{"id":"https://openalex.org/W7162778836","doi":"https://doi.org/10.1109/access.2026.3698160","title":"ATP-VLA: A Robust Grasping Framework Driven by Temporal Asymmetric Multimodal Fusion and Representation Isomorphism","display_name":"ATP-VLA: A Robust Grasping Framework Driven by Temporal Asymmetric Multimodal Fusion and Representation Isomorphism","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7162778836","doi":"https://doi.org/10.1109/access.2026.3698160"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3698160","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3698160","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3698160","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137314815","display_name":"Haocong Duan","orcid":"https://orcid.org/0009-0004-2978-3552"},"institutions":[{"id":"https://openalex.org/I4210136047","display_name":"Weifang University of Science and Technology","ror":"https://ror.org/04ha2bb10","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136047"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haocong Duan","raw_affiliation_strings":["School of Information Science and Engineering, Weifang University of Science and Technology, Shouguang, China"],"raw_orcid":"https://orcid.org/0009-0004-2978-3552","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Weifang University of Science and Technology, Shouguang, China","institution_ids":["https://openalex.org/I4210136047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137392061","display_name":"Guangsen Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136047","display_name":"Weifang University of Science and Technology","ror":"https://ror.org/04ha2bb10","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136047"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangsen Xue","raw_affiliation_strings":["School of Information Science and Engineering, Weifang University of Science and Technology, Shouguang, China"],"raw_orcid":"https://orcid.org/0009-0006-7807-9929","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Weifang University of Science and Technology, Shouguang, China","institution_ids":["https://openalex.org/I4210136047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077814309","display_name":"Zhang Jinyan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136047","display_name":"Weifang University of Science and Technology","ror":"https://ror.org/04ha2bb10","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136047"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinyan Zhang","raw_affiliation_strings":["School of Information Science and Engineering, Weifang University of Science and Technology, Shouguang, China"],"raw_orcid":"https://orcid.org/0009-0005-9126-1787","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Weifang University of Science and Technology, Shouguang, China","institution_ids":["https://openalex.org/I4210136047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137320394","display_name":"Meile Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136047","display_name":"Weifang University of Science and Technology","ror":"https://ror.org/04ha2bb10","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136047"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meile Zhu","raw_affiliation_strings":["School of Information Science and Engineering, Weifang University of Science and Technology, Shouguang, China"],"raw_orcid":"https://orcid.org/0009-0007-8309-9745","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Weifang University of Science and Technology, Shouguang, China","institution_ids":["https://openalex.org/I4210136047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002493051","display_name":"Zhongwei Zhao","orcid":"https://orcid.org/0000-0002-6175-5664"},"institutions":[{"id":"https://openalex.org/I4210136047","display_name":"Weifang University of Science and Technology","ror":"https://ror.org/04ha2bb10","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136047"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongwei Zhao","raw_affiliation_strings":["School of Information Science and Engineering, Weifang University of Science and Technology, Shouguang, China"],"raw_orcid":"https://orcid.org/0009-0001-2827-0323","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Weifang University of Science and Technology, Shouguang, China","institution_ids":["https://openalex.org/I4210136047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8717826,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"83044","last_page":"83054"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4106999933719635,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4106999933719635,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.1257999986410141,"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/T10028","display_name":"Topic Modeling","score":0.04670000076293945,"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/representation","display_name":"Representation (politics)","score":0.6912000179290771},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5734999775886536},{"id":"https://openalex.org/keywords/isomorphism","display_name":"Isomorphism (crystallography)","score":0.44670000672340393},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4016000032424927},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.37299999594688416},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3666999936103821}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6956999897956848},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6912000179290771},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5734999775886536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5570999979972839},{"id":"https://openalex.org/C203436722","wikidata":"https://www.wikidata.org/wiki/Q902950","display_name":"Isomorphism (crystallography)","level":3,"score":0.44670000672340393},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4016000032424927},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37959998846054077},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.37299999594688416},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36890000104904175},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3666999936103821},{"id":"https://openalex.org/C2988995629","wikidata":"https://www.wikidata.org/wiki/Q2915729","display_name":"Matrix algebra","level":3,"score":0.26600000262260437},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3698160","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3698160","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c4c78718a00144a29d812de1ea6366ea","is_oa":true,"landing_page_url":"https://doaj.org/article/c4c78718a00144a29d812de1ea6366ea","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 83044-83054 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3698160","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3698160","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Existing":[0],"vision-language-action":[1],"(VLA)":[2],"models":[3],"are":[4],"highly":[5],"susceptible":[6],"to":[7,162,189],"\u2018\u2018visual":[8,88],"hallucinations\u2019\u2019":[9],"when":[10],"manipulating":[11],"deceptive":[12,128],"objects,":[13],"whereas":[14],"introducing":[15],"high-energy":[16],"tactile":[17,61,92,99,203],"verification":[18],"inherently":[19],"risks":[20],"\u2018\u2018perception-as-destruction.\u2019\u2019":[21],"In":[22],"this":[23],"paper,":[24],"we":[25,45,76,169,205],"propose":[26],"the":[27,69,158,171,181,196,207,211],"Acoustic-Tactile":[28],"Perception":[29],"Vision-":[30],"Language-Action":[31],"(ATP-VLA)":[32],"framework,":[33],"a":[34,47,78,84,108,137,147],"robust":[35],"grasping":[36],"framework":[37],"based":[38],"on":[39,119],"temporal":[40,154,186],"asymmetric":[41],"multimodal":[42],"fusion.":[43],"First,":[44],"introduce":[46],"Representation":[48],"Isomorphism":[49],"mechanism":[50,97,188],"that":[51,132],"unifies":[52],"and":[53,59,114,125,202],"projects":[54],"1D":[55],"transient":[56],"contact":[57],"sounds":[58],"3D":[60],"indentations":[62],"into":[63],"2D":[64],"visual":[65],"tokens,":[66],"effectively":[67,156],"bridging":[68],"semantic":[70],"gap":[71],"across":[72],"heterogeneous":[73],"sensors.":[74],"Second,":[75],"construct":[77],"Dynamic":[79],"Bayesian":[80],"Decision":[81],"Tree":[82],"following":[83],"progressive":[85],"belief-update":[86],"logic:":[87],"prior\u2014low-energy":[89],"acoustic":[90,200],"probing\u2014high-energy":[91],"verification.\u2019\u2019":[93],"This":[94],"cascaded":[95],"routing":[96,187],"triggers":[98],"sensing":[100],"only":[101,135],"upon":[102],"detecting":[103],"cross-modal":[104],"confidence":[105],"conflicts,":[106],"achieving":[107],"global":[109],"balance":[110],"between":[111,199],"computational":[112],"cost":[113],"physical":[115,159,208],"damage":[116,160],"risk.":[117],"Experiments":[118],"standard":[120],"benchmarks":[121],"(e.g.,":[122],"ObjectFolder":[123],"Real)":[124],"our":[126],"custom":[127],"adversarial":[129,167],"dataset":[130],"demonstrate":[131],"ATP-VLA":[133],"not":[134],"achieves":[136],"high":[138],"decision":[139],"matching":[140],"rate":[141,161],"of":[142,183,210],"88.8%,":[143],"but":[144],"also":[145],"exhibits":[146],"strong":[148],"Conservative":[149],"Safety":[150],"Bias":[151],"under":[152],"dynamic":[153],"routing,":[155],"reducing":[157],"3.9%.":[163],"Furthermore,":[164],"through":[165],"extreme":[166],"probing,":[168],"reveal":[170],"Structural":[172],"Hallucination":[173],"limitations":[174],"inherent":[175],"in":[176],"current":[177],"VLA":[178],"models,":[179],"validating":[180],"necessity":[182],"an":[184],"external":[185],"ensure":[190],"system":[191],"safety.":[192],"Finally,":[193],"by":[194],"demonstrating":[195],"positive":[197],"correlation":[198],"attenuation":[201],"deformation,":[204],"validate":[206],"interpretability":[209],"system\u2019s":[212],"decision-making":[213],"process.":[214]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-30T00:00:00"}
