{"id":"https://openalex.org/W4402891929","doi":"https://doi.org/10.1109/tro.2024.3468770","title":"Using Implicit Behavior Cloning and Dynamic Movement Primitive to Facilitate Reinforcement Learning for Robot Motion Planning","display_name":"Using Implicit Behavior Cloning and Dynamic Movement Primitive to Facilitate Reinforcement Learning for Robot Motion Planning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402891929","doi":"https://doi.org/10.1109/tro.2024.3468770"},"language":"en","primary_location":{"id":"doi:10.1109/tro.2024.3468770","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tro.2024.3468770","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1941-0468"],"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 Transactions on Robotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.tue.nl/ws/files/354719295/Using_Implicit_Behavior_Cloning_and_Dynamic_Movement_Primitive_to_Facilitate_Reinforcement_Learning_for_Robot_Motion_Planning.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101743605","display_name":"Zengjie Zhang","orcid":"https://orcid.org/0000-0003-1875-1032"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Zengjie Zhang","raw_affiliation_strings":["Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands","Department of Electrical Engineering, Eindhoven University of Technology, Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-1875-1032","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]},{"raw_affiliation_string":"Department of Electrical Engineering, Eindhoven University of Technology, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058528437","display_name":"Jayden Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jayden Hong","raw_affiliation_strings":["Faculty of Engineering and Computer Science, University of Victoria, Victoria, BC, Canada","Faculty of Engineering and Computer Science, University of Victoria, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Computer Science, University of Victoria, Victoria, BC, Canada","institution_ids":["https://openalex.org/I212119943"]},{"raw_affiliation_string":"Faculty of Engineering and Computer Science, University of Victoria, Canada","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038499955","display_name":"Amir M. Soufi Enayati","orcid":"https://orcid.org/0000-0002-6736-8016"},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Amir M. Soufi Enayati","raw_affiliation_strings":["Faculty of Engineering and Computer Science, University of Victoria, Victoria, BC, Canada","Faculty of Engineering and Computer Science, University of Victoria, Canada"],"raw_orcid":"https://orcid.org/0000-0002-6736-8016","affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Computer Science, University of Victoria, Victoria, BC, Canada","institution_ids":["https://openalex.org/I212119943"]},{"raw_affiliation_string":"Faculty of Engineering and Computer Science, University of Victoria, Canada","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058540009","display_name":"Homayoun Najjaran","orcid":"https://orcid.org/0000-0002-3550-225X"},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Homayoun Najjaran","raw_affiliation_strings":["Faculty of Engineering and Computer Science, University of Victoria, Victoria, BC, Canada","Faculty of Engineering and Computer Science, University of Victoria, Canada"],"raw_orcid":"https://orcid.org/0000-0002-3550-225X","affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Computer Science, University of Victoria, Victoria, BC, Canada","institution_ids":["https://openalex.org/I212119943"]},{"raw_affiliation_string":"Faculty of Engineering and Computer Science, University of Victoria, Canada","institution_ids":["https://openalex.org/I212119943"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2765,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.94931039,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"40","issue":null,"first_page":"4733","last_page":"4749"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9761000275611877,"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":0.9761000275611877,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9506000280380249,"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"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9399999976158142,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7621385455131531},{"id":"https://openalex.org/keywords/cloning","display_name":"Cloning (programming)","score":0.6313983201980591},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6250320672988892},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5985019207000732},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5916695594787598},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.5599076747894287},{"id":"https://openalex.org/keywords/movement","display_name":"Movement (music)","score":0.5526085495948792},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5215751528739929},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07574108242988586},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06413188576698303}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7621385455131531},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.6313983201980591},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6250320672988892},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5985019207000732},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5916695594787598},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.5599076747894287},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.5526085495948792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5215751528739929},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07574108242988586},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06413188576698303},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tro.2024.3468770","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tro.2024.3468770","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1941-0468"],"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 Transactions on Robotics","raw_type":"journal-article"},{"id":"pmh:oai:pure.tue.nl:publications/77524280-d224-4c4b-87c5-58a085026b58","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/77524280-d224-4c4b-87c5-58a085026b58","pdf_url":"https://pure.tue.nl/ws/files/354719295/Using_Implicit_Behavior_Cloning_and_Dynamic_Movement_Primitive_to_Facilitate_Reinforcement_Learning_for_Robot_Motion_Planning.