{"id":"https://openalex.org/W7204015174","doi":null,"title":"Multi-Phase Guidance and Control for Small Satellite Docking via Deep Reinforcement Learning","display_name":"Multi-Phase Guidance and Control for Small Satellite Docking via Deep Reinforcement Learning","publication_year":2026,"publication_date":"2026-08-23","ids":{"openalex":"https://openalex.org/W7204015174"},"language":"en","primary_location":{"id":"pmh:oai:digitalcommons.usu.edu:smallsat-6624","doi":null,"is_oa":true,"landing_page_url":"https://digitalcommons.usu.edu/smallsat/2026/all2026/140","pdf_url":"https://digitalcommons.usu.edu/cgi/viewcontent.cgi?article=6624&context=smallsat","source":{"id":"https://openalex.org/S4377196327","display_name":"Digital Commons - USU (Utah State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I121980950","host_organization_name":"Utah State University","host_organization_lineage":["https://openalex.org/I121980950"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Small Satellite Conference","raw_type":"text"},"volume":null,"type":"conference-paper","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://digitalcommons.usu.edu/cgi/viewcontent.cgi?article=6624&context=smallsat","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076364540","display_name":"Tanner Gill","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gill, Tanner","raw_affiliation_strings":["University of Colorado Boulder"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Colorado Boulder","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138470920","display_name":"Greg Furlich","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Furlich, Greg","raw_affiliation_strings":["University of Colorado Boulder"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Colorado Boulder","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121818769","display_name":"Nisar Ahmed","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmed, Nisar","raw_affiliation_strings":["University of Colorado Boulder"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Colorado Boulder","institution_ids":["https://openalex.org/I188538660"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I188538660"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68793826,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T11082","display_name":"Spacecraft Dynamics and Control","score":0.5684000253677368,"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/T11082","display_name":"Spacecraft Dynamics and Control","score":0.5684000253677368,"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/T11701","display_name":"Space Satellite Systems and Control","score":0.4169999957084656,"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":0.01119999960064888,"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/rendezvous-and-proximity-operations","display_name":"rendezvous and proximity operations","score":0.8830000162124634},{"id":"https://openalex.org/keywords/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.8180000185966492},{"id":"https://openalex.org/keywords/proximal-policy-optimization","display_name":"proximal policy optimization","score":0.8870000243186951}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7537000179290771},{"id":"https://openalex.org/C2779968344","wikidata":"https://www.wikidata.org/wiki/Q3932925","display_name":"Rendezvous","level":3,"score":0.6317999958992004},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5831000208854675},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5462999939918518},{"id":"https://openalex.org/C29829512","wikidata":"https://www.wikidata.org/wiki/Q40218","display_name":"Spacecraft","level":2,"score":0.47279998660087585},{"id":"https://openalex.org/C14185376","wikidata":"https://www.wikidata.org/wiki/Q30232","display_name":"Agile software development","level":2,"score":0.4683000147342682},{"id":"https://openalex.org/C19269812","wikidata":"https://www.wikidata.org/wiki/Q26540","display_name":"Satellite","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.37389999628067017},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.37139999866485596},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31310001015663147},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.3125},{"id":"https://openalex.org/C145424490","wikidata":"https://www.wikidata.org/wiki/Q618465","display_name":"Remotely operated underwater vehicle","level":4,"score":0.3043999969959259},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.28380000591278076},{"id":"https://openalex.org/C104060986","wikidata":"https://www.wikidata.org/wiki/Q180046","display_name":"Space