{"id":"https://openalex.org/W4413917878","doi":"https://doi.org/10.1109/icra55743.2025.11128775","title":"AlignBot: Aligning VLM-Powered Customized Task Planning with User Reminders Through Fine-Tuning for Household Robots","display_name":"AlignBot: Aligning VLM-Powered Customized Task Planning with User Reminders Through Fine-Tuning for Household Robots","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413917878","doi":"https://doi.org/10.1109/icra55743.2025.11128775"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128775","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 Robotics and Automation (ICRA)","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/A5114400013","display_name":"Zhaxizhuoma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhaxizhuoma","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087173663","display_name":"P.C. Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengan Chen","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005377968","display_name":"Ziniu Wu","orcid":"https://orcid.org/0000-0003-1710-8598"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziniu Wu","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046069900","display_name":"Jiawei Sun","orcid":"https://orcid.org/0000-0002-2829-9302"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Sun","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391459","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-2493-1032"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076945936","display_name":"Peng Zhou","orcid":"https://orcid.org/0000-0002-7020-0943"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Peng Zhou","raw_affiliation_strings":["The University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076613604","display_name":"Nieqing Cao","orcid":"https://orcid.org/0000-0003-3414-4603"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nieqing Cao","raw_affiliation_strings":["Xi’ an Jiaotong-Liverpool University"],"affiliations":[{"raw_affiliation_string":"Xi’ an Jiaotong-Liverpool University","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030190829","display_name":"Yan Ding","orcid":"https://orcid.org/0000-0002-7949-4351"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Ding","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100344053","display_name":"Bin Zhao","orcid":"https://orcid.org/0000-0001-8397-7260"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Zhao","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100740146","display_name":"Xuelong Li","orcid":"https://orcid.org/0000-0003-2037-2525"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuelong Li","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5114400013"],"corresponding_institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"],"apc_list":null,"apc_paid":null,"fwci":1.3104,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85006267,"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":"12549","last_page":"12556"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.8077999949455261,"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":0.8077999949455261,"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/T11942","display_name":"Transportation and Mobility Innovations","score":0.7962999939918518,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10525","display_name":"Human-Automation Interaction and Safety","score":0.7814000248908997,"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/task","display_name":"Task (project management)","score":0.7389758229255676},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.734856367111206},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6445212364196777},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"Fine-tuning","score":0.5456363558769226},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5175046920776367},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.3516693115234375},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3324289321899414},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18380582332611084},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17784026265144348},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.13940641283988953}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7389758229255676},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.734856367111206},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6445212364196777},{"id":"https://openalex.org/C157524613","wikidata":"https://www.wikidata.org/wiki/Q2828883","display_name":"Fine-tuning","level":2,"score":0.5456363558769226},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5175046920776367},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3516693115234375},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3324289321899414},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18380582332611084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17784026265144348},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.13940641283988953},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128775","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 Robotics and Automation (ICRA)","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":17,"referenced_works":["https://openalex.org/W2144211451","https://openalex.org/W2912694244","https://openalex.org/W4385299449","https://openalex.org/W4385430674","https://openalex.org/W4386251907","https://openalex.org/W4386320380","https://openalex.org/W4388660746","https://openalex.org/W4388720459","https://openalex.org/W4389009947","https://openalex.org/W4389665359","https://openalex.org/W4401415710","https://openalex.org/W4401553778","https://openalex.org/W4401687172","https://openalex.org/W4402670096","https://openalex.org/W4402727764","https://openalex.org/W4409370047","https://openalex.org/W4412461803"],"related_works":["https://openalex.org/W4390306690","https://openalex.org/W1969209172","https://openalex.org/W4385572141","https://openalex.org/W8302103","https://openalex.org/W3171631314","https://openalex.org/W4281997472","https://openalex.org/W2674584172","https://openalex.org/W3213722473","https://openalex.org/W2110944602","https://openalex.org/W2038741529"],"abstract_inverted_index":{"This":[0,63],"paper":[1],"presents":[2],"AlignBot,":[3,117],"a":[4,53,94,190],"novel":[5],"framework":[6],"designed":[7],"to":[8,36,131,182],"optimize":[9],"VLM-powered":[10,167],"customized":[11,88,160],"task":[12,27,89,109,161],"planning":[13,28,110],"for":[14,61,105,149],"household":[15,123,134],"robots":[16],"by":[17,169],"effectively":[18],"aligning":[19,26,172],"with":[20,29,139,173],"user":[21,30,70,174],"reminders.":[22,46],"In":[23],"domestic":[24],"settings,":[25],"reminders":[31,146],"poses":[32],"significant":[33],"challenges":[34],"due":[35],"the":[37,45,114,129,183],"limited":[38],"quantity,":[39],"diversity,":[40],"and":[41,77,151,166,171,193],"multimodal":[42,137],"nature":[43],"of":[44,69,116],"To":[47,112],"address":[48],"these":[49],"challenges,":[50],"AlignBot":[51,92,157],"employs":[52],"fine-tuned":[54],"LLaVA-7B":[55],"model,":[56],"functioning":[57],"as":[58,72,103],"an":[59],"adapter":[60,64],"GPT-40.":[62],"model":[65],"internalizes":[66],"diverse":[67],"forms":[68],"reminders-such":[71],"personalized":[73],"preferences,":[74],"corrective":[75],"guidance,":[76],"contextual":[78],"assistance-into":[79],"structured":[80],"instruction-formatted":[81],"cues":[82],"that":[83,98,156],"prompt":[84],"GPT-40":[85,185],"in":[86,121],"generating":[87],"plans.":[90],"Additionally,":[91],"integrates":[93],"dynamic":[95],"retrieval":[96],"mechanism":[97],"selects":[99],"task-relevant":[100],"historical":[101],"successes":[102],"prompts":[104],"GPT-40,":[106],"further":[107],"enhancing":[108],"accuracy.":[111],"validate":[113],"effectiveness":[115],"experiments":[118],"are":[119,126,201],"conducted":[120],"real-world":[122],"environments,":[124],"which":[125],"constructed":[127],"within":[128],"laboratory":[130],"replicate":[132],"typical":[133],"settings.":[135],"A":[136],"dataset":[138],"over":[140,194],"1,500":[141],"entries":[142],"derived":[143],"from":[144],"volunteer":[145],"is":[147],"used":[148],"training":[150],"evaluation.":[152],"The":[153],"results":[154],"demonstrate":[155],"significantly":[158],"improves":[159],"planning,":[162],"outperforming":[163],"existing":[164],"LLM-":[165],"planners":[168],"interpreting":[170],"reminders,":[175],"achieving":[176],"86.8":[177],"%":[178],"success":[179],"rate":[180],"compared":[181],"vanilla":[184],"baseline":[186],"at":[187],"21.6%,":[188],"reflecting":[189],"65%":[191],"improvement":[192],"four":[195],"times":[196],"greater":[197],"effectiveness.":[198],"Supplementary":[199],"materials":[200],"available":[202],"at:":[203],"https://yding25.com/AlignBot/":[204]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}