{"id":"https://openalex.org/W3165885159","doi":"https://doi.org/10.1109/tsmc.2022.3228901","title":"Deep Reinforcement Learning With a Stage Incentive Mechanism of Dense Reward for Robotic Trajectory Planning","display_name":"Deep Reinforcement Learning With a Stage Incentive Mechanism of Dense Reward for Robotic Trajectory Planning","publication_year":2022,"publication_date":"2022-12-30","ids":{"openalex":"https://openalex.org/W3165885159","doi":"https://doi.org/10.1109/tsmc.2022.3228901","mag":"3165885159"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2022.3228901","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tsmc.2022.3228901","pdf_url":"https://ieeexplore.ieee.org/ielx7/6221021/10128819/10004017.pdf","source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6221021/10128819/10004017.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082599710","display_name":"Gang Peng","orcid":"https://orcid.org/0000-0001-8801-0972"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Peng","raw_affiliation_strings":["School of Artificial Intelligence and Automation and the Key Laboratory of Image Processing and Intelligent Control, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-8801-0972","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Automation and the Key Laboratory of Image Processing and Intelligent Control, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100602678","display_name":"Jin Yang","orcid":"https://orcid.org/0000-0001-9625-7449"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Yang","raw_affiliation_strings":["School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-9625-7449","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010863275","display_name":"Xinde Li","orcid":"https://orcid.org/0000-0002-1529-4537"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinde Li","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-1529-4537","affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073582470","display_name":"Mohammad Omar Khyam","orcid":"https://orcid.org/0000-0002-1988-2328"},"institutions":[{"id":"https://openalex.org/I74899385","display_name":"Central Queensland University","ror":"https://ror.org/023q4bk22","country_code":"AU","type":"education","lineage":["https://openalex.org/I74899385"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mohammad Omar Khyam","raw_affiliation_strings":["School of Engineering and Technology, Central Queensland University, Melbourne, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0002-1988-2328","affiliations":[{"raw_affiliation_string":"School of Engineering and Technology, Central Queensland University, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I74899385"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3217,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.89368992,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"53","issue":"6","first_page":"3566","last_page":"3573"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9991999864578247,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9743000268936157,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.7592043280601501},{"id":"https://openalex.org/keywords/incentive","display_name":"Incentive","score":0.68454909324646},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6270720362663269},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6076022386550903},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5813880562782288},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5710713267326355},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.514919638633728},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49434757232666016},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4637957215309143},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3520684242248535},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.34189099073410034},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.315066933631897},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16524603962898254},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.14945584535598755},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.09351849555969238},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.08206745982170105}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7592043280601501},{"id":"https://openalex.org/C29122968","wikidata":"https://www.wikidata.org/wiki/Q1414816","display_name":"Incentive","level":2,"score":0.68454909324646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6270720362663269},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6076022386550903},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5813880562782288},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5710713267326355},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.514919638633728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49434757232666016},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4637957215309143},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3520684242248535},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.34189099073410034},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.315066933631897},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16524603962898254},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.14945584535598755},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.09351849555969238},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.08206745982170105},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tsmc.2022.3228901","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tsmc.2022.3228901","pdf_url":"https://ieeexplore.ieee.org/ielx7/6221021/10128819/10004017.pdf","source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2009.12068","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.12068","pdf_url":"https://arxiv.org/pdf/2009.12068","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,"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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2009.12068","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2009.12068","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,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1109/tsmc.2022.3228901","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tsmc.2022.3228901","pdf_url":"https://ieeexplore.ieee.org/ielx7/6221021/10128819/10004017.pdf","source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G2597794988","display_name":null,"funder_award_id":"2019CFB526","funder_id":"https://openalex.org/F4320322186","funder_display_name":"Natural Science Foundation of Hubei Province"},{"id":"https://openalex.org/G4103908599","display_name":null,"funder_award_id":"91748106","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322186","display_name":"Natural Science Foundation of Hubei Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3165885159.pdf","grobid_xml":"https://content.openalex.org/works/W3165885159.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1587979646","https://openalex.org/W2082511574","https://openalex.org/W2145339207","https://openalex.org/W2596874484","https://openalex.org/W2736601468","https://openalex.org/W2750110103","https://openalex.org/W2752941321","https://openalex.org/W2781726626","https://openalex.org/W2782862780","https://openalex.org/W2794259092","https://openalex.org/W2901563868","https://openalex.org/W2904140934","https://openalex.org/W2921851574","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2966477667","https://openalex.org/W2966489275","https://openalex.org/W2971894000","https://openalex.org/W2999017893","https://openalex.org/W3006653248","https://openalex.org/W3009523569","https://openalex.org/W3033320836","https://openalex.org/W3038610377","https://openalex.org/W3085126702","https://openalex.org/W3092429416","https://openalex.org/W3154562887","https://openalex.org/W3216082637","https://openalex.org/W4225947020","https://openalex.org/W4286748781","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6757322120","https://openalex.org/W6768283567","https://openalex.org/W6840380725"],"related_works":["https://openalex.org/W2367468089","https://openalex.org/W2358591856","https://openalex.org/W4306904969","https://openalex.org/W2098133976","https://openalex.org/W2347416728","https://openalex.org/W2468219149","https://openalex.org/W2974100988","https://openalex.org/W2138720691","https://openalex.org/W2215702767","https://openalex.org/W4362501864"],"abstract_inverted_index":{"To":[0],"improve":[1,73,95,138],"the":[2,29,43,53,61,74,77,82,102,130,139],"efficiency":[3],"of":[4,63,76,87,105],"deep":[5],"reinforcement":[6],"learning":[7,44,78,96],"(DRL)-based":[8],"methods":[9],"for":[10],"robot":[11],"manipulator":[12],"trajectory":[13,50],"planning":[14],"in":[15,91],"random":[16],"working":[17],"environments,":[18],"we":[19,98],"present":[20],"three":[21],"dense":[22],"reward":[23,36,68,118,124,133,145],"functions.":[24],"These":[25],"rewards":[26],"differ":[27],"from":[28],"traditional":[30],"sparse":[31],"reward.":[32],"First,":[33],"a":[34,47,66,110,115,121],"posture":[35],"function":[37,69,119,134],"is":[38,70,135],"proposed":[39,71],"to":[40,72,93,137],"speed":[41],"up":[42],"process":[45,79,104],"with":[46],"more":[48],"reasonable":[49],"by":[51,80,101],"modeling":[52,81],"distance":[54,83,86],"and":[55,84,108,120,146],"direction":[56],"constraints,":[57],"which":[58],"can":[59],"reduce":[60],"blindness":[62],"exploration.":[64],"Second,":[65],"stride":[67],"stability":[75],"movement":[85],"joint":[88],"constraints.":[89],"Finally,":[90],"order":[92],"further":[94],"efficiency,":[97],"are":[99],"inspired":[100],"cognitive":[103],"human":[106],"behavior":[107],"propose":[109],"stage":[111],"incentive":[112,117,123,132],"mechanism,":[113],"including":[114],"hard-stage":[116],"soft-stage":[122,131],"function.":[125],"Extensive":[126],"experiments":[127],"show":[128],"that":[129],"able":[136],"convergence":[140],"rate,":[141],"get":[142],"higher":[143],"mean":[144],"lower":[147],"standard":[148],"deviation":[149],"after":[150],"convergence.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2021-06-07T00:00:00"}