{"id":"https://openalex.org/W7131817292","doi":"https://doi.org/10.1109/tase.2026.3668970","title":"Toward Reliable Imitation Learning With Limited Expert Demonstrations via Search-Based Inverse Dynamic Learning","display_name":"Toward Reliable Imitation Learning With Limited Expert Demonstrations via Search-Based Inverse Dynamic Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7131817292","doi":"https://doi.org/10.1109/tase.2026.3668970"},"language":null,"primary_location":{"id":"doi:10.1109/tase.2026.3668970","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2026.3668970","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/A5127481402","display_name":"Zhiliang Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiliang Lin","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0006-1864-9440","affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049290416","display_name":"Z C Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuangzhuang Chen","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-0336-1181","affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127191042","display_name":"Guanming Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanming Zhu","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0005-4843-2739","affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Li Wang","orcid":"https://orcid.org/0000-0001-8707-3269"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Wang","raw_affiliation_strings":["School of Artificial Intelligence, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-8707-3269","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jianqiang Li","orcid":"https://orcid.org/0000-0002-2208-962X"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqiang Li","raw_affiliation_strings":["School of Artificial Intelligence, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2208-962X","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I180726961"],"apc_list":null,"apc_paid":null,"fwci":12.1051,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.97148235,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"23","issue":null,"first_page":"5732","last_page":"5743"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.45829999446868896,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.45829999446868896,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.19110000133514404,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.10350000113248825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.5019000172615051},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.44859999418258667},{"id":"https://openalex.org/keywords/image-stitching","display_name":"Image stitching","score":0.4187999963760376},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.41760000586509705},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.41190001368522644},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.40400001406669617},{"id":"https://openalex.org/keywords/programming-by-demonstration","display_name":"Programming by demonstration","score":0.40059998631477356},{"id":"https://openalex.org/keywords/expert-system","display_name":"Expert system","score":0.3808000087738037}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6660000085830688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6517000198364258},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5612000226974487},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.5019000172615051},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.44859999418258667},{"id":"https://openalex.org/C29081049","wikidata":"https://www.wikidata.org/wiki/Q1364242","display_name":"Image stitching","level":2,"score":0.4187999963760376},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.41760000586509705},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.41190001368522644},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.40400001406669617},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.40059998631477356},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2736999988555908},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2671999931335449},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26570001244544983},{"id":"https://openalex.org/C17816587","wikidata":"https://www.wikidata.org/wiki/Q1501872","display_name":"Inverse kinematics","level":3,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2026.3668970","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2026.3668970","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/G1646442845","display_name":null,"funder_award_id":"62473264","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G196507285","display_name":null,"funder_award_id":"62325307","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3550247469","display_name":null,"funder_award_id":"KJZD20230923113801004","funder_id":"https://openalex.org/F4320326705","funder_display_name":"Science, Technology and Innovation Commission