{"id":"https://openalex.org/W4416749391","doi":"https://doi.org/10.1109/iros60139.2025.11246658","title":"ET-Plan-Bench: Embodied Task-level Planning Benchmark Towards Spatial-Temporal Cognition with Foundation Models","display_name":"ET-Plan-Bench: Embodied Task-level Planning Benchmark Towards Spatial-Temporal Cognition with Foundation Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749391","doi":"https://doi.org/10.1109/iros60139.2025.11246658"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246658","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/A5101749695","display_name":"Lingfeng Zhang","orcid":"https://orcid.org/0000-0003-4891-0073"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Lingfeng Zhang","raw_affiliation_strings":["Huawei Noah&#x2019;s Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x2019;s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002189116","display_name":"Yuening Wang","orcid":"https://orcid.org/0009-0002-0795-9233"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Yuening Wang","raw_affiliation_strings":["Huawei Noah&#x2019;s Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x2019;s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004252201","display_name":"Hongjian Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Hongjian Gu","raw_affiliation_strings":["Huawei Noah&#x2019;s Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x2019;s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114534209","display_name":"Atia Hamidizadeh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Atia Hamidizadeh","raw_affiliation_strings":["Huawei Noah&#x2019;s Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x2019;s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024908803","display_name":"Zhanguang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Zhanguang Zhang","raw_affiliation_strings":["Huawei Noah&#x2019;s Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x2019;s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064580686","display_name":"Yuecheng Liu","orcid":"https://orcid.org/0000-0002-3683-7959"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Yuecheng Liu","raw_affiliation_strings":["Huawei Noah&#x2019;s Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x2019;s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100631521","display_name":"Yutong Wang","orcid":"https://orcid.org/0000-0001-7429-031X"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Yutong Wang","raw_affiliation_strings":["Huawei Noah&#x2019;s Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x2019;s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075234121","display_name":"David Nogu\u00e9s\u2010Bravo","orcid":"https://orcid.org/0000-0002-4060-0153"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"David Gamaliel Arcos Bravo","raw_affiliation_strings":["Huawei Noah&#x2019;s Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x2019;s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102660136","display_name":"Junyi Dong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junyi Dong","raw_affiliation_strings":["Huawei Cloud"],"affiliations":[{"raw_affiliation_string":"Huawei Cloud","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042268476","display_name":"Shunbo Zhou","orcid":"https://orcid.org/0000-0002-6077-4951"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shunbo Zhou","raw_affiliation_strings":["Huawei Cloud"],"affiliations":[{"raw_affiliation_string":"Huawei Cloud","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103079073","display_name":"Tongtong Cao","orcid":"https://orcid.org/0000-0003-1545-8842"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Tongtong Cao","raw_affiliation_strings":["Huawei Noah&#x2019;s Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x2019;s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113273845","display_name":"Xingyue Quan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Xingyue Quan","raw_affiliation_strings":["Huawei Noah&#x2019;s Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x2019;s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011036128","display_name":"Yuzheng Zhuang","orcid":"https://orcid.org/0000-0002-0915-0254"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Yuzheng Zhuang","raw_affiliation_strings":["Huawei Noah&#x2019;s Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x2019;s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074277827","display_name":"Yingxue Zhang","orcid":"https://orcid.org/0000-0002-0947-1875"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Yingxue Zhang","raw_affiliation_strings":["Huawei Noah&#x2019;s Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x2019;s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047509839","display_name":"Jianye Hao","orcid":"https://orcid.org/0000-0002-0422-8235"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Jianye Hao","raw_affiliation_strings":["Huawei Noah&#x2019;s Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x2019;s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":15,"corresponding_author_ids":["https://openalex.org/A5101749695"],"corresponding_institution_ids":["https://openalex.org/I4210159102"],"apc_list":null,"apc_paid":null,"fwci":1.4097,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87373247,"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":"21566","last_page":"21573"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6757000088691711,"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":0.6757000088691711,"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/T11431","display_name":"Action Observation and