{"id":"https://openalex.org/W3000110877","doi":"https://doi.org/10.1109/lra.2020.2965392","title":"Constrained-Space Optimization and Reinforcement Learning for Complex Tasks","display_name":"Constrained-Space Optimization and Reinforcement Learning for Complex Tasks","publication_year":2020,"publication_date":"2020-01-09","ids":{"openalex":"https://openalex.org/W3000110877","doi":"https://doi.org/10.1109/lra.2020.2965392","mag":"3000110877"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2020.2965392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2020.2965392","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.00716","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030468477","display_name":"Ya-Yen Tsai","orcid":"https://orcid.org/0000-0001-8037-355X"},"institutions":[{"id":"https://openalex.org/I4210151473","display_name":"Robotic Technology (United States)","ror":"https://ror.org/05xp03991","country_code":"US","type":"company","lineage":["https://openalex.org/I4210151473"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ya-Yen Tsai","raw_affiliation_strings":["Hamlyn Centre for Robotic Surgery, SW7 2AZ London, U.K"],"affiliations":[{"raw_affiliation_string":"Hamlyn Centre for Robotic Surgery, SW7 2AZ London, U.K","institution_ids":["https://openalex.org/I4210151473"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041909892","display_name":"Bo Xiao","orcid":"https://orcid.org/0000-0001-9361-4340"},"institutions":[{"id":"https://openalex.org/I4210151473","display_name":"Robotic Technology (United States)","ror":"https://ror.org/05xp03991","country_code":"US","type":"company","lineage":["https://openalex.org/I4210151473"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Xiao","raw_affiliation_strings":["Hamlyn Centre for Robotic Surgery, SW7 2AZ London, U.K"],"affiliations":[{"raw_affiliation_string":"Hamlyn Centre for Robotic Surgery, SW7 2AZ London, U.K","institution_ids":["https://openalex.org/I4210151473"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080385974","display_name":"Edward Johns","orcid":"https://orcid.org/0000-0002-8914-8786"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Edward Johns","raw_affiliation_strings":["Robot Learning Lab, Imperial College London, SW7 2AZ London, U.K"],"affiliations":[{"raw_affiliation_string":"Robot Learning Lab, Imperial College London, SW7 2AZ London, U.K","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085036036","display_name":"Guang\u2010Zhong Yang","orcid":"https://orcid.org/0000-0003-4060-4020"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210151473","display_name":"Robotic Technology (United States)","ror":"https://ror.org/05xp03991","country_code":"US","type":"company","lineage":["https://openalex.org/I4210151473"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Guang-Zhong Yang","raw_affiliation_strings":["Hamlyn Centre for Robotic Surgery, SW7 2AZ London, U.K","Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Hamlyn Centre for Robotic Surgery, SW7 2AZ London, U.K","institution_ids":["https://openalex.org/I4210151473"]},{"raw_affiliation_string":"Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030468477"],"corresponding_institution_ids":["https://openalex.org/I4210151473"],"apc_list":null,"apc_paid":null,"fwci":1.484,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.81351985,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"5","issue":"2","first_page":"683","last_page":"690"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10653","display_name":"Robot Manipulation and Learning","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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":0.9925000071525574,"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/T11159","display_name":"Manufacturing Process and Optimization","score":0.984499990940094,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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":0.9010013341903687},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7050525546073914},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6859309673309326},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5528042316436768},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5253623723983765},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5153347849845886},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.49997472763061523},{"id":"https://openalex.org/keywords/smoothness","display_name":"Smoothness","score":0.4944279193878174},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.4606073200702667},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39275437593460083},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.38005584478378296},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11009520292282104}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9010013341903687},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7050525546073914},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6859309673309326},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5528042316436768},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