{"id":"https://openalex.org/W4409426579","doi":"https://doi.org/10.1109/lra.2025.3560830","title":"Safe Multi-Agent Reinforcement Learning for Behavior-Based Cooperative Navigation","display_name":"Safe Multi-Agent Reinforcement Learning for Behavior-Based Cooperative Navigation","publication_year":2025,"publication_date":"2025-04-14","ids":{"openalex":"https://openalex.org/W4409426579","doi":"https://doi.org/10.1109/lra.2025.3560830"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3560830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3560830","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":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/A5069650777","display_name":"Murad Dawood","orcid":null},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Murad Dawood","raw_affiliation_strings":["Humanoid Robots Lab, University of Bonn, Bonn, Germany","Humanoid Robots Lab, University of Bonn, Germany"],"affiliations":[{"raw_affiliation_string":"Humanoid Robots Lab, University of Bonn, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]},{"raw_affiliation_string":"Humanoid Robots Lab, University of Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079893673","display_name":"Sicong Pan","orcid":"https://orcid.org/0000-0003-1994-4266"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sicong Pan","raw_affiliation_strings":["Humanoid Robots Lab, University of Bonn, Bonn, Germany","Humanoid Robots Lab, University of Bonn, Germany"],"affiliations":[{"raw_affiliation_string":"Humanoid Robots Lab, University of Bonn, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]},{"raw_affiliation_string":"Humanoid Robots Lab, University of Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065181173","display_name":"Nils Dengler","orcid":null},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nils Dengler","raw_affiliation_strings":["Humanoid Robots Lab, University of Bonn, Bonn, Germany","Humanoid Robots Lab, University of Bonn, Germany"],"affiliations":[{"raw_affiliation_string":"Humanoid Robots Lab, University of Bonn, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]},{"raw_affiliation_string":"Humanoid Robots Lab, University of Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048199386","display_name":"Siqi Zhou","orcid":"https://orcid.org/0000-0001-7240-546X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Siqi Zhou","raw_affiliation_strings":["Learning Systems and Robotics Lab, Technical University of Munich, Munchen, Germany","Learning Systems and Robotics lab, the Technical University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Learning Systems and Robotics Lab, Technical University of Munich, Munchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Learning Systems and Robotics lab, the Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052147335","display_name":"Angela P. Schoellig","orcid":"https://orcid.org/0000-0003-4012-4668"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Angela P. Schoellig","raw_affiliation_strings":["Learning Systems and Robotics Lab, Technical University of Munich, Munchen, Germany","Learning Systems and Robotics lab, the Technical University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Learning Systems and Robotics Lab, Technical University of Munich, Munchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Learning Systems and Robotics lab, the Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103231515","display_name":"Maren Bennewitz","orcid":"https://orcid.org/0000-0003-4343-3028"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maren Bennewitz","raw_affiliation_strings":["Humanoid Robots Lab, University of Bonn, Bonn, Germany","Humanoid Robots Lab, University of Bonn, Germany"],"affiliations":[{"raw_affiliation_string":"Humanoid Robots Lab, University of Bonn, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]},{"raw_affiliation_string":"Humanoid Robots Lab, University of Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5069650777"],"corresponding_institution_ids":["https://openalex.org/I135140700"],"apc_list":null,"apc_paid":null,"fwci":6.0904,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.96158885,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"10","issue":"6","first_page":"6256","last_page":"6263"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9733999967575073,"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":0.9733999967575073,"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/T11500","display_name":"Evacuation and Crowd Dynamics","score":0.9585000276565552,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9182000160217285,"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":0.7328518033027649},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6497834920883179},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4641619324684143},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3883989453315735},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.258005827665329},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2510671615600586},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.12489691376686096}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7328518033027649},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6497834920883179},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4641619324684143},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3883989453315735},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.258005827665329},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2510671615600586},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.12489691376686096}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3560830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3560830","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":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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W1933691875","https://openalex.org/W2083205586","https://openalex.org/W2605102758","https://openalex.org/W2793010390","https://openalex.org/W2912321781","https://openalex.org/W2968945909","https://openalex.org/W2991232381","https://openalex.org/W3043763914","https://openalex.org/W3119345764","https://openalex.org/W3120459386","https://openalex.org/W3142049818","https://openalex.org/W3187156000","https://openalex.org/W3200149197","https://openalex.org/W3201530632","https://openalex.org/W3207305612","https://openalex.org/W3211667558","https://openalex.org/W4200635426","https://openalex.org/W4285102169","https://openalex.org/W4285102423","https://openalex.org/W4383097628","https://openalex.org/W4383108777","https://openalex.org/W4383108961","https://openalex.org/W4385245566","https://openalex.org/W4385834002","https://openalex.org/W4387623856","https://openalex.org/W4388286283","https://openalex.org/W4391021089","https://openalex.org/W4401415268"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,118,132,139],"address":[4],"the":[5,23,35,42,47,86,120,127,156],"problem":[6],"of":[7,11,59,88,122,155],"behavior-based":[8,99],"cooperative":[9,28,100],"navigation":[10,29,101],"mobile":[12],"robots":[13],"using":[14,37,103],"safe":[15,98],"multi-agent":[16],"reinforcement":[17],"learning":[18,128],"(MARL).":[19],"Our":[20],"work":[21],"is":[22],"first":[24],"to":[25,55,72,78,115],"focus":[26],"on":[27,94,126,148],"without":[30,102],"individual":[31,104],"reference":[32,105],"targets":[33],"for":[34,41],"robots,":[36,96,150],"a":[38,57],"single":[39],"target":[40,112],"formation's":[43],"centroid.":[44],"This":[45],"eliminates":[46],"complexities":[48],"involved":[49],"in":[50,91],"having":[51],"several":[52],"path":[53],"planners":[54],"control":[56,70],"team":[58],"robots.":[60],"To":[61],"ensure":[62],"safety,":[63],"our":[64,89,142],"MARL":[65],"framework":[66],"uses":[67],"model":[68],"predictive":[69],"(MPC)":[71],"prevent":[73],"actions":[74],"that":[75,131,141],"could":[76],"lead":[77],"collisions":[79],"during":[80,136,152],"training":[81,137],"and":[82,93,110,138],"execution.":[83],"We":[84],"demonstrate":[85],"effectiveness":[87],"method":[90],"simulation":[92],"real":[95,149],"achieving":[97],"targets,":[106],"with":[107],"zero":[108],"collisions,":[109],"faster":[111,134],"reaching":[113],"compared":[114],"baselines.":[116],"Finally,":[117],"study":[119],"impact":[121],"MPC":[123],"safety":[124],"filters":[125],"process,":[129],"revealing":[130],"achieve":[133],"convergence":[135],"show":[140],"approach":[143],"can":[144],"be":[145],"safely":[146],"deployed":[147],"even":[151],"early":[153],"stages":[154],"training.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}