of Shenzhen Municipality"},{"id":"https://openalex.org/G4701649649","display_name":null,"funder_award_id":"62527809","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5051009293","display_name":null,"funder_award_id":"2023B1515120038","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"},{"id":"https://openalex.org/G8411257915","display_name":null,"funder_award_id":"62203134","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8955274695","display_name":null,"funder_award_id":"62373257","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/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null},{"id":"https://openalex.org/F4320326705","display_name":"Science, Technology and Innovation Commission of Shenzhen Municipality","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2051228319","https://openalex.org/W2108406823","https://openalex.org/W2122331303","https://openalex.org/W2158782408","https://openalex.org/W2165558283","https://openalex.org/W2172082560","https://openalex.org/W2604382266","https://openalex.org/W2618530766","https://openalex.org/W2963411833","https://openalex.org/W2963469388","https://openalex.org/W2964460729","https://openalex.org/W2998508940","https://openalex.org/W3009593063","https://openalex.org/W3012432597","https://openalex.org/W3138984732","https://openalex.org/W3206739224","https://openalex.org/W4229064201","https://openalex.org/W4234848122","https://openalex.org/W4238286944","https://openalex.org/W4252279978","https://openalex.org/W4285092328","https://openalex.org/W4376166839","https://openalex.org/W4387081555","https://openalex.org/W4389319185","https://openalex.org/W4390968535","https://openalex.org/W4391305615","https://openalex.org/W4393139813","https://openalex.org/W4398793977","https://openalex.org/W4401794499","https://openalex.org/W4402759029","https://openalex.org/W4406921735","https://openalex.org/W4407448669","https://openalex.org/W4407555857","https://openalex.org/W4408441459","https://openalex.org/W4408609488","https://openalex.org/W4409347153","https://openalex.org/W4409363746","https://openalex.org/W4410660767","https://openalex.org/W4411551076","https://openalex.org/W4412604838","https://openalex.org/W4415795277","https://openalex.org/W7103751612","https://openalex.org/W7133228443"],"related_works":[],"abstract_inverted_index":{"Imitation":[0,55],"learning":[1,65],"(IL)":[2],"shows":[3],"its":[4],"superiority":[5],"in":[6],"faster":[7],"strategy":[8],"optimization":[9],"by":[10,66,153],"leveraging":[11],"expert":[12,68,89,98,151,157,171],"demonstrations.":[13],"However,":[14],"as":[15],"one":[16],"of":[17,63,120],"the":[18,31,37,61,85,97,107,147,170],"powerful":[19],"IL":[20],"methods,":[21],"behavior":[22],"cloning":[23],"(BC)":[24],"suffers":[25],"from":[26,36,111,156],"covariate":[27],"shift":[28],"problems,":[29],"where":[30,195],"agent\u2019s":[32],"policy":[33],"drifts":[34],"away":[35],"expert\u2019s,":[38],"leading":[39],"to":[40,59,83,145,178],"compounding":[41],"errors":[42],"and":[43,73,90,113,182,198],"decreased":[44],"generalization":[45],"performance.":[46],"To":[47],"this":[48],"end,":[49],"we":[50],"propose":[51],"Search-based":[52],"Inverse":[53],"Dynamics":[54],"Learning,":[56],"namely":[57],"SIDIL,":[58],"enhance":[60,179],"robustness":[62],"imitation":[64],"augmenting":[67],"demonstrations":[69,152],"via":[70,100],"trajectory":[71],"perturbation":[72],"stitching.":[74],"Specifically,":[75],"SIDIL":[76,130,142],"first":[77],"employs":[78],"a":[79,101,117,160],"nearest-neighbor":[80],"search":[81],"method":[82],"find":[84],"closest":[86],"points":[87],"between":[88],"perturbed":[91],"data,":[92],"generating":[93],"new":[94],"actions":[95],"near":[96],"data":[99],"stitching":[102,154],"strategy.":[103],"By":[104],"exploiting":[105],"this,":[106],"agent":[108],"can":[109],"recover":[110],"deviations":[112],"complete":[114],"tasks":[115,127],"under":[116],"wider":[118],"range":[119],"conditions.":[121],"Experimental":[122],"results":[123,174],"on":[124],"various":[125],"robotic":[126,184],"show":[128],"that":[129],"outperforms":[131],"baseline":[132],"algorithms":[133],"with":[134],"higher":[135,161],"success":[136,164],"rates":[137],"across":[138],"multiple":[139],"tasks.":[140],"Meanwhile,":[141],"is":[143],"allowed":[144],"expand":[146],"attractive":[148],"region":[149],"around":[150],"states":[155,168],"demonstrations,":[158],"enjoying":[159],"task":[162],"completion":[163],"rate":[165],"even":[166],"for":[167,191],"outside":[169],"distribution.":[172],"These":[173],"highlight":[175],"our":[176],"potential":[177],"humanoid":[180],"locomotion":[181],"dexterous":[183],"hand":[185],"manipulation,":[186],"making":[187],"it":[188],"particularly":[189],"suitable":[190],"industrial":[192],"manufacturing":[193],"automation":[194],"adaptability,":[196],"robustness,":[197],"safety":[199],"are":[200],"essential.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-02-28T00:00:00"}