{"id":"https://openalex.org/W4401416687","doi":"https://doi.org/10.1109/icra57147.2024.10611499","title":"Collision Avoidance and Navigation for a Quadrotor Swarm Using End-to-end Deep Reinforcement Learning","display_name":"Collision Avoidance and Navigation for a Quadrotor Swarm Using End-to-end Deep Reinforcement Learning","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401416687","doi":"https://doi.org/10.1109/icra57147.2024.10611499"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10611499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611499","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5011327397","display_name":"Zhehui Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhehui Huang","raw_affiliation_strings":["University of Southern California,Department of Computer Science,Los Angeles,CA,USA,90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Department of Computer Science,Los Angeles,CA,USA,90089","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101214576","display_name":"Zhaojing Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaojing Yang","raw_affiliation_strings":["University of Southern California,Department of Computer Science,Los Angeles,CA,USA,90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Department of Computer Science,Los Angeles,CA,USA,90089","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092206152","display_name":"Rahul Krupani","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rahul Krupani","raw_affiliation_strings":["University of Southern California,Department of Computer Science,Los Angeles,CA,USA,90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Department of Computer Science,Los Angeles,CA,USA,90089","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007877429","display_name":"Bask\u0131n \u015eenba\u015flar","orcid":"https://orcid.org/0000-0001-6424-0503"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bask\u0131n \u015eenba\u015flar","raw_affiliation_strings":["University of Southern California,Department of Computer Science,Los Angeles,CA,USA,90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Department of Computer Science,Los Angeles,CA,USA,90089","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037626146","display_name":"Sumeet Batra","orcid":"https://orcid.org/0009-0002-7403-0774"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sumeet Batra","raw_affiliation_strings":["University of Southern California,Department of Computer Science,Los Angeles,CA,USA,90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Department of Computer Science,Los Angeles,CA,USA,90089","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077367921","display_name":"Gaurav S. Sukhatme","orcid":"https://orcid.org/0000-0003-2408-474X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gaurav S. Sukhatme","raw_affiliation_strings":["University of Southern California,Department of Computer Science,Los Angeles,CA,USA,90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Department of Computer Science,Los Angeles,CA,USA,90089","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"300","last_page":"306"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11622","display_name":"Maritime Navigation and Safety","score":0.9799000024795532,"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/T11622","display_name":"Maritime Navigation and Safety","score":0.9799000024795532,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9596999883651733,"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/T11133","display_name":"UAV Applications and Optimization","score":0.9406999945640564,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/collision-avoidance","display_name":"Collision avoidance","score":0.7981018424034119},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7694826126098633},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6978528499603271},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6296625137329102},{"id":"https://openalex.org/keywords/swarm-behaviour","display_name":"Swarm behaviour","score":0.5167233347892761},{"id":"https://openalex.org/keywords/dead-end","display_name":"Dead end","score":0.47510990500450134},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4618358612060547},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.4078632891178131},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1646111011505127},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.12842506170272827},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.05598929524421692}],"concepts":[{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.7981018424034119},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7694826126098633},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6978528499603271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6296625137329102},{"id":"https://openalex.org/C181335050","wikidata":"https://www.wikidata.org/wiki/Q14915018","display_name":"Swarm