{"id":"https://openalex.org/W4417051996","doi":"https://doi.org/10.1109/lra.2025.3640983","title":"PIDiff: Integrating a High-Performance Transformer Into Diffusion Models for Robust and Efficient Imitation Learning","display_name":"PIDiff: Integrating a High-Performance Transformer Into Diffusion Models for Robust and Efficient Imitation Learning","publication_year":2025,"publication_date":"2025-12-05","ids":{"openalex":"https://openalex.org/W4417051996","doi":"https://doi.org/10.1109/lra.2025.3640983"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2025.3640983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3640983","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","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/A5101835822","display_name":"Yunzhi Huang","orcid":"https://orcid.org/0000-0003-2344-1071"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yunzhi Huang","raw_affiliation_strings":["School of Electrical and Automation Engineering, Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Automation Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100731314","display_name":"Peng Jin","orcid":"https://orcid.org/0000-0003-2228-131X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Jin","raw_affiliation_strings":["School of Electrical and Automation Engineering, Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Automation Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110180311","display_name":"Liang Han","orcid":"https://orcid.org/0009-0002-4899-8933"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Han","raw_affiliation_strings":["School of Electrical and Automation Engineering, Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Automation Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002691168","display_name":"Yingzhao Li","orcid":"https://orcid.org/0000-0002-5699-4097"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingzhao Li","raw_affiliation_strings":["School of Mechatronics Engineering, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"School of Mechatronics Engineering, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112897857","display_name":"Xudong Hou","orcid":"https://orcid.org/0000-0002-0710-2558"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xudong Hou","raw_affiliation_strings":["School of Mechatronics Engineering, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"School of Mechatronics Engineering, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101835822"],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50662917,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"2","first_page":"1626","last_page":"1633"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.48190000653266907,"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":0.48190000653266907,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.19380000233650208,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.07169999927282333,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/inference","display_name":"Inference","score":0.6208000183105469},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6075999736785889},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5781999826431274},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5383999943733215},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4555000066757202},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4399000108242035}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.684499979019165},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6208000183105469},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6075999736785889},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.593500018119812},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5781999826431274},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5383999943733215},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47380000352859497},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4555000066757202},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4399000108242035},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.29820001125335693},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.28279998898506165},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.2809999883174896},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.262800008058548}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3640983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3640983","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2963411833","https://openalex.org/W3175515048","https://openalex.org/W4383108491","https://openalex.org/W4385245566","https://openalex.org/W4385430582","https://openalex.org/W4385430618","https://openalex.org/W4386075524","https://openalex.org/W4386075553","https://openalex.org/W4386076519","https://openalex.org/W4401417422","https://openalex.org/W4402354007","https://openalex.org/W4402354045","https://openalex.org/W4402354127","https://openalex.org/W4402727783","https://openalex.org/W4403337227","https://openalex.org/W4403944333","https://openalex.org/W4415797017","https://openalex.org/W4416749759"],"related_works":[],"abstract_inverted_index":{"Imitation":[0],"learning":[1,18,72],"is":[2],"a":[3,49,54],"critical":[4],"approach":[5,147],"for":[6],"robots":[7],"to":[8,57,90,106],"acquire":[9],"skills":[10],"by":[11],"mimicking":[12],"human":[13],"behavior.":[14],"However,":[15],"traditional":[16],"imitation":[17],"frameworks":[19],"often":[20],"exhibit":[21],"poor":[22],"action":[23],"prediction":[24],"accuracy":[25],"and":[26,52,70,74,83,134,163],"low":[27],"robustness":[28],"when":[29],"handling":[30],"complex":[31],"tasks.":[32],"To":[33,110],"tackle":[34],"these":[35],"limitations,":[36],"we":[37,77,118],"propose":[38],"the":[39,64,68,79,87,93,97,102,113],"PIDiff":[40],"policy":[41],"that":[42,145],"integrates":[43],"an":[44],"enhanced":[45,164],"linear-complexity":[46],"Transformer":[47,89],"with":[48],"diffusion":[50,98,103],"model":[51],"introduces":[53],"PointNet-based":[55],"encoder":[56],"efficiently":[58],"extract":[59],"visual":[60],"features,":[61],"thereby":[62],"enhancing":[63],"policy's":[65],"understanding":[66],"of":[67,115],"environment":[69],"improving":[71],"efficiency":[73],"robustness.":[75,165],"Specifically,":[76],"introduce":[78],"designed":[80],"SubLink":[81],"Block":[82],"CrossLink":[84],"Block,":[85],"enabling":[86],"improved":[88],"serve":[91],"as":[92],"noise":[94],"predictor":[95],"in":[96,131,137],"strategy":[99],"while":[100],"retaining":[101],"model's":[104],"ability":[105],"capture":[107],"multi-modal":[108],"distributions.":[109],"comprehensively":[111],"evaluate":[112],"effectiveness":[114],"our":[116,146],"method,":[117],"conducted":[119],"systematic":[120],"experiments":[121],"across":[122],"multiple":[123],"tasks":[124],"on":[125],"three":[126],"robotic":[127],"manipulation":[128],"benchmark":[129],"platforms":[130],"simulation":[132],"environments":[133],"performed":[135],"evaluations":[136],"various":[138],"real-world":[139],"scenarios.":[140],"The":[141],"experimental":[142],"results":[143],"demonstrate":[144],"significantly":[148],"outperforms":[149],"baseline":[150],"methods,":[151],"achieving":[152],"higher":[153],"success":[154],"rates,":[155],"faster":[156],"inference":[157],"speeds,":[158],"reduced":[159],"GPU":[160],"memory":[161],"usage,":[162]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-12-05T00:00:00"}