{"id":"https://openalex.org/W4411446374","doi":"https://doi.org/10.1109/lra.2025.3581430","title":"Learning Behaviours for Decentralised Multi-Robot Collision Avoidance in Constrained Pathways Using Curriculum Reinforcement Learning","display_name":"Learning Behaviours for Decentralised Multi-Robot Collision Avoidance in Constrained Pathways Using Curriculum Reinforcement Learning","publication_year":2025,"publication_date":"2025-06-19","ids":{"openalex":"https://openalex.org/W4411446374","doi":"https://doi.org/10.1109/lra.2025.3581430"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3581430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3581430","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063478434","display_name":"Md Mostafizur Rahman Komol","orcid":"https://orcid.org/0000-0001-9746-8109"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Md Mostafizur Rahman Komol","raw_affiliation_strings":["Robotics Groups, Data61, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Pullenvale, QLD, Australia","School of Electrical Engineering and Robotics, Queensland University of Technology, Brisbane, QLD, Australia"],"raw_orcid":"https://orcid.org/0000-0001-9746-8109","affiliations":[{"raw_affiliation_string":"Robotics Groups, Data61, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Pullenvale, QLD, Australia","institution_ids":["https://openalex.org/I1292875679"]},{"raw_affiliation_string":"School of Electrical Engineering and Robotics, Queensland University of Technology, Brisbane, QLD, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014231573","display_name":"Brendan Tidd","orcid":"https://orcid.org/0000-0002-7721-7799"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Brendan Tidd","raw_affiliation_strings":["Robotics Groups, Data61, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Pullenvale, QLD, Australia","Robotics Groups, Data61, Pullenvale, QLD, Australia"],"raw_orcid":"https://orcid.org/0000-0002-7721-7799","affiliations":[{"raw_affiliation_string":"Robotics Groups, Data61, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Pullenvale, QLD, Australia","institution_ids":["https://openalex.org/I1292875679"]},{"raw_affiliation_string":"Robotics Groups, Data61, Pullenvale, QLD, Australia","institution_ids":["https://openalex.org/I42894916"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065533636","display_name":"Will N. Browne","orcid":"https://orcid.org/0000-0001-8979-2224"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Will Browne","raw_affiliation_strings":["Robotics Groups, Data61, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Pullenvale, QLD, Australia","School of Electrical Engineering and Robotics, Queensland University of Technology, Brisbane, QLD, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8979-2224","affiliations":[{"raw_affiliation_string":"Robotics Groups, Data61, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Pullenvale, QLD, Australia","institution_ids":["https://openalex.org/I1292875679"]},{"raw_affiliation_string":"School of Electrical Engineering and Robotics, Queensland University of Technology, Brisbane, QLD, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078908478","display_name":"Fr\u00e9d\u00e9ric Maire","orcid":"https://orcid.org/0000-0002-6212-7651"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]},{"id":"https://openalex.org/I2801453606","display_name":"Australian Government","ror":"https://ror.org/0314h5y94","country_code":"AU","type":"government","lineage":["https://openalex.org/I2801453606"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Frederic Maire","raw_affiliation_strings":["School of Electrical Engineering and Robotics, Queensland University of Technology, Brisbane, QLD, Australia","Commonwealth Scientific and Industrial Research Organisation (CSIRO), Australian Government, Australia"],"raw_orcid":"https://orcid.org/0000-0002-6212-7651","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Robotics, Queensland University of Technology, Brisbane, QLD, Australia","institution_ids":["https://openalex.org/I160993911"]},{"raw_affiliation_string":"Commonwealth Scientific and Industrial Research Organisation (CSIRO), Australian Government, Australia","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I2801453606"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076006629","display_name":"Jason Williams","orcid":"https://orcid.org/0000-0002-2416-075X"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jason Williams","raw_affiliation_strings":["Robotics Groups, Data61, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Pullenvale, QLD, Australia","Robotics Groups, Data61, Pullenvale, QLD, Australia"],"raw_orcid":"https://orcid.org/0000-0002-2416-075X","affiliations":[{"raw_affiliation_string":"Robotics Groups, Data61, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Pullenvale, QLD, Australia","institution_ids":["https://openalex.org/I1292875679"]},{"raw_affiliation_string":"Robotics Groups, Data61, Pullenvale, QLD, Australia","institution_ids":["https://openalex.org/I42894916"]}]},{"author_position":"last","author":{"id":null,"display_name":"David Howard","orcid":"https://orcid.org/0000-0002-5012-7224"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David Howard","raw_affiliation_strings":["Robotics Groups, Data61, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Pullenvale, QLD, Australia","Robotics Groups, Data61, Pullenvale, QLD, Australia"],"raw_orcid":"https://orcid.org/0000-0002-5012-7224","affiliations":[{"raw_affiliation_string":"Robotics Groups, Data61, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Pullenvale, QLD, Australia","institution_ids":["https://openalex.org/I1292875679"]},{"raw_affiliation_string":"Robotics