{"id":"https://openalex.org/W4236814501","doi":"https://doi.org/10.2514/6.2020-0458","title":"Guidance for Closed-Loop Transfers using Reinforcement Learning with Application to Libration Point Orbits","display_name":"Guidance for Closed-Loop Transfers using Reinforcement Learning with Application to Libration Point Orbits","publication_year":2020,"publication_date":"2020-01-05","ids":{"openalex":"https://openalex.org/W4236814501","doi":"https://doi.org/10.2514/6.2020-0458"},"language":"en","primary_location":{"id":"doi:10.2514/6.2020-0458","doi":"https://doi.org/10.2514/6.2020-0458","is_oa":false,"landing_page_url":"https://doi.org/10.2514/6.2020-0458","pdf_url":null,"source":{"id":"https://openalex.org/S4363604158","display_name":"AIAA SciTech Forum","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":"AIAA Scitech 2020 Forum","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dspace.mit.edu/bitstream/1721.1/137731/2/2020_scitech07.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017957493","display_name":"Nicholas B. LaFarge","orcid":"https://orcid.org/0000-0002-5623-3714","observed_orcids":["https://orcid.org/0000-0002-5623-3714"]},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholas B. LaFarge","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070304298","display_name":"Daniel Miller","orcid":"https://orcid.org/0000-0001-5750-5083","observed_orcids":["https://orcid.org/0000-0001-5750-5083"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Miller","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069943922","display_name":"Kathleen Connor Howell","orcid":"https://orcid.org/0000-0002-1298-5017","observed_orcids":["https://orcid.org/0000-0002-1298-5017"]},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kathleen C. Howell","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087614402","display_name":"Richard Linares","orcid":"https://orcid.org/0000-0001-8325-7378","observed_orcids":["https://orcid.org/0000-0001-8325-7378","https://orcid.org/0000-0003-0797-2470"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Linares","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.2673,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.97932991,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"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":0.9330999851226807,"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":0.9330999851226807,"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":0.051600001752376556,"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":0.004399999976158142,"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/reinforcement-learning","display_name":"reinforcement learning","score":0.6079999804496765},{"id":"https://openalex.org/keywords/libration-point-orbits","display_name":"libration point orbits","score":0.9760000109672546},{"id":"https://openalex.org/keywords/cislunar-space","display_name":"cislunar space","score":0.7789999842643738},{"id":"https://openalex.org/keywords/nonlinear-equations-of-motion","display_name":"nonlinear equations of motion","score":0.875},{"id":"https://openalex.org/keywords/flight-computer","display_name":"flight computer","score":0.34299999475479126},{"id":"https://openalex.org/keywords/spacecraft-trajectory-control","display_name":"spacecraft trajectory control","score":0.4490000009536743}],"concepts":[{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6458191275596619},{"id":"https://openalex.org/C98133451","wikidata":"https://www.wikidata.org/wiki/Q6542718","display_name":"Libration (molecule)","level":3,"score":0.6326323747634888},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6249194145202637},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6189680099487305},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.5365064144134521},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5094063878059387},{"id":"https://openalex.org/C3019251811","wikidata":"https://www.wikidata.org/wiki/Q5135346","display_name":"Closed loop","level":2,"score":0.47830989956855774},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.30490607023239136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2834950089454651},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17681938409805298},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.16611966490745544},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12421134114265442},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.2514/6.2020-0458","doi":"https://doi.org/10.2514/6.2020-0458","is_oa":false,"landing_page_url":"https://doi.org/10.2514/6.2020-0458","pdf_url":null,"source":{"id":"https://openalex.org/S4363604158","display_name":"AIAA SciTech Forum","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":"AIAA Scitech 2020 Forum","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/137731","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/137731","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/137731/2/2020_scitech07.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MIT web domain","raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/137731","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/137731","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/137731/2/2020_scitech07.