{"id":"https://openalex.org/W2993287881","doi":"https://doi.org/10.1109/kse.2019.8919269","title":"A Hierarchical Deep Deterministic Policy Gradients for Swarm Navigation","display_name":"A Hierarchical Deep Deterministic Policy Gradients for Swarm Navigation","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2993287881","doi":"https://doi.org/10.1109/kse.2019.8919269","mag":"2993287881"},"language":"en","primary_location":{"id":"doi:10.1109/kse.2019.8919269","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kse.2019.8919269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 11th International Conference on Knowledge and Systems Engineering (KSE)","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/A5000949562","display_name":"Hung The Nguyen","orcid":"https://orcid.org/0000-0003-0053-0274"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hung The Nguyen","raw_affiliation_strings":["MITI, MAST Institute of Information Technology, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"MITI, MAST Institute of Information Technology, Hanoi, Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042524342","display_name":"Tung Nguyen","orcid":"https://orcid.org/0000-0001-8437-1113"},"institutions":[{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tung Nguyen","raw_affiliation_strings":["School of Engineering and IT, University of New South Wales, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"School of Engineering and IT, University of New South Wales, Canberra, Australia","institution_ids":["https://openalex.org/I188329596","https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068818841","display_name":"Do-Van Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I177233841","display_name":"Vietnam National University, Hanoi","ror":"https://ror.org/02jmfj006","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Do-Van Nguyen","raw_affiliation_strings":["HMI Lab, Vietnam National University \u2013 UET, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"HMI Lab, Vietnam National University \u2013 UET, Hanoi, Vietnam","institution_ids":["https://openalex.org/I177233841"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113788877","display_name":"Thanh\u2010Ha Le","orcid":null},"institutions":[{"id":"https://openalex.org/I177233841","display_name":"Vietnam National University, Hanoi","ror":"https://ror.org/02jmfj006","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Thanh-Ha Le","raw_affiliation_strings":["HMI Lab, Vietnam National University \u2013 UET, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"HMI Lab, Vietnam National University \u2013 UET, Hanoi, Vietnam","institution_ids":["https://openalex.org/I177233841"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5000949562"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1768,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56130226,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9994999766349792,"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":0.9994999766349792,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9987000226974487,"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":0.9940000176429749,"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/swarm-behaviour","display_name":"Swarm behaviour","score":0.920659065246582},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7545853853225708},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.723697304725647},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5856136083602905},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5828889608383179},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.573502779006958},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5379671454429626},{"id":"https://openalex.org/keywords/swarm-robotics","display_name":"Swarm robotics","score":0.4978032112121582},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.49362123012542725},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36457759141921997},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.35642194747924805},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10670667886734009}],"concepts":[{"id":"https://openalex.org/C181335050","wikidata":"https://www.wikidata.org/wiki/Q14915018","display_name":"Swarm behaviour","level":2,"score":0.920659065246582},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7545853853225708},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.723697304725647},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5856136083602905},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5828889608383179},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.573502779006958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5379671454429626},{"id":"https://openalex.org/C169337768","wikidata":"https://www.wikidata.org/wiki/Q2446723","display_name":"Swarm robotics","level":3,"score":0.4978032112121582},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.49362123012542725},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36457759141921997},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.35642194747924805},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10670667886734009},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/kse.2019.8919269","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kse.2019.8919269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 