{"id":"https://openalex.org/W4409020455","doi":"https://doi.org/10.1109/bigcomp64353.2025.00061","title":"Relaxed HLP: A Metric for Flexible High-Level Plan Evaluation in Embodied Environments","display_name":"Relaxed HLP: A Metric for Flexible High-Level Plan Evaluation in Embodied Environments","publication_year":2025,"publication_date":"2025-02-09","ids":{"openalex":"https://openalex.org/W4409020455","doi":"https://doi.org/10.1109/bigcomp64353.2025.00061"},"language":"en","primary_location":{"id":"doi:10.1109/bigcomp64353.2025.00061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigcomp64353.2025.00061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Big Data and Smart Computing (BigComp)","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/A5081281228","display_name":"Suyeon Shin","orcid":"https://orcid.org/0000-0002-0780-4963"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Suyeon Shin","raw_affiliation_strings":["Seoul National University,Interdisciplinary Program in AI (IPAI),Seoul,Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Interdisciplinary Program in AI (IPAI),Seoul,Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050928023","display_name":"Byoung\u2010Tak Zhang","orcid":"https://orcid.org/0000-0001-9890-0389"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byoung-Tak Zhang","raw_affiliation_strings":["AI Institute Seoul National University,Seoul,Korea"],"affiliations":[{"raw_affiliation_string":"AI Institute Seoul National University,Seoul,Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5081281228"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06120434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"295","last_page":"298"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.3370000123977661,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.3370000123977661,"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/T11810","display_name":"Complex Systems and Decision Making","score":0.2985999882221222,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.8319147825241089},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6931977868080139},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.64826500415802},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.5696118474006653},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3730490803718567},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21060627698898315},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.188167005777359},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.09059658646583557},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.07519158720970154}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.8319147825241089},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6931977868080139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.64826500415802},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.5696118474006653},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3730490803718567},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21060627698898315},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.188167005777359},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.09059658646583557},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.07519158720970154},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigcomp64353.2025.00061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigcomp64353.2025.00061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Big Data and Smart Computing (BigComp)","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":6,"referenced_works":["https://openalex.org/W3034758614","https://openalex.org/W4365512576","https://openalex.org/W4390874280","https://openalex.org/W6798219303","https://openalex.org/W6802203484","https://openalex.org/W6865293754"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2380179524","https://openalex.org/W4283365723","https://openalex.org/W2963001125","https://openalex.org/W2091233881","https://openalex.org/W2352366064","https://openalex.org/W4250820896","https://openalex.org/W2124102101"],"abstract_inverted_index":{"As":[0],"the":[1,75,108,127,179,205],"field":[2],"of":[3,35,77,110,173,181,207,221],"robotics":[4],"advances,":[5],"Embodied":[6],"Instruction":[7],"Following":[8],"(EIF)":[9],"has":[10],"emerged":[11],"as":[12,44],"a":[13,38,100,138,169,217],"key":[14,158],"challenge":[15],"in":[16,210,224],"artificial":[17],"intelligence.":[18],"EIF":[19,225],"tasks":[20],"require":[21],"agents":[22],"to":[23,99,142,197],"interpret":[24],"and":[25,32,56,164],"execute":[26],"natural":[27],"language":[28],"instructions":[29,118],"by":[30,148],"predicting":[31],"completing":[33],"sequences":[34],"subgoals":[36],"within":[37],"physical":[39],"environment.":[40],"Traditional":[41],"evaluation":[42],"metrics\u2014such":[43],"Success":[45],"Rate":[46],"(SR),":[47],"Goal":[48],"Condition":[49],"(GC),":[50],"Path":[51,57],"Length":[52,58],"Weighted":[53,59],"SR":[54],"(PLWSR),":[55],"GC":[60],"(PLWGC)\u2014primarily":[61],"focus":[62],"on":[63,95],"task":[64,85],"success":[65],"following":[66],"low-level":[67],"control":[68],"actions.":[69],"However,":[70],"these":[71,132],"metrics":[72],"inadequately":[73],"assess":[74],"accuracy":[76],"high-level":[78,91,144,174,222],"planning,":[79],"which":[80],"is":[81],"critical":[82],"for":[83,89,120,150],"overall":[84],"performance.":[86],"Existing":[87],"methods":[88],"evaluating":[90],"planning":[92,145,223],"often":[93],"rely":[94],"comparing":[96],"predicted":[97],"plans":[98],"single":[101],"human-annotated":[102],"ground":[103,199],"truth":[104],"trajectory,":[105],"implicitly":[106],"assuming":[107],"existence":[109],"only":[111],"one":[112],"correct":[113],"solution.":[114],"In":[115],"practice,":[116],"many":[117],"allow":[119],"multiple":[121],"valid":[122,152],"trajectories":[123],"that":[124,188],"can":[125],"achieve":[126],"same":[128],"goal.":[129],"To":[130],"address":[131],"limitations,":[133],"we":[134],"propose":[135],"Relaxed":[136,154,182,208],"HLP,":[137],"novel":[139],"metric":[140],"designed":[141],"evaluate":[143],"more":[146,170,191,218],"flexibly":[147],"accounting":[149],"alternative":[151],"plans.":[153],"HLP":[155,183,209],"introduces":[156],"three":[157],"considerations:":[159],"temporal":[160],"agnosticism,":[161,163],"spatial":[162],"interchangeable":[165],"actions,":[166],"thus":[167],"enabling":[168],"comprehensive":[171],"assessment":[172,220],"plan":[175],"accuracy.":[176],"We":[177],"validate":[178],"effectiveness":[180],"through":[184],"human":[185,194],"evaluations,":[186],"demonstrating":[187],"it":[189],"aligns":[190],"closely":[192],"with":[193],"judgment":[195],"compared":[196],"traditional":[198],"truth-based":[200],"metrics.":[201],"Our":[202],"results":[203],"underscore":[204],"robustness":[206],"capturing":[211],"diverse,":[212],"semantically":[213],"equivalent":[214],"plans,":[215],"offering":[216],"accurate":[219],"tasks.":[226]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}