{"id":"https://openalex.org/W3205884910","doi":"https://doi.org/10.1109/robio54168.2021.9739519","title":"Human-Aware Robot Navigation via Reinforcement Learning with Hindsight Experience Replay and Curriculum Learning","display_name":"Human-Aware Robot Navigation via Reinforcement Learning with Hindsight Experience Replay and Curriculum Learning","publication_year":2021,"publication_date":"2021-12-27","ids":{"openalex":"https://openalex.org/W3205884910","doi":"https://doi.org/10.1109/robio54168.2021.9739519","mag":"3205884910"},"language":"en","primary_location":{"id":"doi:10.1109/robio54168.2021.9739519","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio54168.2021.9739519","pdf_url":null,"source":{"id":"https://openalex.org/S4363607846","display_name":"2021 IEEE International Conference on Robotics and Biomimetics (ROBIO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101829323","display_name":"Keyu Li","orcid":"https://orcid.org/0000-0001-8893-1261"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Keyu Li","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Electronic Engineering,China","Department of Electronic Engineering, The Chinese University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Electronic Engineering,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101138518","display_name":"Ye Lu","orcid":"https://orcid.org/0009-0009-4948-9680"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ye Lu","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Electronic Engineering,China","Department of Electronic Engineering, The Chinese University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Electronic Engineering,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021531143","display_name":"Max Q.\u2010H. Meng","orcid":"https://orcid.org/0000-0002-5255-5898"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Max Q.-H. Meng","raw_affiliation_strings":["Southern University of Science and Technology in Shenzhen,Department of Electronic and Electrical Engineering,China","Department of Electronic and Electrical Engineering, Southern University of Science and Technology in Shenzhen, China","Shenzhen Research Institute of the Chinese University of Hong Kong in Shenzhen, China","Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology in Shenzhen,Department of Electronic and Electrical Engineering,China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Department of Electronic and Electrical Engineering, Southern University of Science and Technology in Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Shenzhen Research Institute of the Chinese University of Hong Kong in Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"346","last_page":"351"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11500","display_name":"Evacuation and Crowd Dynamics","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11500","display_name":"Evacuation and Crowd Dynamics","score":0.9998999834060669,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.9847000241279602,"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/hindsight-bias","display_name":"Hindsight bias","score":0.8521032333374023},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7943235635757446},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7610235810279846},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6431574821472168},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.6126890182495117},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5969258546829224},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5601901412010193},{"id":"https://openalex.org/keywords/mobile-robot-navigation","display_name":"Mobile robot navigation","score":0.48665863275527954},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4735892415046692},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3589986562728882},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.2793046832084656},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11883023381233215}],"concepts":[{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.8521032333374023},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7943235635757446},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7610235810279846},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6431574821472168},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.6126890182495117},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5969258546829224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5601901412010193},{"id":"https://openalex.org/C26990112","wikidata":"https://www.wikidata.org/wiki/Q6887224","display_name":"Mobile robot navigation","level":5,"score":0.48665863275527954},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4735892415046692},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3589986562728882},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.2793046832084656},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11883023381233215},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio54168.2021.9739519","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio54168.2021.9739519","pdf_url":null,"source":{"id":"https://openalex.org/S4363607846","display_name":"2021 IEEE International Conference on Robotics and Biomimetics (ROBIO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338440","display_name":"HORIZON EUROPE Health","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W192919555","https://openalex.org/W1996785616","https://openalex.org/W2082585576","https://openalex.org/W2167052694","https://openalex.org/W2604216058","https://openalex.org/W2790644544","https://openalex.org/W2890001928","https://openalex.org/W2962853428","https://openalex.org/W2962954724","https://openalex.org/W2963809389","https://openalex.org/W2964001908","https://openalex.org/W2964319688","https://openalex.org/W3000915986","https://openalex.org/W3132973354","https://openalex.org/W3135181254","https://openalex.org/W3205841225","https://openalex.org/W4300799055","https://openalex.org/W6740801417","https://openalex.org/W6754379355","https://openalex.org/W6791585401"],"related_works":["https://openalex.org/W2093507260","https://openalex.org/W2122871747","https://openalex.org/W2562628082","https://openalex.org/W3114279067","https://openalex.org/W2378318959","https://openalex.org/W2083994890","https://openalex.org/W2369541203","https://openalex.org/W2360994936","https://openalex.org/W3081536868","https://openalex.org/W2523265608"],"abstract_inverted_index":{"In":[0,76],"recent":[1,45],"years,":[2],"the":[3,13,61,81,90,105,114,129,134],"growing":[4],"demand":[5],"for":[6],"more":[7],"intelligent":[8],"service":[9],"robots":[10],"is":[11,69,142],"pushing":[12],"development":[14],"of":[15,83,139],"mobile":[16],"robot":[17],"navigation":[18,53,98,108,131,160],"algorithms":[19],"to":[20,51,74,93,112,126],"allow":[21],"safe":[22],"and":[23,44,72,96,119],"efficient":[24,95],"operation":[25],"in":[26,38,55,66,99,133,144],"a":[27,56,100,145],"dense":[28,135],"crowd.":[29,136],"Reinforcement":[30],"learning":[31,121],"(RL)":[32],"approaches":[33],"have":[34],"shown":[35],"superior":[36],"ability":[37],"solving":[39],"sequential":[40],"decision":[41],"making":[42],"problems,":[43],"work":[46],"has":[47],"explored":[48],"its":[49],"potential":[50],"learn":[52,128,158],"polices":[54],"socially":[57],"compliant":[58],"manner.":[59],"However,":[60],"expert":[62],"demonstration":[63,91,164],"data":[64],"used":[65],"existing":[67],"methods":[68],"usually":[70],"expensive":[71],"difficult":[73],"obtain.":[75],"this":[77],"work,":[78],"we":[79,110],"consider":[80],"task":[82],"training":[84],"an":[85],"RL":[86,125],"agent":[87],"without":[88,161],"employing":[89],"data,":[92],"achieve":[94],"collision-free":[97],"crowded":[101],"environment.":[102,149],"To":[103],"address":[104],"sparse":[106],"reward":[107],"problem,":[109],"propose":[111],"incorporate":[113],"hindsight":[115],"experience":[116],"replay":[117],"(HER)":[118],"curriculum":[120],"(CL)":[122],"techniques":[123],"with":[124],"efficiently":[127],"optimal":[130],"policy":[132],"The":[137,150],"effectiveness":[138],"our":[140,154],"method":[141,155],"validated":[143],"simulated":[146],"crowd-robot":[147],"coexisting":[148],"results":[151],"demonstrate":[152],"that":[153],"can":[156],"effectively":[157],"human-aware":[159],"requiring":[162],"additional":[163],"data.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}