{"id":"https://openalex.org/W4415250823","doi":"https://doi.org/10.1109/hpec67600.2025.11196444","title":"Evaluation of Habitat Robotics using Large Language Models","display_name":"Evaluation of Habitat Robotics using Large Language Models","publication_year":2025,"publication_date":"2025-09-15","ids":{"openalex":"https://openalex.org/W4415250823","doi":"https://doi.org/10.1109/hpec67600.2025.11196444"},"language":"en","primary_location":{"id":"doi:10.1109/hpec67600.2025.11196444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec67600.2025.11196444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5115589574","display_name":"W. Li","orcid":"https://orcid.org/0009-0006-8639-5657"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"William Li","raw_affiliation_strings":["Artificial Intelligence Group MIT Lincoln Lab"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Group MIT Lincoln Lab","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081605181","display_name":"Lei Hamilton","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Hamilton","raw_affiliation_strings":["Artificial Intelligence Group MIT Lincoln Lab"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Group MIT Lincoln Lab","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120024857","display_name":"Kaise Al-natour","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaise Al-Natour","raw_affiliation_strings":["Artificial Intelligence Group MIT Lincoln Lab"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Group MIT Lincoln Lab","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080140364","display_name":"Sanjeev Mohindra","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Mohindra","raw_affiliation_strings":["Artificial Intelligence Group MIT Lincoln Lab"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Group MIT Lincoln Lab","institution_ids":["https://openalex.org/I4210122954"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5115589574"],"corresponding_institution_ids":["https://openalex.org/I4210122954"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3966816,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.9455000162124634,"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/T13382","display_name":"Robotics and Automated Systems","score":0.9455000162124634,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9401000142097473,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/robotics","display_name":"Robotics","score":0.7016000151634216},{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.6736000180244446},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.6449000239372253},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5676000118255615},{"id":"https://openalex.org/keywords/cognitive-robotics","display_name":"Cognitive robotics","score":0.5356000065803528},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5156999826431274}],"concepts":[{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.7016000151634216},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6919000148773193},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.6736000180244446},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.6449000239372253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5949000120162964},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5676000118255615},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.5356000065803528},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5156999826431274},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42719998955726624},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41679999232292175},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.36239999532699585},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35530000925064087},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C86610423","wikidata":"https://www.wikidata.org/wiki/Q1925081","display_name":"Metamodeling","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.289900004863739},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27070000767707825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec67600.2025.11196444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec67600.2025.11196444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE High Performance Extreme Computing Conference (HPEC)","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":5,"referenced_works":["https://openalex.org/W3009928773","https://openalex.org/W4367016688","https://openalex.org/W4402354126","https://openalex.org/W4402670901","https://openalex.org/W4402671950"],"related_works":[],"abstract_inverted_index":{"This":[0,99],"paper":[1],"focuses":[2],"on":[3,58],"evaluating":[4],"the":[5,17,51],"effectiveness":[6],"of":[7,104],"Large":[8],"Language":[9],"Models":[10],"at":[11],"solving":[12],"embodied":[13,85,107],"robotic":[14,27,44,84,108],"tasks":[15],"using":[16],"Meta":[18,21,59],"PARTNER":[19,60],"benchmark.":[20],"PARTNR":[22],"provides":[23,100],"simplified":[24],"environments":[25],"and":[26,77,95],"interactions":[28],"within":[29],"randomized":[30,35],"indoor":[31],"kitchen":[32,36],"scenes.":[33],"Each":[34],"scene":[37],"is":[38],"given":[39],"a":[40,101],"task":[41],"where":[42],"two":[43],"agents":[45],"cooperatively":[46],"work":[47],"together":[48],"to":[49],"solve":[50],"task.":[52],"We":[53],"evaluated":[54],"multiple":[55],"frontier":[56],"models":[57,67,73],"environments.":[61,86],"Our":[62],"results":[63],"indicate":[64],"that":[65],"reasoning":[66],"like":[68,74],"OpenAI":[69,75],"o3-mini":[70,87],"outperform":[71,89],"non-reasoning":[72],"GPT-4o":[76],"Llama":[78],"3":[79],"when":[80],"operating":[81],"in":[82],"PARTNR\u2019s":[83],"displayed":[88],"across":[90],"centralized,":[91],"decentralized,":[92],"full":[93],"observability,":[94],"partial":[96],"observability":[97],"configurations.":[98],"promising":[102],"avenue":[103],"research":[105],"for":[106],"development.":[109]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-16T00:00:00"}
