{"id":"https://openalex.org/W4388623345","doi":"https://doi.org/10.1109/ro-man57019.2023.10309591","title":"SocNavGym: A Reinforcement Learning Gym for Social Navigation","display_name":"SocNavGym: A Reinforcement Learning Gym for Social Navigation","publication_year":2023,"publication_date":"2023-08-28","ids":{"openalex":"https://openalex.org/W4388623345","doi":"https://doi.org/10.1109/ro-man57019.2023.10309591"},"language":"en","primary_location":{"id":"doi:10.1109/ro-man57019.2023.10309591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man57019.2023.10309591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","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/A5023381180","display_name":"Aditya Kapoor","orcid":"https://orcid.org/0000-0002-2539-2675"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aditya Kapoor","raw_affiliation_strings":["Tata Consultancy Services, Research &#x0026; Innovation,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tata Consultancy Services, Research &#x0026; Innovation,India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084909237","display_name":"Sushant Swamy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148827","display_name":"Birla Institute of Technology and Science, Pilani - Goa Campus","ror":"https://ror.org/046sh6j17","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210148827","https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sushant Swamy","raw_affiliation_strings":["Birla Institute of Technology and Science,Goa,India","Birla Institute of Technology and Science, Goa, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Birla Institute of Technology and Science,Goa,India","institution_ids":["https://openalex.org/I4210148827"]},{"raw_affiliation_string":"Birla Institute of Technology and Science, Goa, India","institution_ids":["https://openalex.org/I4210148827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022988401","display_name":"Pilar Bachiller","orcid":"https://orcid.org/0000-0003-0690-7749"},"institutions":[{"id":"https://openalex.org/I80606768","display_name":"Universidad de Extremadura","ror":"https://ror.org/0174shg90","country_code":"ES","type":"education","lineage":["https://openalex.org/I80606768"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Pilar Bachiller","raw_affiliation_strings":["Universidad de Extremadura,Computer and Communication Technology Department,Spain","Computer and Communication Technology Department, Universidad de Extremadura, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad de Extremadura,Computer and Communication Technology Department,Spain","institution_ids":["https://openalex.org/I80606768"]},{"raw_affiliation_string":"Computer and Communication Technology Department, Universidad de Extremadura, Spain","institution_ids":["https://openalex.org/I80606768"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078013087","display_name":"Luis J. Manso","orcid":"https://orcid.org/0000-0003-2616-1120"},"institutions":[{"id":"https://openalex.org/I169199633","display_name":"Aston University","ror":"https://ror.org/05j0ve876","country_code":"GB","type":"education","lineage":["https://openalex.org/I169199633"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Luis J. Manso","raw_affiliation_strings":["Aston University,Autonomous Robotics and Perception Laboratory,Computer Science Department,UK","Computer Science Department, Autonomous Robotics and Perception Laboratory, Aston University, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aston University,Autonomous Robotics and Perception Laboratory,Computer Science Department,UK","institution_ids":["https://openalex.org/I169199633"]},{"raw_affiliation_string":"Computer Science Department, Autonomous Robotics and Perception Laboratory, Aston University, UK","institution_ids":["https://openalex.org/I169199633"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4135,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.61112557,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2010","last_page":"2017"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10525","display_name":"Human-Automation Interaction and Safety","score":0.9973999857902527,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9965000152587891,"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":0.8499048948287964},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.740433394908905},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5492427945137024},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.5208590626716614},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4902506470680237},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4748418927192688},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47311660647392273},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46908465027809143},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44227468967437744},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4250746965408325},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4204387664794922},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3791496157646179}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8499048948287964},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.740433394908905},