{"id":"https://openalex.org/W7212061104","doi":"https://doi.org/10.48550/arxiv.2609.06061","title":"SCoCaT: Success Conditioned Constrained Reinforcement Learning for Spacecraft Docking","display_name":"SCoCaT: Success Conditioned Constrained Reinforcement Learning for Spacecraft Docking","publication_year":2026,"publication_date":"2026-09-05","ids":{"openalex":"https://openalex.org/W7212061104","doi":"https://doi.org/10.48550/arxiv.2609.06061"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.06061","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.06061","pdf_url":"https://arxiv.org/pdf/2609.06061","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.06061","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5152494170","display_name":"Aman Arora","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]},{"id":"https://openalex.org/I4405259781","display_name":"Interdisciplinary Centre for Security, Reliability and Trust","ror":"https://ror.org/02qav7c04","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577","https://openalex.org/I4405259781"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Arora, Aman","raw_affiliation_strings":["SnT -Interdisciplinary Centre for Security , Reliability and Trust University of Luxembourg , Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SnT -Interdisciplinary Centre for Security , Reliability and Trust University of Luxembourg , Luxembourg","institution_ids":["https://openalex.org/I186903577","https://openalex.org/I4405259781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143786804","display_name":"Ricard Marsal I Castan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Castan, Ricard Marsal I","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093054933","display_name":"Matteo El-Hariry","orcid":"https://orcid.org/0009-0007-5231-5898","observed_orcids":["https://orcid.org/0009-0007-5231-5898"]},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]},{"id":"https://openalex.org/I4405259781","display_name":"Interdisciplinary Centre for Security, Reliability and Trust","ror":"https://ror.org/02qav7c04","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577","https://openalex.org/I4405259781"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"El-Hariry, Matteo","raw_affiliation_strings":["SnT -Interdisciplinary Centre for Security , Reliability and Trust University of Luxembourg , Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SnT -Interdisciplinary Centre for Security , Reliability and Trust University of Luxembourg , Luxembourg","institution_ids":["https://openalex.org/I186903577","https://openalex.org/I4405259781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085280731","display_name":"Miguel A. Olivares-M\u00e9ndez","orcid":"https://orcid.org/0000-0001-8824-3231","observed_orcids":["https://orcid.org/0000-0001-8824-3231"]},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]},{"id":"https://openalex.org/I4405259781","display_name":"Interdisciplinary Centre for Security, Reliability and Trust","ror":"https://ror.org/02qav7c04","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577","https://openalex.org/I4405259781"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Olivares-Mendez, Miguel","raw_affiliation_strings":["SnT -Interdisciplinary Centre for Security , Reliability and Trust University of Luxembourg , Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SnT -Interdisciplinary Centre for Security , Reliability and Trust University of Luxembourg , Luxembourg","institution_ids":["https://openalex.org/I186903577","https://openalex.org/I4405259781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"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":0.9878000020980835,"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":0.9878000020980835,"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":0.010700000450015068,"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":0.0005000000237487257,"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/constrained-reinforcement-learning","display_name":"constrained reinforcement learning","score":0.8270000219345093},{"id":"https://openalex.org/keywords/spacecraft-docking","display_name":"spacecraft docking","score":0.8840000033378601},{"id":"https://openalex.org/keywords/safety-critical-robotics","display_name":"safety-critical robotics","score":0.6259999871253967},{"id":"https://openalex.org/keywords/cubesat","display_name":"CubeSat","score":0.49000000953674316},{"id":"https://openalex.org/keywords/proximity-operations","display_name":"proximity operations","score":0.7519999742507935},{"id":"https://openalex.org/keywords/sim-to-real-transfer","display_name":"sim-to-real transfer","score":0.9150000214576721},{"id":"https://openalex.org/keywords/constraint-compliance","display_name":"constraint compliance","score":0.5490000247955322}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6866000294685364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6159999966621399},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.5533000230789185},{"id":"https://openalex.org/C29829512","wikidata":"https://www.wikidata.org/wiki/Q40218","display_name":"Spacecraft","level":2,"score":0.5490000247955322},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.49869999289512634},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.4943000078201294},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4925000071525574},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C2781133158","wikidata":"https://www.wikidata.org/wiki/Q1088669","display_name":"Survivability","level":2,"score":0.3898000121116638},{"id":"https://openalex.org/C137105694","wikidata":"https://www.wikidata.org/wiki/Q3407510","display_name":"Local