{"id":"https://openalex.org/W4416749915","doi":"https://doi.org/10.1109/iros60139.2025.11247209","title":"Sensing Differently: Unifying Vision, Language, Posture and Tactile in Robotic Perception","display_name":"Sensing Differently: Unifying Vision, Language, Posture and Tactile in Robotic Perception","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749915","doi":"https://doi.org/10.1109/iros60139.2025.11247209"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247209","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247209","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101043328","display_name":"Yanmin Zhou","orcid":"https://orcid.org/0000-0001-9003-4471"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Zhou","raw_affiliation_strings":["Tongji University,College of Electronics and Information Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,College of Electronics and Information Engineering","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yiyang Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiyang Jin","raw_affiliation_strings":["Tongji University,College of Electronics and Information Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,College of Electronics and Information Engineering","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100737197","display_name":"Rong Jiang","orcid":"https://orcid.org/0009-0000-7642-932X"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Jiang","raw_affiliation_strings":["Tongji University,College of Electronics and Information Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,College of Electronics and Information Engineering","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353701","display_name":"Xin Li","orcid":"https://orcid.org/0000-0001-6003-7719"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["Tongji University,College of Electronics and Information Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,College of Electronics and Information Engineering","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000024164","display_name":"Hongrui Sang","orcid":"https://orcid.org/0000-0002-8026-1328"},"institutions":[{"id":"https://openalex.org/I96733725","display_name":"Shanghai Maritime University","ror":"https://ror.org/04z7qrj66","country_code":"CN","type":"education","lineage":["https://openalex.org/I96733725"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongrui Sang","raw_affiliation_strings":["Shanghai Maritime University,School of Logistics Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Maritime University,School of Logistics Engineering","institution_ids":["https://openalex.org/I96733725"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051224603","display_name":"Shuo Jiang","orcid":"https://orcid.org/0000-0003-3645-6301"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Jiang","raw_affiliation_strings":["Tongji University,College of Electronics and Information Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,College of Electronics and Information Engineering","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100424175","display_name":"Zhipeng Wang","orcid":"https://orcid.org/0000-0003-3039-7582"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhipeng Wang","raw_affiliation_strings":["Tongji University,College of Electronics and Information Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,College of Electronics and Information Engineering","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049557511","display_name":"Bin He","orcid":"https://orcid.org/0000-0003-3193-6269"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin He","raw_affiliation_strings":["Tongji University,College of Electronics and Information Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,College of Electronics and Information Engineering","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.4954574,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20479","last_page":"20486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.5993000268936157,"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":0.5993000268936157,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2142000049352646,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.04259999841451645,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.7603999972343445},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6381999850273132},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5548999905586243},{"id":"https://openalex.org/keywords/tactile-sensor","display_name":"Tactile sensor","score":0.5512999892234802},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.5152000188827515},{"id":"https://openalex.org/keywords/proprioception","display_name":"Proprioception","score":0.4916999936103821},{"id":"https://openalex.org/keywords/tactile-perception","display_name":"Tactile perception","score":0.448199987411499},{"id":"https://openalex.org/keywords/tactile-stimuli","display_name":"Tactile