{"id":"https://openalex.org/W4411687934","doi":"https://doi.org/10.1109/lra.2025.3583620","title":"Online Planning for Multi-UAV Pursuit-Evasion in Unknown Environments Using Deep Reinforcement Learning","display_name":"Online Planning for Multi-UAV Pursuit-Evasion in Unknown Environments Using Deep Reinforcement Learning","publication_year":2025,"publication_date":"2025-06-26","ids":{"openalex":"https://openalex.org/W4411687934","doi":"https://doi.org/10.1109/lra.2025.3583620"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3583620","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2025.3583620","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/lra.2025.3583620","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100380044","display_name":"Jiayu Chen","orcid":"https://orcid.org/0000-0001-9472-3872"},"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":"Jiayu Chen","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9472-3872","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011646653","display_name":"Chao Yu","orcid":"https://orcid.org/0000-0001-6975-0158"},"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"],"raw_orcid":"https://orcid.org/0000-0001-6975-0158","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002272580","display_name":"Guosheng Li","orcid":"https://orcid.org/0000-0003-0676-2199"},"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":"Guosheng Li","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenhao Tang","orcid":"https://orcid.org/0009-0003-4126-2269"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Tang","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0003-4126-2269","affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112743737","display_name":"Shilong Ji","orcid":"https://orcid.org/0009-0005-0113-0485"},"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":"Shilong Ji","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-0113-0485","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102780588","display_name":"Xinyi Yang","orcid":"https://orcid.org/0000-0002-3775-4952"},"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":"Xinyi Yang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3775-4952","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Botian Xu","raw_affiliation_strings":["Beijing Zhongguancun Academy, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1460-7204","affiliations":[{"raw_affiliation_string":"Beijing Zhongguancun Academy, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023755254","display_name":"Huazhong Yang","orcid":"https://orcid.org/0000-0003-2421-353X"},"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":"Huazhong Yang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2421-353X","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100445061","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0001-6108-5157"},"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"],"raw_orcid":"https://orcid.org/0000-0001-6108-5157","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5100380044"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":7.9327,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.97532238,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"10","issue":"8","first_page":"8196","last_page":"8203"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9998999834060669,"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":0.9998999834060669,"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/T12158","display_name":"Guidance and Control Systems","score":0.9998999834060669,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9962000250816345,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7444199919700623},{"id":"https://openalex.org/keywords/evasion","display_name":"Evasion (ethics)","score":0.5453793406486511},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5331066846847534},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.47978025674819946},{"id":"https://openalex.org/keywords/pursuit-evasion","display_name":"Pursuit-evasion","score":0.46779686212539673},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4460318684577942},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2563930153846741},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.11920320987701416},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09080982208251953}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7444199919700623},{"id":"https://openalex.org/C2781251061","wikidata":"https://www.wikidata.org/wiki/Q5416089","display_name":"Evasion (ethics)","level":3,"score":0.5453793406486511},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5331066846847534},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47978025674819946},{"id":"https://openalex.org/C2778388243","wikidata":"https://www.wikidata.org/wiki/Q7261573","display_name":"Pursuit-evasion","level":2,"score":0.46779686212539673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4460318684577942},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2563930153846741},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.11920320987701416},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09080982208251953},{"id":"https://openalex.org/C203014093","wikidata":"https://www.wikidata.org/wiki/Q101929","display_name":"Immunology","level":1,"score":0.0},{"id":"https://openalex.org/C8891405","wikidata":"https://www.wikidata.org/wiki/Q1059","display_name":"Immune