{"id":"https://openalex.org/W4413925704","doi":"https://doi.org/10.1109/icra55743.2025.11128705","title":"Guiding Long-Horizon Task and Motion Planning with Vision Language Models","display_name":"Guiding Long-Horizon Task and Motion Planning with Vision Language Models","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413925704","doi":"https://doi.org/10.1109/icra55743.2025.11128705"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128705","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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/A5052479960","display_name":"Zhutian Yang","orcid":"https://orcid.org/0000-0002-6952-4465"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhutian Yang","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015917510","display_name":"Caelan Reed Garrett","orcid":"https://orcid.org/0000-0002-6474-1276"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Caelan Garrett","raw_affiliation_strings":["NVIDIA Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Research","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108257764","display_name":"Dieter Fox","orcid":"https://orcid.org/0009-0009-4694-9127"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dieter Fox","raw_affiliation_strings":["NVIDIA Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Research","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063238208","display_name":"Tom\u00e1s Lozano\u2010P\u00e9rez","orcid":"https://orcid.org/0000-0002-8657-2450"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tom\u00e1s Lozano-P\u00e9rez","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012862284","display_name":"Leslie Pack Kaelbling","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leslie Pack Kaelbling","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16847","last_page":"16853"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9441999793052673,"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":0.9441999793052673,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9203000068664551,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6737703084945679},{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.6029783487319946},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5773946046829224},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.540920078754425},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.5202361345291138},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46644896268844604},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4224685728549957},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3665950894355774},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.14394047856330872},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14167547225952148},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.1362479329109192},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08228936791419983}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6737703084945679},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.6029783487319946},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5773946046829224},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.540920078754425},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.5202361345291138},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46644896268844604},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4224685728549957},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3665950894355774},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.14394047856330872},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14167547225952148},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.1362479329109192},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08228936791419983},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128705","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1184315049","display_name":"Robotics: Flexible manipulation without prior shape models","funder_award_id":"2214177","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2501215608","display_name":null,"funder_award_id":"FA9550-22-1-0249","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G3938712152","display_name":null,"funder_award_id":"N00014-22-1-2740","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6077541890","display_name":null,"funder_award_id":"W911NF-23-1-0034","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309369","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W3001865277","https://openalex.org/W3128894241","https://openalex.org/W4383097638","https://openalex.org/W4383108457","https://openalex.org/W4385430665","https://openalex.org/W4388660746","https://openalex.org/W4389665359","https://openalex.org/W4401414087","https://openalex.org/W4405785256"],"related_works":["https://openalex.org/W4233159725","https://openalex.org/W2347391878","https://openalex.org/W3049557657","https://openalex.org/W3150915502","https://openalex.org/W2347250522","https://openalex.org/W2111158727","https://openalex.org/W4388749683","https://openalex.org/W1809059965","https://openalex.org/W3196817267","https://openalex.org/W1976600725"],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1],"(VLM)":[2],"can":[3,67],"generate":[4,68,115],"plausible":[5],"high-level":[6],"plans":[7],"when":[8],"prompted":[9],"with":[10,166],"a":[11,39,44,106,112,124,130,151],"goal,":[12],"the":[13,18,30,73,137],"context,":[14],"an":[15],"image":[16],"of":[17,76,100,186],"scene,":[19],"and":[20,35,64,78,94,118,126,164,177,196],"any":[21],"planning":[22,108],"constraints.":[23],"However,":[24],"there":[25],"is":[26,139],"no":[27],"guarantee":[28],"that":[29,71,90,110,122,157,175],"predicted":[31],"actions":[32,77,161],"are":[33,56],"geometrically":[34],"kinematically":[36],"feasible":[37],"for":[38,142,214],"particular":[40],"robot":[41,152],"embodiment.":[42],"As":[43],"result,":[45],"many":[46,101],"prerequisite":[47],"steps":[48],"such":[49],"as":[50],"opening":[51],"drawers":[52],"to":[53,87,114,168,190,202,207],"access":[54],"objects":[55],"often":[57],"omitted":[58],"in":[59,162,184],"their":[60],"plans.":[61],"Robot":[62],"task":[63,125,198],"motion":[65,69,127],"planners":[66],"trajectories":[70],"respect":[72],"geometric":[74],"feasibility":[75],"insert":[79],"physically":[80],"necessary":[81],"actions,":[82],"but":[83],"do":[84],"not":[85],"scale":[86],"everyday":[88],"problems":[89],"require":[91,158],"common-sense":[92],"knowledge":[93],"involve":[95],"large":[96],"state":[97],"spaces":[98],"comprised":[99],"variables.":[102],"We":[103,144],"propose":[104],"VLM-TAMP,":[105],"hierarchical":[107],"algorithm":[109],"leverages":[111],"VLM":[113,138],"both":[116,183],"semantically-meaningful":[117],"horizon-reducing":[119],"intermediate":[120],"subgoals":[121],"guide":[123],"planner.":[128],"When":[129],"subgoal":[131],"or":[132],"action":[133,181],"cannot":[134],"be":[135],"refined,":[136],"queried":[140],"again":[141],"replanning.":[143],"evaluate":[145],"VLMTAMP":[146],"on":[147],"kitchen":[148],"tasks":[149],"where":[150],"must":[153],"accomplish":[154],"cooking":[155],"goals":[156],"performing":[159],"30-50":[160],"sequence":[163],"interacting":[165],"up":[167],"21":[169],"objects.":[170],"VLM-TAMP":[171],"substantially":[172],"outperforms":[173],"baselines":[174],"rigidly":[176],"independently":[178],"execute":[179],"VLM-generated":[180],"sequences,":[182],"terms":[185],"success":[187],"rates":[188],"(50":[189],"100":[191,203],"%":[192,204],"versus":[193,205],"0":[194],"%)":[195],"average":[197],"completion":[199],"percentage":[200],"(72":[201],"15":[206],"45":[208],"%).":[209],"See":[210],"project":[211],"site":[212],"https://zt-yang.github.io/vlm-tamp-robot/":[213],"more":[215],"information.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":11}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}