{"id":"https://openalex.org/W4405270155","doi":"https://doi.org/10.1109/tase.2024.3513354","title":"Trajectory Progress-Based Prioritizing and Intrinsic Reward Mechanism for Robust Training of Robotic Manipulations","display_name":"Trajectory Progress-Based Prioritizing and Intrinsic Reward Mechanism for Robust Training of Robotic Manipulations","publication_year":2024,"publication_date":"2024-12-11","ids":{"openalex":"https://openalex.org/W4405270155","doi":"https://doi.org/10.1109/tase.2024.3513354"},"language":"en","primary_location":{"id":"doi:10.1109/tase.2024.3513354","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2024.3513354","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","raw_type":"journal-article"},"type":"article","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/A5070029533","display_name":"Weixiang Liang","orcid":"https://orcid.org/0000-0002-7658-0983"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]},{"id":"https://openalex.org/I6469544","display_name":"City University of Macau","ror":"https://ror.org/04gpd4q15","country_code":"MO","type":"education","lineage":["https://openalex.org/I6469544"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Weixiang Liang","raw_affiliation_strings":["Department of Electromechanical Engineering, State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau, China","State Key Laboratory of Internet of Things for Smart City and Department of Electromechanical Engineering, University of Macau, Macau, China"],"raw_orcid":"https://orcid.org/0000-0002-7658-0983","affiliations":[{"raw_affiliation_string":"Department of Electromechanical Engineering, State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498","https://openalex.org/I6469544"]},{"raw_affiliation_string":"State Key Laboratory of Internet of Things for Smart City and Department of Electromechanical Engineering, University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498","https://openalex.org/I6469544"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013630392","display_name":"Yinlong Liu","orcid":"https://orcid.org/0000-0002-6468-8233"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]},{"id":"https://openalex.org/I6469544","display_name":"City University of Macau","ror":"https://ror.org/04gpd4q15","country_code":"MO","type":"education","lineage":["https://openalex.org/I6469544"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Yinlong Liu","raw_affiliation_strings":["Department of Electromechanical Engineering, State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau, China","State Key Laboratory of Internet of Things for Smart City and Department of Electromechanical Engineering, University of Macau, Macau, China"],"raw_orcid":"https://orcid.org/0000-0002-6468-8233","affiliations":[{"raw_affiliation_string":"Department of Electromechanical Engineering, State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498","https://openalex.org/I6469544"]},{"raw_affiliation_string":"State Key Laboratory of Internet of Things for Smart City and Department of Electromechanical Engineering, University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498","https://openalex.org/I6469544"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101616905","display_name":"Jikun Wang","orcid":"https://orcid.org/0000-0002-0201-2844"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]},{"id":"https://openalex.org/I6469544","display_name":"City University of Macau","ror":"https://ror.org/04gpd4q15","country_code":"MO","type":"education","lineage":["https://openalex.org/I6469544"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Jikun Wang","raw_affiliation_strings":["Department of Electromechanical Engineering, State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau, China","State Key Laboratory of Internet of Things for Smart City and Department of Electromechanical Engineering, University of Macau, Macau, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electromechanical Engineering, State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498","https://openalex.org/I6469544"]},{"raw_affiliation_string":"State Key Laboratory of Internet of Things for Smart City and Department of Electromechanical Engineering, University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498","https://openalex.org/I6469544"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011123518","display_name":"Zhi-Xin Yang","orcid":"https://orcid.org/0000-0001-9151-7758"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]},{"id":"https://openalex.org/I6469544","display_name":"City University of Macau","ror":"https://ror.org/04gpd4q15","country_code":"MO","type":"education","lineage":["https://openalex.org/I6469544"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Zhi-Xin Yang","raw_affiliation_strings":["Department of Electromechanical