{"id":"https://openalex.org/W7124417134","doi":"https://doi.org/10.52202/083087-0116","title":"Safe Reinforcement Learning for Autonomous Rendezvous and Proximity Operations: Balancing Safety and Performance in CubeSat Docking Missions","display_name":"Safe Reinforcement Learning for Autonomous Rendezvous and Proximity Operations: Balancing Safety and Performance in CubeSat Docking Missions","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7124417134","doi":"https://doi.org/10.52202/083087-0116"},"language":"en","primary_location":{"id":"doi:10.52202/083087-0116","doi":"https://doi.org/10.52202/083087-0116","is_oa":false,"landing_page_url":"https://doi.org/10.52202/083087-0116","pdf_url":null,"source":{"id":"https://openalex.org/S7407096176","display_name":"IAF Astrodynamics Symposium","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IAF Astrodynamics Symposium","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5081172506","display_name":"S. Rotondi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Simone Rotondi","raw_affiliation_strings":["Sapienza University of Rome"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099585883","display_name":"Valentina Becchetti","orcid":"https://orcid.org/0009-0008-8560-1775","observed_orcids":["https://orcid.org/0009-0008-8560-1775"]},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Valentina Becchetti","raw_affiliation_strings":["University of Rome \u201cLa Sapienza\u201d"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rome \u201cLa Sapienza\u201d","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009792137","display_name":"Stefano Carletta","orcid":"https://orcid.org/0000-0001-6773-4250","observed_orcids":["https://orcid.org/0000-0001-6773-4250"]},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Stefano Carletta","raw_affiliation_strings":["Sapienza University of Rome"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009770666","display_name":"Alessandro Giuseppi","orcid":"https://orcid.org/0000-0001-5503-8506","observed_orcids":["https://orcid.org/0000-0001-5503-8506"]},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Giuseppi","raw_affiliation_strings":["Sapienza University of Rome"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I861853513"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.56983351,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1315","last_page":"1327"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11701","display_name":"Space Satellite Systems and Control","score":0.611299991607666,"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"}},"topics":[{"id":"https://openalex.org/T11701","display_name":"Space Satellite Systems and Control","score":0.611299991607666,"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":0.2506999969482422,"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/T11082","display_name":"Spacecraft Dynamics and Control","score":0.12999999523162842,"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/safe-reinforcement-learning","display_name":"safe reinforcement learning","score":0.9860000014305115},{"id":"https://openalex.org/keywords/safety-performance-trade-off","display_name":"safety-performance trade-off","score":0.6700000166893005},{"id":"https://openalex.org/keywords/soft-actor-critic","display_name":"soft actor-critic","score":0.9739999771118164},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"collision avoidance","score":0.7360000014305115},{"id":"https://openalex.org/keywords/on-orbit-servicing","display_name":"on-orbit servicing","score":0.7580000162124634},{"id":"https://openalex.org/keywords/formation-flying","display_name":"formation flying","score":0.6809999942779541},{"id":"https://openalex.org/keywords/actuator-faults","display_name":"actuator faults","score":0.5090000033378601},{"id":"https://openalex.org/keywords/unmodeled-dynamics","display_name":"unmodeled dynamics","score":0.6290000081062317}],"concepts":[{"id":"https://openalex.org/C2779968344","wikidata":"https://www.wikidata.org/wiki/Q3932925","display_name":"Rendezvous","level":3,"score":0.6518999934196472},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5760999917984009},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.572700023651123},{"id":"https://openalex.org/C41685203","wikidata":"https://www.wikidata.org/wiki/Q1974042","display_name":"Docking (animal)","level":2,"score":0.45249998569488525},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3725000023841858},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3675000071525574},{"id":"https://openalex.org/C2775936636","wikidata":"https://www.wikidata.org/wiki/Q1142930","display_name":"CubeSat","level":3,"score":0.3555000126361847},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.35260000824928284},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.27630001306533813}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.52202/083087-0116","doi":"https://doi.org/10.52202/083087-0116","is_oa":false,"landing_page_url":"https://doi.org/10.52202/083087-0116","pdf_url":null,"source":{"id":"https://openalex.org/S7407096176","display_name":"IAF