Synchronization","score":0.07249999791383743,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.028699999675154686,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.9061999917030334},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7106999754905701},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5796999931335449},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.49970000982284546},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.4876999855041504},{"id":"https://openalex.org/keywords/embodied-agent","display_name":"Embodied agent","score":0.47620001435279846},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.46480000019073486},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4309000074863434}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.9061999917030334},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7106999754905701},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6363999843597412},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5796999931335449},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5383999943733215},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.49970000982284546},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4876999855041504},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.47620001435279846},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.46480000019073486},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4309000074863434},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.42489999532699585},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.40959998965263367},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4090999960899353},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.4074000120162964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3903999924659729},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.3325999975204468},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.31929999589920044},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.30959999561309814},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2854999899864197},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246658","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2799002257","https://openalex.org/W3004037805","https://openalex.org/W3034758614","https://openalex.org/W4389518753","https://openalex.org/W4402716288","https://openalex.org/W4402753977","https://openalex.org/W4402772286","https://openalex.org/W4402776116","https://openalex.org/W4411119249","https://openalex.org/W4413155645","https://openalex.org/W4416034567"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,32,84,101,233],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"have":[7],"catalyzed":[8],"numerous":[9],"efforts":[10],"to":[11,15,93,139,219],"apply":[12],"these":[13,54,172],"technologies":[14],"embodied":[16,67,81,102,234],"tasks,":[17,82,179],"with":[18,144,186],"a":[19,65,75,190,205,216],"particular":[20],"focus":[21],"on":[22,176],"high-level":[23],"task":[24,27,68,103,235],"planning":[25,69,236],"and":[26,41,46,77,88,110,115,117,147,158,165,196,210,229],"decomposition.":[28],"LLMs":[29],"face":[30],"challenges":[31],"understanding":[33,106,192],"the":[34,49,131,145,148,220],"physical":[35],"world,":[36],"especially":[37],"regarding":[38],"spatial,":[39,194],"temporal,":[40,195],"causal":[42,118,197],"relationships":[43,55],"among":[44],"objects":[45],"actions.":[47],"Moreover,":[48],"current":[50],"benchmarks":[51],"for":[52,150],"evaluating":[53],"are":[56],"limited.":[57],"To":[58],"further":[59,231],"investigate":[60],"this":[61],"domain,":[62],"we":[63],"introduce":[64],"novel":[66],"benchmark,":[70],"ET-Plan-Bench.":[71],"This":[72],"benchmark":[73,201],"features":[74],"controllable":[76],"diverse":[78],"array":[79],"of":[80,86,98,112,120,122,193],"varying":[83],"levels":[85],"difficulty":[87],"complexity.":[89],"It":[90],"is":[91],"designed":[92],"evaluate":[94],"two":[95],"critical":[96],"dimensions":[97],"LLMs\u2019":[99],"application":[100],"understanding:":[104],"spatial":[105],"(including":[107],"relation":[108],"constraints":[109],"occlusion":[111],"target":[113],"objects)":[114],"temporal":[116],"comprehension":[119],"sequences":[121],"actions":[123],"within":[124],"an":[125],"environment.":[126],"Utilizing":[127],"multi-source":[128],"simulators":[129],"as":[130,152,204],"backend":[132],"simulator,":[133],"ET-Plan-Bench":[134],"provides":[135],"immediate":[136],"environmental":[137],"feedback":[138],"LLMs,":[140],"enabling":[141],"dynamic":[142],"interaction":[143],"environment":[146],"capacity":[149],"re-planning":[151],"necessary.":[153],"We":[154,224],"evaluated":[155],"state-of-the-art":[156],"open-source":[157],"closed-source":[159],"foundational":[160,222,238],"models,":[161],"including":[162],"GPT-4,":[163],"Llama,":[164],"Mistral,":[166],"using":[167],"our":[168,200],"proposed":[169],"benchmark.":[170],"While":[171],"models":[173],"perform":[174],"adequately":[175],"simple":[177],"navigation":[178],"their":[180],"performance":[181],"significantly":[182],"deteriorates":[183],"when":[184],"con-fronted":[185],"tasks":[187],"that":[188,214],"demand":[189],"deeper":[191],"relationships.":[198],"Consequently,":[199],"distinguishes":[202],"itself":[203],"large-scale,":[206],"quantifiable,":[207],"highly":[208],"automated,":[209],"fine-grained":[211],"diagnostic":[212],"framework":[213],"presents":[215],"substantial":[217],"challenge":[218],"latest":[221],"models.":[223,239],"hope":[225],"it":[226],"will":[227],"inspire":[228],"propel":[230],"research":[232],"utilizing":[237],"Code":[240],"available":[241],"at:":[242],"https://github.com/ET-Plan-Bench/ET-Plan-Bench":[243]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-11-28T00:00:00"}