system","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3583620","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2025.3583620","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/lra.2025.3583620","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2025.3583620","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2045798616","display_name":null,"funder_award_id":"62325405","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5811851265","display_name":null,"funder_award_id":"62406159","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8583944549","display_name":null,"funder_award_id":"2024T170496","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1672238326","https://openalex.org/W1976698879","https://openalex.org/W2016437006","https://openalex.org/W2023775503","https://openalex.org/W2049287102","https://openalex.org/W2113286054","https://openalex.org/W2146682436","https://openalex.org/W2160484294","https://openalex.org/W2183469038","https://openalex.org/W2331855880","https://openalex.org/W2567355071","https://openalex.org/W2567811016","https://openalex.org/W2605102758","https://openalex.org/W2768629321","https://openalex.org/W2883532348","https://openalex.org/W2972273284","https://openalex.org/W3000179003","https://openalex.org/W3001813235","https://openalex.org/W3035829937","https://openalex.org/W3093345403","https://openalex.org/W3140147451","https://openalex.org/W3205953818","https://openalex.org/W3209101326","https://openalex.org/W4213246061","https://openalex.org/W4221155562","https://openalex.org/W4286748781","https://openalex.org/W4304480072","https://openalex.org/W4386295377","https://openalex.org/W4387245268","https://openalex.org/W4388634771","https://openalex.org/W4391019623","https://openalex.org/W4392843802","https://openalex.org/W4405014268","https://openalex.org/W4410852497","https://openalex.org/W6607789260","https://openalex.org/W6685444567","https://openalex.org/W6840380725"],"related_works":["https://openalex.org/W2057376130","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W2091926052","https://openalex.org/W2352258019","https://openalex.org/W4248803515","https://openalex.org/W3037033265","https://openalex.org/W2124277904","https://openalex.org/W4220855336"],"abstract_inverted_index":{"Multi-UAV":[0],"pursuit-evasion,":[1],"where":[2],"pursuers":[3],"aim":[4],"to":[5,33,44,48,54,92,133,180],"capture":[6,139],"evaders,":[7],"poses":[8],"a":[9,71,137,153,157,169],"key":[10],"challenge":[11],"for":[12,79,195],"UAV":[13],"swarm":[14],"intelligence.":[15],"Multi-agent":[16],"reinforcement":[17],"learning":[18],"(MARL)":[19],"has":[20],"demonstrated":[21],"potential":[22],"in":[23,82,96,129,168,198],"modeling":[24],"cooperative":[25,97],"behaviors,":[26],"but":[27],"most":[28],"RL-based":[29,185],"approaches":[30],"remain":[31],"constrained":[32],"simplifed":[34],"simulations":[35],"with":[36,136],"limited":[37],"dynamics":[38,145],"or":[39,61],"fxed":[40,64],"scenarios.":[41,120],"Previous":[42],"attempts":[43],"deploy":[45,162,183],"RL":[46],"policy":[47,98,116,155,164,186],"real-world":[49],"pursuit-evasion":[50,197],"are":[51,206],"largely":[52],"restricted":[53],"two-dimensional":[55],"scenarios,":[56,131],"such":[57],"as":[58],"ground":[59],"vehicles":[60],"UAVs":[62,148],"at":[63,208],"altitudes.":[65],"In":[66],"this":[67,175],"paper,":[68],"we":[69,151],"propose":[70],"novel":[72],"MARL-based":[73],"algorithm":[74],"that":[75],"learns":[76],"online":[77],"planning":[78],"multi-UAV":[80,196],"pursuitevasion":[81],"unknown":[83,199],"environments":[84],"(OPEN).":[85],"OPEN":[86,101],"introduces":[87],"an":[88,103,184],"evader":[89],"prediction-enhanced":[90],"network":[91],"tackle":[93],"partial":[94],"observability":[95],"learning.":[99],"Additionally,":[100],"proposes":[102],"adaptive":[104],"environment":[105],"generator":[106],"within":[107],"MARL":[108],"training,":[109,150],"enabling":[110],"higher":[111],"exploration":[112],"effciency":[113],"and":[114,161,182,190,204],"better":[115],"generalization":[117],"across":[118],"diverse":[119],"Simulations":[121],"show":[122],"our":[123,173],"method":[124],"signifcantly":[125],"outperforms":[126],"all":[127],"baselines":[128],"challenging":[130],"generalizing":[132],"unseen":[134],"scenarios":[135],"100%":[138],"rate.":[140],"Finally,":[141],"after":[142],"integrating":[143],"calibrated":[144],"models":[146],"of":[147],"into":[149],"derive":[152,181],"feasible":[154],"via":[156],"two-stage":[158],"reward":[159],"refnement":[160],"the":[163,177],"on":[165],"real":[166],"quadrotors":[167],"zero-shot":[170],"manner.":[171],"To":[172],"knowledge,":[174],"is":[176],"frst":[178],"work":[179],"using":[187],"collective":[188],"thrust":[189],"body":[191],"rates":[192],"control":[193],"commands":[194],"environments.":[200],"The":[201],"open-source":[202],"code":[203],"videos":[205],"available":[207],"https://sites.google.":[209],"com/view/pursuit-evasion-rl.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}