{"id":"https://openalex.org/W4415524625","doi":"https://doi.org/10.1109/humanoids65713.2025.11203081","title":"Grounded Task Axes: Zero-Shot Semantic Skill Generalization via Task-Axis Controllers and Visual Foundation Models","display_name":"Grounded Task Axes: Zero-Shot Semantic Skill Generalization via Task-Axis Controllers and Visual Foundation Models","publication_year":2025,"publication_date":"2025-09-30","ids":{"openalex":"https://openalex.org/W4415524625","doi":"https://doi.org/10.1109/humanoids65713.2025.11203081"},"language":null,"primary_location":{"id":"doi:10.1109/humanoids65713.2025.11203081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids65713.2025.11203081","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":"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/A5059235013","display_name":"M. Yunus Seker","orcid":"https://orcid.org/0009-0006-7775-3504"},"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":true,"raw_author_name":"M. Yunus Seker","raw_affiliation_strings":["Carnegie Mellon University, The Robotics Institute,USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, The Robotics Institute,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041306584","display_name":"Shobhit Aggarwal","orcid":"https://orcid.org/0000-0002-0911-0631"},"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":"Shobhit Aggarwal","raw_affiliation_strings":["Carnegie Mellon University, Manufacturing Futures Institute,USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Manufacturing Futures Institute,USA","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, The Robotics Institute,USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, The Robotics Institute,USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059235013"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17009227,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"791","last_page":"798"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.9520999789237976,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.9520999789237976,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9147999882698059,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7351999878883362},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6241000294685364},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.51419997215271},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.5135999917984009},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5073000192642212},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.48170000314712524},{"id":"https://openalex.org/keywords/position-paper","display_name":"Position paper","score":0.4700999855995178},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4577000141143799}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7351999878883362},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6383000016212463},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6241000294685364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.607200026512146},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.51419997215271},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5135999917984009},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5073000192642212},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.505299985408783},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.48170000314712524},{"id":"https://openalex.org/C78780964","wikidata":"https://www.wikidata.org/wiki/Q7233193","display_name":"Position paper","level":2,"score":0.4700999855995178},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4577000141143799},{"id":"https://openalex.org/C156325361","wikidata":"https://www.wikidata.org/wiki/Q1152864","display_name":"Grounded theory","level":3,"score":0.45680001378059387},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.45320001244544983},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.3743000030517578},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3537999987602234},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.35040000081062317},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3149000108242035},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29750001430511475},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.29330000281333923},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.259799987077713}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/humanoids65713.2025.11203081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids65713.2025.11203081","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2016958754","https://openalex.org/W2105660272","https://openalex.org/W2116341587","https://openalex.org/W2136719407","https://openalex.org/W2415216611","https://openalex.org/W2965567119","https://openalex.org/W2984756091","https://openalex.org/W3036760152","https://openalex.org/W3205002254","https://openalex.org/W4312933868","https://openalex.org/W4401414814","https://openalex.org/W4403337227","https://openalex.org/W4404446892","https://openalex.org/W4413924995","https://openalex.org/W4414079217"],"related_works":[],"abstract_inverted_index":{"Transferring":[0],"skills":[1,50,55,127],"between":[2,25],"different":[3],"objects":[4,27],"remains":[5],"one":[6],"of":[7,11,60,96,103,125,131,143],"the":[8,21,82,93,101,126,129],"core":[9],"challenges":[10],"open-world":[12],"robot":[13],"manipulation.":[14],"Generalization":[15],"needs":[16],"to":[17,44],"take":[18],"into":[19,56],"account":[20],"high-level":[22],"structural":[23],"differences":[24],"distinct":[26],"while":[28],"still":[29],"maintaining":[30],"similar":[31,141],"low-level":[32],"interaction":[33],"control.":[34],"In":[35],"this":[36,122],"paper,":[37],"we":[38,53],"propose":[39],"an":[40,68,79],"example-based":[41,123],"zero-shot":[42],"approach":[43],"skill":[45],"transfer.":[46],"Rather":[47],"than":[48],"treating":[49],"as":[51,72,135],"atomic,":[52],"decompose":[54],"a":[57,73,97],"prioritized":[58],"list":[59],"grounded":[61,85],"task-axis":[62],"(GTA)":[63],"controllers.":[64],"Each":[65],"GTAC":[66],"defines":[67],"adaptable":[69],"controller,":[70,77],"such":[71,134],"position":[74,95],"or":[75,100],"force":[76],"along":[78],"axis.":[80],"Importantly,":[81],"GTACs":[83],"are":[84],"in":[86],"object":[87],"key":[88],"points":[89],"and":[90,155,159,162],"axes,":[91],"e.g.,":[92],"relative":[94],"screw":[98],"head":[99],"axis":[102],"its":[104],"shaft.":[105],"Zero-shot":[106],"transfer":[107,165],"is":[108],"thus":[109],"achieved":[110],"by":[111],"finding":[112],"semantically-similar":[113],"grounding":[114,124],"features":[115],"on":[116,149],"novel":[117],"target":[118],"objects.":[119,144],"We":[120,145],"achieve":[121],"through":[128],"use":[130],"foundation":[132],"models,":[133],"SD-DINO,":[136],"that":[137],"can":[138],"detect":[139],"semantically":[140],"keypoints":[142],"evaluate":[146],"our":[147],"framework":[148],"real-robot":[150],"experiments,":[151],"including":[152],"screwing,":[153],"pouring,":[154],"spatula":[156],"scraping":[157],"tasks,":[158],"demonstrate":[160],"robust":[161],"versatile":[163],"controller":[164],"for":[166],"each.":[167]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}