{"id":"https://openalex.org/W3033852677","doi":"https://doi.org/10.1109/acirs55390.2022.9845515","title":"Multi-Task Reinforcement Learning based Mobile Manipulation Control for Dynamic Object Tracking and Grasping","display_name":"Multi-Task Reinforcement Learning based Mobile Manipulation Control for Dynamic Object Tracking and Grasping","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W3033852677","doi":"https://doi.org/10.1109/acirs55390.2022.9845515","mag":"3033852677"},"language":"en","primary_location":{"id":"doi:10.1109/acirs55390.2022.9845515","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acirs55390.2022.9845515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 7th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)","raw_type":"proceedings-article"},"type":"preprint","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/A5100390514","display_name":"Cong Wang","orcid":"https://orcid.org/0000-0003-0547-315X"},"institutions":[{"id":"https://openalex.org/I142078773","display_name":"Shenyang Institute of Automation","ror":"https://ror.org/00ft6nj33","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4391768281","display_name":"State Key Laboratory of Robotics","ror":"https://ror.org/03pcw1780","country_code":null,"type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366","https://openalex.org/I4391768281"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Wang","raw_affiliation_strings":["Shenyang Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Robotics,Shenyang,China,110016","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenyang Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Robotics,Shenyang,China,110016","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366","https://openalex.org/I4391768281"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009480530","display_name":"Qifeng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I142078773","display_name":"Shenyang Institute of Automation","ror":"https://ror.org/00ft6nj33","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4391768281","display_name":"State Key Laboratory of Robotics","ror":"https://ror.org/03pcw1780","country_code":null,"type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366","https://openalex.org/I4391768281"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qifeng Zhang","raw_affiliation_strings":["Shenyang Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Robotics,Shenyang,China,110016"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenyang Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Robotics,Shenyang,China,110016","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366","https://openalex.org/I4391768281"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618787","display_name":"Xiaohui Wang","orcid":"https://orcid.org/0000-0002-3415-5612"},"institutions":[{"id":"https://openalex.org/I142078773","display_name":"Shenyang Institute of Automation","ror":"https://ror.org/00ft6nj33","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4391768281","display_name":"State Key Laboratory of Robotics","ror":"https://ror.org/03pcw1780","country_code":null,"type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366","https://openalex.org/I4391768281"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohui Wang","raw_affiliation_strings":["Shenyang Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Robotics,Shenyang,China,110016"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenyang Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Robotics,Shenyang,China,110016","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366","https://openalex.org/I4391768281"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036606180","display_name":"Shida Xu","orcid":"https://orcid.org/0009-0004-9815-1356"},"institutions":[{"id":"https://openalex.org/I32062511","display_name":"Heriot-Watt University","ror":"https://ror.org/04mghma93","country_code":"GB","type":"education","lineage":["https://openalex.org/I32062511"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shida Xu","raw_affiliation_strings":["Heriot-Watt University,Edinburgh Centre for Robotics Edinburgh Centre for Robotics,Edinburgh,UK,EH14 4AS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Heriot-Watt University,Edinburgh Centre for Robotics Edinburgh Centre for Robotics,Edinburgh,UK,EH14 4AS","institution_ids":["https://openalex.org/I32062511"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034972272","display_name":"Yvan P\u00e9tillot","orcid":"https://orcid.org/0000-0002-1596-289X"},"institutions":[{"id":"https://openalex.org/I32062511","display_name":"Heriot-Watt University","ror":"https://ror.org/04mghma93","country_code":"GB","type":"education","lineage":["https://openalex.org/I32062511"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yvan Petillot","raw_affiliation_strings":["Heriot-Watt University,Edinburgh Centre for Robotics Edinburgh Centre for Robotics,Edinburgh,UK,EH14 4AS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Heriot-Watt University,Edinburgh Centre for Robotics Edinburgh Centre for Robotics,Edinburgh,UK,EH14 4AS","institution_ids":["https://openalex.org/I32062511"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100350760","display_name":"Sen Wang","orcid":"https://orcid.org/0000-0003-1537-8834"},"institutions":[{"id":"https://openalex.org/I32062511","display_name":"Heriot-Watt University","ror":"https://ror.org/04mghma93","country_code":"GB","type":"education","lineage":["https://openalex.org/I32062511"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sen Wang","raw_affiliation_strings":["Heriot-Watt University,Edinburgh Centre for Robotics Edinburgh Centre for Robotics,Edinburgh,UK,EH14 