{"id":"https://openalex.org/W4415524157","doi":"https://doi.org/10.1109/humanoids65713.2025.11203167","title":"Audio-Visual Contact Classification for Tree Structures in Agriculture","display_name":"Audio-Visual Contact Classification for Tree Structures in Agriculture","publication_year":2025,"publication_date":"2025-09-30","ids":{"openalex":"https://openalex.org/W4415524157","doi":"https://doi.org/10.1109/humanoids65713.2025.11203167"},"language":null,"primary_location":{"id":"doi:10.1109/humanoids65713.2025.11203167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids65713.2025.11203167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE-RAS 24th International Conference on Humanoid Robots (Humanoids)","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":null,"display_name":"Ryan Spears","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan Spears","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005896564","display_name":"Moon Young Lee","orcid":"https://orcid.org/0000-0003-4956-9241"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Moonyoung Lee","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067346459","display_name":"George Kantor","orcid":"https://orcid.org/0000-0001-7088-8533"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Kantor","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005091065","display_name":"Oliver Kroemer","orcid":"https://orcid.org/0000-0003-2007-3867"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oliver Kroemer","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"760","last_page":"767"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.8363999724388123,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.8363999724388123,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.7714999914169312,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11164","display_name":"Remote Sensing and LiDAR Applications","score":0.6991999745368958,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5756000280380249},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5568000078201294},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5507000088691711},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5293999910354614},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4925999939441681},{"id":"https://openalex.org/keywords/viewpoints","display_name":"Viewpoints","score":0.4399999976158142},{"id":"https://openalex.org/keywords/tree-structure","display_name":"Tree structure","score":0.3296999931335449},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3237999975681305}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6384999752044678},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.607200026512146},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5756000280380249},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5568000078201294},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5507000088691711},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5293999910354614},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4925999939441681},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.4399999976158142},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.400299996137619},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34380000829696655},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.3296999931335449},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.31470000743865967},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C163985040","wikidata":"https://www.wikidata.org/wiki/Q1172399","display_name":"Data acquisition","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.27639999985694885},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26460000872612},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26159998774528503}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/humanoids65713.2025.11203167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids65713.2025.11203167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE-RAS 24th International Conference on Humanoid Robots (Humanoids)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2775635818","https://openalex.org/W2963486077","https://openalex.org/W3006646738","https://openalex.org/W3012241275","https://openalex.org/W3036474525","https://openalex.org/W3093377669","https://openalex.org/W3176573865","https://openalex.org/W3196974791","https://openalex.org/W3207828822","https://openalex.org/W3217595080","https://openalex.org/W4281887079","https://openalex.org/W4282912956","https://openalex.org/W4365814887","https://openalex.org/W4372260310","https://openalex.org/W4383108392","https://openalex.org/W4383108703","https://openalex.org/W4383109035","https://openalex.org/W4390577913","https://openalex.org/W4401414232","https://openalex.org/W4401416238","https://openalex.org/W4401416290","https://openalex.org/W4401416644","https://openalex.org/W4402726993","https://openalex.org/W4410949812"],"related_works":[],"abstract_inverted_index":{"Contact-rich":[0],"manipulation":[1,38,156],"tasks":[2],"in":[3,55,142,157],"agriculture,":[4],"such":[5],"as":[6],"pruning":[7],"and":[8,52,72,102,127,162],"harvesting,":[9],"require":[10],"robots":[11],"to":[12,18,40,50,75,131],"physically":[13],"interact":[14],"with":[15],"tree":[16],"structures":[17],"maneuver":[19],"through":[20],"cluttered":[21],"foliage.":[22],"Identifying":[23],"whether":[24],"the":[25,36,77,150],"robot":[26],"is":[27,33,46,88],"contacting":[28],"rigid":[29],"or":[30,83],"soft":[31],"materials":[32],"critical":[34],"for":[35,98,155],"downstream":[37],"policy":[39],"be":[41],"safe,":[42],"yet":[43],"vision":[44],"alone":[45],"often":[47],"insufficient":[48],"due":[49],"occlusion":[51],"limited":[53],"viewpoints":[54],"this":[56],"unstructured":[57],"environment.":[58],"To":[59],"address":[60],"this,":[61],"we":[62],"propose":[63],"a":[64,123,132],"multi-modal":[65],"classification":[66],"framework":[67],"that":[68,89,113],"fuses":[69],"vibrotactile":[70],"(audio)":[71],"visual":[73,107],"inputs":[74],"identify":[76],"contact":[78,100],"class:":[79],"leaf,":[80],"twig,":[81],"trunk,":[82],"ambient.":[84],"Our":[85],"key":[86],"insight":[87],"contact-induced":[90],"vibrations":[91],"carry":[92],"material-specific":[93],"signals,":[94],"making":[95],"audio":[96],"effective":[97],"detecting":[99],"events":[101],"distinguishing":[103],"material":[104],"types,":[105],"while":[106],"features":[108],"add":[109],"complementary":[110],"semantic":[111],"cues":[112],"support":[114],"more":[115],"fine-grained":[116],"classification.":[117],"We":[118],"collect":[119],"training":[120],"data":[121],"using":[122],"hand-held":[124],"sensor":[125],"probe":[126,134],"demonstrate":[128],"zero-shot":[129],"generalization":[130],"robot-mounted":[133],"embodiment,":[135],"achieving":[136],"an":[137],"F1":[138],"score":[139],"of":[140,152],"0.82":[141],"our":[143],"optimal":[144],"timewindow":[145],"configuration.":[146],"These":[147],"results":[148],"underscore":[149],"potential":[151],"audio-visual":[153],"learning":[154],"unstructured,":[158],"contactrich":[159],"environments.":[160],"Website":[161],"source":[163],"code":[164],"are":[165],"available":[166],"at":[167],"https://tree-classification.vercel.app/":[168]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-24T00:00:00"}
