153},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4142058789730072},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.2837779223918915},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08909180760383606},{"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros.2018.8593410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8593410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5600000023841858,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W86393979","https://openalex.org/W1963649406","https://openalex.org/W1989846948","https://openalex.org/W1993643921","https://openalex.org/W2045134164","https://openalex.org/W2057134775","https://openalex.org/W2079713137","https://openalex.org/W2129751259","https://openalex.org/W2165852544","https://openalex.org/W2167052694","https://openalex.org/W2217815767","https://openalex.org/W2522340145","https://openalex.org/W2552629326","https://openalex.org/W2565402511","https://openalex.org/W2565555125","https://openalex.org/W2604216058","https://openalex.org/W2618194107","https://openalex.org/W2962887844","https://openalex.org/W2963073167","https://openalex.org/W6731058215"],"related_works":["https://openalex.org/W2382313969","https://openalex.org/W2965558985","https://openalex.org/W2497892377","https://openalex.org/W2896858210","https://openalex.org/W2616297316","https://openalex.org/W2260064841","https://openalex.org/W2681895808","https://openalex.org/W2352681809","https://openalex.org/W2493438666","https://openalex.org/W2724299411"],"abstract_inverted_index":{"For":[0,124],"a":[1,17,90,135],"service":[2],"robot,":[3],"it":[4,43,76],"is":[5,44,68,77,212],"not":[6,160],"adequate":[7],"to":[8,47,54,71,80,137,150,166,171,180,185,202,214],"let":[9],"its":[10,168],"navigational":[11],"movement":[12],"be":[13],"based":[14,120],"only":[15,161],"on":[16,121],"single":[18],"metric,":[19],"such":[20],"as":[21,89],"minimum":[22],"distance":[23],"path.":[24],"In":[25,95],"the":[26,29,35,51,60,72,82,100,108,126,139,151,182,186,194,205],"environment":[27,145,206],"where":[28],"robot":[30,36,52,109,130],"and":[31,117,170,207],"humans":[32],"are":[33],"coexisting,":[34],"should":[37],"always":[38],"perform":[39,48,172,215],"social":[40,49,84,112,188,218],"navigation":[41,85,113],"whenever":[42],"moving.":[45],"However,":[46],"navigation,":[50],"needs":[53],"follow":[55],"certain":[56],"\u201csocial":[57],"norms\u201d":[58],"of":[59,128,141],"environment.":[61],"Recently,":[62],"deep":[63],"reinforcement":[64,102],"learning":[65,103,125],"(DRL)":[66],"technique":[67],"popularly":[69],"applied":[70],"robotics":[73],"field;":[74],"yet,":[75],"rarely":[78],"used":[79],"solve":[81],"mentioned":[83],"problem,":[86],"generally":[87],"deemed":[88],"high":[91],"dimension":[92],"complex":[93],"problem.":[94],"this":[96],"paper,":[97],"we":[98,133],"propose":[99],"composite":[101],"(CRL)":[104],"framework":[105],"under":[106],"which":[107],"learns":[110],"appropriate":[111],"with":[114],"sensor":[115],"input":[116],"reward":[118,183],"update":[119],"human":[122,129,178],"feedback.":[123],"aspect":[127],"interaction":[131],"(HRI),":[132],"provide":[134],"method":[136],"facilitate":[138],"training":[140],"DRL":[142],"in":[143,204],"real":[144],"by":[146],"incorporating":[147],"prior":[148],"knowledge":[149],"system.":[152],"It":[153],"turns":[154],"out":[155],"that":[156,193,209],"our":[157,210],"CRL":[158,196],"system":[159,197,211],"can":[162,198],"incrementally":[163],"learn":[164,200],"how":[165,201],"set":[167],"velocity":[169],"HRI":[173,216],"but":[174],"also":[175],"keep":[176],"collecting":[177],"feedback":[179],"synchronize":[181],"functions":[184],"current":[187],"norms.":[189],"The":[190],"experiments":[191],"show":[192,208],"proposed":[195],"safely":[199],"navigate":[203],"able":[213],"for":[217],"navigation.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}