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Zhang, Z, Hong, J, Soufi Enayati, A M & Najjaran, H 2024, 'Using Implicit Behavior Cloning and Dynamic Movement Primitive to Facilitate Reinforcement Learning for Robot Motion Planning', IEEE Transactions on Robotics, vol. 40, pp. 4733-4749. https://doi.org/10.1109/TRO.2024.3468770","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.tue.nl:publications/77524280-d224-4c4b-87c5-58a085026b58","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/77524280-d224-4c4b-87c5-58a085026b58","pdf_url":"https://pure.tue.nl/ws/files/354719295/Using_Implicit_Behavior_Cloning_and_Dynamic_Movement_Primitive_to_Facilitate_Reinforcement_Learning_for_Robot_Motion_Planning.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Zhang, Z, Hong, J, Soufi Enayati, A M & Najjaran, H 2024, 'Using Implicit Behavior Cloning and Dynamic Movement Primitive to Facilitate Reinforcement Learning for Robot Motion Planning', IEEE Transactions on Robotics, vol. 40, pp. 4733-4749. https://doi.org/10.1109/TRO.2024.3468770","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1775966864","display_name":null,"funder_award_id":"543881-19","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G3708286853","display_name":null,"funder_award_id":"CRDPJ 543881-19","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402891929.pdf","grobid_xml":"https://content.openalex.org/works/W4402891929.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W130216483","https://openalex.org/W1982100856","https://openalex.org/W1993730936","https://openalex.org/W2010953845","https://openalex.org/W2060914855","https://openalex.org/W2071444114","https://openalex.org/W2109572794","https://openalex.org/W2142224528","https://openalex.org/W2151927054","https://openalex.org/W2775482448","https://openalex.org/W2786205197","https://openalex.org/W2900582619","https://openalex.org/W2921955147","https://openalex.org/W2936507074","https://openalex.org/W2963099939","https://openalex.org/W2963411833","https://openalex.org/W2972941110","https://openalex.org/W2976205474","https://openalex.org/W2978612180","https://openalex.org/W2981260474","https://openalex.org/W2994446013","https://openalex.org/W3006097963","https://openalex.org/W3034269714","https://openalex.org/W3088310808","https://openalex.org/W3091091967","https://openalex.org/W3100789280","https://openalex.org/W3117414450","https://openalex.org/W3117893216","https://openalex.org/W3128528928","https://openalex.org/W3130777366","https://openalex.org/W3133933269","https://openalex.org/W3134939669","https://openalex.org/W3137253783","https://openalex.org/W3139187989","https://openalex.org/W3158592412","https://openalex.org/W3165149185","https://openalex.org/W3206385822","https://openalex.org/W3214738088","https://openalex.org/W3215337761","https://openalex.org/W4225839319","https://openalex.org/W4229007060","https://openalex.org/W4285048301","https://openalex.org/W4285102525","https://openalex.org/W4293232200","https://openalex.org/W4293241531","https://openalex.org/W4296683478","https://openalex.org/W4312587811","https://openalex.org/W4321607911","https://openalex.org/W6755421158","https://openalex.org/W6774529172","https://openalex.org/W6800425027","https://openalex.org/W6802632727","https://openalex.org/W6803376173","https://openalex.org/W6838833932","https://openalex.org/W6841549819"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435","https://openalex.org/W4391331176"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"for":[3,104,162],"motion":[4,32,79,151],"planning":[5,33,80,84],"of":[6,16,53,68,112,134,160],"multi-degree-of-freedom":[7],"robots":[8],"still":[9],"suffers":[10],"from":[11],"low":[12],"efficiency":[13],"in":[14],"terms":[15],"slow":[17],"training":[18,49,66,123],"speed":[19,50,67,124],"and":[20,41,51,70,125,153],"poor":[21],"generalizability.":[22],"In":[23],"this":[24],"article,":[25],"we":[26,89],"propose":[27],"a":[28,74,82,92,97,139,146],"novel":[29,147],"RL-based":[30],"robot":[31,163],"framework":[34],"that":[35,77,100],"uses":[36],"implicit":[37],"behavior":[38],"cloning":[39],"(IBC)":[40],"dynamic":[42],"movement":[43],"primitive":[44],"(DMP)":[45],"to":[46,63,138,156],"improve":[47],"the":[48,65,110,113,117,132,135,158],"generalizability":[52],"an":[54],"off-policy":[55],"RL":[56,119,161],"agent.":[57],"IBC":[58],"utilizes":[59],"human":[60,93,154],"demonstration":[61,94,155],"data":[62],"leverage":[64,157],"RL,":[69],"DMP":[71],"serves":[72],"as":[73],"heuristic":[75],"model":[76],"transfers":[78],"into":[81],"simpler":[83],"space.":[85],"To":[86],"support":[87],"this,":[88],"also":[90],"create":[91],"dataset":[95],"using":[96,150],"pick-and-place":[98],"experiment":[99,130],"can":[101],"be":[102],"used":[103],"similar":[105],"studies.":[106],"Comparison":[107],"studies":[108],"reveal":[109],"advantage":[111],"proposed":[114,136],"method":[115,137],"over":[116],"conventional":[118],"agents":[120],"with":[121],"faster":[122],"higher":[126],"scores.":[127],"A":[128],"real-robot":[129],"indicates":[131],"applicability":[133],"simple":[140],"assembly":[141],"task.":[142],"Our":[143],"work":[144],"provides":[145],"perspective":[148],"on":[149],"primitives":[152],"performance":[159],"applications.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}