consistency","level":4,"score":0.38580000400543213},{"id":"https://openalex.org/C55660270","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization","level":2,"score":0.37279999256134033},{"id":"https://openalex.org/C199622910","wikidata":"https://www.wikidata.org/wiki/Q1128326","display_name":"Constraint satisfaction problem","level":3,"score":0.3637999892234802},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3346000015735626},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C72898154","wikidata":"https://www.wikidata.org/wiki/Q458038","display_name":"Flight envelope","level":3,"score":0.3231000006198883},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.3027999997138977},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C2778134712","wikidata":"https://www.wikidata.org/wiki/Q1047307","display_name":"Bundle","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C110521144","wikidata":"https://www.wikidata.org/wiki/Q193460","display_name":"Scalar field","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C44616089","wikidata":"https://www.wikidata.org/wiki/Q30158686","display_name":"Constraint satisfaction","level":3,"score":0.2806999981403351},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.27140000462532043},{"id":"https://openalex.org/C172707124","wikidata":"https://www.wikidata.org/wiki/Q423488","display_name":"Actuator","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C53469067","wikidata":"https://www.wikidata.org/wiki/Q505735","display_name":"Lagrangian","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2574999928474426},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.25440001487731934}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.06061","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.06061","pdf_url":"https://arxiv.org/pdf/2609.06061","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2609.06061","doi":"https://doi.org/10.48550/arxiv.2609.06061","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.06061","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.06061","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.06061","pdf_url":"https://arxiv.org/pdf/2609.06061","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1282667882","display_name":null,"funder_award_id":"101161690","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212061104.pdf","grobid_xml":"https://content.openalex.org/works/W7212061104.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4205613166","https://openalex.org/W7133207217","https://openalex.org/W7204548139","https://openalex.org/W7127541628","https://openalex.org/W3164473225","https://openalex.org/W4280636619","https://openalex.org/W2889696653","https://openalex.org/W6911785259","https://openalex.org/W4389740637","https://openalex.org/W2803543472"],"abstract_inverted_index":{"Termination-based":[0],"constrained":[1],"reinforcement":[2],"learning":[3],"is":[4,28],"attractive":[5],"for":[6,56,190],"safety-critical":[7,164],"robotic":[8],"deployments:":[9],"it":[10],"avoids":[11],"online":[12],"optimization":[13],"at":[14],"inference,":[15],"scales":[16],"easily":[17],"to":[18,30,95,112,132],"many":[19],"constraints":[20,80,98],"via":[21,152],"a":[22,61,73,129,147,173,186],"single":[23],"scalar":[24],"per":[25],"constraint,":[26],"and":[27,126,178,185],"simpler":[29],"implement":[31],"than":[32],"commonly":[33],"used":[34],"Lagrangian":[35],"methods.":[36],"Instead":[37],"of":[38,65,181,200],"pricing":[39],"violations":[40,48],"through":[41],"summed":[42],"cost":[43],"penalties,":[44],"this":[45,66,124,139],"approach":[46],"makes":[47,104],"structurally":[49],"unprofitable":[50],"by":[51],"shortening":[52],"the":[53,84,88,92,97,101,107,158,176,198],"effective":[54],"horizon":[55],"each":[57],"violation.":[58],"We":[59,122,142],"identify":[60],"structural":[62],"failure":[63],"mode":[64],"method":[67],"class":[68],"on":[69],"terminal-navigation":[70],"tasks:":[71],"reaching":[72],"precise":[74],"goal":[75,89,108],"configuration":[76],"while":[77,162],"satisfying":[78],"safety":[79],"that":[81,128,145],"tighten":[82],"along":[83],"final":[85],"approach.":[86],"When":[87],"sits":[90],"inside":[91],"region":[93,109],"close":[94],"where":[96],"become":[99],"active,":[100],"survival-weighted":[102],"objective":[103],"dwelling":[105],"outside":[106],"strictly":[110],"preferable":[111],"entering,":[113],"producing":[114],"high":[115],"constraint":[116,165],"compliance":[117],"with":[118],"low":[119],"task":[120,159],"completion.":[121],"formalize":[123],"pathology":[125],"show":[127],"minimal":[130],"augmentation":[131],"off-the-shelf":[133],"RL":[134],"algorithms":[135],"like":[136],"PPO":[137],"resolves":[138],"``feasibility":[140],"collapse''.":[141],"empirically":[143],"demonstrate":[144],"adding":[146],"dense":[148],"per-step":[149],"success":[150],"signal":[151],"an":[153],"auxiliary":[154],"value":[155],"critic":[156],"improves":[157],"completion":[160],"rate":[161],"maintaining":[163],"compliance.":[166],"Validation":[167],"across":[168],"two":[169],"representative":[170],"spacecraft":[171],"platforms:":[172],"6U-CubeSat":[174],"spanning":[175],"mass":[177],"degree-of-freedom":[179],"envelope":[180],"operational":[182],"proximity":[183],"operations,":[184],"floating":[187],"platform":[188],"testbed":[189],"zero-shot":[191],"sim-to-real":[192],"transfer":[193],"in":[194],"our":[195],"laboratory,":[196],"supports":[197],"generality":[199],"these":[201],"findings.":[202]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-10T00:00:00"}