{"id":"https://openalex.org/W4413926242","doi":"https://doi.org/10.1109/icra55743.2025.11127461","title":"Safe Multi-Agent Navigation Guided by Goal-Conditioned Safe Reinforcement Learning","display_name":"Safe Multi-Agent Navigation Guided by Goal-Conditioned Safe Reinforcement Learning","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413926242","doi":"https://doi.org/10.1109/icra55743.2025.11127461"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.17813","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027754160","display_name":"Meng Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meng Feng","raw_affiliation_strings":["Massachusetts Institute of Technology,Computer Science and Artificial Intelligence Laboratory,Cambridge,01239"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Computer Science and Artificial Intelligence Laboratory,Cambridge,01239","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007436080","display_name":"Viraj Parimi","orcid":"https://orcid.org/0000-0002-7867-780X"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Viraj Parimi","raw_affiliation_strings":["Massachusetts Institute of Technology,Computer Science and Artificial Intelligence Laboratory,Cambridge,01239"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Computer Science and Artificial Intelligence Laboratory,Cambridge,01239","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101709620","display_name":"Brian Williams","orcid":"https://orcid.org/0000-0002-1057-3940"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Williams","raw_affiliation_strings":["Massachusetts Institute of Technology,Computer Science and Artificial Intelligence Laboratory,Cambridge,01239"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Computer Science and Artificial Intelligence Laboratory,Cambridge,01239","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":4.1535,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94741245,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"16869","last_page":"16875"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9713000059127808,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9713000059127808,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11622","display_name":"Maritime Navigation and Safety","score":0.9146999716758728,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8236594200134277},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6384714841842651},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5333663821220398},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.43556857109069824},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.41044217348098755},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29925715923309326},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19541919231414795}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8236594200134277},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6384714841842651},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5333663821220398},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43556857109069824},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.41044217348098755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29925715923309326},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19541919231414795},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icra55743.2025.11127461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2502.17813","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.17813","pdf_url":"https://arxiv.org/pdf/2502.17813","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.17813","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.17813","pdf_url":"https://arxiv.org/pdf/2502.17813","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1508965793","https://openalex.org/W1989407213","https://openalex.org/W2191404279","https://openalex.org/W2912063360","https://openalex.org/W2951360122","https://openalex.org/W2963099939","https://openalex.org/W2964997335","https://openalex.org/W3009928773","https://openalex.org/W4206497039","https://openalex.org/W4405785409"],"related_works":["https://openalex.org/W2371091044","https://openalex.org/W2171010636","https://openalex.org/W87513465","https://openalex.org/W2786230833","https://openalex.org/W1966803121","https://openalex.org/W2391666574","https://openalex.org/W3203256658","https://openalex.org/W2352650970","https://openalex.org/W1544514152","https://openalex.org/W1493952344"],"abstract_inverted_index":{"Safe":[0],"navigation":[1,95,198,218],"is":[2,39,271],"essential":[3],"for":[4,16,94,211,215,255],"autonomous":[5],"systems":[6],"operating":[7],"in":[8,57,231,250,258],"hazardous":[9,261],"environments.":[10,262],"Traditional":[11],"planning":[12,76,153],"methods":[13],"are":[14,147],"effective":[15],"solving":[17],"long-horizon":[18,54],"tasks":[19],"but":[20,50],"depend":[21],"on":[22,47],"the":[23,72,120,134,156,166,195,225,245],"availability":[24],"of":[25,41,74,227,247],"a":[26,67,91,115,130,183],"graph":[27,116,150,181],"representation":[28],"with":[29,117],"prede-fined":[30],"distance":[31,100,252],"metrics.":[32],"In":[33,62,200],"contrast,":[34],"safe":[35,78,87,186,197,229],"Reinforcement":[36],"Learning":[37],"(RL)":[38],"capable":[40],"learning":[42],"complex":[43,259],"behaviors":[44],"without":[45],"relying":[46],"manual":[48],"heuristics":[49],"fails":[51],"to":[52,89,163,193,207],"solve":[53],"tasks,":[55],"particularly":[56],"goal-conditioned":[58,83,92,228],"and":[59,77,86,101,128,152,170,182,260,265],"multi-agent":[60,196,232],"scenarios.":[61],"this":[63,178,191],"paper,":[64],"we":[65,189,202],"introduce":[66],"novel":[68],"method":[69,81,124,249],"that":[70,133],"integrates":[71],"strengths":[73],"both":[75],"RL.":[79],"Our":[80,263],"leverages":[82],"RL":[84,88,230],"(GCRL)":[85],"learn":[90],"policy":[93],"while":[96],"concurrently":[97],"estimating":[98],"cumulative":[99],"safety":[102],"levels":[103],"using":[104],"learned":[105,157],"value":[106,158],"functions":[107,159],"via":[108,155],"an":[109],"automated":[110],"self-training":[111],"algorithm.":[112],"By":[113],"constructing":[114],"states":[118],"from":[119],"replay":[121],"buffer,":[122],"our":[123,161,248],"prunes":[125],"unsafe":[126],"edges":[127],"generates":[129],"waypoint-based":[131,209],"plan":[132],"agent":[135],"then":[136],"executes":[137],"by":[138],"following":[139],"those":[140],"waypoints":[141],"sequentially":[142],"until":[143],"their":[144,216],"goal":[145],"locations":[146],"reached.":[148],"This":[149,222],"pruning":[151],"approach":[154,162,192],"allows":[160],"flexibly":[164],"balance":[165],"trade-off":[167],"between":[168],"faster":[169],"safer":[171,217],"routes":[172],"especially":[173],"over":[174,219],"extended":[175,220],"horizons.":[176,221],"Utilizing":[177],"unified":[179],"high-level":[180],"shared":[184],"low-level":[185],"GCRL":[187],"policy,":[188],"extend":[190],"address":[194],"problem.":[199],"particular,":[201],"leverage":[203],"Conflict-Based":[204],"Search":[205],"(CBS)":[206],"create":[208],"plans":[210],"multiple":[212,256],"agents":[213,257],"allowing":[214],"integration":[223],"enhances":[224],"scalability":[226],"scenarios,":[233],"enabling":[234],"efficient":[235],"coordination":[236],"among":[237],"agents.":[238],"Extensive":[239],"benchmarking":[240],"against":[241],"state-of-the-art":[242],"baselines":[243],"demonstrates":[244],"effectiveness":[246],"achieving":[251],"goals":[253],"safely":[254],"code":[264],"further":[266],"details":[267],"about":[268],"or":[269],"work":[270],"available":[272],"at":[273],"https://safe-visual-mapf-mers.csail.mit.edu/.":[274]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}