{"id":"https://openalex.org/W4416758241","doi":"https://doi.org/10.31224/5877","title":"Multi-Agent Spacecraft Docking with Reinforcement Learning","display_name":"Multi-Agent Spacecraft Docking with Reinforcement Learning","publication_year":2025,"publication_date":"2025-11-27","ids":{"openalex":"https://openalex.org/W4416758241","doi":"https://doi.org/10.31224/5877"},"language":"en","primary_location":{"id":"doi:10.31224/5877","doi":"https://doi.org/10.31224/5877","is_oa":true,"landing_page_url":"https://doi.org/10.31224/5877","pdf_url":"https://engrxiv.org/preprint/download/5877/9769/8180","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://engrxiv.org/preprint/download/5877/9769/8180","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120386772","display_name":"Selim Olgu Pilav","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Selim Olgu Pilav","raw_affiliation_strings":["Independant Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independant Researcher","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5120386772"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.4916999936103821,"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":0.4916999936103821,"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/T11701","display_name":"Space Satellite Systems and Control","score":0.36820000410079956,"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/T11082","display_name":"Spacecraft Dynamics and Control","score":0.13279999792575836,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spacecraft-docking","display_name":"spacecraft docking","score":0.8209999799728394},{"id":"https://openalex.org/keywords/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.996999979019165},{"id":"https://openalex.org/keywords/chaser-spacecraft","display_name":"chaser spacecraft","score":0.6079999804496765},{"id":"https://openalex.org/keywords/tumbling-target","display_name":"tumbling target","score":0.9520000219345093},{"id":"https://openalex.org/keywords/low-thrust-propulsion","display_name":"low-thrust propulsion","score":0.7649999856948853},{"id":"https://openalex.org/keywords/fuel-efficiency","display_name":"fuel economy","score":0.9869999885559082},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"collision avoidance","score":0.7609999775886536},{"id":"https://openalex.org/keywords/decentralized-control","display_name":"decentralized control","score":0.6110000014305115},{"id":"https://openalex.org/keywords/agent-communication","display_name":"agent communication","score":0.8140000104904175}],"concepts":[{"id":"https://openalex.org/C29829512","wikidata":"https://www.wikidata.org/wiki/Q40218","display_name":"Spacecraft","level":2,"score":0.8737000226974487},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8217999935150146},{"id":"https://openalex.org/C41685203","wikidata":"https://www.wikidata.org/wiki/Q1974042","display_name":"Docking (animal)","level":2,"score":0.6093000173568726},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5281999707221985},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5063999891281128},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3582000136375427},{"id":"https://openalex.org/C104060986","wikidata":"https://www.wikidata.org/wiki/Q180046","display_name":"Space exploration","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3529999852180481},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.31049999594688416},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3003999888896942},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2924000024795532},{"id":"https://openalex.org/C79487989","wikidata":"https://www.wikidata.org/wiki/Q934680","display_name":"Vehicle dynamics","level":2,"score":0.28450000286102295}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.31224/5877","doi":"https://doi.org/10.31224/5877","is_oa":true,"landing_page_url":"https://doi.org/10.31224/5877","pdf_url":"https://engrxiv.org/preprint/download/5877/9769/8180","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.31224/5877","doi":"https://doi.org/10.31224/5877","is_oa":true,"landing_page_url":"https://doi.org/10.31224/5877","pdf_url":"https://engrxiv.org/preprint/download/5877/9769/8180","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416758241.pdf","grobid_xml":"https://content.openalex.org/works/W4416758241.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4417437528","https://openalex.org/W3047627630","https://openalex.org/W7018266341","https://openalex.org/W4392941524","https://openalex.org/W6921724480","https://openalex.org/W7127438054","https://openalex.org/W4388039692","https://openalex.org/W7128715970","https://openalex.org/W4386104429","https://openalex.org/W3158127795"],"abstract_inverted_index":{"This":[0],"research":[1,144],"explores":[2],"the":[3,81,85,126,146,169],"application":[4],"of":[5,84,128,148,179],"Multi-Agent":[6,42],"Reinforcement":[7],"Learning":[8],"(MARL)":[9],"to":[10,38,57,80,88,131,163],"a":[11,21,48,59,97,136,176],"cooperative":[12],"spacecraft":[13,19,40,132],"docking":[14,37,62,112,133,138],"problem":[15],"with":[16,96],"three":[17],"chaser":[18],"and":[20,71,106,113,167,175],"lightly":[22],"tumbling":[23],"target.":[24],"The":[25,53,92,143],"study":[26],"extends":[27],"Proximal":[28,43],"Policy":[29,44],"Optimisation":[30,45],"(PPO)":[31],"based":[32],"single-agent":[33],"reinforcement":[34,149],"learning":[35,150],"(RL)":[36],"multi-agent":[39,155],"using":[41],"(MAPPO),":[46],"targeting":[47],"simple":[49],"3-DOF":[50],"planar":[51],"setup.":[52],"primary":[54],"goal":[55],"is":[56,94,118,161],"develop":[58],"safe,":[60],"decentralised":[61],"policy":[63,93,170],"that":[64,100],"accounts":[65],"for":[66,152,171],"low-thrust":[67],"constraints,":[68],"fuel":[69,104],"efficiency,":[70],"inter-agent":[72],"communication":[73],"limitations.":[74],"Agents":[75],"are":[76],"only":[77],"given":[78],"access":[79],"noisy":[82],"measurement":[83],"nearest":[86],"agent":[87],"mimic":[89],"large":[90,177],"constellations.":[91],"trained":[95],"reward":[98],"function":[99],"penalises":[101],"position,":[102],"velocity,":[103],"consumption,":[105],"angular":[107],"errors":[108],"while":[109],"encouraging":[110],"successful":[111],"collision":[114],"avoidance.":[115],"Experimental":[116],"validation":[117],"conducted":[119],"via":[120],"Monte":[121],"Carlo":[122],"simulations.":[123],"Results":[124],"demonstrate":[125],"feasibility":[127],"applying":[129],"MARL":[130],"tasks,":[134],"achieving":[135],"99.1%":[137],"success":[139],"rate":[140],"in":[141],"simulation.":[142],"highlights":[145],"potential":[147],"approaches":[151],"future":[153],"distributed":[154],"space":[156],"missions.":[157],"However,":[158],"further":[159],"work":[160],"needed":[162],"address":[164],"robustness":[165],"concerns":[166],"optimise":[168],"more":[172],"complex":[173],"scenarios":[174],"number":[178],"agents.":[180]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2025-11-28T00:00:00"}