behaviour","level":2,"score":0.5167233347892761},{"id":"https://openalex.org/C2986709869","wikidata":"https://www.wikidata.org/wiki/Q398589","display_name":"Dead end","level":3,"score":0.47510990500450134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4618358612060547},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.4078632891178131},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1646111011505127},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.12842506170272827},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.05598929524421692},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10611499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611499","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.550000011920929,"display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W178419168","https://openalex.org/W1518641734","https://openalex.org/W2072839015","https://openalex.org/W2082040042","https://openalex.org/W2109656638","https://openalex.org/W2162991084","https://openalex.org/W2191404279","https://openalex.org/W2573311857","https://openalex.org/W2588802774","https://openalex.org/W2736601468","https://openalex.org/W2912909357","https://openalex.org/W2963809389","https://openalex.org/W2972941110","https://openalex.org/W3003669699","https://openalex.org/W3021230401","https://openalex.org/W3025769768","https://openalex.org/W3099578266","https://openalex.org/W3103572865","https://openalex.org/W3115747676","https://openalex.org/W3124581711","https://openalex.org/W3164923438","https://openalex.org/W3183413118","https://openalex.org/W3184074274","https://openalex.org/W3199476173","https://openalex.org/W4229007520","https://openalex.org/W4251229830","https://openalex.org/W4285102199","https://openalex.org/W4308637970","https://openalex.org/W4313072389","https://openalex.org/W4321608219","https://openalex.org/W4381245790","https://openalex.org/W4381573173","https://openalex.org/W4383109303","https://openalex.org/W4385245566","https://openalex.org/W4401417407","https://openalex.org/W6629386063","https://openalex.org/W6732837357","https://openalex.org/W6741002519","https://openalex.org/W6780153092","https://openalex.org/W6784049536","https://openalex.org/W6801377368","https://openalex.org/W6854162696"],"related_works":["https://openalex.org/W3045722011","https://openalex.org/W3179968364","https://openalex.org/W3016188207","https://openalex.org/W4293268064","https://openalex.org/W4400488565","https://openalex.org/W2218833963","https://openalex.org/W2964709658","https://openalex.org/W4240479622","https://openalex.org/W4246369259","https://openalex.org/W2151749779"],"abstract_inverted_index":{"End-to-end":[0],"deep":[1],"reinforcement":[2],"learning":[3,144],"(DRL)":[4],"for":[5,125],"quadrotor":[6,36,74],"control":[7,73,148],"promises":[8],"many":[9],"benefits":[10],"\u2013":[11],"easy":[12],"deployment,":[13],"task":[14],"generalization":[15],"and":[16,86,112,146,172],"real-time":[17],"execution":[18],"capability.":[19],"Prior":[20],"end-to-end":[21,69,152],"DRL-based":[22],"methods":[23],"have":[24],"showcased":[25],"the":[26,44,49,57,91,109,116,136,141],"ability":[27],"to":[28,72,95,106,108,157,163],"deploy":[29],"learned":[30],"controllers":[31],"onto":[32],"single":[33],"quadrotors":[34],"or":[35],"teams":[37],"maneuvering":[38],"in":[39,76,98,170,179],"simple,":[40],"obstacle-free":[41],"environments.":[42,100],"However,":[43],"addition":[45],"of":[46,51,59,90,120,143],"obstacles":[47],"increases":[48],"number":[50],"possible":[52],"interactions":[53,114],"exponentially,":[54],"thereby":[55],"increasing":[56],"difficulty":[58],"training":[60],"RL":[61],"policies.":[62],"In":[63],"this":[64,121],"work,":[65],"we":[66],"propose":[67],"an":[68,103],"DRL":[70,153],"approach":[71,161],"swarms":[75],"environments":[77],"with":[78,151,166,175],"obstacles.":[79],"We":[80,101],"provide":[81],"our":[82],"agents":[83],"a":[84,87],"curriculum":[85],"replay":[88],"buffer":[89],"clipped":[92],"collision":[93],"episodes":[94],"improve":[96],"performance":[97],"obstacle-rich":[99],"implement":[102],"attention":[104],"mechanism":[105,122],"attend":[107],"neighbor":[110],"robots":[111,165,174],"obstacle":[113,168,177],"-":[115],"first":[117,137],"successful":[118],"demonstration":[119],"on":[123,129],"policies":[124,149],"swarm":[126],"behavior":[127],"deployed":[128],"severely":[130],"compute-constrained":[131],"hardware.":[132],"Our":[133,160],"work":[134,138],"is":[135],"that":[139,154],"demonstrates":[140],"possibility":[142],"neighbor-avoiding":[145],"obstacle-avoiding":[147],"trained":[150],"transfers":[155],"zero-shot":[156],"real":[158],"quadrotors.":[159],"scales":[162],"32":[164],"80%":[167],"density":[169,178],"simulation":[171],"8":[173],"20%":[176],"physical":[180],"deployment.":[181],"Website:":[182],"https://sites.google.com/view/obst-avoid-swarm-rl":[183]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}