{"id":"https://openalex.org/W2921714676","doi":"https://doi.org/10.1109/robio.2018.8665049","title":"Control of Free-Floating Space Robots to Capture Targets Using Soft Q-Learning","display_name":"Control of Free-Floating Space Robots to Capture Targets Using Soft Q-Learning","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2921714676","doi":"https://doi.org/10.1109/robio.2018.8665049","mag":"2921714676"},"language":"en","primary_location":{"id":"doi:10.1109/robio.2018.8665049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio.2018.8665049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"},"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/A5100713324","display_name":"Changzhi Yan","orcid":"https://orcid.org/0000-0002-9040-170X"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changzhi Yan","raw_affiliation_strings":["Artificial Intelligence and Robotics, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence and Robotics, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100739516","display_name":"Qiyuan Zhang","orcid":"https://orcid.org/0000-0001-6562-9633"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiyuan Zhang","raw_affiliation_strings":["Artificial Intelligence and Robotics, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence and Robotics, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100603518","display_name":"Zhaoyang Liu","orcid":"https://orcid.org/0000-0001-9712-5720"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoyang Liu","raw_affiliation_strings":["Artificial Intelligence and Robotics, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence and Robotics, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100737125","display_name":"Xueqian Wang","orcid":"https://orcid.org/0000-0003-3542-0593"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueqian Wang","raw_affiliation_strings":["Artificial Intelligence and Robotics, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence and Robotics, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100644630","display_name":"Bin Liang","orcid":"https://orcid.org/0000-0002-8591-8843"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Liang","raw_affiliation_strings":["Artificial Intelligence and Robotics, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence and Robotics, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.9658,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.9577108,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"654","last_page":"660"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11701","display_name":"Space Satellite Systems and Control","score":0.9994999766349792,"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":0.9994999766349792,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9136000275611877,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10325","display_name":"Astro and Planetary Science","score":0.8999999761581421,"subfield":{"id":"https://openalex.org/subfields/3103","display_name":"Astronomy and Astrophysics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7345532178878784},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6923742890357971},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5531502962112427},{"id":"https://openalex.org/keywords/robotic-spacecraft","display_name":"Robotic spacecraft","score":0.5373393893241882},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.536019504070282},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4540274441242218},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.4527169167995453},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.45142853260040283},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.4300358295440674},{"id":"https://openalex.org/keywords/free-space","display_name":"Free space","score":0.4243807792663574},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41980451345443726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4008135199546814},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.3433484137058258},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.32248327136039734},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09420552849769592},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09034562110900879}],"concepts":[{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7345532178878784},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6923742890357971},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5531502962112427},{"id":"https://openalex.org/C26355699","wikidata":"https://www.wikidata.org/wiki/Q1378139","display_name":"Robotic spacecraft","level":3,"score":0.5373393893241882},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.536019504070282},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4540274441242218},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4527169167995453},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.45142853260040283},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.4300358295440674},{"id":"https://openalex.org/C2988672794","wikidata":"https://www.wikidata.org/wiki/Q11475","display_name":"Free space","level":2,"score":0.4243807792663574},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41980451345443726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4008135199546814},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3433484137058258},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.32248327136039734},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09420552849769592},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09034562110900879},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio.2018.8665049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio.2018.8665049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8600000143051147,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W64088143","https://openalex.org/W1986027544","https://openalex.org/W2025389731","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2173248099","https://openalex.org/W2327917411","https://openalex.org/W2511837229","https://openalex.org/W2566467060","https://openalex.org/W2575705757","https://openalex.org/W2594103415","https://openalex.org/W2609650878","https://openalex.org/W2949561945","https://openalex.org/W2963099933","https://openalex.org/W2963267001","https://openalex.org/W2963403593","https://openalex.org/W2963864421","https://openalex.org/W2963956018","https://openalex.org/W2964161785","https://openalex.org/W4214717370","https://openalex.org/W4299879948","https://openalex.org/W6682849425","https://openalex.org/W6725708968"],"related_works":["https://openalex.org/W618248309","https://openalex.org/W2377336366","https://openalex.org/W1568097102","https://openalex.org/W1601203902","https://openalex.org/W2075798043","https://openalex.org/W4390419160","https://openalex.org/W2102464536","https://openalex.org/W4225671779","https://openalex.org/W2361332776","https://openalex.org/W2897407000"],"abstract_inverted_index":{"In":[0],"this":[1,124],"work,":[2],"a":[3,21],"new":[4],"control":[5],"method":[6,17,125],"for":[7,48],"free-floating":[8,128,145],"space":[9,49,129,146],"robots":[10,147],"to":[11,42,78,155],"capture":[12,156],"targets":[13],"is":[14,76],"proposed.":[15],"This":[16],"can":[18,110,153],"efficiently":[19],"train":[20,43],"variety":[22],"of":[23,32],"target":[24,158],"capturing":[25],"policies":[26,47,97,152],"without":[27],"knowing":[28],"the":[29,33,54,58,67,72,80,85,108,113,127,140,144,157],"dynamic":[30],"models":[31],"robot":[34,109,130],"system.":[35],"We":[36,121],"use":[37],"soft":[38,55,94],"Q-learning":[39,95],"(SQL)":[40],"algorithm":[41],"stochastic":[44,60,149],"energy":[45,150],"based":[46,65,151],"manipulator":[50,135],"motion":[51],"planning.":[52],"Firstly,":[53],"Q-network":[56],"and":[57,103,133,139],"state-conditioned":[59],"policy":[61,104],"network":[62],"are":[63,88],"constructed":[64],"on":[66,126],"maximum":[68],"entropy":[69,105],"objective.":[70],"Then,":[71],"experience":[73],"replay":[74],"pool":[75],"built":[77],"store":[79],"training":[81],"samples":[82],"with":[83,131,148],"which":[84],"both":[86,100],"networks":[87],"trained":[89],"under":[90],"SQL":[91],"procedures.":[92],"Finally,":[93],"trains":[96],"that":[98,107,143],"maximize":[99],"accumulated":[101],"reward":[102],"such":[106],"successfully":[111],"perform":[112],"task":[114],"while":[115],"act":[116],"as":[117,119],"randomly":[118],"possible.":[120],"have":[122],"validated":[123],"single-arm":[132],"duel-arm":[134],"in":[136,159],"simulation":[137],"respectively":[138],"results":[141],"show":[142],"manage":[154],"different":[160],"ways.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}