{"id":"https://openalex.org/W7130322989","doi":"https://doi.org/10.1109/tencon66050.2025.11375516","title":"Coordinated Dual-ARM Manipulation Using Reinforcement Learning: A Soft Actor-Critic Approach on the Poppy Humanoid","display_name":"Coordinated Dual-ARM Manipulation Using Reinforcement Learning: A Soft Actor-Critic Approach on the Poppy Humanoid","publication_year":2025,"publication_date":"2025-10-27","ids":{"openalex":"https://openalex.org/W7130322989","doi":"https://doi.org/10.1109/tencon66050.2025.11375516"},"language":null,"primary_location":{"id":"doi:10.1109/tencon66050.2025.11375516","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon66050.2025.11375516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TENCON 2025 - 2025 IEEE Region 10 Conference (TENCON)","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/A5146708503","display_name":"Allen Jacob George","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101034","display_name":"Birla Institute of Technology and Science - Hyderabad Campus","ror":"https://ror.org/014ctt859","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210101034","https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Allen Jacob George","raw_affiliation_strings":["BITS Pilani,Dept. of Electrical & Electronics Engg.,Hyderabad,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BITS Pilani,Dept. of Electrical & Electronics Engg.,Hyderabad,India","institution_ids":["https://openalex.org/I4210101034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010049263","display_name":"A. Sarkar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101034","display_name":"Birla Institute of Technology and Science - Hyderabad Campus","ror":"https://ror.org/014ctt859","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210101034","https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Abhishek Sarkar","raw_affiliation_strings":["BITS Pilani,Dept. of Mechanical Engg.,Hyderabad,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BITS Pilani,Dept. of Mechanical Engg.,Hyderabad,India","institution_ids":["https://openalex.org/I4210101034"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089686987","display_name":"Joyjit Mukherjee","orcid":"https://orcid.org/0000-0003-1682-3434"},"institutions":[{"id":"https://openalex.org/I4210101034","display_name":"Birla Institute of Technology and Science - Hyderabad Campus","ror":"https://ror.org/014ctt859","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210101034","https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Joyjit Mukherjee","raw_affiliation_strings":["BITS Pilani,Dept. of Electrical & Electronics Engg.,Hyderabad,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BITS Pilani,Dept. of Electrical & Electronics Engg.,Hyderabad,India","institution_ids":["https://openalex.org/I4210101034"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210101034"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.69343787,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"582","last_page":"586"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.838100016117096,"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":0.838100016117096,"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":0.05480000004172325,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.04610000178217888,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7275999784469604},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.7141000032424927},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6793000102043152},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.6532999873161316},{"id":"https://openalex.org/keywords/torso","display_name":"Torso","score":0.49300000071525574},{"id":"https://openalex.org/keywords/grippers","display_name":"Grippers","score":0.4406000077724457},{"id":"https://openalex.org/keywords/poppy","display_name":"Poppy","score":0.43639999628067017}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7285000085830688},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7275999784469604},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7141000032424927},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6793000102043152},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.6532999873161316},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6037999987602234},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5008999705314636},{"id":"https://openalex.org/C523889960","wikidata":"https://www.wikidata.org/wiki/Q160695","display_name":"Torso","level":2,"score":0.49300000071525574},{"id":"https://openalex.org/C2775960376","wikidata":"https://www.wikidata.org/wiki/Q1435859","display_name":"Grippers","level":2,"score":0.4406000077724457},{"id":"https://openalex.org/C2776295790","wikidata":"https://www.wikidata.org/wiki/Q967457","display_name":"Poppy","level":2,"score":0.43639999628067017},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.430400013923645},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3287999927997589},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.32739999890327454},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3163999915122986},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.29120001196861267},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26489999890327454},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25949999690055847},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tencon66050.2025.11375516","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon66050.2025.11375516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TENCON 2025 - 2025 IEEE Region 10 Conference (TENCON)","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":17,"referenced_works":["https://openalex.org/W2106296284","https://openalex.org/W2147168033","https://openalex.org/W2562662934","https://openalex.org/W2792852625","https://openalex.org/W3093995467","https://openalex.org/W3116496379","https://openalex.org/W3128256958","https://openalex.org/W3169794354","https://openalex.org/W3206200647","https://openalex.org/W4206073426","https://openalex.org/W4360764669","https://openalex.org/W4362672763","https://openalex.org/W4388083256","https://openalex.org/W4390968395","https://openalex.org/W4393241311","https://openalex.org/W4407743178","https://openalex.org/W4413944821"],"related_works":[],"abstract_inverted_index":{"In":[0,38,65],"this":[1],"work,":[2],"we":[3,89],"present":[4],"a":[5,42,69,81],"reinforcement":[6,105],"learningbased":[7],"framework":[8],"for":[9],"dual-arm":[10,151],"object":[11,28,63,79,152],"manipulation":[12,114],"using":[13,47],"the":[14,22,32,39,48,59,66,77,108,119,126,133],"Poppy":[15,127],"humanoid":[16],"robot":[17,128],"platform.":[18],"Our":[19],"approach":[20],"addresses":[21],"challenges":[23],"of":[24,98,118],"coordinated":[25,113],"grasping":[26,153],"and":[27,58,138,154,158],"transport":[29],"by":[30,124],"decomposing":[31],"task":[33],"into":[34],"two":[35],"sequential":[36],"stages.":[37],"first":[40],"stage,":[41,68],"single":[43],"policy":[44,72],"is":[45,73],"trained":[46,74],"Soft":[49],"Actor-Critic":[50],"(SAC)":[51],"algorithm":[52],"to":[53,61,75,80,110,143],"simultaneously":[54],"control":[55],"both":[56],"arms":[57],"torso":[60],"perform":[62,150],"grasping.":[64],"second":[67],"separate":[70],"SAC":[71],"move":[76],"grasped":[78],"specified":[82],"target":[83],"location.":[84],"To":[85],"improve":[86],"learning":[87,106],"efficiency,":[88],"incorporate":[90],"human":[91],"demonstration":[92],"data":[93],"during":[94],"training.":[95],"This":[96],"integration":[97],"expert":[99],"guidance":[100],"with":[101,156],"sample":[102],"efficient":[103],"deep":[104],"enables":[107],"system":[109],"achieve":[111],"robust,":[112],"behavior.":[115],"Further":[116],"validation":[117],"simulation":[120,134,137],"results":[121,140],"were":[122],"tested":[123],"putting":[125],"joint":[129],"trajectories":[130],"generated":[131],"from":[132],"results.":[135],"Both":[136],"experimental":[139],"are":[141],"shown":[142],"demonstrate":[144],"that":[145],"our":[146],"method":[147],"can":[148],"successfully":[149],"relocation":[155],"stable":[157],"synchronized":[159],"motion.":[160]},"counts_by_year":[],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2026-02-19T00:00:00"}