{"id":"https://openalex.org/W3003266338","doi":"https://doi.org/10.1109/iros40897.2019.8968263","title":"Pixel-Attentive Policy Gradient for Multi-Fingered Grasping in Cluttered Scenes","display_name":"Pixel-Attentive Policy Gradient for Multi-Fingered Grasping in Cluttered Scenes","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3003266338","doi":"https://doi.org/10.1109/iros40897.2019.8968263","mag":"3003266338"},"language":"en","primary_location":{"id":"doi:10.1109/iros40897.2019.8968263","doi":"https://doi.org/10.1109/iros40897.2019.8968263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8968263","pdf_url":null,"source":{"id":"https://openalex.org/S4393918188","display_name":"IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":"2153-0858","issn":["2153-0858"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1903.03227","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101494739","display_name":"Bohan Wu","orcid":"https://orcid.org/0000-0003-0588-459X","observed_orcids":["https://orcid.org/0000-0003-0588-459X"]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bohan Wu","raw_affiliation_strings":["Columbia University Robotics Group, Columbia University,New York,USA,NY 10027","Columbia University Robotics Group, Columbia University, New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University Robotics Group, Columbia University,New York,USA,NY 10027","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Columbia University Robotics Group, Columbia University, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056689854","display_name":"Iretiayo Akinola","orcid":"https://orcid.org/0000-0001-8398-8138","observed_orcids":["https://orcid.org/0000-0001-8398-8138"]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Iretiayo Akinola","raw_affiliation_strings":["Columbia University Robotics Group, Columbia University,New York,USA,NY 10027","Columbia University Robotics Group, Columbia University, New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University Robotics Group, Columbia University,New York,USA,NY 10027","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Columbia University Robotics Group, Columbia University, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112627047","display_name":"Peter K. Allen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter K. Allen","raw_affiliation_strings":["Columbia University Robotics Group, Columbia University,New York,USA,NY 10027","Columbia University Robotics Group, Columbia University, New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University Robotics Group, Columbia University,New York,USA,NY 10027","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Columbia University Robotics Group, Columbia University, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":2.2956,"has_fulltext":true,"cited_by_count":40,"citation_normalized_percentile":{"value":0.91890824,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1789","last_page":"1796"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7612000107765198,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7612000107765198,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.23839999735355377,"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":9.999999747378752e-05,"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/on-policy-learning","display_name":"on-policy learning","score":0.8790000081062317},{"id":"https://openalex.org/keywords/sim-to-real-transfer","display_name":"sim-to-real transfer","score":0.8209999799728394},{"id":"https://openalex.org/keywords/depth-maps","display_name":"depth images","score":0.3930000066757202},{"id":"https://openalex.org/keywords/attention-mechanism","display_name":"attention mechanism","score":0.906000018119812},{"id":"https://openalex.org/keywords/cluttered-scenes","display_name":"cluttered scenes","score":0.8330000042915344},{"id":"https://openalex.org/keywords/grasp-success-rate","display_name":"grasp success rate","score":0.7059999704360962},{"id":"https://openalex.org/keywords/robotic-hand","display_name":"robotic hand","score":0.4320000112056732}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8028874397277832},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7536532878875732},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.6928644180297852},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.6522295475006104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6475744843482971},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5735083818435669},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5667260885238647},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.4828782379627228},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4742283523082733},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.46983736753463745},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.46882957220077515},{"id":"https://openalex.org/C16038011","wikidata":"https://www.wikidata.org/wiki/Q62912","display_name":"Cartesian coordinate system","level":2,"score":0.46382585167884827},{"id":"https://openalex.org/C90738871","wikidata":"https://www.wikidata.org/wiki/Q41642869","display_name":"Configuration