{"id":"https://openalex.org/W4416748538","doi":"https://doi.org/10.1109/iros60139.2025.11246743","title":"Multi-UAV Formation Control with Static and Dynamic Obstacle Avoidance via Reinforcement Learning","display_name":"Multi-UAV Formation Control with Static and Dynamic Obstacle Avoidance via Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748538","doi":"https://doi.org/10.1109/iros60139.2025.11246743"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5120779233","display_name":"Yuqing Xie","orcid":"https://orcid.org/0000-0001-5720-6649"},"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":"Yuqing Xie","raw_affiliation_strings":["Tsinghua University,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054149338","display_name":"Chao Yu","orcid":"https://orcid.org/0000-0002-4279-2152"},"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":"Chao Yu","raw_affiliation_strings":["Tsinghua University,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hongzhi Zang","orcid":null},"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":"Hongzhi Zang","raw_affiliation_strings":["Tsinghua University,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080013325","display_name":"Feng Gao","orcid":"https://orcid.org/0000-0001-7374-9491"},"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":"Feng Gao","raw_affiliation_strings":["Tsinghua University,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078640314","display_name":"Wenhao Tang","orcid":"https://orcid.org/0000-0002-8835-9215"},"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":"Wenhao Tang","raw_affiliation_strings":["Tsinghua University,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042269156","display_name":"Jingyi Huang","orcid":"https://orcid.org/0000-0001-6715-6681"},"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":"Jingyi Huang","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100380042","display_name":"Jiayu Chen","orcid":"https://orcid.org/0000-0001-9396-0059"},"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":"Jiayu Chen","raw_affiliation_strings":["Tsinghua University,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102953539","display_name":"Botian Xu","orcid":"https://orcid.org/0000-0002-1460-7204"},"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":"Botian Xu","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022960717","display_name":"Yi Wu","orcid":"https://orcid.org/0000-0003-0365-5590"},"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":"Yi Wu","raw_affiliation_strings":["Tsinghua University,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115591843","display_name":"Yu Wang","orcid":"https://orcid.org/0009-0005-0661-311X"},"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":"Yu Wang","raw_affiliation_strings":["Tsinghua University,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5120779233"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":5.4779,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.96117355,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"20410","last_page":"20417"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.7172999978065491,"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":0.7172999978065491,"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/T11133","display_name":"UAV Applications and Optimization","score":0.0851999968290329,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.06650000065565109,"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":0.8029999732971191},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.7771000266075134},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.7585999965667725},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6352999806404114},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.6146000027656555},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5320000052452087},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5131000280380249},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.49559998512268066}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8029999732971191},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.7771000266075134},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.7585999965667725},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.723800003528595},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6352999806404114},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.6146000027656555},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5320000052452087},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5131000280380249},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.49559998512268066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46709999442100525},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4156999886035919},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.41200000047683716},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.34200000762939453},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3073999881744385},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.258899986743927}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":32,"referenced_works":["https://openalex.org/W1933691875","https://openalex.org/W1980755499","https://openalex.org/W2004531419","https://openalex.org/W2107292630","https://openalex.org/W2159411986","https://openalex.org/W2409707557","https://openalex.org/W2787958879","https://openalex.org/W2884236119","https://openalex.org/W2991677703","https://openalex.org/W3006868075","https://openalex.org/W3007080643","https://openalex.org/W3135496326","https://openalex.org/W3183413118","https://openalex.org/W3201530632","https://openalex.org/W3207644545","https://openalex.org/W3211667558","https://openalex.org/W4229007520","https://openalex.org/W4285102199","https://openalex.org/W4313855813","https://openalex.org/W4383108711","https://openalex.org/W4385451853","https://openalex.org/W4385490702","https://openalex.org/W4385834002","https://openalex.org/W4389925830","https://openalex.org/W4391019623","https://openalex.org/W4392169689","https://openalex.org/W4394862905","https://openalex.org/W4400678990","https://openalex.org/W4400810669","https://openalex.org/W4401415952","https://openalex.org/W4401416687","https://openalex.org/W4405013818"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"tackles":[2],"the":[3,28,35,40,56,153],"challenging":[4],"task":[5,29],"of":[6,27,136,155],"maintaining":[7],"formation":[8,74,108,140],"among":[9],"multiple":[10],"unmanned":[11],"aerial":[12],"vehicles":[13],"(UAVs)":[14],"while":[15],"avoiding":[16],"both":[17,119,129],"static":[18],"and":[19,39,76,91,110,121,131,139,145,160],"dynamic":[20],"obstacles":[21],"during":[22],"directed":[23,70],"flight.":[24],"The":[25,80],"complexity":[26],"arises":[30],"from":[31],"its":[32],"multi-objective":[33],"nature,":[34],"large":[36],"exploration":[37],"space,":[38],"sim-to-real":[41],"gap.":[42],"To":[43],"address":[44],"these":[45],"challenges,":[46],"we":[47,59,100],"propose":[48],"a":[49,63],"two-stage":[50],"reinforcement":[51],"learning":[52,94,158],"(RL)":[53],"pipeline.":[54],"In":[55],"first":[57],"stage,":[58],"randomly":[60],"search":[61],"for":[62],"reward":[64,85],"function":[65,86],"that":[66,125],"balances":[67],"key":[68],"objectives:":[69],"flight,":[71],"obstacle":[72,114,147],"avoidance,":[73],"maintenance,":[75],"zero-shot":[77],"policy":[78,97],"deployment.":[79],"second":[81],"stage":[82],"applies":[83],"this":[84],"to":[87,95,106,112],"more":[88],"complex":[89],"scenarios":[90],"utilizes":[92],"curriculum":[93,157],"accelerate":[96],"training.":[98],"Additionally,":[99],"incorporate":[101],"an":[102],"attention-based":[103,161],"observation":[104],"encoder":[105],"improve":[107],"maintenance":[109,141],"adaptability":[111],"varying":[113],"densities.":[115],"Experimental":[116],"results":[117],"in":[118,134],"simulation":[120],"real-world":[122],"environments":[123],"demonstrate":[124],"our":[126,156],"method":[127],"outperforms":[128],"planning-based":[130],"RL-based":[132],"baselines":[133],"terms":[135],"collision-free":[137],"rates":[138],"across":[142],"static,":[143],"dynamic,":[144],"mixed":[146],"scenarios.":[148],"Ablation":[149],"studies":[150],"further":[151],"confirm":[152],"effectiveness":[154],"strategy":[159],"encoder.":[162],"Animated":[163],"demonstrations":[164],"are":[165],"available":[166],"at:":[167],"https://sites.google.com/view/uav-formation-with-avoidance/.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-11-28T00:00:00"}