{"id":"https://openalex.org/W2796152145","doi":"https://doi.org/10.1109/icra.2019.8793736","title":"Visual Robot Task Planning","display_name":"Visual Robot Task Planning","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2796152145","doi":"https://doi.org/10.1109/icra.2019.8793736","mag":"2796152145"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2019.8793736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8793736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1804.00062","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044926286","display_name":"Chris Paxton","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Paxton","raw_affiliation_strings":["Department of Computer Science, The Johns Hopkins University, Baltimore, MD, USA","[Dept. of Computer Science, The Johns Hopkins University, Baltimore, MD, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"[Dept. of Computer Science, The Johns Hopkins University, Baltimore, MD, USA]","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077503210","display_name":"Yotam Barnoy","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yotam Barnoy","raw_affiliation_strings":["Department of Computer Science, The Johns Hopkins University, Baltimore, MD, USA","[Dept. of Computer Science, The Johns Hopkins University, Baltimore, MD, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"[Dept. of Computer Science, The Johns Hopkins University, Baltimore, MD, USA]","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044895481","display_name":"Kapil D. Katyal","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kapil Katyal","raw_affiliation_strings":["Department of Computer Science, The Johns Hopkins University, Baltimore, MD, USA","[Dept. of Computer Science, The Johns Hopkins University, Baltimore, MD, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"[Dept. of Computer Science, The Johns Hopkins University, Baltimore, MD, USA]","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063457506","display_name":"Raman Arora","orcid":"https://orcid.org/0000-0003-2002-3923"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raman Arora","raw_affiliation_strings":["Department of Computer Science, The Johns Hopkins University, Baltimore, MD, USA","[Dept. of Computer Science, The Johns Hopkins University, Baltimore, MD, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"[Dept. of Computer Science, The Johns Hopkins University, Baltimore, MD, USA]","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041383246","display_name":"Gregory D. Hager","orcid":"https://orcid.org/0000-0002-6662-9763"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gregory D. Hager","raw_affiliation_strings":["Department of Computer Science, The Johns Hopkins University, Baltimore, MD, USA","[Dept. of Computer Science, The Johns Hopkins University, Baltimore, MD, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"[Dept. of Computer Science, The Johns Hopkins University, Baltimore, MD, USA]","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8832","last_page":"8838"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.996999979019165,"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":0.996999979019165,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9965000152587891,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.7241252064704895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7077847123146057},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6893270611763},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6264067888259888},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5588078498840332},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5456857681274414},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.4721885919570923},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.450607031583786},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4472653269767761},{"id":"https://openalex.org/keywords/futures-contract","display_name":"Futures contract","score":0.4347867965698242},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4186168313026428},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4175414443016052},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40363067388534546},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1513580083847046}],"concepts":[{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.7241252064704895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7077847123146057},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6893270611763},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6264067888259888},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5588078498840332},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5456857681274414},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.4721885919570923},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.450607031583786},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4472653269767761},{"id":"https://openalex.org/C106306483","wikidata":"https://www.wikidata.org/wiki/Q183984","display_name":"Futures