{"id":"https://openalex.org/W7138055160","doi":"https://doi.org/10.48550/arxiv.2603.14367","title":"HomeGuard: VLM-based Embodied Safeguard for Identifying Contextual Risk in Household Task","display_name":"HomeGuard: VLM-based Embodied Safeguard for Identifying Contextual Risk in Household Task","publication_year":2026,"publication_date":"2026-03-15","ids":{"openalex":"https://openalex.org/W7138055160","doi":"https://doi.org/10.48550/arxiv.2603.14367"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.14367","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14367","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.14367","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129655395","display_name":"Xiaoya Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Xiaoya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129741950","display_name":"Yijin Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yijin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004129136","display_name":"Zeren Chen","orcid":"https://orcid.org/0000-0001-7412-8347"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zeren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016975410","display_name":"Ruocheng Wang","orcid":"https://orcid.org/0000-0002-7171-6634"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Ruocheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120309150","display_name":"Bingrui Sima","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sima, Bingrui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102521317","display_name":"Enshen Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Enshen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129683214","display_name":"Lu Sheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sheng, Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129654716","display_name":"Dongrui Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Dongrui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129670621","display_name":"Jing Shao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shao, Jing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.49000000953674316,"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":0.49000000953674316,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.12680000066757202,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.10159999877214432,"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":0.6262999773025513},{"id":"https://openalex.org/keywords/safeguard","display_name":"Safeguard","score":0.6103000044822693},{"id":"https://openalex.org/keywords/hazard","display_name":"Hazard","score":0.5633000135421753},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5536999702453613},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.5047000050544739},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.46129998564720154},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.45410001277923584},{"id":"https://openalex.org/keywords/risk-perception","display_name":"Risk perception","score":0.4415999948978424},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4408999979496002},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.41609999537467957}],"concepts":[{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.6442999839782715},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6262999773025513},{"id":"https://openalex.org/C2780771206","wikidata":"https://www.wikidata.org/wiki/Q3271761","display_name":"Safeguard","level":2,"score":0.6103000044822693},{"id":"https://openalex.org/C49261128","wikidata":"https://www.wikidata.org/wiki/Q1132455","display_name":"Hazard","level":2,"score":0.5633000135421753},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5554999709129333},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5536999702453613},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.5047000050544739},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.46129998564720154},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.45410001277923584},{"id":"https://openalex.org/C163355716","wikidata":"https://www.wikidata.org/wiki/Q2154783","display_name":"Risk perception","level":3,"score":0.4415999948978424},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4408999979496002},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.41609999537467957},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4025000035762787},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.38670000433921814},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3774999976158142},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C32896092","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Risk management","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3303999900817871},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.328000009059906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3197000026702881},{"id":"https://openalex.org/C86804380","wikidata":"https://www.wikidata.org/wiki/Q5164479","display_name":"Construction site safety","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.310699999332428},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C22507642","wikidata":"https://www.wikidata.org/wiki/Q1069369","display_name":"Hazardous waste","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C2777055276","wikidata":"https://www.wikidata.org/wiki/Q7936580","display_name":"Visual approach","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.14367","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14367","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.14367","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14367","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.563392698764801}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1],"(VLMs)":[2],"empower":[3],"embodied":[4],"agents":[5],"to":[6,14,24,81,118,140],"execute":[7],"complex":[8],"instructions,":[9],"yet":[10],"they":[11],"remain":[12],"vulnerable":[13],"contextual":[15],"safety":[16,166],"risks":[17,54],"where":[18],"benign":[19],"commands":[20],"become":[21],"hazardous":[22],"due":[23],"subtle":[25],"environmental":[26],"states.":[27],"Existing":[28],"safeguards":[29],"often":[30],"prove":[31],"inadequate.":[32],"Rule-based":[33],"methods":[34],"lack":[35],"scalability":[36],"in":[37,52],"object-dense":[38],"scenes,":[39],"whereas":[40],"model-based":[41],"approaches":[42],"relying":[43],"on":[44,93],"prompt":[45],"engineering":[46],"suffer":[47],"from":[48],"unfocused":[49],"perception,":[50],"resulting":[51],"missed":[53],"or":[55],"hallucinations.":[56],"To":[57],"address":[58],"this,":[59],"we":[60],"propose":[61],"an":[62],"architecture-agnostic":[63],"safeguard":[64],"featuring":[65],"Context-Guided":[66],"Chain-of-Thought":[67],"(CG-CoT).":[68],"This":[69],"mechanism":[70],"decomposes":[71],"risk":[72,133],"assessment":[73],"into":[74],"active":[75],"perception":[76],"that":[77,125],"sequentially":[78],"anchors":[79,152],"attention":[80],"interaction":[82],"targets":[83],"and":[84,106,165,170],"relevant":[85],"spatial":[86,156],"neighborhoods,":[87],"followed":[88],"by":[89,136],"semantic":[90],"judgment":[91],"based":[92],"this":[94,99],"visual":[95,151],"evidence.":[96],"We":[97],"support":[98],"approach":[100],"with":[101,115],"a":[102,107],"curated":[103],"grounding":[104],"dataset":[105],"two-stage":[108],"training":[109],"strategy":[110],"utilizing":[111],"Reinforcement":[112],"Fine-Tuning":[113],"(RFT)":[114],"process":[116],"rewards":[117],"enforce":[119],"precise":[120],"intermediate":[121],"grounding.":[122],"Experiments":[123],"demonstrate":[124],"our":[126],"model":[127],"HomeGuard":[128],"significantly":[129],"enhances":[130],"safety,":[131],"improving":[132],"match":[134],"rates":[135],"over":[137],"30%":[138],"compared":[139],"base":[141],"models":[142],"while":[143],"reducing":[144],"oversafety.":[145],"Beyond":[146],"hazard":[147],"detection,":[148],"the":[149],"generated":[150],"serve":[153],"as":[154],"actionable":[155],"constraints":[157],"for":[158],"downstream":[159],"planners,":[160],"facilitating":[161],"explicit":[162],"collision":[163],"avoidance":[164],"trajectory":[167],"generation.":[168],"Code":[169],"data":[171],"are":[172],"released":[173],"under":[174],"https://github.com/AI45Lab/HomeGuard":[175]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-18T00:00:00"}