{"id":"https://openalex.org/W7129096717","doi":"https://doi.org/10.1109/lra.2026.3665444","title":"Augmented Reality for RObots (ARRO): Pointing Visuomotor Policies Towards Visual Robustness","display_name":"Augmented Reality for RObots (ARRO): Pointing Visuomotor Policies Towards Visual Robustness","publication_year":2026,"publication_date":"2026-02-16","ids":{"openalex":"https://openalex.org/W7129096717","doi":"https://doi.org/10.1109/lra.2026.3665444"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2026.3665444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3665444","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5008927094","display_name":"Reihaneh Mirjalili","orcid":null},"institutions":[{"id":"https://openalex.org/I3130238102","display_name":"Lutheran University of Applied Sciences Nuremberg","ror":"https://ror.org/01tbgce33","country_code":"DE","type":"education","lineage":["https://openalex.org/I3130238102"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Reihaneh Mirjalili","raw_affiliation_strings":["Department of Computer Science and Artificial Intelligence, University of Technology Nuremberg, Nuremberg, Germany"],"raw_orcid":"https://orcid.org/0009-0002-9248-581X","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence, University of Technology Nuremberg, Nuremberg, Germany","institution_ids":["https://openalex.org/I3130238102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094008630","display_name":"Tobias J\u00fclg","orcid":null},"institutions":[{"id":"https://openalex.org/I3130238102","display_name":"Lutheran University of Applied Sciences Nuremberg","ror":"https://ror.org/01tbgce33","country_code":"DE","type":"education","lineage":["https://openalex.org/I3130238102"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias J\u00fclg","raw_affiliation_strings":["Department of Computer Science and Artificial Intelligence, University of Technology Nuremberg, Nuremberg, Germany"],"raw_orcid":"https://orcid.org/0009-0005-7098-7802","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence, University of Technology Nuremberg, Nuremberg, Germany","institution_ids":["https://openalex.org/I3130238102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126156013","display_name":"Florian Walter","orcid":null},"institutions":[{"id":"https://openalex.org/I3130238102","display_name":"Lutheran University of Applied Sciences Nuremberg","ror":"https://ror.org/01tbgce33","country_code":"DE","type":"education","lineage":["https://openalex.org/I3130238102"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florian Walter","raw_affiliation_strings":["Department of Computer Science and Artificial Intelligence, University of Technology Nuremberg, Nuremberg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-8279-7476","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence, University of Technology Nuremberg, Nuremberg, Germany","institution_ids":["https://openalex.org/I3130238102"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084499878","display_name":"Wolfram Burgard","orcid":"https://orcid.org/0000-0002-5680-6500"},"institutions":[{"id":"https://openalex.org/I3130238102","display_name":"Lutheran University of Applied Sciences Nuremberg","ror":"https://ror.org/01tbgce33","country_code":"DE","type":"education","lineage":["https://openalex.org/I3130238102"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wolfram Burgard","raw_affiliation_strings":["Department of Computer Science and Artificial Intelligence, University of Technology Nuremberg, Nuremberg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-5680-6500","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence, University of Technology Nuremberg, Nuremberg, Germany","institution_ids":["https://openalex.org/I3130238102"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3130238102"],"apc_list":null,"apc_paid":null,"fwci":8.8388,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.96069895,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":"11","issue":"4","first_page":"4785","last_page":"4792"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.5422999858856201,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.5422999858856201,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.0892999991774559,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.07000000029802322,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7279000282287598},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6888999938964844},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.46950000524520874},{"id":"https://openalex.org/keywords/augmented-reality","display_name":"Augmented