{"id":"https://openalex.org/W4389667429","doi":"https://doi.org/10.1109/iros55552.2023.10341948","title":"Risk-Sensitive Mobile Robot Navigation in Crowded Environment via Offline Reinforcement Learning","display_name":"Risk-Sensitive Mobile Robot Navigation in Crowded Environment via Offline Reinforcement Learning","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389667429","doi":"https://doi.org/10.1109/iros55552.2023.10341948"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10341948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341948","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5087969621","display_name":"Jiaxu Wu","orcid":"https://orcid.org/0000-0002-5978-6963"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jiaxu Wu","raw_affiliation_strings":["Graduate School of Engineering, The University of Tokyo,Department of Precision Engineering,Bunkyo-ku,Tokyo,Japan,113\u20138656"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, The University of Tokyo,Department of Precision Engineering,Bunkyo-ku,Tokyo,Japan,113\u20138656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100606470","display_name":"Yusheng Wang","orcid":"https://orcid.org/0000-0002-9743-4942"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusheng Wang","raw_affiliation_strings":["Graduate School of Engineering, The University of Tokyo,Department of Precision Engineering,Bunkyo-ku,Tokyo,Japan,113\u20138656"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, The University of Tokyo,Department of Precision Engineering,Bunkyo-ku,Tokyo,Japan,113\u20138656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064103302","display_name":"Hajime Asama","orcid":"https://orcid.org/0000-0002-9482-497X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hajime Asama","raw_affiliation_strings":["Graduate School of Engineering, The University of Tokyo,Department of Precision Engineering,Bunkyo-ku,Tokyo,Japan,113\u20138656"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, The University of Tokyo,Department of Precision Engineering,Bunkyo-ku,Tokyo,Japan,113\u20138656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056335309","display_name":"Qi An","orcid":"https://orcid.org/0000-0001-7641-2632"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Qi An","raw_affiliation_strings":["Graduate School of Frontier Sciences, The University of Tokyo,Department of Human and Engineered Environmental Studies,Kashiwa,Chiba,Japan,277\u20138563"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Frontier Sciences, The University of Tokyo,Department of Human and Engineered Environmental Studies,Kashiwa,Chiba,Japan,277\u20138563","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021260328","display_name":"Atsushi Yamashita","orcid":"https://orcid.org/0000-0003-1280-069X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Yamashita","raw_affiliation_strings":["Graduate School of Frontier Sciences, The University of Tokyo,Department of Human and Engineered Environmental Studies,Kashiwa,Chiba,Japan,277\u20138563"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Frontier Sciences, The University of Tokyo,Department of Human and Engineered Environmental Studies,Kashiwa,Chiba,Japan,277\u20138563","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.5437,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66502258,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"7456","last_page":"7462"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11500","display_name":"Evacuation and Crowd Dynamics","score":0.9997000098228455,"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":0.9997000098228455,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9973999857902527,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9916999936103821,"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":0.7902854681015015},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7686960697174072},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6012048721313477},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5992403030395508},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5925086140632629},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.5648356080055237},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5449811220169067},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.511765718460083},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4259503185749054},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.40709859132766724}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7902854681015015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7686960697174072},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