exploration","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.27630001306533813},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.27619999647140503},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.2736999988555908},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:digitalcommons.usu.edu:smallsat-6624","doi":null,"is_oa":true,"landing_page_url":"https://digitalcommons.usu.edu/smallsat/2026/all2026/140","pdf_url":"https://digitalcommons.usu.edu/cgi/viewcontent.cgi?article=6624&context=smallsat","source":{"id":"https://openalex.org/S4377196327","display_name":"Digital Commons - USU (Utah State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I121980950","host_organization_name":"Utah State University","host_organization_lineage":["https://openalex.org/I121980950"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Small Satellite Conference","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:digitalcommons.usu.edu:smallsat-6624","doi":null,"is_oa":true,"landing_page_url":"https://digitalcommons.usu.edu/smallsat/2026/all2026/140","pdf_url":"https://digitalcommons.usu.edu/cgi/viewcontent.cgi?article=6624&context=smallsat","source":{"id":"https://openalex.org/S4377196327","display_name":"Digital Commons - USU (Utah State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I121980950","host_organization_name":"Utah State University","host_organization_lineage":["https://openalex.org/I121980950"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Small Satellite Conference","raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204015174.pdf","grobid_xml":"https://content.openalex.org/works/W7204015174.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4392601806","https://openalex.org/W7221769026","https://openalex.org/W7128715970","https://openalex.org/W7126091504","https://openalex.org/W4416748357","https://openalex.org/W3047627630","https://openalex.org/W3158127795","https://openalex.org/W7027679697","https://openalex.org/W6891963359","https://openalex.org/W4393342892"],"abstract_inverted_index":{"As":[0],"interest":[1],"in":[2,19,145],"small":[3,76],"satellite":[4,77,118],"Rendezvous,":[5],"Proximity":[6],"Operations,":[7],"and":[8,28,45,53,99,135,158,187,219],"Docking":[9],"(RPOD)":[10],"grows,":[11],"so":[12],"does":[13],"the":[14,34,82,93,96,104,115,146,154,195],"need":[15],"for":[16,33,119,136],"high-level":[17],"autonomy":[18,79],"space":[20,37],"systems.":[21],"Current":[22],"systems":[23],"relying":[24],"on":[25,41,68],"constrained":[26],"hardware":[27],"ground-in-the-loop":[29],"decision-making":[30],"are":[31],"ill-equipped":[32],"evolving,":[35],"contested":[36],"domain.":[38],"Recent":[39],"research":[40,74,218],"autonomous":[42,221],"spacecraft":[43],"guidance":[44,98],"control":[46,52,100],"has":[47],"moved":[48],"beyond":[49],"established":[50],"optimal":[51],"trajectory":[54],"optimization":[55],"methods":[56],"to":[57,102,121,138,161],"incorporate":[58],"Reinforcement":[59],"Learning":[60],"(RL),":[61],"though":[62],"these":[63],"efforts":[64],"have":[65],"predominantly":[66],"focused":[67],"a":[69,86,143,163,174,199,205],"single":[70],"operational":[71],"phase.":[72,111],"This":[73,112],"advances":[75],"docking":[78,184,201],"by":[80],"formulating":[81],"reference":[83],"scenario":[84],"as":[85,142],"Hierarchical":[87],"Markov":[88],"Decision":[89],"Process":[90],"(H-MDP),":[91],"expanding":[92],"scope":[94],"of":[95],"learned":[97],"algorithm":[101],"span":[103],"full":[105],"mission":[106,124,188],"profile":[107],"rather":[108],"than":[109],"one":[110],"structure":[113],"rewards":[114],"agile":[116],"deputy":[117],"learning":[120],"transition":[122],"between":[123],"phases,":[125],"modifying":[126],"its":[127],"behavior":[128],"from":[129],"long-range":[130],"rendezvous":[131],"through":[132],"final":[133],"approach,":[134],"adapting":[137],"changing":[139],"conditions":[140],"such":[141],"shift":[144],"chief":[147],"satellite's":[148],"pointing":[149],"mode.":[150],"The":[151,179],"framework":[152],"uses":[153],"Basilisk":[155],"astrodynamics":[156],"simulator":[157],"BSK-RL":[159],"library":[160],"train":[162],"Proximal":[164],"Policy":[165],"Optimization":[166],"(PPO)":[167],"agent":[168],"under":[169],"high-fidelity":[170],"orbital":[171],"dynamics,":[172],"creating":[173],"lightweight,":[175],"robust":[176],"training":[177],"pipeline.":[178],"analysis":[180],"quantifies":[181],"total":[182],"delta-V,":[183],"ingress":[185],"characteristics,":[186],"success":[189,202],"across":[190],"randomized":[191],"initial":[192],"conditions,":[193],"with":[194],"trained":[196],"policy":[197],"achieving":[198],"99.2%":[200],"rate":[203],"over":[204],"500-run":[206],"Monte":[207],"Carlo":[208],"analysis,":[209],"demonstrating":[210],"how":[211],"H-MDP":[212],"structures":[213],"can":[214],"bridge":[215],"single-phase":[216],"RL":[217],"mission-ready":[220],"G&C.":[222]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-23T00:00:00"}