reality","score":0.36809998750686646},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.35409998893737793},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.352400004863739},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.3391999900341034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7595999836921692},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7279000282287598},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6888999938964844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6829000115394592},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6116999983787537},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.46950000524520874},{"id":"https://openalex.org/C153715457","wikidata":"https://www.wikidata.org/wiki/Q254183","display_name":"Augmented reality","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.35409998893737793},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.352400004863739},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3276999890804291},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.32330000400543213},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2639000117778778}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2026.3665444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3665444","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2158782408","https://openalex.org/W2605102758","https://openalex.org/W2925241625","https://openalex.org/W2963184124","https://openalex.org/W2963689319","https://openalex.org/W2968116426","https://openalex.org/W3094502228","https://openalex.org/W3122520957","https://openalex.org/W3175995235","https://openalex.org/W4385245566","https://openalex.org/W4385403849","https://openalex.org/W4385430538","https://openalex.org/W4385430679","https://openalex.org/W4385431288","https://openalex.org/W4401415042","https://openalex.org/W4401415287","https://openalex.org/W4401416041","https://openalex.org/W4401417065","https://openalex.org/W4402353985","https://openalex.org/W4402354041","https://openalex.org/W4402354047","https://openalex.org/W4402354082","https://openalex.org/W4402354127","https://openalex.org/W4402702968","https://openalex.org/W4403337227","https://openalex.org/W4404612908","https://openalex.org/W4414050913","https://openalex.org/W4414079054"],"related_works":[],"abstract_inverted_index":{"Visuomotor":[0],"policies":[1,22],"trained":[2],"on":[3,117],"human":[4],"expert":[5],"demonstrations":[6],"have":[7],"recently":[8],"shown":[9],"strong":[10],"performance":[11,160],"across":[12],"a":[13,47,118],"wide":[14],"range":[15,119],"of":[16,66,77,120],"robotic":[17],"manipulation":[18,122],"tasks.":[19],"However,":[20],"these":[21],"remain":[23],"highly":[24],"sensitive":[25],"to":[26,60,99,166,175],"domain":[27],"shifts":[28],"stemming":[29],"from":[30],"background":[31],"or":[32,80],"robot":[33,139],"embodiment":[34],"changes,":[35],"which":[36],"limits":[37],"their":[38],"generalization":[39],"capabilities.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44],"present":[45],"ARRO,":[46],"novel":[48],"visual":[49,85],"representation":[50],"that":[51],"leverages":[52],"zero-shot":[53],"open-vocabulary":[54],"segmentation":[55,177],"and":[56,87,94,102,127,130,135,145,171],"object":[57],"detection":[58],"models":[59],"efficiently":[61],"mask":[62],"out":[63],"task-irrelevant":[64],"regions":[65],"the":[67,78,104],"scene":[68,100],"in":[69,124,154],"real":[70],"time":[71],"without":[72],"requiring":[73],"additional":[74,107],"training,":[75],"modeling":[76],"setup,":[79],"camera":[81],"calibration.":[82],"By":[83],"filtering":[84],"distractors":[86],"overlaying":[88],"virtual":[89],"guides":[90],"during":[91],"both":[92,125],"training":[93],"inference,":[95],"ARRO":[96,113,157],"improves":[97],"robustness":[98,173],"variations":[101],"reduces":[103],"need":[105],"for":[106,163],"data":[108],"collection.":[109],"We":[110],"extensively":[111],"evaluate":[112],"with":[114,137],"Diffusion":[115],"Policy":[116],"tabletop":[121],"tasks":[123],"simulation":[126],"real-world":[128],"environments,":[129],"further":[131],"demonstrate":[132],"its":[133],"compatibility":[134],"effectiveness":[136],"generalist":[138],"policies,":[140],"such":[141],"as":[142],"Octo,":[143],"OpenVLA":[144],"<inline-formula":[146],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[147],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[148],"notation=\"LaTeX\">$\\pi":[149],"_{0}$</tex-math></inline-formula>.":[150],"Across":[151],"all":[152],"settings":[153],"our":[155,181],"evaluation,":[156],"yields":[158],"consistent":[159],"gains,":[161],"allows":[162],"selective":[164],"masking":[165],"choose":[167],"between":[168],"different":[169],"objects,":[170],"shows":[172],"even":[174],"challenging":[176],"conditions.":[178],"Videos":[179],"showcasing":[180],"results":[182],"are":[183],"available":[184],"at:https://augmented-reality-for-robots.github.io":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2026-02-17T00:00:00"}