Groups, Data61, Pullenvale, QLD, Australia","institution_ids":["https://openalex.org/I42894916"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.9129,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.94775935,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"10","issue":"8","first_page":"8538","last_page":"8545"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.998199999332428,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.998199999332428,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9937999844551086,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.8753275871276855},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.7914952039718628},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.529769241809845},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4820295572280884},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.44707152247428894},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.43020182847976685},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.42140671610832214},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3817983567714691},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3310825824737549},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.30987799167633057},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.09889629483222961},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.09549540281295776},{"id":"https://openalex.org/keywords/pedagogy","display_name":"Pedagogy","score":0.08774769306182861}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8753275871276855},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.7914952039718628},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.529769241809845},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4820295572280884},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.44707152247428894},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.43020182847976685},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.42140671610832214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3817983567714691},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3310825824737549},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.30987799167633057},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.09889629483222961},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09549540281295776},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.08774769306182861}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3581430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3581430","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5899999737739563}],"awards":[],"funders":[{"id":"https://openalex.org/F2991578505","display_name":"Centre for Robotics, Queensland University of Technology","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2006455928","https://openalex.org/W3031798691","https://openalex.org/W4360825542","https://openalex.org/W4378770523","https://openalex.org/W4402742723","https://openalex.org/W4403555635","https://openalex.org/W4405786457","https://openalex.org/W6605295560","https://openalex.org/W6640174482","https://openalex.org/W6677443899","https://openalex.org/W6679000354","https://openalex.org/W6683616146","https://openalex.org/W6757093819","https://openalex.org/W6758518918","https://openalex.org/W6775683342","https://openalex.org/W6784493787","https://openalex.org/W6787618195","https://openalex.org/W6790442149","https://openalex.org/W6792087746","https://openalex.org/W6803127796","https://openalex.org/W6803458320","https://openalex.org/W6844303096","https://openalex.org/W6852597288","https://openalex.org/W6873058007","https://openalex.org/W7058486760"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W1819938260","https://openalex.org/W2340892746","https://openalex.org/W3163022373","https://openalex.org/W2742483371","https://openalex.org/W3005999311"],"abstract_inverted_index":{"Mobile":[0],"robot":[1,56],"teams":[2],"often":[3],"require":[4],"decentralised":[5],"autonomous":[6],"navigation":[7,20],"through":[8,57,70],"narrow":[9,58],"gaps":[10],"in":[11,29,52,143,150,158,165],"limited":[12],"communication":[13],"environments":[14],"(e.g.,":[15],"underground":[16],"search-and-rescue":[17],"operations).":[18],"Existing":[19],"approaches":[21],"exhibit":[22],"suboptimal":[23],"performance":[24],"for":[25,68],"avoiding":[26],"multi-robot":[27,128],"collisions":[28],"such":[30],"bottlenecks":[31],"due":[32,83],"to":[33,36,64,84,107,134,156],"an":[34,122],"inability":[35],"address":[37],"the":[38,42,85],"dynamic":[39],"nature":[40],"of":[41,89],"robots.":[43],"Initial":[44],"work":[45],"utilising":[46],"reinforcement":[47,74,98],"learning":[48,75,99],"has":[49],"demonstrated":[50],"success":[51],"navigating":[53,69],"a":[54,95,140],"single":[55],"gaps.":[59],"However,":[60],"when":[61],"training":[62,119],"agents":[63],"produce":[65],"give-way":[66,144],"behaviour":[67,106,145],"constrained":[71],"gaps,":[72],"end-to-end":[73],"using":[76],"simple":[77,180],"rewards":[78],"suffers":[79],"from":[80],"slow":[81],"convergence":[82],"increased":[86],"search":[87],"space":[88],"viable":[90],"policies.":[91],"This":[92,125],"paper":[93],"introduces":[94],"novel":[96],"curriculum":[97],"framework,":[100],"incorporating":[101,160],"amulti-robot":[102],"bootstrap":[103],"curriculumwith":[104],"preprogrammed":[105],"guide":[108],"initial":[109],"policy":[110],"formation,":[111],"subsequently":[112],"refined":[113],"by":[114],"agap":[115],"curriculumthat":[116],"progressively":[117],"reduces":[118],"complexity":[120],"towards":[121],"optimal":[123],"policy.":[124],"framework":[126],"learns":[127],"interaction":[129,187],"behaviours,":[130],"which":[131],"are":[132],"impractical":[133],"program":[135],"manually.":[136],"Our":[137],"model":[138],"achieves":[139],"99%":[141],"success-rate":[142,154],"generation":[146],"without":[147],"inter-agent":[148],"communications":[149],"high-fidelity":[151],"simulations.":[152],"The":[153,179],"reduced":[155],"73%":[157],"simulations":[159],"noisy":[161],"sensors,":[162],"and":[163,176],"60%":[164],"field-robot":[166],"tests,":[167],"substantiating":[168],"our":[169],"model's":[170],"practical":[171],"viability":[172],"despite":[173],"sensor":[174],"noise":[175],"real-world":[177],"uncertainties.":[178],"benchmark":[181],"methods":[182],"lack":[183],"efficiency":[184],"with":[185],"basic":[186],"behaviours.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}