{"id":"https://openalex.org/W4416748392","doi":"https://doi.org/10.1109/iros60139.2025.11246368","title":"Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Models","display_name":"Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748392","doi":"https://doi.org/10.1109/iros60139.2025.11246368"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5114860961","display_name":"Qi Wu","orcid":"https://orcid.org/0000-0002-2114-9037"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qi Wu","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077274536","display_name":"Zipeng Fu","orcid":"https://orcid.org/0000-0002-7462-7215"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zipeng Fu","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018420548","display_name":"Xuxin Cheng","orcid":"https://orcid.org/0009-0002-6244-2931"},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuxin Cheng","raw_affiliation_strings":["UC San Diego"],"affiliations":[{"raw_affiliation_string":"UC San Diego","institution_ids":["https://openalex.org/I2800935791"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100424276","display_name":"Xiaolong Wang","orcid":"https://orcid.org/0000-0003-3355-3632"},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaolong Wang","raw_affiliation_strings":["UC San Diego"],"affiliations":[{"raw_affiliation_string":"UC San Diego","institution_ids":["https://openalex.org/I2800935791"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005431772","display_name":"Chelsea Finn","orcid":"https://orcid.org/0000-0001-6298-0874"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chelsea Finn","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5114860961"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":1.3185,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86051407,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8826","last_page":"8833"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.43209999799728394,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.43209999799728394,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.16689999401569366,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.05779999867081642,"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/object","display_name":"Object (grammar)","score":0.6061000227928162},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5848000049591064},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4788999855518341},{"id":"https://openalex.org/keywords/reachability","display_name":"Reachability","score":0.46860000491142273},{"id":"https://openalex.org/keywords/agile-software-development","display_name":"Agile software development","score":0.4602000117301941},{"id":"https://openalex.org/keywords/revolute-joint","display_name":"Revolute joint","score":0.4593000113964081},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.45500001311302185},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.3465999960899353}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6937999725341797},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6061000227928162},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5857999920845032},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5848000049591064},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5329999923706055},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4788999855518341},{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.46860000491142273},{"id":"https://openalex.org/C14185376","wikidata":"https://www.wikidata.org/wiki/Q30232","display_name":"Agile software development","level":2,"score":0.4602000117301941},{"id":"https://openalex.org/C5643039","wikidata":"https://www.wikidata.org/wiki/Q3819341","display_name":"Revolute joint","level":3,"score":0.4593000113964081},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.45500001311302185},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42329999804496765},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3465999960899353},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C161759796","wikidata":"https://www.wikidata.org/wiki/Q3982902","display_name":"Teleoperation","level":3,"score":0.3248000144958496},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2989000082015991},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.27720001339912415},{"id":"https://openalex.org/C95038775","wikidata":"https://www.wikidata.org/wiki/Q22857","display_name":"Climbing","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2685999870300293},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C2779908020","wikidata":"https://www.wikidata.org/wiki/Q1424704","display_name":"Legged robot","level":3,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":52,"referenced_works":["https://openalex.org/W1502718064","https://openalex.org/W1853143499","https://openalex.org/W2026582138","https://openalex.org/W2059114576","https://openalex.org/W2117425572","https://openalex.org/W2142992961","https://openalex.org/W2160455972","https://openalex.org/W2294151168","https://openalex.org/W2569791289","https://openalex.org/W2614308505","https://openalex.org/W2738358082","https://openalex.org/W2911087563","https://openalex.org/W2944561196","https://openalex.org/W2951360122","https://openalex.org/W2968764556","https://openalex.org/W3093922502","https://openalex.org/W3175254947","https://openalex.org/W3206363598","https://openalex.org/W3206771627","https://openalex.org/W3207033168","https://openalex.org/W4200235017","https://openalex.org/W4205430897","https://openalex.org/W4214634122","https://openalex.org/W4225529872","https://openalex.org/W4226143977","https://openalex.org/W4283787029","https://openalex.org/W4312574175","https://openalex.org/W4383097638","https://openalex.org/W4383108291","https://openalex.org/W4383108438","https://openalex.org/W4386038305","https://openalex.org/W4387653674","https://openalex.org/W4388720459","https://openalex.org/W4388895019","https://openalex.org/W4392646028","https://openalex.org/W4401413688","https://openalex.org/W4401414436","https://openalex.org/W4401414804","https://openalex.org/W4401415287","https://openalex.org/W4401415792","https://openalex.org/W4401417048","https://openalex.org/W4402300083","https://openalex.org/W4402354036","https://openalex.org/W4402354083","https://openalex.org/W4402660140","https://openalex.org/W4402716288","https://openalex.org/W4402753923","https://openalex.org/W4404612908","https://openalex.org/W4405785085","https://openalex.org/W4405786041","https://openalex.org/W4405786528","https://openalex.org/W4413926133"],"related_works":[],"abstract_inverted_index":{"Learning-Based":[0],"methods":[1],"have":[2],"achieved":[3],"strong":[4],"performance":[5],"for":[6,29,50,62,74,96],"quadrupedal":[7,51],"locomotion.":[8],"However,":[9],"several":[10],"challenges":[11],"prevent":[12],"quadrupeds":[13],"from":[14],"learning":[15],"helpful":[16],"indoor":[17,44,55],"skills":[18,76],"that":[19],"require":[20],"interaction":[21],"with":[22,87,145],"environments":[23,109,124],"and":[24,38,41,79,82,91,99,125],"humans:":[25],"lack":[26],"of":[27],"end-effectors":[28],"manipulation,":[30,64],"limited":[31],"semantic":[32,97],"under-standing":[33],"using":[34,71],"only":[35],"simulation":[36,70],"data,":[37],"low":[39],"traversability":[40],"reachability":[42],"in":[43,54,69,106],"environments.":[45,56],"We":[46,102],"present":[47],"a":[48,59,65,88,134,142,146],"system":[49,105,118],"mobile":[52],"manipulation":[53],"It":[57],"uses":[58],"front-mounted":[60],"gripper":[61],"object":[63],"low-level":[66],"controller":[67],"trained":[68],"egocentric":[72,93],"depth":[73],"agile":[75],"like":[77,128],"climbing":[78,140],"whole-body":[80],"tilting,":[81],"pre-trained":[83],"vision-language":[84],"models":[85],"(VLMs)":[86],"third-person":[89],"fisheye":[90],"an":[92],"RGB":[94],"camera":[95],"understanding":[98],"command":[100],"generation.":[101],"evaluate":[103],"our":[104],"two":[107],"unseen":[108],"without":[110],"any":[111],"real-world":[112],"data":[113],"collection":[114],"or":[115],"training.":[116],"Our":[117],"can":[119],"zero-shot":[120],"generalize":[121],"to":[122,132],"these":[123],"complete":[126],"tasks,":[127],"following":[129],"user\u2019s":[130],"commands":[131],"fetch":[133],"randomly":[135],"placed":[136],"stuff":[137],"toy":[138],"after":[139],"over":[141],"queen-sized":[143],"bed,":[144],"60%":[147],"success":[148],"rate.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-11-28T00:00:00"}