5253623723983765},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5153347849845886},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.49997472763061523},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.4944279193878174},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.4606073200702667},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39275437593460083},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38005584478378296},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11009520292282104},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2020.2965392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2020.2965392","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2004.00716","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.00716","pdf_url":"https://arxiv.org/pdf/2004.00716","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.00716","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.00716","pdf_url":"https://arxiv.org/pdf/2004.00716","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[],"awards":[{"id":"https://openalex.org/G1623289732","display_name":null,"funder_award_id":"EP/L020688/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G2819266950","display_name":null,"funder_award_id":"EP/P012779/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5703964369","display_name":null,"funder_award_id":"EP/H009744/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6661093488","display_name":"Personalised Stent Graft Manufacturing for Endovascular Intervention","funder_award_id":"EP/L020688/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1540685400","https://openalex.org/W1977655452","https://openalex.org/W1986014385","https://openalex.org/W2013293242","https://openalex.org/W2018346149","https://openalex.org/W2027197837","https://openalex.org/W2048076085","https://openalex.org/W2110304639","https://openalex.org/W2133552775","https://openalex.org/W2136719407","https://openalex.org/W2145339207","https://openalex.org/W2153682458","https://openalex.org/W2161395589","https://openalex.org/W2257979135","https://openalex.org/W2577634205","https://openalex.org/W2622604310","https://openalex.org/W2741122588","https://openalex.org/W2766302693","https://openalex.org/W2785379783","https://openalex.org/W2788862220","https://openalex.org/W2803616302","https://openalex.org/W2909098022","https://openalex.org/W2913500548","https://openalex.org/W2952629144","https://openalex.org/W2962764547","https://openalex.org/W2963099939","https://openalex.org/W2963363446","https://openalex.org/W2963376229","https://openalex.org/W2963826726","https://openalex.org/W2965916140","https://openalex.org/W2969060758","https://openalex.org/W6632235069","https://openalex.org/W6679700999","https://openalex.org/W6728925229","https://openalex.org/W6738980247","https://openalex.org/W6745661885","https://openalex.org/W6748314335","https://openalex.org/W6748645729","https://openalex.org/W6751285671"],"related_works":["https://openalex.org/W2374250903","https://openalex.org/W2393022482","https://openalex.org/W2377346130","https://openalex.org/W1546413948","https://openalex.org/W2361092061","https://openalex.org/W2263832889","https://openalex.org/W2243884323","https://openalex.org/W2319775965","https://openalex.org/W3213722473","https://openalex.org/W2110944602"],"abstract_inverted_index":{"Learning":[0],"from":[1,77],"demonstration":[2],"is":[3,16,57,75,84,107],"increasingly":[4],"used":[5],"for":[6,20,43],"transferring":[7],"operator":[8],"manipulation":[9,62],"skills":[10,63],"to":[11,18,59,65,87,91,97],"robots.":[12],"In":[13],"practice,":[14],"it":[15],"important":[17],"cater":[19],"limited":[21],"data":[22],"and":[23,39,132],"imperfect":[24],"human":[25],"demonstrations,":[26],"as":[27,29,135,137],"well":[28,136],"underlying":[30],"safety":[31],"constraints.":[32],"This":[33],"article":[34],"presents":[35],"a":[36,66,110],"constrained-space":[37],"optimization":[38],"reinforcement":[40,54,80],"learning":[41,55,81],"scheme":[42],"managing":[44],"complex":[45],"tasks.":[46],"Through":[47],"interactions":[48],"within":[49],"the":[50,53,61,72,78,89,98,104,116,120,126,129,138],"constrained":[51],"space,":[52],"agent":[56],"trained":[58],"optimize":[60],"according":[64],"defined":[67],"reward":[68],"function.":[69],"After":[70],"learning,":[71],"optimal":[73],"policy":[74,118],"derived":[76],"well-trained":[79],"agent,":[82],"which":[83],"then":[85],"implemented":[86],"guide":[88],"robot":[90],"conduct":[92],"tasks":[93],"that":[94,115],"are":[95],"similar":[96],"experts'":[99,121],"demonstrations.":[100],"The":[101],"effectiveness":[102],"of":[103,125,128],"proposed":[105],"method":[106],"verified":[108],"with":[109],"robotic":[111],"suturing":[112],"task,":[113],"demonstrating":[114],"learned":[117],"outperformed":[119],"demonstrations":[122],"in":[123],"terms":[124],"smoothness":[127],"joint":[130],"motion":[131],"end-effector":[133],"trajectories,":[134],"overall":[139],"task":[140],"completion":[141],"time.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2020-01-23T00:00:00"}