6012048721313477},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5992403030395508},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5925086140632629},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.5648356080055237},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5449811220169067},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.511765718460083},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4259503185749054},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.40709859132766724},{"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/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10341948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341948","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W178419168","https://openalex.org/W1583837637","https://openalex.org/W2093846318","https://openalex.org/W2167052694","https://openalex.org/W2604216058","https://openalex.org/W2890001928","https://openalex.org/W3008967682","https://openalex.org/W3033324992","https://openalex.org/W3090935992","https://openalex.org/W3095493513","https://openalex.org/W3096954237","https://openalex.org/W3115517346","https://openalex.org/W3116651890","https://openalex.org/W3129986830","https://openalex.org/W3131623996","https://openalex.org/W3150718622","https://openalex.org/W3201700917","https://openalex.org/W3202169896","https://openalex.org/W4211070925","https://openalex.org/W4285117889","https://openalex.org/W4311992093","https://openalex.org/W6757469721","https://openalex.org/W6763486065","https://openalex.org/W6784643869","https://openalex.org/W6800973767","https://openalex.org/W6839116273"],"related_works":["https://openalex.org/W2770234245","https://openalex.org/W96612179","https://openalex.org/W4229499248","https://openalex.org/W2566006169","https://openalex.org/W1567818861","https://openalex.org/W2987774938","https://openalex.org/W4256492088","https://openalex.org/W632915154","https://openalex.org/W2055733372","https://openalex.org/W3022067003"],"abstract_inverted_index":{"Mobile":[0],"robot":[1,194],"navigation":[2,74,150,220,248],"in":[3,16,221],"a":[4,122,142,153,157,163,181,196,222],"human-populated":[5],"environment":[6],"has":[7,30,105,195],"been":[8,31],"of":[9,72,97,108,132,173,201,239],"great":[10],"interest":[11],"to":[12,20,33,39,52,58,63,115,184,188,198,218],"the":[13,41,60,70,73,78,82,86,98,102,106,130,133,170,174,186,189,193,202,206,213,226,231,236,240,247,251],"research":[14],"community":[15],"recent":[17],"years,":[18],"referred":[19],"as":[21,119,180],"crowd":[22],"navigation.":[23],"Currently,":[24],"offline":[25,134,148,175,227,242],"reinforcement":[26],"learning":[27],"(RL)-based":[28],"method":[29,215],"introduced":[32],"this":[34,139],"domain,":[35],"for":[36,65],"its":[37,56],"ability":[38],"alleviate":[40],"sim2real":[42],"gap":[43],"brought":[44],"by":[45,205],"online":[46],"RL":[47,135,149,176,243],"which":[48],"relies":[49],"on":[50],"simulators":[51],"execute":[53],"training,":[54],"and":[55,85,128,156,178,230],"scalability":[57],"use":[59],"same":[61],"dataset":[62,229],"train":[64],"differently":[66],"customized":[67],"rewards.":[68],"However,":[69],"performance":[71],"policy":[75,104,151,177,191],"suffered":[76],"from":[77,225],"distributional":[79],"shift":[80],"between":[81],"training":[83,99,207],"data":[84,100],"input":[87,95],"during":[88,137],"deployment,":[89,138],"since":[90],"when":[91,192],"it":[92],"gets":[93],"an":[94,110],"out":[96,200],"distribution,":[101],"learned":[103,168],"risk":[107,126,154,182,232],"choosing":[109],"erroneous":[111],"action":[112],"that":[113,146,212],"leads":[114],"catastrophic":[116],"failure":[117],"such":[118],"colliding":[120],"with":[121,152],"human.":[123],"To":[124],"realize":[125],"sensitivity":[127],"improve":[129],"safety":[131],"agent":[136,244],"work":[140],"proposes":[141],"multipolicy":[143],"control":[144,187],"framework":[145],"combines":[147],"detector":[155,183,233],"force-based":[158],"risk-avoiding":[159,190],"policy.":[160],"In":[161],"particular,":[162],"Lyapunov":[164],"density":[165],"model":[166],"is":[167],"using":[169],"latent":[171],"feature":[172],"works":[179],"switch":[185],"tendency":[197],"go":[199],"area":[203],"supported":[204],"data.":[208],"Experimental":[209],"results":[210],"showed":[211],"proposed":[214],"was":[216],"able":[217],"learn":[219],"crowded":[223],"scene":[224],"trajectory":[228],"substantially":[234],"reduces":[235],"collision":[237],"rate":[238],"vanilla":[241],"while":[245],"maintaining":[246],"efficiency":[249],"outperforming":[250],"state-of-the-art":[252],"methods.":[253]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}