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MIT web domain","raw_type":"Article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6250689750","display_name":"AT THE PRESENT TIME  DEEP-SPACE MISSIONS ARE PLANNED IN THE SAME WAY AS THEY HAVE BEEN FOR DECADES: USING BRUTE FORCE COMPUTATIONS OVER MANY MISSION PARAMETERS. SUCH CONSIDERATIONS INCLUDE THE MASS  THRUST  AND POWER GENERATION CAPABILITIES OF A PROBE AND/OR THE DESTINATIONS THAT MAKE UP ITS JOURNEY. NEW TECHNOLOGIES  HOWEVER  ARE POSED TO DRAMATICALLY ENHANCE THIS PROCESS. ADVANCES IN REINFORCEMENT LEARNING (RL) AND DEEP NEURAL NETWORKS OFFER PERFORMANCE THAT CAN MATCH OR EVEN SURPASS THAT OF CURRENT STATE-OF-THEART METHODS IN COMPLEX TASKS WITH LARGE DESIGN SPACES. THIS PROPOSAL SEEKS TO APPLY THIS TECHNOLOGY TO THE GENERATION AND CONTROL OF ENERGY EFFICIENT  LOW-THRUST SPACECRAFT TRAJECTORIES. THE PROPOSED WORK WILL USE AN ACTOR-CRITIC BASED POLICY APPROACH TO EXPLORE TRAJECTORY PROBLEMS. THE INNOVATION IN THIS METHOD IS THAT THE CRITIC WILL USE CONCEPTS FROM TRANSFER LEARNING TO GENERALIZE CONTROL PROBLEMS OVER MANY APPLICATIONS. THE LEARNING AGENT WILL THEREFORE BE ABLE TO LEARN THE FEATURES OF AN OPTIMIZED TRAJECTORY FROM THOSE THAT IT HAD PREVIOUSLY GENERATED  AND THEN USE THIS KNOWLEDGE TO DISCOVER NEW TRAJECTORY SOLUTIONS TO OTHER PROBLEMS. THIS WORK WILL ALSO EXPLORE AN ACTOR-CRITIC FRAMEWORK FOR CONTINUOUS ACTION PROBLEMS WHERE CONTINUOUS CONTROL IS DESIRED AND FOR PROBLEMS WITH DYNAMIC CONSTRAINTS. BY APPLYING RL TO THE DESIGN OF INTERPLANETARY MISSIONS  FUTURE SPACECRAFT WILL BE ABLE TO MORE EASILY FOLLOW LOW-THRUST TRAJECTORIES AND TAKE ADVANTAGE OF MULTI-BODY DYNAMICS  INSTEAD OF THE TRADITIONAL HOHMANN TRANSFER. NON-STANDARD ORBITS ABOUT LIBRATION POINTS WOULD ALSO BE MADE MORE AVAILABLE. FURTHERMORE  BY NOT REQUIRING LARGE COMPUTATIONAL RESOURCES  THIS TECHNOLOGY COULD BE APPLIED TO FUTURE MANNED MISSIONS FOR ONBOARD MISSION PLANNING. THE INCREASED FREEDOM IN MISSION DESIGN AFFORDED BY THIS TECHNOLOGY WOULD OFFER SIGNIFICANT BENEFITS TO BOTH NASA AND OTHER SPACEFLIGHT PROGRAMS","funder_award_id":"80NSSC18K1141","funder_id":"https://openalex.org/F4320306101","funder_display_name":"National Aeronautics and Space Administration"}],"funders":[{"id":"https://openalex.org/F4320306101","display_name":"National Aeronautics and Space Administration","ror":"https://ror.org/027ka1x80"},{"id":"https://openalex.org/F4320309036","display_name":"Purdue University","ror":"https://ror.org/02dqehb95"},{"id":"https://openalex.org/F4320309369","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4236814501.pdf","grobid_xml":"https://content.openalex.org/works/W4236814501.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W18638522","https://openalex.org/W1191599655","https://openalex.org/W2016641210","https://openalex.org/W2046376809","https://openalex.org/W2121083523","https://openalex.org/W2126165958","https://openalex.org/W2317614177","https://openalex.org/W2323944440","https://openalex.org/W2517675682","https://openalex.org/W2883672905","https://openalex.org/W2918780870","https://openalex.org/W2941124771","https://openalex.org/W2944046049"],"related_works":["https://openalex.org/W6945184174","https://openalex.org/W3163277281","https://openalex.org/W4386167352","https://openalex.org/W7113364722","https://openalex.org/W2912411486","https://openalex.org/W4292409592","https://openalex.org/W4205213396","https://openalex.org/W6889011483","https://openalex.org/W7139920779","https://openalex.org/W7202249630"],"abstract_inverted_index":{"While":[0],"human":[1],"presence":[2],"in":[3,37],"cislunar":[4],"space":[5],"continues":[6],"to":[7,72,97],"expand,":[8],"so":[9],"too":[10],"does":[11],"the":[12,38,49,52,78,81,87],"demand":[13],"for":[14],"\u2018lightweight\u2019":[15],"automated":[16],"on-board":[17],"processes.":[18],"In":[19],"nonlinear":[20,53],"dynamical":[21,39],"environments,":[22],"computationally":[23],"efficient":[24],"guidance":[25,67],"strategies":[26],"are":[27],"challenging.":[28],"Many":[29],"traditional":[30],"approaches":[31],"rely":[32],"on":[33,62],"either":[34],"simplifying":[35],"assumptions":[36],"model":[40],"or":[41],"abundant":[42],"computational":[43],"resources.":[44],"The":[45,66],"proposed":[46],"controller":[47],"employs":[48],"use":[50],"of":[51,55,89],"equations":[54],"motion":[56],"without":[57],"imposing":[58],"a":[59,63,90],"heavy":[60],"workload":[61],"flight":[64],"computer.":[65],"framework":[68],"is":[69],"nevertheless":[70],"able":[71],"leverage":[73],"high-performance":[74],"computing":[75],"by":[76],"separating":[77],"training":[79],"from":[80],"resulting":[82],"controller.":[83],"Practical":[84],"examples":[85],"demonstrate":[86],"flexibility":[88],"reinforcement":[91],"learning":[92],"approach,":[93],"and":[94],"suggest":[95],"extendability":[96],"higher-fidelity":[98],"domains.":[99]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":4}],"updated_date":"2026-10-20T09:52:01.089006","created_date":"2022-05-12T00:00:00"}