Astrodynamics Symposium","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IAF Astrodynamics Symposium","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.uniroma1.it:11573/1767032","doi":null,"is_oa":false,"landing_page_url":"https://hdl.handle.net/11573/1767032","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4389740637","https://openalex.org/W7126091504","https://openalex.org/W7084070314","https://openalex.org/W7169831035","https://openalex.org/W7162076414","https://openalex.org/W7128715970","https://openalex.org/W4205613166","https://openalex.org/W4402489538","https://openalex.org/W6891963359","https://openalex.org/W4388692804"],"abstract_inverted_index":{"Autonomous":[0],"Rendezvous":[1],"and":[2,8,20,39,54,61,83,87,107,205,240,257,289],"Proximity":[3],"Operations":[4],"(ARPOD)":[5],"for":[6,15,276,312],"CubeSats":[7],"small":[9],"satellites":[10],"are":[11],"becoming":[12],"increasingly":[13],"important":[14],"on-orbit":[16],"servicing,":[17],"formation":[18],"flying,":[19],"debris":[21],"mitigation.":[22],"These":[23],"operations":[24,210],"present":[25],"unique":[26],"challenges:":[27],"the":[28,102,118,125,135,144,156,188,195,248,266,281,287,300,303],"spacecraft":[29],"must":[30],"navigate":[31],"complex":[32],"dynamics,":[33,70],"operate":[34],"under":[35],"strict":[36],"safety":[37,169,291],"constraints,":[38,170],"adapt":[40],"to":[41,68,85,97,133,165,184,214,226,253,307],"uncertain":[42],"environmental":[43],"conditions.":[44],"Traditional":[45],"control":[46,115],"techniques,":[47],"such":[48,171],"as":[49,172,272],"Linear":[50],"Quadratic":[51],"Regulators":[52],"(LQR)":[53],"Model":[55],"Predictive":[56],"Control":[57],"(MPC)":[58],"offer":[59],"stability":[60],"theoretical":[62],"guarantees":[63],"but":[64],"struggle":[65],"when":[66,212],"exposed":[67],"unmodeled":[69],"external":[71],"disturbances,":[72],"or":[73,112,178,217],"actuator":[74],"faults.":[75],"By":[76,190],"contrast,":[77],"Reinforcement":[78,129,270],"Learning":[79,130,271],"(RL)":[80],"offers":[81],"flexibility":[82,282],"adaptability":[84],"nonlinear":[86],"partially":[88],"observable":[89],"environments.":[90],"Still,":[91],"its":[92],"exploration-driven":[93],"learning":[94,261,311],"often":[95],"leads":[96],"unsafe":[98,200],"behaviours,":[99],"especially":[100],"in":[101,138],"critical":[103,274],"phases":[104],"of":[105,114,127,168,187,268,283,302],"approach":[106,223,239],"docking,":[108],"where":[109,233],"collisions,":[110],"misalignments":[111],"loss":[113],"could":[116,182],"jeopardise":[117],"mission.":[119,189],"In":[120],"this":[121,192],"work,":[122],"we":[123],"propose":[124],"use":[126],"Safe":[128,221,249,269],"(Safe":[131],"RL)":[132],"address":[134],"safety-performance":[136],"trade-off":[137],"autonomous":[139,238],"RPOD":[140,231],"operations.":[141],"We":[142,246],"extend":[143],"Soft":[145],"Actor-Critic":[146],"(SAC)":[147],"framework":[148],"with":[149,243,286],"an":[150],"auxiliary":[151],"Safety":[152,193,304],"Critic,":[153,194],"which":[154],"estimates":[155],"probability":[157],"that":[158,181],"a":[159,166,185,227,234,244,273],"given":[160],"state-action":[161],"pair":[162],"will":[163,298],"lead":[164,183],"violation":[167],"collision":[173],"risk,":[174],"excessive":[175],"relative":[176],"velocity,":[177],"orientation":[179],"misalignment":[180],"failure":[186],"incorporating":[191],"agent":[196],"can":[197],"actively":[198],"avoid":[199],"actions":[201],"during":[202],"both":[203,254],"training":[204],"execution,":[206],"ensuring":[207],"safe":[208],"proximity":[209],"even":[211],"adapting":[213],"new":[215],"conditions":[216],"system":[218],"dynamics.":[219],"The":[220],"RL":[222,250],"is":[224],"applied":[225],"simulated":[228],"SE(2)":[229],"planar":[230],"scenario,":[232],"12U":[235],"CubeSat":[236,278],"performs":[237],"docking":[241],"manoeuvres":[242],"target.":[245],"compare":[247],"agent\u2019s":[251],"performance":[252],"classical":[255],"controllers":[256],"standard":[258],"deep":[259],"reinforcement":[260],"agents.":[262],"This":[263],"work":[264,297],"highlights":[265],"potential":[267],"enabler":[275],"next-generation":[277],"autonomy,":[279],"combining":[280],"learning-based":[284],"approaches":[285],"robustness":[288],"operational":[290],"demanded":[292],"by":[293],"space":[294],"missions.":[295],"Future":[296],"explore":[299],"extension":[301],"Critic":[305],"concept":[306],"incorporate":[308],"real-time":[309],"onboard":[310],"adaptive":[313],"anomaly":[314],"handling.":[315]},"counts_by_year":[],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2026-01-17T00:00:00"}