4AS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Heriot-Watt University,Edinburgh Centre for Robotics Edinburgh Centre for Robotics,Edinburgh,UK,EH14 4AS","institution_ids":["https://openalex.org/I32062511"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9709,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.72851095,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"34","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9901999831199646,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9840999841690063,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8031184673309326},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7612271308898926},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.640180766582489},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6095234751701355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5573081970214844},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5443257093429565},{"id":"https://openalex.org/keywords/mobile-manipulator","display_name":"Mobile manipulator","score":0.5000927448272705},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.49917173385620117},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4985334873199463},{"id":"https://openalex.org/keywords/joystick","display_name":"Joystick","score":0.47700265049934387},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46930932998657227},{"id":"https://openalex.org/keywords/agile-software-development","display_name":"Agile software development","score":0.45929211378097534},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41308173537254333},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.370508074760437},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.2503824234008789},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.21918192505836487},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15451163053512573}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8031184673309326},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7612271308898926},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.640180766582489},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6095234751701355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5573081970214844},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5443257093429565},{"id":"https://openalex.org/C190727649","wikidata":"https://www.wikidata.org/wiki/Q1941532","display_name":"Mobile manipulator","level":4,"score":0.5000927448272705},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.49917173385620117},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4985334873199463},{"id":"https://openalex.org/C96439379","wikidata":"https://www.wikidata.org/wiki/Q178805","display_name":"Joystick","level":2,"score":0.47700265049934387},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46930932998657227},{"id":"https://openalex.org/C14185376","wikidata":"https://www.wikidata.org/wiki/Q30232","display_name":"Agile software development","level":2,"score":0.45929211378097534},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41308173537254333},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.370508074760437},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2503824234008789},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.21918192505836487},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15451163053512573},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acirs55390.2022.9845515","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acirs55390.2022.9845515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 7th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.5099999904632568}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2040663525","https://openalex.org/W2613516642","https://openalex.org/W2925173345","https://openalex.org/W2963019788"],"related_works":["https://openalex.org/W2975200075","https://openalex.org/W2007544051","https://openalex.org/W2047788632","https://openalex.org/W2123436641","https://openalex.org/W1837097281","https://openalex.org/W1966410754","https://openalex.org/W2965672371","https://openalex.org/W2363840281","https://openalex.org/W2325242284","https://openalex.org/W2789220062"],"abstract_inverted_index":{"Agile":[0],"control":[1,44],"of":[2,8,59],"mobile":[3,42,127],"manipulator":[4],"is":[5,32,46],"challenging":[6],"because":[7],"the":[9,14,18,65,69,85],"high":[10],"complexity":[11],"coupled":[12],"by":[13],"robotic":[15],"system":[16],"and":[17,23,54,79,108],"unstructured":[19],"working":[20],"environment.":[21],"Tracking":[22],"grasping":[24,110],"a":[25,29,38,125],"dynamic":[26,51,60,100,114],"object":[27,52],"with":[28,102],"random":[30,77,99],"trajectory":[31],"even":[33],"harder.":[34],"In":[35],"this":[36],"paper,":[37],"multi-task":[39],"reinforcement":[40],"learning-based":[41],"manipulation":[43],"framework":[45],"proposed":[47],"to":[48,97],"achieve":[49],"general":[50],"tracking":[53,106],"grasping.":[55],"Several":[56],"basic":[57],"types":[58],"trajectories":[61,101],"are":[62,82],"chosen":[63],"as":[64],"training":[66,86],"set":[67],"for":[68,113],"task.":[70],"To":[71],"improve":[72],"policy":[73,94,118],"generalization":[74],"in":[75],"practice,":[76],"noise":[78],"dynamics":[80],"randomization":[81],"introduced":[83],"during":[84],"process.":[87],"Extensive":[88],"experiments":[89],"show":[90],"that":[91],"our":[92],"trained":[93,117],"can":[95,119],"adapt":[96],"unseen":[98],"about":[103],"0.1":[104],"m":[105],"error":[107],"75%":[109],"success":[111],"rate":[112],"objects.":[115],"The":[116],"also":[120],"be":[121],"successfully":[122],"deployed":[123],"on":[124],"real":[126],"manipulator.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}