{"id":"https://openalex.org/W4394698426","doi":"https://doi.org/10.1109/tai.2024.3387401","title":"Stabilizing Diffusion Model for Robotic Control With Dynamic Programming and Transition Feasibility","display_name":"Stabilizing Diffusion Model for Robotic Control With Dynamic Programming and Transition Feasibility","publication_year":2024,"publication_date":"2024-04-10","ids":{"openalex":"https://openalex.org/W4394698426","doi":"https://doi.org/10.1109/tai.2024.3387401"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2024.3387401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2024.3387401","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Artificial Intelligence","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/A5100327745","display_name":"Haoran Li","orcid":"https://orcid.org/0000-0003-2559-9585"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Li","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2559-9585","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107519376","display_name":"Yaocheng Zhang","orcid":"https://orcid.org/0009-0002-0973-0467"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaocheng Zhang","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-0973-0467","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100663352","display_name":"Haowei Wen","orcid":"https://orcid.org/0000-0003-1901-7876"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haowei Wen","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1901-7876","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080193690","display_name":"Yuanheng Zhu","orcid":"https://orcid.org/0000-0001-5384-423X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanheng Zhu","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5384-423X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100624298","display_name":"Dongbin Zhao","orcid":"https://orcid.org/0000-0001-8218-9633"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbin Zhao","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8218-9633","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3601,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.9291147,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"5","issue":"9","first_page":"4585","last_page":"4594"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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":0.9987000226974487,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9954000115394592,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9883000254631042,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.6047794222831726},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5863354802131653},{"id":"https://openalex.org/keywords/transition","display_name":"Transition (genetics)","score":0.549841046333313},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5063835382461548},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4165470004081726},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.35627931356430054},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3395598232746124},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.22320669889450073},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.19325056672096252},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18523988127708435},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1352018415927887},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.117133229970932},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11503031849861145}],"concepts":[{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6047794222831726},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5863354802131653},{"id":"https://openalex.org/C194232998","wikidata":"https://www.wikidata.org/wiki/Q1606712","display_name":"Transition (genetics)","level":3,"score":0.549841046333313},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5063835382461548},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4165470004081726},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.35627931356430054},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3395598232746124},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.22320669889450073},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.19325056672096252},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18523988127708435},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1352018415927887},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.117133229970932},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11503031849861145},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2024.3387401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2024.3387401","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1331717323","display_name":null,"funder_award_id":"62103409","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G800914696","display_name":null,"funder_award_id":"62136008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8564052084","display_name":null,"funder_award_id":"2021132","funder_id":"https://openalex.org/F4320322847","funder_display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W2051228319","https://openalex.org/W2735039185","https://openalex.org/W2963890729","https://openalex.org/W2966477753","https://openalex.org/W2978455699","https://openalex.org/W2991355586","https://openalex.org/W2993185773","https://openalex.org/W3016525976","https://openalex.org/W3105636206","https://openalex.org/W4214928275","https://openalex.org/W4229944339","https://openalex.org/W4281661031","https://openalex.org/W4287756699","https://openalex.org/W4308080451","https://openalex.org/W4308167501","https://openalex.org/W4312309366","https://openalex.org/W4312335991","https://openalex.org/W4318242039","https://openalex.org/W4324323374","https://openalex.org/W4360584316","https://openalex.org/W4366850766","https://openalex.org/W4387561000","https://openalex.org/W6684921986","https://openalex.org/W6757469721","https://openalex.org/W6763704811","https://openalex.org/W6765775151","https://openalex.org/W6769342953","https://openalex.org/W6771270455","https://openalex.org/W6771428195","https://openalex.org/W6776601253","https://openalex.org/W6777091672","https://openalex.org/W6779265984","https://openalex.org/W6779656125","https://openalex.org/W6779823529","https://openalex.org/W6780159193","https://openalex.org/W6783713337","https://openalex.org/W6796289742","https://openalex.org/W6800425027","https://openalex.org/W6802659552","https://openalex.org/W6804244202","https://openalex.org/W6838327568","https://openalex.org/W6838483015","https://openalex.org/W6839089550","https://openalex.org/W6840815571","https://openalex.org/W6841549819","https://openalex.org/W6842456838","https://openalex.org/W6843816287","https://openalex.org/W6846142413","https://openalex.org/W6846827642","https://openalex.org/W6847081674","https://openalex.org/W6849187823","https://openalex.org/W6850686577","https://openalex.org/W6851312059","https://openalex.org/W6851885053","https://openalex.org/W6856947211"],"related_works":["https://openalex.org/W1727353606","https://openalex.org/W2292168444","https://openalex.org/W2360747494","https://openalex.org/W2277236374","https://openalex.org/W2126787609","https://openalex.org/W1932159282","https://openalex.org/W2392008502","https://openalex.org/W4312006216","https://openalex.org/W4280540706","https://openalex.org/W1527211675"],"abstract_inverted_index":{"Due":[0],"to":[1,19,38,67,110,114,126],"its":[2],"strong":[3],"ability":[4,113],"in":[5],"distribution":[6],"representation,":[7],"the":[8,24,35,42,58,62,74,82,89,94,99,102,105,112,119,124,133,146,157],"diffusion":[9,36,63,91,134,153],"model":[10,37,64],"has":[11],"been":[12],"incorporated":[13],"into":[14],"offline":[15],"reinforcement":[16],"learning":[17],"(RL)":[18],"cover":[20],"diverse":[21],"trajectories":[22,44],"of":[23,61,88],"complex":[25],"behavior":[26,40,72],"policy.":[27],"However,":[28],"this":[29],"also":[30],"causes":[31],"several":[32],"challenges.":[33],"Training":[34],"imitate":[39],"from":[41,46,54],"collected":[43],"suffers":[45],"limited":[47],"stitching":[48],"capability":[49],"which":[50,86],"derives":[51],"better":[52],"policies":[53],"suboptimal":[55,116],"trajectories.":[56,117],"Furthermore,":[57],"inherent":[59],"randomness":[60],"can":[65],"lead":[66],"unpredictable":[68],"control":[69],"and":[70,93,107,149],"dangerous":[71],"for":[73],"robot.":[75],"To":[76],"address":[77],"these":[78],"concerns,":[79],"we":[80,122],"propose":[81],"Value-learning-based":[83],"Decision":[84],"Diffuser(V-DD),":[85],"consists":[87],"trajectory":[90,95,130],"module(TDM)":[92],"evaluation":[96],"module(TEM).":[97],"During":[98,118],"training":[100],"process,":[101,121],"TDM":[103],"combines":[104],"state-value":[106],"classifier-free":[108],"guidance":[109],"bolster":[111],"stitch":[115],"inference":[120],"design":[123],"TEM":[125],"select":[127],"a":[128],"feasible":[129],"generated":[131],"by":[132],"model.":[135],"Empirical":[136],"results":[137,144],"demonstrate":[138],"that":[139],"our":[140],"method":[141],"delivers":[142],"competitive":[143],"on":[145,156],"D4RL":[147],"benchmark":[148],"substantially":[150],"outperforms":[151],"current":[152],"model-based":[154],"methods":[155],"real-world":[158],"robot":[159],"task.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":11}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}