{"id":"https://openalex.org/W3024672368","doi":"https://doi.org/10.1109/icra40945.2020.9197415","title":"Action Image Representation: Learning Scalable Deep Grasping Policies with Zero Real World Data","display_name":"Action Image Representation: Learning Scalable Deep Grasping Policies with Zero Real World Data","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W3024672368","doi":"https://doi.org/10.1109/icra40945.2020.9197415","mag":"3024672368"},"language":"en","primary_location":{"id":"doi:10.1109/icra40945.2020.9197415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.06594","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065802887","display_name":"Mohi Khansari","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohi Khansari","raw_affiliation_strings":["X, The Moonshot Factory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"X, The Moonshot Factory","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039293409","display_name":"Daniel Kappler","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Kappler","raw_affiliation_strings":["X, The Moonshot Factory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"X, The Moonshot Factory","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037464692","display_name":"Jianlan Luo","orcid":"https://orcid.org/0009-0008-8029-7794"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianlan Luo","raw_affiliation_strings":["University of California, Berkeley","University of California\u2013Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California\u2013Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076509678","display_name":"Jeff Bingham","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeff Bingham","raw_affiliation_strings":["X, The Moonshot Factory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"X, The Moonshot Factory","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080415080","display_name":"Mrinal Kalakrishnan","orcid":"https://orcid.org/0000-0003-4292-9857"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mrinal Kalakrishnan","raw_affiliation_strings":["X, The Moonshot Factory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"X, The Moonshot Factory","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0591,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.85875006,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3597","last_page":"3603"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998999834060669,"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":0.9998999834060669,"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/T10868","display_name":"Soft Robotics and Applications","score":0.9775999784469604,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T10784","display_name":"Muscle activation and electromyography studies","score":0.9674000144004822,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.8231922388076782},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7767074108123779},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6897892355918884},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6273754835128784},{"id":"https://openalex.org/keywords/image-translation","display_name":"Image translation","score":0.6181197166442871},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.568363606929779},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5050728917121887},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4984781742095947},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4876324236392975},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.42632439732551575},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.38596123456954956},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3490658402442932},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.148534893989563}],"concepts":[{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.8231922388076782},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7767074108123779},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6897892355918884},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6273754835128784},{"id":"https://openalex.org/C2779757391","wikidata":"https://www.wikidata.org/wiki/Q6002292","display_name":"Image translation","level":3,"score":0.6181197166442871},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.568363606929779},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5050728917121887},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4984781742095947},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4876324236392975},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.42632439732551575},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.38596123456954956},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3490658402442932},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.148534893989563},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icra40945.2020.9197415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2005.06594","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.06594","pdf_url":"https://arxiv.org/pdf/2005.06594","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3024672368","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2005.06594","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2005.06594","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2005.06594","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2005.06594","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.06594","pdf_url":"https://arxiv.org/pdf/2005.06594","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3024672368.pdf","grobid_xml":"https://content.openalex.org/works/W3024672368.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W70651934","https://openalex.org/W1503925285","https://openalex.org/W1510186039","https://openalex.org/W1577352482","https://openalex.org/W1820657498","https://openalex.org/W1986533639","https://openalex.org/W1999156278","https://openalex.org/W2036637075","https://openalex.org/W2064878003","https://openalex.org/W2085949256","https://openalex.org/W2161047498","https://openalex.org/W2201912979","https://openalex.org/W2205950488","https://openalex.org/W2561523096","https://openalex.org/W2577484822","https://openalex.org/W2600030077","https://openalex.org/W2605102758","https://openalex.org/W2725320964","https://openalex.org/W2953249127","https://openalex.org/W2962736495","https://openalex.org/W2962746398","https://openalex.org/W2962899390","https://openalex.org/W2963276406","https://openalex.org/W2963390419","https://openalex.org/W2963484919","https://openalex.org/W2967842640","https://openalex.org/W6740023956","https://openalex.org/W6757358677"],"related_works":["https://openalex.org/W3089793705","https://openalex.org/W2973410975","https://openalex.org/W2786068615","https://openalex.org/W2989940186","https://openalex.org/W2791992091","https://openalex.org/W2963480821","https://openalex.org/W3111869590","https://openalex.org/W3209559888","https://openalex.org/W2797353904","https://openalex.org/W2751002011","https://openalex.org/W2963601560","https://openalex.org/W3132056922","https://openalex.org/W2626926650","https://openalex.org/W2190016714","https://openalex.org/W3203188154","https://openalex.org/W3097996169","https://openalex.org/W2891823673","https://openalex.org/W1920293286","https://openalex.org/W2303185727","https://openalex.org/W3105950545"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"Action":[3,51,95,120,172,199],"Image,":[4],"a":[5,77,98,106,149,195,208],"new":[6],"grasp":[7,21,68,79,99,112,202],"proposal":[8,100],"representation":[9,146,174],"that":[10,57,116,135,144,168,194],"allows":[11],"learning":[12],"an":[13,81,102,119,171],"end-to-end":[14],"deep-grasping":[15],"policy.":[16],"Our":[17,164],"model":[18,210],"achieves":[19],"84%":[20],"success":[22,203],"on":[23,34,54,84,148,181,186],"172":[24],"real":[25],"world":[26],"objects":[27,36,139],"while":[28],"being":[29],"trained":[30,123,197],"only":[31],"in":[32,64],"simulation":[33],"48":[35],"with":[37,198,211],"just":[38],"naive":[39],"domain":[40,177],"randomization.":[41],"Similar":[42],"to":[43,62,110,127],"computer":[44],"vision":[45],"problems,":[46],"such":[47],"as":[48,101,219],"object":[49,58,82],"detection,":[50],"Image":[52,96,121,173,200],"builds":[53],"the":[55,74,92,212],"idea":[56],"features":[59,131],"are":[60,125],"invariant":[61,71],"translation":[63],"image":[65,103],"space.":[66],"Therefore,":[67],"quality":[69],"is":[70,89],"when":[72],"evaluating":[73],"object-gripper":[75],"relationship;":[76],"successful":[78],"for":[80],"depends":[83],"its":[85],"local":[86],"context,":[87],"but":[88,215],"independent":[90],"of":[91,132,151],"surrounding":[93],"environment.":[94],"represents":[97],"and":[104,140,160,184],"uses":[105],"deep":[107],"convolutional":[108],"network":[109,196],"infer":[111],"quality.":[113],"We":[114,142],"show":[115,143,193],"by":[117],"using":[118,216],"representation,":[122],"networks":[124,169],"able":[126],"extract":[128],"local,":[129],"salient":[130],"grasping":[133],"tasks":[134],"generalize":[136],"across":[137],"different":[138],"environments.":[141],"this":[145],"works":[147],"variety":[150],"inputs,":[152],"including":[153],"color":[154],"images":[155,158],"(RGB),":[156],"depth":[157],"(D),":[159],"combined":[161],"color-depth":[162],"(RGB-D).":[163],"experimental":[165],"results":[166],"demonstrate":[167],"utilizing":[170],"exhibit":[175],"strong":[176],"transfer":[178],"between":[179],"training":[180],"simulated":[182],"data":[183],"inference":[185],"real-world":[187],"sensor":[188],"streams.":[189],"Finally,":[190],"our":[191],"experiments":[192],"improves":[201],"(84%":[204],"vs.":[205],"53%)":[206],"over":[207],"baseline":[209],"same":[213],"structure,":[214],"actions":[217],"encoded":[218],"vectors.":[220]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}