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5492427945137024},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5208590626716614},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4902506470680237},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4748418927192688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47311660647392273},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46908465027809143},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44227468967437744},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4250746965408325},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4204387664794922},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3791496157646179},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ro-man57019.2023.10309591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man57019.2023.10309591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W601228132","https://openalex.org/W2014718708","https://openalex.org/W2104866159","https://openalex.org/W2142943472","https://openalex.org/W2167052694","https://openalex.org/W2227909145","https://openalex.org/W2292220267","https://openalex.org/W2320277277","https://openalex.org/W2424778531","https://openalex.org/W2600643276","https://openalex.org/W2766373678","https://openalex.org/W2951799221","https://openalex.org/W2963001155","https://openalex.org/W2971426775","https://openalex.org/W2991653934","https://openalex.org/W3090725241","https://openalex.org/W3099342209","https://openalex.org/W3103340056","https://openalex.org/W3108686333","https://openalex.org/W3128195783","https://openalex.org/W3131623996","https://openalex.org/W3134972302","https://openalex.org/W3135883000","https://openalex.org/W3149166261","https://openalex.org/W3176999807","https://openalex.org/W3205400264","https://openalex.org/W4293245975","https://openalex.org/W4295719664","https://openalex.org/W4299364732","https://openalex.org/W4382762613","https://openalex.org/W4383109004","https://openalex.org/W6685444567","https://openalex.org/W6735650757","https://openalex.org/W6736278117","https://openalex.org/W6744862160","https://openalex.org/W6745935785","https://openalex.org/W6754379355","https://openalex.org/W6756486208","https://openalex.org/W6758065289","https://openalex.org/W6758701467","https://openalex.org/W6773108241","https://openalex.org/W6783171900","https://openalex.org/W6801905440","https://openalex.org/W6802933825","https://openalex.org/W6853961047"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W2087343574","https://openalex.org/W4246352526","https://openalex.org/W2121910908"],"abstract_inverted_index":{"It":[0,139],"is":[1,120,177],"essential":[2],"for":[3,98],"autonomous":[4],"robots":[5],"to":[6,38,124,131,144,155,162,179,194,200,230],"be":[7,35,128,142,192],"socially":[8],"compliant":[9],"while":[10],"navigating":[11],"in":[12,27,48,77,202,228],"human-populated":[13],"environments.":[14],"Machine":[15],"Learning":[16,21],"and,":[17],"especially,":[18],"Deep":[19],"Reinforcement":[20],"have":[22],"recently":[23],"gained":[24],"considerable":[25],"traction":[26],"the":[28,39,54,62,68,78,113,215,219,231],"field":[29],"of":[30,50,56,64,107,115,135,159],"Social":[31],"Navigation.":[32],"This":[33],"can":[34,102,127,140,191],"partially":[36],"attributed":[37],"resulting":[40],"policies":[41,182],"not":[42],"being":[43],"bound":[44],"by":[45,72],"human":[46],"limitations":[47],"terms":[49],"code":[51],"complexity":[52],"or":[53],"number":[55],"variables":[57],"that":[58,101,189,214],"are":[59,88],"handled.":[60],"Unfortunately,":[61],"lack":[63],"safety":[65],"guarantees":[66],"and":[67,111,126,149,154],"large":[69],"data":[70],"requirements":[71],"DRL":[73],"algorithms":[74],"make":[75],"learning":[76],"real":[79],"world":[80],"unfeasible.":[81],"To":[82],"bridge":[83],"this":[84],"gap,":[85],"simulation":[86,96],"environments":[87],"frequently":[89],"used.":[90],"We":[91],"propose":[92],"SocNavGym,":[93],"an":[94,196],"advanced":[95,225],"environment":[97],"social":[99,108,117,136,151,208,226],"navigation":[100,109,137],"generate":[103,132],"a":[104,157,170,174],"wide":[105],"variety":[106,158],"scenarios":[110],"facilitates":[112],"development":[114],"intelligent":[116],"agents.":[118],"SocNavGym":[119,190],"lightweight,":[121],"fast,":[122],"easy":[123],"use,":[125],"effortlessly":[129],"configured":[130,143],"different":[133,147],"types":[134],"scenarios.":[138,209],"also":[141,168,212],"work":[145],"with":[146],"hand-crafted":[148],"data-driven":[150,220],"reward":[152,221,233],"signals":[153],"yield":[156],"evaluation":[160],"metrics":[161],"benchmark":[163],"agents\u2019":[164],"performance.":[165],"Further,":[166],"we":[167],"provide":[169,187],"case":[171],"study":[172],"where":[173],"Dueling-DQN":[175],"agent":[176,197],"trained":[178,217],"learn":[180],"social-navigation":[181],"using":[183,218],"SocNavGym.":[184],"The":[185],"results":[186],"evidence":[188],"used":[193],"train":[195],"from":[198],"scratch":[199],"navigate":[201],"simple":[203],"as":[204,206],"well":[205],"complex":[207],"Our":[210],"experiments":[211],"show":[213],"agents":[216],"function":[222],"display":[223],"more":[224],"compliance":[227],"comparison":[229],"heuristic-based":[232],"function.":[234]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
