{"id":"https://openalex.org/W3137413199","doi":"https://doi.org/10.1109/iros51168.2021.9636369","title":"CLAMGen: Closed-Loop Arm Motion Generation via Multi-view Vision-Based RL","display_name":"CLAMGen: Closed-Loop Arm Motion Generation via Multi-view Vision-Based RL","publication_year":2021,"publication_date":"2021-09-27","ids":{"openalex":"https://openalex.org/W3137413199","doi":"https://doi.org/10.1109/iros51168.2021.9636369","mag":"3137413199"},"language":"en","primary_location":{"id":"doi:10.1109/iros51168.2021.9636369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636369","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5056689854","display_name":"Iretiayo Akinola","orcid":"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, New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, New York","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061218022","display_name":"Zizhao Wang","orcid":null},"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":"Zizhao Wang","raw_affiliation_strings":["Columbia University, New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, New York","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108078524","display_name":"Peter J. Allen","orcid":null},"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 Allen","raw_affiliation_strings":["Columbia University, New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, New York","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":0.191,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.46381348,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9998000264167786,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9998000264167786,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9995999932289124,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7954531908035278},{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.7015367746353149},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7000424265861511},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6413754224777222},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6377694010734558},{"id":"https://openalex.org/keywords/robotic-arm","display_name":"Robotic arm","score":0.5492298007011414},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.5380809307098389},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.535365104675293},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5207969546318054},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4550895690917969},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.42298731207847595},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.350868284702301},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20132163166999817},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16399282217025757}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7954531908035278},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.7015367746353149},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7000424265861511},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6413754224777222},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6377694010734558},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.5492298007011414},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.5380809307098389},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.535365104675293},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5207969546318054},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4550895690917969},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.42298731207847595},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.350868284702301},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20132163166999817},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16399282217025757},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros51168.2021.9636369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636369","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W131069610","https://openalex.org/W567721252","https://openalex.org/W1971086298","https://openalex.org/W2019965290","https://openalex.org/W2099893201","https://openalex.org/W2103120971","https://openalex.org/W2104332709","https://openalex.org/W2155968351","https://openalex.org/W2746553466","https://openalex.org/W2781726626","https://openalex.org/W2786658125","https://openalex.org/W2793998795","https://openalex.org/W2795756076","https://openalex.org/W2810785043","https://openalex.org/W2885010347","https://openalex.org/W2890290306","https://openalex.org/W2900152462","https://openalex.org/W2904246096","https://openalex.org/W2905364877","https://openalex.org/W2950872548","https://openalex.org/W2963092423","https://openalex.org/W2963099939","https://openalex.org/W2963409832","https://openalex.org/W2963439114","https://openalex.org/W2963572779","https://openalex.org/W2964001908","https://openalex.org/W2964077562","https://openalex.org/W2964239169","https://openalex.org/W2964250417","https://openalex.org/W2967727187","https://openalex.org/W2967969632","https://openalex.org/W2970776272","https://openalex.org/W2977481643","https://openalex.org/W2982643477","https://openalex.org/W2987329987","https://openalex.org/W3021208093","https://openalex.org/W3089931053","https://openalex.org/W3094997269","https://openalex.org/W3115293622","https://openalex.org/W3135861075","https://openalex.org/W4205276953","https://openalex.org/W4287626351","https://openalex.org/W4289115845","https://openalex.org/W4289294484","https://openalex.org/W4293583840","https://openalex.org/W4295837424","https://openalex.org/W4297672196","https://openalex.org/W4300799055","https://openalex.org/W6605295560","https://openalex.org/W6616173779","https://openalex.org/W6692405165","https://openalex.org/W6729556111","https://openalex.org/W6740801417","https://openalex.org/W6746151189","https://openalex.org/W6747473740","https://openalex.org/W6748798971","https://openalex.org/W6748972340","https://openalex.org/W6750409132","https://openalex.org/W6752808292","https://openalex.org/W6753243525","https://openalex.org/W6753557484","https://openalex.org/W6756256016","https://openalex.org/W6756848961","https://openalex.org/W6757592117","https://openalex.org/W6767518175","https://openalex.org/W6768511085","https://openalex.org/W6770463744","https://openalex.org/W6775634482","https://openalex.org/W6784833371","https://openalex.org/W6784930079"],"related_works":["https://openalex.org/W2046459260","https://openalex.org/W2967463586","https://openalex.org/W2765830098","https://openalex.org/W1971989957","https://openalex.org/W2517338020","https://openalex.org/W3157641275","https://openalex.org/W4312300846","https://openalex.org/W2615757685","https://openalex.org/W2098782634","https://openalex.org/W3000546688"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,21,41,47,61,82,88,114,119],"vision-based":[3],"reinforcement":[4],"learning":[5,81,106,154],"(RL)":[6],"approach":[7],"for":[8,90],"closed-loop":[9],"trajectory":[10,18],"generation":[11,19],"in":[12,37,181],"an":[13],"arm":[14],"reaching":[15],"problem.":[16],"Arm":[17],"is":[20,134],"fundamental":[22],"robotics":[23],"problem":[24],"which":[25],"entails":[26],"finding":[27],"collision-free":[28],"paths":[29],"to":[30,39,59,77,127,146,158,173],"move":[31],"the":[32,54,57,70,125,131],"robot\u2019s":[33],"body":[34],"(e.g.":[35,43],"arm)":[36],"order":[38],"satisfy":[40],"goal":[42],"place":[44],"end-effector":[45],"at":[46],"point).":[48],"While":[49],"classical":[50],"methods":[51],"typically":[52],"require":[53],"model":[55],"of":[56,72,169,183],"environment":[58],"solve":[60],"planning,":[62],"search":[63],"or":[64],"optimization":[65],"problem,":[66],"learning-based":[67],"approaches":[68],"hold":[69],"promise":[71],"directly":[73],"mapping":[74],"from":[75,144,162],"observations":[76],"robot":[78],"actions.":[79],"However,":[80],"collision-avoidance":[83],"policy":[84,123,133],"using":[85],"RL":[86,122,174],"remains":[87],"challenge":[89],"various":[91],"reasons,":[92],"including,":[93],"but":[94],"not":[95],"limited":[96],"to,":[97],"partial":[98],"observability,":[99],"poor":[100],"exploration,":[101,129],"low":[102],"sample":[103,167],"efficiency,":[104],"and":[105,130,140,156,166],"instabilities.":[107],"To":[108],"address":[109],"these":[110],"challenges,":[111],"we":[112,151],"present":[113],"residual-RL":[115],"method":[116,177],"that":[117],"leverages":[118],"greedy":[120],"goal-reaching":[121],"as":[124],"base":[126,132],"improve":[128,159],"augmented":[135],"with":[136],"residual":[137,141],"state-action":[138],"values":[139],"actions":[142],"learned":[143],"images":[145],"avoid":[147],"obstacles.":[148],"Further":[149],"more,":[150],"introduce":[152],"novel":[153],"objectives":[155],"techniques":[157],"3D":[160],"understanding":[161],"multiple":[163],"image":[164],"views":[165],"efficiency":[168],"our":[170,176],"algorithm.":[171],"Compared":[172],"baselines,":[175],"achieves":[178],"superior":[179],"performance":[180],"terms":[182],"success":[184],"rate.":[185]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}