space","level":2,"score":0.4184938371181488},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13382959365844727},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09399905800819397},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"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":3,"locations":[{"id":"doi:10.1109/iros40897.2019.8968263","doi":"https://doi.org/10.1109/iros40897.2019.8968263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8968263","pdf_url":null,"source":{"id":"https://openalex.org/S4393918188","display_name":"IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":"2153-0858","issn":["2153-0858"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1903.03227","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.03227","pdf_url":"https://arxiv.org/pdf/1903.03227","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1903.03227","doi":"https://doi.org/10.48550/arxiv.1903.03227","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1903.03227","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1903.03227","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.03227","pdf_url":"https://arxiv.org/pdf/1903.03227","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3452126483","display_name":"NRI: FND: Scalable Multimodal Tactile Sensing for Robotic Manipulators in Manufacturing","funder_award_id":"1734557","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4398652528","display_name":"NRI: Collaborative Research: Multimodal Brain Computer Interface for Human-Robot Interaction","funder_award_id":"1527747","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8517755155","display_name":null,"funder_award_id":"1734557","funder_id":"https://openalex.org/F4320337391","funder_display_name":"Division of Civil, Mechanical and Manufacturing Innovation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337391","display_name":"Division of Civil, Mechanical and Manufacturing Innovation","ror":"https://ror.org/028yd4c30"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3003266338.pdf","grobid_xml":"https://content.openalex.org/works/W3003266338.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1999156278","https://openalex.org/W2036637075","https://openalex.org/W2080279876","https://openalex.org/W2106215490","https://openalex.org/W2111516378","https://openalex.org/W2112036576","https://openalex.org/W2121863487","https://openalex.org/W2123079020","https://openalex.org/W2123365775","https://openalex.org/W2155007355","https://openalex.org/W2190691619","https://openalex.org/W2205950488","https://openalex.org/W2288514685","https://openalex.org/W2565639579","https://openalex.org/W2601066903","https://openalex.org/W2605102758","https://openalex.org/W2626073992","https://openalex.org/W2736601468","https://openalex.org/W2758237641","https://openalex.org/W2766108544","https://openalex.org/W2788575380","https://openalex.org/W2794537597","https://openalex.org/W2798255267","https://openalex.org/W2804743778","https://openalex.org/W2810785043","https://openalex.org/W2890646997","https://openalex.org/W2905464683","https://openalex.org/W2964161785","https://openalex.org/W3112422759","https://openalex.org/W3149673177","https://openalex.org/W4214717370","https://openalex.org/W4394671432","https://openalex.org/W6687484953","https://openalex.org/W6741002519"],"related_works":["https://openalex.org/W3008273191","https://openalex.org/W4285164516","https://openalex.org/W2991006694","https://openalex.org/W4221161758","https://openalex.org/W2972694654","https://openalex.org/W4401762353","https://openalex.org/W7083679467","https://openalex.org/W4396821558","https://openalex.org/W7085053932","https://openalex.org/W4386821595"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,11,32,69,73,120],"on-policy":[3,51],"reinforcement":[4],"learning":[5,9,131],"(RL)":[6],"methods":[7],"enabled":[8],"agents":[10],"virtual":[12],"environments":[13],"to":[14,40,57,90,94,101],"master":[15],"complex":[16],"tasks":[17],"with":[18,105],"high-dimensional":[19],"and":[20,23,45,108,141],"continuous":[21],"observation":[22],"action":[24],"spaces.":[25],"However,":[26],"leveraging":[27],"this":[28,98,128],"family":[29],"of":[30,50,77,127,132,148,150],"algorithms":[31],"multi-fingered":[33,65,133],"robotic":[34,66],"grasping":[35,67],"remains":[36],"a":[37,64,80,85,110],"challenge":[38],"due":[39],"large":[41],"sim-to-real":[42],"fidelity":[43,107],"gaps":[44,60],"the":[46,74,78,95,102,124,151],"high":[47,106],"sample":[48],"complexity":[49],"RL":[52],"algorithms.":[53],"This":[54],"work":[55],"aims":[56],"bridge":[58],"these":[59],"by":[61],"first":[62],"reinforcement-learning":[63],"policy":[68],"simulation":[70],"that":[71,114,135],"operates":[72],"pixel":[75,88],"space":[76,89,92],"input:":[79],"single":[81],"depth":[82,96],"image.":[83],"Using":[84],"mapping":[86],"from":[87],"Cartesian":[91],"according":[93],"map,":[97],"method":[99,129],"transfers":[100],"real":[103],"world":[104],"introduces":[109],"novel":[111],"attention":[112],"mechanism":[113],"substantially":[115],"improves":[116],"grasp":[117],"success":[118],"rate":[119],"cluttered":[121],"environments.":[122],"Finally,":[123],"direct-generative":[125],"nature":[126],"allows":[130],"grasps":[134],"have":[136],"flexible":[137],"end-effector":[138],"positions,":[139],"orientations":[140],"rotations,":[142],"as":[143,145],"well":[144],"all":[146],"degrees":[147],"freedom":[149],"hand.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":1}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2020-02-07T00:00:00"}