{"id":"https://openalex.org/W2524264252","doi":"https://doi.org/10.1109/icra.2017.7989037","title":"Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning","display_name":"Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2524264252","doi":"https://doi.org/10.1109/icra.2017.7989037","mag":"2524264252"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2017.7989037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2017.7989037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1609.07845","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112212974","display_name":"Yu Fan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]},{"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":"Yu Fan Chen","raw_affiliation_strings":["Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, US","Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, 77 Massachusetts Ave., Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, US","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, 77 Massachusetts Ave., Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210143601","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103165484","display_name":"Miao Liu","orcid":"https://orcid.org/0009-0001-9103-696X"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miao Liu","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","[IBM Thomas J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"[IBM Thomas J. Watson Research Center, Yorktown Heights, NY 10598, USA]","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064513857","display_name":"Michael Everett","orcid":"https://orcid.org/0000-0001-9377-6745"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]},{"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":"Michael Everett","raw_affiliation_strings":["Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, USA","Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, 77 Massachusetts Ave., Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, 77 Massachusetts Ave., Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210143601","https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011665886","display_name":"Jonathan P. How","orcid":"https://orcid.org/0000-0001-8576-1930"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]},{"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":"Jonathan P. How","raw_affiliation_strings":["Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, USA","Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, 77 Massachusetts Ave., Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, 77 Massachusetts Ave., Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210143601","https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":45,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"285","last_page":"292"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9997000098228455,"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":0.9997000098228455,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9947999715805054,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/unobservable","display_name":"Unobservable","score":0.8884389400482178},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8748121857643127},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.7949910163879395},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7442430257797241},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.5811364054679871},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46026021242141724},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.44153568148612976},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4341808259487152},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4308396875858307},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.425432950258255},{"id":"https://openalex.org/keywords/reciprocal","display_name":"Reciprocal","score":0.42489105463027954},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41696101427078247},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20761451125144958},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08943906426429749},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.07085248827934265}],"concepts":[{"id":"https://openalex.org/C2780695315","wikidata":"https://www.wikidata.org/wiki/Q3799040","display_name":"Unobservable","level":2,"score":0.8884389400482178},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8748121857643127},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.7949910163879395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7442430257797241},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.5811364054679871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46026021242141724},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.44153568148612976},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4341808259487152},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4308396875858307},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.425432950258255},{"id":"https://openalex.org/C2777742833","wikidata":"https://www.wikidata.org/wiki/Q1964083","display_name":"Reciprocal","level":2,"score":0.42489105463027954},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41696101427078247},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20761451125144958},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08943906426429749},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.07085248827934265},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icra.2017.7989037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2017.7989037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1609.07845","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1609.07845","pdf_url":"https://arxiv.org/pdf/1609.07845","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"},{"id":"pmh:oai:dspace.mit.edu:1721.1/114720","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/114720","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv","raw_type":"http://purl.org/eprint/type/ConferencePaper"},{"id":"doi:10.48550/arxiv.1609.07845","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1609.07845","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:2524264252","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1609.07845","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1609.07845","pdf_url":"https://arxiv.org/pdf/1609.07845","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"id":"https://metadata.un.org/sdg/10","score":0.5099999904632568,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2524264252.pdf","grobid_xml":"https://content.openalex.org/works/W2524264252.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W192919555","https://openalex.org/W630739203","https://openalex.org/W1489244333","https://openalex.org/W1967907012","https://openalex.org/W1969622215","https://openalex.org/W1991425199","https://openalex.org/W1996785616","https://openalex.org/W2046431055","https://openalex.org/W2062731992","https://openalex.org/W2065427145","https://openalex.org/W2071005201","https://openalex.org/W2072195747","https://openalex.org/W2072956256","https://openalex.org/W2082585576","https://openalex.org/W2097639646","https://openalex.org/W2136207702","https://openalex.org/W2142943472","https://openalex.org/W2145339207","https://openalex.org/W2168424616","https://openalex.org/W2227909145","https://openalex.org/W2257979135","https://openalex.org/W2963454359","https://openalex.org/W6640325754"],"related_works":["https://openalex.org/W2963809389","https://openalex.org/W2981629587","https://openalex.org/W2145339207","https://openalex.org/W2058934927","https://openalex.org/W245307822","https://openalex.org/W3037099908","https://openalex.org/W2947253566","https://openalex.org/W2964319688","https://openalex.org/W2472522594","https://openalex.org/W2888820391","https://openalex.org/W2943945842","https://openalex.org/W3034159639","https://openalex.org/W2945637496","https://openalex.org/W2972878485","https://openalex.org/W3107802040","https://openalex.org/W2766566185","https://openalex.org/W2501721661","https://openalex.org/W3109221829","https://openalex.org/W2764095730","https://openalex.org/W3037791281"],"abstract_inverted_index":{"Finding":[0],"feasible,":[1],"collision-free":[2,122],"paths":[3,30,143],"for":[4,119],"multiagent":[5,51],"systems":[6],"can":[7,42],"be":[8,43],"challenging,":[9],"particularly":[10],"in":[11,130,142],"non-communicating":[12],"scenarios":[13],"where":[14],"each":[15],"agent's":[16,97],"intent":[17],"(e.g.":[18],"goal)":[19,150],"is":[20],"unobservable":[21],"to":[22,74,92,147],"the":[23,38,67,80,89,93,108,128,131,149],"others.":[24],"In":[25],"particular,":[26],"finding":[27,120],"time":[28,91,146],"efficient":[29,114],"often":[31],"requires":[32],"anticipating":[33],"interaction":[34,72],"with":[35,103,153],"neighboring":[36],"agents,":[37],"process":[39],"of":[40,60,107],"which":[41,64],"computationally":[44],"prohibitive.":[45],"This":[46],"work":[47],"presents":[48],"a":[49,57,84,121,159],"decentralized":[50],"collision":[52,156,161],"avoidance":[53,157,162],"algorithm":[54],"based":[55],"on":[56],"novel":[58],"application":[59],"deep":[61],"reinforcement":[62],"learning,":[63],"effectively":[65],"offloads":[66],"online":[68],"computation":[69],"(for":[70],"predicting":[71],"patterns)":[73],"an":[75,96],"offline":[76],"learning":[77],"procedure.":[78],"Specifically,":[79],"proposed":[81],"approach":[82],"develops":[83],"value":[85,109],"network":[86,110],"that":[87],"encodes":[88],"estimated":[90],"goal":[94],"given":[95],"joint":[98],"configuration":[99],"(positions":[100],"and":[101],"velocities)":[102],"its":[104],"neighbors.":[105],"Use":[106],"not":[111],"only":[112],"admits":[113],"(i.e.,":[115,145],"real-time":[116],"implementable)":[117],"queries":[118],"velocity":[123],"vector,":[124],"but":[125],"also":[126],"considers":[127],"uncertainty":[129],"other":[132],"agents'":[133],"motion.":[134],"Simulation":[135],"results":[136],"show":[137],"more":[138],"than":[139],"26%":[140],"improvement":[141],"quality":[144],"reach":[148],"when":[151],"compared":[152],"optimal":[154],"reciprocal":[155],"(ORCA),":[158],"state-of-the-art":[160],"strategy.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}