{"id":"https://openalex.org/W4285102485","doi":"https://doi.org/10.1109/icra46639.2022.9812251","title":"Learning Multi-step Robotic Manipulation Policies from Visual Observation of Scene and Q-value Predictions of Previous Action","display_name":"Learning Multi-step Robotic Manipulation Policies from Visual Observation of Scene and Q-value Predictions of Previous Action","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W4285102485","doi":"https://doi.org/10.1109/icra46639.2022.9812251"},"language":"en","primary_location":{"id":"doi:10.1109/icra46639.2022.9812251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9812251","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","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":"2022 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/A5031476331","display_name":"Sulabh Kumra","orcid":"https://orcid.org/0000-0003-2792-0969"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sulabh Kumra","raw_affiliation_strings":["Rochester Institute of Technology,Rochester,NY,USA","Rochester Institute of Technology, Rochester, NY, USA","OSARO Inc, San Francisco, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology,Rochester,NY,USA","institution_ids":["https://openalex.org/I155173764"]},{"raw_affiliation_string":"Rochester Institute of Technology, Rochester, NY, USA","institution_ids":["https://openalex.org/I155173764"]},{"raw_affiliation_string":"OSARO Inc, San Francisco, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038392758","display_name":"Shirin Joshi","orcid":null},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]},{"id":"https://openalex.org/I4210137693","display_name":"Siemens (United States)","ror":"https://ror.org/04axb7e79","country_code":"US","type":"company","lineage":["https://openalex.org/I1325886976","https://openalex.org/I4210137693"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Shirin Joshi","raw_affiliation_strings":["Siemens Corporation, Corporate Technology,Berkeley,CA","Siemens Corporation, Corporate Technology, Berkeley, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens Corporation, Corporate Technology,Berkeley,CA","institution_ids":["https://openalex.org/I1325886976"]},{"raw_affiliation_string":"Siemens Corporation, Corporate Technology, Berkeley, CA","institution_ids":["https://openalex.org/I4210137693"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023942737","display_name":"Ferat Sahin","orcid":"https://orcid.org/0000-0002-9813-7165"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ferat Sahin","raw_affiliation_strings":["Rochester Institute of Technology,Rochester,NY,USA","Rochester Institute of Technology, Rochester, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology,Rochester,NY,USA","institution_ids":["https://openalex.org/I155173764"]},{"raw_affiliation_string":"Rochester Institute of Technology, Rochester, NY, USA","institution_ids":["https://openalex.org/I155173764"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7014,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58383655,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"8245","last_page":"8251"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9839000105857849,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9717000126838684,"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":0.7572169303894043},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6876412630081177},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6400162577629089},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6392479538917542},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6048311591148376},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5859826803207397},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5046263933181763},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4957800805568695},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.4396982491016388},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4245885908603668},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4226142466068268},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10758838057518005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7572169303894043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6876412630081177},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6400162577629089},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6392479538917542},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6048311591148376},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5859826803207397},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5046263933181763},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4957800805568695},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.4396982491016388},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4245885908603668},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4226142466068268},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10758838057518005},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra46639.2022.9812251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9812251","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","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":"2022 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":29,"referenced_works":["https://openalex.org/W1892339738","https://openalex.org/W1968069998","https://openalex.org/W1994200336","https://openalex.org/W2036637075","https://openalex.org/W2155007355","https://openalex.org/W2300618187","https://openalex.org/W2788781499","https://openalex.org/W2890646997","https://openalex.org/W2955863859","https://openalex.org/W2962736495","https://openalex.org/W2962746398","https://openalex.org/W2962793652","https://openalex.org/W2963326767","https://openalex.org/W2963411833","https://openalex.org/W2963713397","https://openalex.org/W2991276239","https://openalex.org/W3004003541","https://openalex.org/W3006398608","https://openalex.org/W3008535267","https://openalex.org/W3091471537","https://openalex.org/W3091677803","https://openalex.org/W3092037789","https://openalex.org/W3101103779","https://openalex.org/W3130885760","https://openalex.org/W3210940825","https://openalex.org/W3216082637","https://openalex.org/W6682849425","https://openalex.org/W6748523217","https://openalex.org/W6785308759"],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W2413243053","https://openalex.org/W410723623","https://openalex.org/W2015341305","https://openalex.org/W2035068594","https://openalex.org/W4225593417","https://openalex.org/W2573498121","https://openalex.org/W3022298670","https://openalex.org/W3160494304","https://openalex.org/W3006162251"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,119],"focus":[4],"on":[5,98,206],"multi-step":[6,156],"manipulation":[7,67,158],"tasks":[8,18,159,199,209],"that":[9,22,28,40,93,100,127,168,191],"involve":[10],"long-horizon":[11],"planning":[12],"and":[13,37,65,76,106,163,175,184,193],"considers":[14],"progress":[15,107],"reversal.":[16],"Such":[17],"interlace":[19],"high-level":[20],"reasoning":[21,39],"consists":[23],"of":[24,73,79,117,139,146,181,213],"the":[25,62,74,80,95,109,115,131,136,144,172,214],"expected":[26],"states":[27],"can":[29],"be":[30],"attained":[31],"to":[32,60,102,135,152],"achieve":[33],"an":[34],"overall":[35,110],"task":[36,111],"low-level":[38],"decides":[41],"what":[42],"actions":[43,99,129],"will":[44],"yield":[45],"these":[46],"states.":[47],"We":[48,83,142],"propose":[49],"a":[50,85,121],"sample":[51],"efficient":[52],"Previous":[53],"Action":[54],"Conditioned":[55],"Robotic":[56],"Manipulation":[57],"Network":[58],"(PAC-RoManNet)":[59],"learn":[61,153],"action-value":[63,77],"functions":[64],"predict":[66],"action":[68,132,185],"candidates":[69,133],"from":[70,130],"visual":[71],"observation":[72],"scene":[75],"predictions":[78],"previous":[81],"action.":[82],"define":[84],"Task":[86],"Progress":[87],"based":[88,97],"Gaussian":[89],"(TPG)":[90],"reward":[91,96],"function":[92],"computes":[94],"lead":[101],"successful":[103],"motion":[104],"primitives":[105],"towards":[108],"goal.":[112],"To":[113],"balance":[114],"ratio":[116],"exploration/exploitation,":[118],"introduce":[120],"Loss":[122],"Adjusted":[123],"Exploration":[124],"(LAE)":[125],"policy":[126],"determines":[128],"according":[134],"Boltzmann":[137],"distribution":[138],"loss":[140],"estimates.":[141],"demonstrate":[143],"effectiveness":[145],"our":[147,169],"approach":[148],"by":[149],"training":[150],"PAC-RoManNet":[151],"several":[154],"challenging":[155],"robotic":[157],"in":[160,179],"both":[161],"simulation":[162],"real-world.":[164],"Experimental":[165],"results":[166],"show":[167,190],"method":[170],"outperforms":[171],"existing":[173],"methods":[174],"achieves":[176],"state-of-the-art":[177],"performance":[178],"terms":[180],"success":[182],"rate":[183],"efficiency.":[186],"The":[187],"ablation":[188],"studies":[189],"TPG":[192],"LAE":[194],"are":[195],"especially":[196],"beneficial":[197],"for":[198],"like":[200],"multiple":[201],"block":[202],"stacking.":[203],"Additional":[204],"experiments":[205],"Ravens-10":[207],"benchmark":[208],"suggest":[210],"good":[211],"generalizability":[212],"proposed":[215],"PAC-RoManNet.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}