{"id":"https://openalex.org/W4412795708","doi":"https://doi.org/10.1109/tits.2025.3591239","title":"Toward Multi-Task Generalization in Autonomous Navigation: A Human-in-the-Loop Adversarial Reinforcement Learning With Diffusion Policy","display_name":"Toward Multi-Task Generalization in Autonomous Navigation: A Human-in-the-Loop Adversarial Reinforcement Learning With Diffusion Policy","publication_year":2025,"publication_date":"2025-07-31","ids":{"openalex":"https://openalex.org/W4412795708","doi":"https://doi.org/10.1109/tits.2025.3591239"},"language":"en","primary_location":{"id":"doi:10.1109/tits.2025.3591239","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2025.3591239","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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 Intelligent Transportation Systems","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/A5070291172","display_name":"Dong Hu","orcid":"https://orcid.org/0000-0001-7172-8152"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Dong Hu","raw_affiliation_strings":["Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong","Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-7172-8152","affiliations":[{"raw_affiliation_string":"Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081848769","display_name":"Chao Huang","orcid":"https://orcid.org/0000-0003-3023-4388"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chao Huang","raw_affiliation_strings":["Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong","Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0003-3023-4388","affiliations":[{"raw_affiliation_string":"Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044215622","display_name":"Jingda Wu","orcid":"https://orcid.org/0000-0002-7336-4492"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingda Wu","raw_affiliation_strings":["School of Mechanical Engineering, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7336-4492","affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001917503","display_name":"Xin Yuan","orcid":"https://orcid.org/0000-0001-5056-171X"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xin Yuan","raw_affiliation_strings":["School of Electrical and Mechanical Engineering, The University of Adelaide, Adelaide, SA, Australia"],"raw_orcid":"https://orcid.org/0000-0001-5056-171X","affiliations":[{"raw_affiliation_string":"School of Electrical and Mechanical Engineering, The University of Adelaide, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I5681781"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5070291172"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":6.5198,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.96351549,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"26","issue":"11","first_page":"19493","last_page":"19507"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9934999942779541,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9934999942779541,"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/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.9710999727249146,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9417999982833862,"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/adversarial-system","display_name":"Adversarial system","score":0.8043249845504761},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7853168249130249},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7825686931610107},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6031299233436584},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5783088803291321},{"id":"https://openalex.org/keywords/human-in-the-loop","display_name":"Human-in-the-loop","score":0.5715895891189575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5414336919784546},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.523838996887207},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3630473017692566},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20742836594581604},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18770766258239746}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8043249845504761},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7853168249130249},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7825686931610107},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6031299233436584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5783088803291321},{"id":"https://openalex.org/C2780626000","wikidata":"https://www.wikidata.org/wiki/Q5936775","display_name":"Human-in-the-loop","level":2,"score":0.5715895891189575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5414336919784546},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.523838996887207},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3630473017692566},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20742836594581604},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18770766258239746},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tits.2025.3591239","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2025.3591239","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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 Intelligent Transportation Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1731081199","https://openalex.org/W2549200707","https://openalex.org/W2788862220","https://openalex.org/W2966994213","https://openalex.org/W3038618902","https://openalex.org/W3127561923","https://openalex.org/W3161618639","https://openalex.org/W4282944694","https://openalex.org/W4297510490","https://openalex.org/W4360884927","https://openalex.org/W4362014203","https://openalex.org/W4386702654","https://openalex.org/W4386718967","https://openalex.org/W4386824909","https://openalex.org/W4387195417","https://openalex.org/W4388868804","https://openalex.org/W4390446303","https://openalex.org/W4391800510","https://openalex.org/W4395028520","https://openalex.org/W4396758988","https://openalex.org/W4400524848","https://openalex.org/W4401417422","https://openalex.org/W4405022723","https://openalex.org/W4406457544","https://openalex.org/W4408712150","https://openalex.org/W4411086205","https://openalex.org/W4412403975","https://openalex.org/W4412972170","https://openalex.org/W4415797647"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W4367173559","https://openalex.org/W4409348652","https://openalex.org/W4404795748","https://openalex.org/W4405627308","https://openalex.org/W4404893116","https://openalex.org/W2782058284"],"abstract_inverted_index":{"Due":[0],"to":[1,20,103,119,124,144],"the":[2,139,145,171],"complexity":[3],"and":[4,23,52,77,92,107,122,128,137,163],"variability":[5],"of":[6,113,159,174],"real-world":[7],"environments,":[8],"data-driven":[9],"autonomous":[10,14,38,175],"navigation":[11,176],"strategies":[12],"for":[13,37,75,170],"ground":[15],"vehicles":[16],"have":[17],"significant":[18],"potential":[19],"improve":[21,104,120],"performance":[22],"adaptability":[24,123],"in":[25,55,126,135,157],"diverse":[26],"scenarios.":[27,58],"Reinforcement":[28],"learning":[29,93],"(RL)":[30],"has":[31],"emerged":[32],"as":[33,87],"a":[34,65,84,167],"promising":[35,168],"approach":[36,152],"navigation.":[39],"However,":[40],"existing":[41,155],"RL":[42,70],"methods":[43,156],"often":[44],"struggle":[45],"with":[46,71],"low":[47],"sample":[48],"efficiency,":[49,160],"limited":[50],"adaptability,":[51,165],"poor":[53],"generalization":[54],"dynamic":[56],"multi-task":[57,164],"To":[59],"address":[60],"these":[61],"issues,":[62],"we":[63],"propose":[64],"novel":[66],"framework:":[67],"human-in-the-loop":[68],"adversarial":[69,115],"diffusion":[72,85],"policy,":[73],"designed":[74],"scalable":[76],"robust":[78],"policy":[79,88,109,141],"learning.":[80],"This":[81],"framework":[82],"leverages":[83],"model":[86],"network,":[89],"effectively":[90],"exploring":[91],"high-dimensional,":[94],"multi-modal":[95],"behavior":[96],"distributions.":[97,129],"It":[98],"also":[99],"integrates":[100],"human":[101],"feedback":[102],"data":[105],"efficiency":[106],"stabilize":[108],"training.":[110],"On":[111],"top":[112],"this,":[114],"training":[116],"is":[117,133,142,181],"employed":[118],"robustness":[121],"change":[125],"tasks":[127],"The":[130,178],"proposed":[131],"method":[132],"trained":[134],"simulation,":[136],"then":[138],"well-trained":[140],"transferred":[143],"real-world.":[146],"Experimental":[147],"results":[148],"demonstrate":[149],"that":[150],"this":[151],"significantly":[153],"outperforms":[154],"terms":[158],"stability,":[161],"generalization,":[162],"offering":[166],"solution":[169],"next":[172],"generation":[173],"systems.":[177],"supplementary":[179],"video":[180],"available":[182],"at":[183],"https://youtu.be/JH3knw0I5lU":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}