Engineering, State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau, China","State Key Laboratory of Internet of Things for Smart City and Department of Electromechanical Engineering, University of Macau, Macau, China"],"raw_orcid":"https://orcid.org/0000-0001-9151-7758","affiliations":[{"raw_affiliation_string":"Department of Electromechanical Engineering, State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498","https://openalex.org/I6469544"]},{"raw_affiliation_string":"State Key Laboratory of Internet of Things for Smart City and Department of Electromechanical Engineering, University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498","https://openalex.org/I6469544"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3724,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.56936978,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"22","issue":null,"first_page":"9829","last_page":"9842"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9940000176429749,"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":0.9940000176429749,"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/T10571","display_name":"Robotic Mechanisms and Dynamics","score":0.9797000288963318,"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/T10805","display_name":"Vehicle Dynamics and Control Systems","score":0.9580000042915344,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/trajectory","display_name":"Trajectory","score":0.6365283131599426},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.6163345575332642},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5381985306739807},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.48494914174079895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4785381257534027},{"id":"https://openalex.org/keywords/grippers","display_name":"Grippers","score":0.47430944442749023},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.470737099647522},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4463287889957428},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4105187952518463},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.35408443212509155},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.23069527745246887},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10438215732574463}],"concepts":[{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6365283131599426},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.6163345575332642},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5381985306739807},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.48494914174079895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4785381257534027},{"id":"https://openalex.org/C2775960376","wikidata":"https://www.wikidata.org/wiki/Q1435859","display_name":"Grippers","level":2,"score":0.47430944442749023},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.470737099647522},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4463287889957428},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4105187952518463},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.35408443212509155},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.23069527745246887},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10438215732574463},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2024.3513354","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2024.3513354","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2380914304","display_name":null,"funder_award_id":"0075/2023/AMJ","funder_id":"https://openalex.org/F4320321655","funder_display_name":"Science and Technology Development Fund"},{"id":"https://openalex.org/G4130411185","display_name":null,"funder_award_id":"0003/2023/RIB1","funder_id":"https://openalex.org/F4320321655","funder_display_name":"Science and Technology Development Fund"},{"id":"https://openalex.org/G4720968450","display_name":null,"funder_award_id":"2023A0505030003","funder_id":"https://openalex.org/F4320324202","funder_display_name":"Guangdong Science and Technology Department"},{"id":"https://openalex.org/G4769791754","display_name":null,"funder_award_id":"001/2024/SKL","funder_id":"https://openalex.org/F4320321655","funder_display_name":"Science and Technology Development Fund"},{"id":"https://openalex.org/G5335157455","display_name":null,"funder_award_id":"2020B1515130001","funder_id":"https://openalex.org/F4320324202","funder_display_name":"Guangdong Science and Technology Department"}],"funders":[{"id":"https://openalex.org/F4320321655","display_name":"Science and Technology Development Fund","ror":"https://ror.org/044vr6g03"},{"id":"https://openalex.org/F4320324202","display_name":"Guangdong Science and Technology