contract","level":2,"score":0.4347867965698242},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4186168313026428},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4175414443016052},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40363067388534546},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1513580083847046},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icra.2019.8793736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8793736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1804.00062","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.00062","pdf_url":"https://arxiv.org/pdf/1804.00062","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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.1804.00062","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1804.00062","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},{"id":"mag:2796152145","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1804.00062","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.00062","pdf_url":"https://arxiv.org/pdf/1804.00062","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[{"id":"https://openalex.org/G2456170329","display_name":"NRI: Collaborative Research: Experiential Learning for Robots: From Physics to Actions to Tasks","funder_award_id":"1637949","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/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320317236","display_name":"Maryland Advanced Research Computing Center","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2796152145.pdf","grobid_xml":"https://content.openalex.org/works/W2796152145.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W2059351324","https://openalex.org/W2106363968","https://openalex.org/W2236144517","https://openalex.org/W2258731934","https://openalex.org/W2281096776","https://openalex.org/W2296146598","https://openalex.org/W2400532028","https://openalex.org/W2401640538","https://openalex.org/W2403069916","https://openalex.org/W2434014514","https://openalex.org/W2443711627","https://openalex.org/W2528489519","https://openalex.org/W2550336733","https://openalex.org/W2552465644","https://openalex.org/W2557519264","https://openalex.org/W2561079189","https://openalex.org/W2572730214","https://openalex.org/W2592538810","https://openalex.org/W2599174273","https://openalex.org/W2600009170","https://openalex.org/W2739083961","https://openalex.org/W2741768657","https://openalex.org/W2762014360","https://openalex.org/W2949354685","https://openalex.org/W2950848044","https://openalex.org/W2963522749","https://openalex.org/W2963634205","https://openalex.org/W2964161785","https://openalex.org/W6692405165","https://openalex.org/W6712884540","https://openalex.org/W6713184877","https://openalex.org/W6713563955","https://openalex.org/W6735030908","https://openalex.org/W6741519989","https://openalex.org/W6741940250","https://openalex.org/W6745407062","https://openalex.org/W6766234440","https://openalex.org/W6779669310"],"related_works":["https://openalex.org/W2767661932","https://openalex.org/W2963447367","https://openalex.org/W3034358814","https://openalex.org/W2039967891","https://openalex.org/W2571632457","https://openalex.org/W2752385657","https://openalex.org/W2593574970","https://openalex.org/W3103282518","https://openalex.org/W2792868485","https://openalex.org/W3207647944","https://openalex.org/W164072472","https://openalex.org/W3204941861","https://openalex.org/W2398020923","https://openalex.org/W3170205466","https://openalex.org/W2594865990","https://openalex.org/W2810723160","https://openalex.org/W3089739707","https://openalex.org/W2967901646","https://openalex.org/W3015079645","https://openalex.org/W1597170221"],"abstract_inverted_index":{"Prospection":[0],"is":[1],"key":[2],"to":[3,19,84,111,116,124,131,141],"solving":[4],"challenging":[5],"problems":[6],"in":[7,34,93],"new":[8],"environments,":[9,97],"but":[10],"it":[11],"has":[12],"not":[13],"been":[14],"deeply":[15],"explored":[16],"as":[17],"applied":[18],"task":[20,29,145],"planning":[21,64],"for":[22],"perception-driven":[23],"robotics.":[24],"We":[25],"propose":[26],"visual":[27,136],"robot":[28],"planning,":[30],"where":[31],"we":[32,56],"take":[33],"an":[35],"input":[36],"image":[37],"and":[38,46,62,98,129,138,143],"must":[39],"generate":[40,76,142],"a":[41,58,69,94,104,113,117,151],"sequence":[42],"of":[43,71,88,90,96,106,150],"high-level":[44,91],"actions":[45,92,102],"associated":[47,63],"observations":[48],"that":[49,66,74],"achieve":[50],"some":[51],"task.":[52],"In":[53],"this":[54,81,140],"paper,":[55],"describe":[57],"neural":[59],"network":[60],"architecture":[61],"algorithm":[65],"(1)":[67],"learns":[68],"representation":[70],"the":[72,86],"world":[73],"can":[75],"prospective":[77],"futures,":[78],"(2)":[79],"uses":[80],"generative":[82],"model":[83],"simulate":[85],"result":[87],"sequences":[89],"variety":[95],"(3)":[99],"evaluates":[100],"these":[101],"via":[103],"variant":[105],"Monte":[107],"Carlo":[108],"Tree":[109],"Search":[110],"find":[112],"viable":[114],"solution":[115],"particular":[118],"problem.":[119],"Our":[120],"approach":[121],"allows":[122],"us":[123],"visualize":[125,144],"intermediate":[126],"motion":[127],"goals":[128],"learn":[130],"plan":[132],"complex":[133],"activity":[134],"from":[135],"information,":[137],"used":[139],"plans":[146],"on":[147],"held-out":[148],"examples":[149],"block-stacking":[152],"simulation.":[153]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}