11th International Conference on Knowledge and Systems Engineering (KSE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1506587822","https://openalex.org/W1526585386","https://openalex.org/W1542670833","https://openalex.org/W1981826826","https://openalex.org/W2009785399","https://openalex.org/W2039245308","https://openalex.org/W2083205586","https://openalex.org/W2099618002","https://openalex.org/W2107544712","https://openalex.org/W2113507916","https://openalex.org/W2115775310","https://openalex.org/W2119120935","https://openalex.org/W2121863487","https://openalex.org/W2144954802","https://openalex.org/W2145339207","https://openalex.org/W2147928602","https://openalex.org/W2173248099","https://openalex.org/W2567990716","https://openalex.org/W2586894404","https://openalex.org/W2594219313","https://openalex.org/W2734878594","https://openalex.org/W2791797404","https://openalex.org/W2887120114","https://openalex.org/W2897749494","https://openalex.org/W2899003551","https://openalex.org/W2963864421","https://openalex.org/W4214717370","https://openalex.org/W6631486384","https://openalex.org/W6676669290","https://openalex.org/W6684921986","https://openalex.org/W6741408367"],"related_works":["https://openalex.org/W1871202614","https://openalex.org/W4233987368","https://openalex.org/W1988876749","https://openalex.org/W65954170","https://openalex.org/W2518382144","https://openalex.org/W2350154411","https://openalex.org/W4229451618","https://openalex.org/W617387166","https://openalex.org/W2787547275","https://openalex.org/W1966857494"],"abstract_inverted_index":{"The":[0],"problem":[1],"of":[2,11,31,47,52,101,117,119,147,156,172,176,209,221,235],"swarm":[3,30,54,86,149,158],"navigation":[4,87,154],"recently":[5],"becomes":[6],"a":[7,29,130,180,215],"significant":[8],"topic":[9],"because":[10],"its":[12,222,225],"suitability":[13],"for":[14,85,241,267],"various":[15],"applications":[16],"like":[17],"search":[18],"and":[19,44,164,228,258,281],"rescue":[20],"with":[21,67,72,114,278],"autonomous":[22],"systems.":[23],"However,":[24],"when":[25,49,213],"it":[26,203],"comes":[27],"to":[28,36,63,76,95,105,139,192,206,255,262,271],"learning":[32,57,120],"agents,":[33],"one":[34,236],"has":[35],"face":[37],"the":[38,45,50,53,123,145,153,157,170,173,194,207,210,229,232,242,249,268,274,288],"challenges":[39],"from":[40,188],"huge":[41],"state":[42,107],"spaces":[43,108],"lack":[46],"scalability":[48,201],"size":[51,208],"increases.":[55],"Reinforcement":[56],"(RL)":[58],"approaches,":[59],"which":[60],"allow":[61,259],"agents":[62,121,291],"interact":[64],"not":[65,111],"only":[66,218],"each":[68,279],"other":[69,280],"but":[70,99],"also":[71],"their":[73,284],"operational":[74],"environment":[75,182,275],"obtain":[77],"optimal":[78,265],"policies,":[79],"are":[80,103,292],"considered":[81],"as":[82,202],"promising":[83],"techniques":[84],"problems.":[88],"Different":[89],"RL":[90],"algorithms":[91],"have":[92],"been":[93],"used":[94],"solve":[96],"these":[97,177],"problems":[98],"most":[100],"them":[102],"limited":[104],"discrete":[106],"and/or":[109],"do":[110],"scale":[112],"well":[113],"an":[115,264],"increase":[116],"number":[118],"in":[122,144,179],"swarm.":[124,211],"In":[125],"this":[126],"paper,":[127],"we":[128,167,217],"propose":[129],"Swarm":[131],"Hierarchical":[132],"Deep":[133],"Deterministic":[134],"Policy":[135],"Gradients":[136],"(SH-DDPGs)":[137],"framework":[138],"address":[140],"both":[141],"drawbacks":[142],"above":[143],"context":[146],"leader-follower":[148],"navigation.":[150],"By":[151],"decomposing":[152],"task":[155],"into":[159],"two":[160],"primitive":[161],"sub-tasks:":[162],"leader-following":[163],"collision":[165],"avoidance,":[166],"can":[168,238],"guarantee":[169],"convergence":[171],"training":[174,214],"processes":[175],"sub-tasks":[178],"continuous":[181],"before":[183],"combining":[184],"output":[185],"actions":[186],"produced":[187],"those":[189],"trained":[190,233],"models":[191],"complete":[193],"entire":[195],"task.":[196],"Moreover,":[197],"our":[198],"method":[199],"represents":[200],"is":[204,253],"independent":[205],"Firstly,":[212],"follower,":[216],"use":[219],"information":[220],"neighbors":[223],"within":[224],"local":[226],"view":[227],"leader.":[230],"Secondly,":[231],"model":[234],"follower":[237],"be":[239],"reapplied":[240],"remaining":[243],"followers.":[244],"Training":[245],"results":[246],"show":[247],"that":[248,287],"proposed":[250],"SH-DDPGs":[251],"algorithm":[252],"able":[254],"converge":[256],"quickly":[257],"followers":[260],"agent":[261],"learn":[263],"policy":[266],"whole":[269],"group":[270],"navigate":[272],"through":[273],"without":[276],"colliding":[277],"flexibly":[282],"optimize":[283],"formation":[285],"so":[286],"distances":[289],"among":[290],"minimized.":[293]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}