{"id":"https://openalex.org/W4411171604","doi":"https://doi.org/10.1109/tase.2025.3578326","title":"Confidence-Aware Robust Dynamical Distance Constrained Reinforcement Learning for Social Robot Navigation","display_name":"Confidence-Aware Robust Dynamical Distance Constrained Reinforcement Learning for Social Robot Navigation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411171604","doi":"https://doi.org/10.1109/tase.2025.3578326"},"language":"en","primary_location":{"id":"doi:10.1109/tase.2025.3578326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3578326","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automation Science and Engineering","raw_type":"journal-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/A5056762881","display_name":"Kai Zhu","orcid":"https://orcid.org/0000-0003-1272-4295"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kai Zhu","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029929713","display_name":"Tao Xue","orcid":"https://orcid.org/0000-0001-7499-6160"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Xue","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100375792","display_name":"Tao Zhang","orcid":"https://orcid.org/0000-0002-2980-6281"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Zhang","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056762881"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":4.2588,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.9430605,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"22","issue":null,"first_page":"16572","last_page":"16590"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9143000245094299,"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"}},"topics":[{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9143000245094299,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9046000242233276,"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":0.664150059223175},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5909154415130615},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.563194751739502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.537301242351532},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.45467644929885864},{"id":"https://openalex.org/keywords/social-robot","display_name":"Social robot","score":0.41721558570861816},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.415590763092041},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.33709317445755005}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.664150059223175},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5909154415130615},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.563194751739502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.537301242351532},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.45467644929885864},{"id":"https://openalex.org/C162947575","wikidata":"https://www.wikidata.org/wiki/Q2005645","display_name":"Social robot","level":5,"score":0.41721558570861816},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.415590763092041},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.33709317445755005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2025.3578326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3578326","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6399999856948853}],"awards":[{"id":"https://openalex.org/G4753124599","display_name":null,"funder_award_id":"U21B6002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8160902691","display_name":null,"funder_award_id":"2021ZD0110900","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W192919555","https://openalex.org/W1820081798","https://openalex.org/W1845972764","https://openalex.org/W2071005201","https://openalex.org/W2082585576","https://openalex.org/W2130750514","https://openalex.org/W2142943472","https://openalex.org/W2167052694","https://openalex.org/W2604216058","https://openalex.org/W2807455070","https://openalex.org/W2890001928","https://openalex.org/W2905385096","https://openalex.org/W2940129212","https://openalex.org/W2953931148","https://openalex.org/W2963575966","https://openalex.org/W2963809389","https://openalex.org/W2964040381","https://openalex.org/W2964319688","https://openalex.org/W2966735560","https://openalex.org/W2968104655","https://openalex.org/W2968547875","https://openalex.org/W3129432647","https://openalex.org/W3130520215","https://openalex.org/W3131623996","https://openalex.org/W3134972302","https://openalex.org/W3137313110","https://openalex.org/W3152777725","https://openalex.org/W3158253560","https://openalex.org/W3166557699","https://openalex.org/W3173331501","https://openalex.org/W3189576409","https://openalex.org/W3195968524","https://openalex.org/W3204195554","https://openalex.org/W3205043174","https://openalex.org/W3205400264","https://openalex.org/W3206025046","https://openalex.org/W4200273815","https://openalex.org/W4205377509","https://openalex.org/W4206497039","https://openalex.org/W4207010920","https://openalex.org/W4220817121","https://openalex.org/W4310297558","https://openalex.org/W4353056919","https://openalex.org/W4362014203","https://openalex.org/W4383109004","https://openalex.org/W4385767976","https://openalex.org/W4390224158","https://openalex.org/W4394698794","https://openalex.org/W6638088447","https://openalex.org/W6687063787","https://openalex.org/W6733118196","https://openalex.org/W6735677848","https://openalex.org/W6737893269","https://openalex.org/W6741002519","https://openalex.org/W6747790125","https://openalex.org/W6768831546","https://openalex.org/W6771280675","https://openalex.org/W6785517317","https://openalex.org/W6796876376","https://openalex.org/W6802038118","https://openalex.org/W6838566501","https://openalex.org/W6846050948","https://openalex.org/W6855512891","https://openalex.org/W6856924951"],"related_works":["https://openalex.org/W2122871747","https://openalex.org/W3114279067","https://openalex.org/W2171912896","https://openalex.org/W2765343127","https://openalex.org/W3134988587","https://openalex.org/W2133150803","https://openalex.org/W2175869054","https://openalex.org/W2724299411","https://openalex.org/W2164234705","https://openalex.org/W2175714038"],"abstract_inverted_index":{"Navigating":[0],"in":[1,93,170,200],"a":[2,11,37,49,56,111,119,192],"crowded":[3],"social":[4,27],"environment":[5,59],"without":[6],"collisions":[7],"or":[8],"freezing":[9],"is":[10],"crucial":[12],"and":[13,63,79,90,121,148,157,177,186,203],"challenging":[14],"task.":[15],"Recent":[16],"studies":[17],"have":[18],"demonstrated":[19],"considerable":[20],"success":[21,175],"using":[22],"Deep":[23],"Reinforcement":[24,68],"Learning":[25,69],"for":[26],"robot":[28],"navigation.":[29],"However,":[30],"the":[31,64,75,80,94,105,127,130,145,149,153,167,181],"lack":[32],"of":[33,66,77,82,129,144,152],"safety":[34,51,123,142,185],"guarantees":[35],"remains":[36],"prevalent":[38],"problem":[39],"among":[40],"these":[41],"methods.":[42,72],"To":[43],"address":[44],"this":[45],"limitation,":[46],"we":[47,85,103,134],"present":[48],"comprehensive":[50],"framework":[52],"that":[53,162,194],"builds":[54],"upon":[55],"novel":[57],"multi-agent":[58],"single-agent":[60],"decision-making":[61],"formulation":[62],"strengths":[65],"Safe":[67,137],"(Safe":[70],"RL)":[71],"First,":[73],"considering":[74],"uncertainty":[76,89],"pedestrians":[78],"inaccuracy":[81],"trajectory":[83],"predictions,":[84],"explicitly":[86],"embed":[87],"confidence-weighted":[88],"risk":[91,150],"measurement":[92],"interaction":[95],"graph":[96],"network":[97],"to":[98,139],"induce":[99],"adaptive":[100],"policies.":[101],"Next,":[102],"replace":[104],"state-wise":[106,141],"robust-form":[107],"unshaped":[108],"cost":[109],"with":[110],"cumulative":[112],"robust":[113],"dynamical":[114],"distance":[115],"constraint,":[116],"which":[117],"establishes":[118],"stronger":[120],"essential":[122],"objective":[124],"while":[125],"ensuring":[126],"invariance":[128],"optimal":[131],"policy.":[132],"Then":[133],"use":[135],"reachability-based":[136],"RL":[138],"ensure":[140],"assurance":[143],"feasible":[146],"part":[147],"minimization":[151],"infeasible":[154],"part.":[155],"Simulation":[156],"virtual-reality":[158],"evaluation":[159],"results":[160],"demonstrate":[161],"our":[163],"proposed":[164,189],"method":[165,190],"outperforms":[166],"state-of-the-art":[168],"methods":[169],"various":[171],"metrics,":[172],"such":[173],"as":[174],"rate":[176],"collision":[178,197],"energy,":[179],"achieving":[180],"best":[182],"trade-off":[183],"between":[184],"efficiency.":[187],"Our":[188],"yields":[191],"policy":[193],"exhibits":[195],"desired":[196],"avoidance":[198],"behavior":[199],"both":[201],"simulation":[202],"real-world":[204],"experiments.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}