{"id":"https://openalex.org/W7102603268","doi":"https://doi.org/10.48550/arxiv.2510.25548","title":"Using VLM Reasoning to Constrain Task and Motion Planning","display_name":"Using VLM Reasoning to Constrain Task and Motion Planning","publication_year":2025,"publication_date":"2025-10-29","ids":{"openalex":"https://openalex.org/W7102603268","doi":"https://doi.org/10.48550/arxiv.2510.25548"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2510.25548","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.25548","pdf_url":"https://arxiv.org/pdf/2510.25548","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.25548","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yan, Muyang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan, Muyang","raw_affiliation_strings":["Department of Computer Science , Purdue University , West Lafayette , IN 47907 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Purdue University , West Lafayette , IN 47907 , USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093211845","display_name":"Miras Mengdibayev","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengdibayev, Miras","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Floros, Ardon","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Floros, Ardon","raw_affiliation_strings":["Department of Computer Science , Purdue University , West Lafayette , IN 47907 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Purdue University , West Lafayette , IN 47907 , USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137349549","display_name":"Weihang Guo","orcid":"https://orcid.org/0000-0003-4193-7433","observed_orcids":["https://orcid.org/0000-0003-4193-7433"]},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guo, Weihang","raw_affiliation_strings":["Department of Computer Science , Purdue University , West Lafayette , IN 47907 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Purdue University , West Lafayette , IN 47907 , USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067205988","display_name":"Lydia E. Kavraki","orcid":"https://orcid.org/0000-0003-0699-8038","observed_orcids":["https://orcid.org/0000-0003-0699-8038"]},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kavraki, Lydia E.","raw_affiliation_strings":["Department of Computer Science , Purdue University , West Lafayette , IN 47907 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Purdue University , West Lafayette , IN 47907 , USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088789391","display_name":"Zachary K. Kingston","orcid":"https://orcid.org/0000-0002-3896-5110","observed_orcids":["https://orcid.org/0000-0002-3896-5110"]},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kingston, Zachary","raw_affiliation_strings":["Department of Computer Science , Purdue University , West Lafayette , IN 47907 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Purdue University , West Lafayette , IN 47907 , USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.7505000233650208,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.7505000233650208,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.2240999937057495,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.014000000432133675,"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/task-and-motion-planning","display_name":"task and motion planning","score":0.9959999918937683},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.7319999933242798},{"id":"https://openalex.org/keywords/plan-feasibility","display_name":"plan feasibility","score":0.3889999985694885},{"id":"https://openalex.org/keywords/search-space-pruning","display_name":"search space pruning","score":0.3869999945163727}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.8064000010490417},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.7993000149726868},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7379999756813049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6935999989509583},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6082000136375427},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5928999781608582},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5878000259399414},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.5753999948501587},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5418000221252441},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5236999988555908},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4560000002384186},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.35679998993873596},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30149999260902405},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2784999907016754},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2510.25548","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.25548","pdf_url":"https://arxiv.org/pdf/2510.25548","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.25548","doi":"https://doi.org/10.48550/arxiv.2510.25548","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.25548","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.25548","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.25548","pdf_url":"https://arxiv.org/pdf/2510.25548","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3535963571","display_name":"A Framework for Manipulation Planning and Execution under Uncertainty in Partially-Known Environments","funder_award_id":"2336612","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3784340456","display_name":"Elements: Scalable Next-Generation Software Infrastructure for High-Dimensional Search","funder_award_id":"2411219","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310133","display_name":"Rice University","ror":"https://ror.org/008zs3103"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7102603268.pdf","grobid_xml":"https://content.openalex.org/works/W7102603268.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"task":[1,6,80],"and":[2,61,149],"motion":[3,57],"planning,":[4,58],"high-level":[5],"planning":[7,154],"is":[8,46,141],"done":[9],"over":[10],"an":[11],"abstraction":[12,38],"of":[13,27,36,103,109,170],"the":[14,25,33,37,105,123,173],"world":[15],"to":[16,77,114,125,143,166],"enable":[17],"efficient":[18],"search":[19,93],"in":[20,63,157],"long-horizon":[21],"robotics":[22],"problems.":[23],"However,":[24,82],"feasibility":[26],"these":[28,83,127],"task-level":[29,48],"plans":[30,49],"relies":[31],"on":[32,95,132],"downward":[34,118,161],"refinability":[35,45],"into":[39],"continuous":[40],"motion.":[41],"When":[42],"a":[43,101,120,167],"domain's":[44],"poor,":[47],"that":[50,138],"appear":[51],"valid":[52],"may":[53],"ultimately":[54],"fail":[55],"during":[56,129],"requiring":[59],"replanning":[60],"resulting":[62],"slower":[64],"overall":[65],"performance.":[66],"Prior":[67],"works":[68],"mitigate":[69],"this":[70],"by":[71],"encoding":[72],"refinement":[73,89,119,162],"issues":[74,116],"as":[75],"constraints":[76,87,146],"prune":[78],"infeasible":[79,96],"plans.":[81],"approaches":[84],"only":[85],"add":[86],"upon":[88],"failure,":[90],"expending":[91],"significant":[92],"effort":[94],"branches.":[97],"We":[98],"propose":[99],"VIZ-COAST,":[100],"method":[102],"leveraging":[104],"common-sense":[106],"spatial":[107],"reasoning":[108],"large":[110],"pretrained":[111],"Vision-Language":[112],"Models":[113],"identify":[115],"with":[117],"priori,":[121],"bypassing":[122],"need":[124],"fix":[126],"failures":[128,163],"planning.":[130],"Experiments":[131],"three":[133],"challenging":[134],"TAMP":[135],"domains":[136],"show":[137],"our":[139],"approach":[140],"able":[142],"extract":[144],"plausible":[145],"from":[147,172],"images":[148],"domain":[150],"descriptions,":[151],"drastically":[152],"reducing":[153],"times":[155],"and,":[156],"some":[158],"cases,":[159],"eliminating":[160],"altogether,":[164],"generalizing":[165],"diverse":[168],"range":[169],"instances":[171],"broader":[174],"domain.":[175]},"counts_by_year":[],"updated_date":"2026-10-15T10:00:46.086208","created_date":"2025-10-31T00:00:00"}