{"id":"https://openalex.org/W4401414814","doi":"https://doi.org/10.1109/icra57147.2024.10610923","title":"DINOBot: Robot Manipulation via Retrieval and Alignment with Vision Foundation Models","display_name":"DINOBot: Robot Manipulation via Retrieval and Alignment with Vision Foundation Models","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401414814","doi":"https://doi.org/10.1109/icra57147.2024.10610923"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610923","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610923","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5085711106","display_name":"Norman Di Palo","orcid":"https://orcid.org/0009-0004-8518-4861"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Norman Di Palo","raw_affiliation_strings":["The Robot Learning Lab at Imperial College London"],"affiliations":[{"raw_affiliation_string":"The Robot Learning Lab at Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080385974","display_name":"Edward Johns","orcid":"https://orcid.org/0000-0002-8914-8786"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Edward Johns","raw_affiliation_strings":["The Robot Learning Lab at Imperial College London"],"affiliations":[{"raw_affiliation_string":"The Robot Learning Lab at Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5085711106"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":7.6288,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.97923356,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2798","last_page":"2805"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9997000098228455,"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":0.9997000098228455,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9970999956130981,"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/computer-science","display_name":"Computer science","score":0.676571249961853},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.6694325804710388},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6317480802536011},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5783690810203552},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4661995470523834}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.676571249961853},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.6694325804710388},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6317480802536011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5783690810203552},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4661995470523834},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610923","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610923","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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":56,"referenced_works":["https://openalex.org/W2143727296","https://openalex.org/W2159683855","https://openalex.org/W2194775991","https://openalex.org/W2338894059","https://openalex.org/W2786195469","https://openalex.org/W2811406147","https://openalex.org/W2925241625","https://openalex.org/W2963488874","https://openalex.org/W3028830971","https://openalex.org/W3035198432","https://openalex.org/W3044296014","https://openalex.org/W3109908659","https://openalex.org/W3159481202","https://openalex.org/W3207359859","https://openalex.org/W3214310824","https://openalex.org/W3214952050","https://openalex.org/W4221159977","https://openalex.org/W4287083362","https://openalex.org/W4287671529","https://openalex.org/W4293583299","https://openalex.org/W4312297897","https://openalex.org/W4313133881","https://openalex.org/W4321319299","https://openalex.org/W4366208220","https://openalex.org/W4385430535","https://openalex.org/W4385430582","https://openalex.org/W4387210492","https://openalex.org/W4387964188","https://openalex.org/W4390578009","https://openalex.org/W4390871749","https://openalex.org/W4401416102","https://openalex.org/W4404446892","https://openalex.org/W6747898553","https://openalex.org/W6748232849","https://openalex.org/W6750394531","https://openalex.org/W6752823625","https://openalex.org/W6769035977","https://openalex.org/W6784173345","https://openalex.org/W6784333009","https://openalex.org/W6791353385","https://openalex.org/W6796613488","https://openalex.org/W6801810553","https://openalex.org/W6810080435","https://openalex.org/W6811470611","https://openalex.org/W6839256673","https://openalex.org/W6840720034","https://openalex.org/W6843515625","https://openalex.org/W6845226490","https://openalex.org/W6846496272","https://openalex.org/W6851800889","https://openalex.org/W6852930566","https://openalex.org/W6857159348","https://openalex.org/W6857294093","https://openalex.org/W6857414764","https://openalex.org/W6857469302","https://openalex.org/W6860345358"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"We":[0],"propose":[1],"DINOBot,":[2],"a":[3,30,67],"novel":[4,31,60],"imitation":[5],"learning":[6,91],"framework":[7],"for":[8],"robot":[9],"manipulation,":[10],"which":[11],"leverages":[12],"the":[13,40,59,80],"image-level":[14,81],"and":[15,49,82,93,96],"pixel-level":[16,83],"capabilities":[17],"of":[18,69,85],"features":[19,37],"extracted":[20],"from":[21],"Vision":[22],"Transformers":[23],"trained":[24],"with":[25,29,58],"DINO.":[26],"When":[27],"interacting":[28],"object,":[32],"DINOBot":[33],"first":[34],"uses":[35,51],"these":[36],"to":[38,54,62],"retrieve":[39],"most":[41],"visually":[42],"similar":[43],"object":[44,53,61],"experienced":[45],"during":[46],"human":[47],"demonstrations,":[48],"then":[50],"this":[52],"align":[55],"its":[56],"endeffector":[57],"enable":[63],"effective":[64],"interaction.":[65],"Through":[66],"series":[68],"real-world":[70],"experiments":[71],"on":[72],"everyday":[73],"tasks,":[74],"we":[75],"show":[76],"that":[77],"exploiting":[78],"both":[79],"properties":[84],"vision":[86],"foundation":[87],"models":[88],"enables":[89],"unprecedented":[90],"efficiency":[92],"generalisation.":[94],"Videos":[95],"code":[97],"are":[98],"available":[99],"at":[100],"https://www.robot-learning.uk/dinobot.":[101]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-01T08:55:55.761014","created_date":"2025-10-10T00:00:00"}