Department","ror":"https://ror.org/00tjzgn92"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2258669850","https://openalex.org/W1513401665","https://openalex.org/W4283263216","https://openalex.org/W3160851599","https://openalex.org/W2078285315","https://openalex.org/W2964156592","https://openalex.org/W2527333706","https://openalex.org/W2903025760","https://openalex.org/W4289147272","https://openalex.org/W1640559846"],"abstract_inverted_index":{"Training":[0],"robots":[1,223],"by":[2,62,272],"model-free":[3,38],"deep":[4],"reinforcement":[5,220,252],"learning":[6,183,221,253,303],"(DRL)":[7],"to":[8,26,30,47,80,95,118,172,177,224,236,263,282,382,386],"carry":[9],"out":[10],"robotic":[11,136,187,209,351],"manipulation":[12,137,188,226,345,352],"tasks":[13,138,227,346],"without":[14],"sufficient":[15],"successful":[16,376],"experiences":[17],"is":[18,24,93,113,175,323,364,371],"challenging.":[19],"Hindsight":[20],"experience":[21],"replay":[22],"(HER)":[23],"introduced":[25,114],"enable":[27],"DRL":[28,39],"agents":[29,126,302],"learn":[31,225],"from":[32,42,379],"failure":[33],"experiences.":[34],"However,":[35,248],"the":[36,58,63,85,107,125,128,232,241,249,264,320,326,335,362,387,400,405,408],"HER-enabled":[37],"still":[40],"suffers":[41],"limited":[43],"training":[44,117,152,258],"performance":[45,261],"due":[46,262,385],"its":[48,159],"uniform":[49,265],"sampling":[50,97,266],"strategy":[51],"and":[52,147,158,165,181,196,202,211,243,260,267,310,349,356,369,392],"scarcity":[53],"of":[54,130,156,189,219,315,342,375,407],"reward":[55],"information":[56],"in":[57,67,77,115,134,151,162,308,319,325,347,399,413],"task":[59,131,269,403],"environment.":[60],"Inspired":[61,271],"progress":[64,279],"incentive":[65,280],"mechanism":[66,281],"human":[68,273],"psychology,":[69],"we":[70],"propose":[71],"Progress":[72,108],"Intrinsic":[73,109],"Motivation-based":[74],"HER":[75,146],"(P-HER)":[76],"this":[78,275],"work":[79,174,276],"overcome":[81],"these":[82],"difficulties.":[83],"First,":[84],"Trajectory":[86],"Progress-based":[87],"Prioritized":[88],"Experience":[89],"Replay":[90],"(TPPER)":[91],"module":[92,112],"developed":[94],"prioritize":[96],"valuable":[98,284,304],"trajectory":[99,285,305],"data":[100,286],"thereby":[101],"achieving":[102],"more":[103],"efficient":[104],"training.":[105,289],"Second,":[106],"Reward":[110],"(PIR)":[111],"agent":[116],"add":[119],"extra":[120],"intrinsic":[121,299],"rewards":[122,300],"for":[123,185,207,234,287,301,333,366,411],"encouraging":[124],"throughout":[127],"exploration":[129],"space.":[132],"Experiments":[133],"challenging":[135],"demonstrate":[139],"that":[140,296,361],"our":[141],"P-HER":[142,157],"method":[143,184,322,363],"outperforms":[144],"original":[145],"state-of-the-art":[148],"HER-based":[149,251],"methods":[150],"performance.":[153],"Our":[154],"code":[155],"experimental":[160],"videos":[161],"both":[163,367],"virtual":[164],"real":[166,350,383,401],"environments":[167,353,368],"are":[168,200,255,354],"available":[169],"athttps://github.com/weixiang-smart/P-HER.":[170],"Note":[171],"Practitioners\u2014This":[173],"motivated":[176],"develop":[178],"a":[179,278,292,330],"fast":[180,309],"effective":[182,288,365],"intelligent":[186],"typical":[190],"industrial":[191,414],"tasks,":[192],"including":[193],"pushing,":[194],"picking,":[195],"placing":[197],"workpieces,":[198],"which":[199,229,328,359],"essential":[201],"fundamental":[203],"processing":[204],"plan":[205],"activities":[206],"accomplishing":[208],"machining":[210],"assembly":[212],"applications":[213],"towards":[214],"smart":[215],"manufacturing.":[216],"The":[217,313,338,394],"introduction":[218],"enables":[222],"autonomously,":[228],"can":[230],"save":[231],"effort":[233],"engineers":[235],"teach":[237],"or":[238],"hard":[239],"program":[240],"robot":[242],"also":[244],"reduce":[245],"labor":[246],"costs.":[247],"existing":[250],"algorithms":[254],"with":[256],"low":[257],"efficiency":[259],"scant":[268],"reward.":[270],"learning,":[274],"introduces":[277],"identify":[283],"In":[290],"addition,":[291],"novel":[293],"rewarding":[294,321],"method,":[295],"applies":[297],"additional":[298],"space,":[306],"results":[307],"robust":[311],"learning.":[312],"setting":[314],"important":[316],"weight":[317],"parameters":[318],"given":[324],"paper,":[327],"provides":[329],"practical":[331],"reference":[332],"applying":[334],"proposed":[336],"algorithm.":[337],"average":[339,373],"success":[340,396],"rate":[341,377,397],"two":[343],"actual":[344],"simulation":[348,380,391],"96%":[355],"92.5%,":[357],"respectively,":[358],"demonstrates":[360],"there":[370],"3.5%":[372],"gap":[374],"dropping":[378],"scenarios":[381],"ones":[384],"inherent":[388],"mismatches":[389],"between":[390],"reality.":[393],"high":[395],"demonstrated":[398],"Workpieces-sorting":[402],"exemplifies":[404],"potential":[406],"trained":[409],"policies":[410],"application":[412],"scenarios.":[415]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}