stimuli","score":0.42239999771118164},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.3840000033378601}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.7603999972343445},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6883000135421753},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6381999850273132},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6251999735832214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.555899977684021},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5548999905586243},{"id":"https://openalex.org/C46722567","wikidata":"https://www.wikidata.org/wiki/Q7674139","display_name":"Tactile sensor","level":3,"score":0.5512999892234802},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.5152000188827515},{"id":"https://openalex.org/C171790689","wikidata":"https://www.wikidata.org/wiki/Q1129066","display_name":"Proprioception","level":2,"score":0.4916999936103821},{"id":"https://openalex.org/C3017819093","wikidata":"https://www.wikidata.org/wiki/Q328835","display_name":"Tactile perception","level":3,"score":0.448199987411499},{"id":"https://openalex.org/C2987654038","wikidata":"https://www.wikidata.org/wiki/Q859031","display_name":"Tactile stimuli","level":3,"score":0.42239999771118164},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3873000144958496},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3840000033378601},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3797000050544739},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.36010000109672546},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.3564999997615814},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.3540000021457672},{"id":"https://openalex.org/C2776010242","wikidata":"https://www.wikidata.org/wiki/Q4677575","display_name":"Active perception","level":3,"score":0.3151000142097473},{"id":"https://openalex.org/C2982962833","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information fusion","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C2778360479","wikidata":"https://www.wikidata.org/wiki/Q1289489","display_name":"Haptic perception","level":3,"score":0.301800012588501},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C161759796","wikidata":"https://www.wikidata.org/wiki/Q3982902","display_name":"Teleoperation","level":3,"score":0.2759999930858612},{"id":"https://openalex.org/C111151474","wikidata":"https://www.wikidata.org/wiki/Q1653368","display_name":"iCub","level":4,"score":0.2549999952316284},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247209","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247209","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2092031140","https://openalex.org/W2587044120","https://openalex.org/W2775635818","https://openalex.org/W2963915174","https://openalex.org/W3091465854","https://openalex.org/W3095319910","https://openalex.org/W3133866887","https://openalex.org/W3176445421","https://openalex.org/W4312528276","https://openalex.org/W4385430679","https://openalex.org/W4385430681","https://openalex.org/W4386065512","https://openalex.org/W4390873312","https://openalex.org/W4391329928","https://openalex.org/W4402354011","https://openalex.org/W4402726993","https://openalex.org/W7104024387"],"related_works":[],"abstract_inverted_index":{"Multi-modal":[0],"fusion":[1],"perception":[2],"enhances":[3,140],"robotic":[4],"performance":[5,142],"in":[6,50,152,159],"complex":[7],"tasks":[8,27,146],"by":[9],"providing":[10],"more":[11],"comprehensive":[12],"information":[13,57],"than":[14],"single":[15],"modality.":[16],"While":[17],"tactile":[18,59,89],"and":[19,60,62,67,83,88,106],"proprioceptive":[20],"sensing":[21],"are":[22,47],"effective":[23,125],"for":[24,55],"direct":[25],"contact":[26],"like":[28,58],"grasping,":[29],"current":[30],"research":[31],"mainly":[32],"focuses":[33],"on":[34],"vision-language":[35],"fusion,":[36],"neglecting":[37],"other":[38],"embodied":[39,56],"modalities.":[40],"The":[41,112,154],"primary":[42],"challenges":[43],"of":[44,143],"this":[45,129],"limitation":[46],"the":[48,141],"difficulty":[49],"generating":[51],"natural":[52],"language":[53,84,121],"labels":[54],"proprioception":[61],"aligning":[63],"them":[64],"with":[65,86,147],"vision":[66,82],"language.":[68],"To":[69],"address":[70],"this,":[71],"we":[72,131],"introduce":[73],"VLaPT,":[74],"a":[75,133,149],"novel":[76],"multi-modal":[77,135],"grasping":[78],"dataset":[79,113],"that":[80],"aligns":[81],"(VL)":[85],"posture":[87],"(PT),":[90],"enabling":[91],"robots":[92],"to":[93,98],"sense":[94],"differently":[95],"from":[96],"environment":[97],"self.":[99],"VLaPT":[100,155],"includes":[101],"75":[102],"objects,":[103],"1,533":[104],"grasps,":[105],"over":[107],"78K":[108],"synchronized":[109],"vision-language-posturetactile":[110],"pairs.":[111],"incorporates":[114],"structured,":[115],"rich-text":[116],"descriptions":[117],"generated":[118],"using":[119],"modality-level":[120],"annotation":[122],"templates,":[123],"ensuring":[124],"cross-modality":[126],"alignment.":[127],"Leveraging":[128],"dataset,":[130],"trained":[132],"lightweight":[134],"alignment":[136],"framework,":[137],"CLIP-ME,":[138],"which":[139],"several":[144],"downstream":[145],"only":[148],"5%":[150],"increase":[151],"parameters.":[153],"is":[156],"publicly":[157],"available":[158],"https://huggingface.co/datasets/xsdfasfgsa/VLaPT.":[160]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-28T00:00:00"}
