{"id":"https://openalex.org/W7131104845","doi":"https://doi.org/10.1109/robio66223.2025.11377273","title":"Unity RL Playground: A Versatile Reinforcement Learning Framework for Mobile Robots","display_name":"Unity RL Playground: A Versatile Reinforcement Learning Framework for Mobile Robots","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7131104845","doi":"https://doi.org/10.1109/robio66223.2025.11377273"},"language":null,"primary_location":{"id":"doi:10.1109/robio66223.2025.11377273","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio66223.2025.11377273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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/A5002825007","display_name":"L. Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Linqi Ye","raw_affiliation_strings":["School of Future Technology, Shanghai University,Shanghai,China,200444"],"affiliations":[{"raw_affiliation_string":"School of Future Technology, Shanghai University,Shanghai,China,200444","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113121751","display_name":"Rankun Li","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rankun Li","raw_affiliation_strings":["School of Future Technology, Shanghai University,Shanghai,China,200444"],"affiliations":[{"raw_affiliation_string":"School of Future Technology, Shanghai University,Shanghai,China,200444","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126623235","display_name":"Xiaowen Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaowen Hu","raw_affiliation_strings":["School of Future Technology, Shanghai University,Shanghai,China,200444"],"affiliations":[{"raw_affiliation_string":"School of Future Technology, Shanghai University,Shanghai,China,200444","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100364802","display_name":"Jin Li","orcid":"https://orcid.org/0000-0002-6131-456X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayi Li","raw_affiliation_strings":["Tsinghua University,Navigation and Control Research Center,Department of Automation,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Navigation and Control Research Center,Department of Automation,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101754705","display_name":"Boyang Xing","orcid":"https://orcid.org/0000-0003-0495-8040"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boyang Xing","raw_affiliation_strings":["National and Local Co-Built Humanoid Robotics Innovation Center"],"affiliations":[{"raw_affiliation_string":"National and Local Co-Built Humanoid Robotics Innovation Center","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126600887","display_name":"Yan Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Peng","raw_affiliation_strings":["School of Future Technology, Shanghai University,Shanghai,China,200444"],"affiliations":[{"raw_affiliation_string":"School of Future Technology, Shanghai University,Shanghai,China,200444","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126600735","display_name":"Bin Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Liang","raw_affiliation_strings":["Tsinghua University,Navigation and Control Research Center,Department of Automation,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Navigation and Control Research Center,Department of Automation,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5002825007"],"corresponding_institution_ids":["https://openalex.org/I113940042"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.88547965,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1702","last_page":"1707"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8604000210762024,"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":0.8604000210762024,"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":0.020099999383091927,"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":0.014800000004470348,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.73089998960495},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.6793000102043152},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6714000105857849},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.4311999976634979},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4203999936580658},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.390500009059906},{"id":"https://openalex.org/keywords/compatibility","display_name":"Compatibility (geochemistry)","score":0.373199999332428}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.73089998960495},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.6793000102043152},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6714000105857849},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6132000088691711},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5281000137329102},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.4311999976634979},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4203999936580658},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.390500009059906},{"id":"https://openalex.org/C2778648169","wikidata":"https://www.wikidata.org/wiki/Q967768","display_name":"Compatibility (geochemistry)","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.3612000048160553},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3280999958515167},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31690001487731934},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3086000084877014},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3059999942779541},{"id":"https://openalex.org/C162947575","wikidata":"https://www.wikidata.org/wiki/Q2005645","display_name":"Social robot","level":5,"score":0.2976999878883362},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2953999936580658},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.29269999265670776},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.2766999900341034},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.275299996137619},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio66223.2025.11377273","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio66223.2025.11377273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W4205430897","https://openalex.org/W4367016688","https://openalex.org/W4383109371","https://openalex.org/W4392763392"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"Unity":[3,15,17],"RL":[4,18],"Playground,":[5],"an":[6],"open-source":[7],"reinforcement":[8],"learning":[9,66],"framework":[10],"built":[11],"on":[12],"top":[13],"of":[14,23],"ML-Agents.":[16],"Playground":[19],"automates":[20],"the":[21,41,90],"process":[22],"training":[24,53],"mobile":[25],"robots":[26],"to":[27,46,72],"perform":[28],"various":[29],"locomotion":[30],"tasks":[31],"such":[32],"as":[33],"walking,":[34],"running,":[35],"and":[36,68,78,89],"jumping":[37],"in":[38,74],"simulation,":[39],"with":[40,60],"potential":[42],"for":[43,54],"seamless":[44],"transfer":[45],"real":[47],"hardware.":[48],"Key":[49],"features":[50],"include":[51],"one-click":[52],"imported":[55],"robot":[56,62,75],"models,":[57],"universal":[58],"compatibility":[59],"diverse":[61],"configurations,":[63],"multi-mode":[64],"motion":[65],"capabilities,":[67],"extreme":[69],"performance":[70],"testing":[71],"aid":[73],"design":[76],"optimization":[77],"morphological":[79],"evolution.":[80],"The":[81],"attached":[82],"video":[83],"can":[84],"be":[85],"found":[86],"at":[87,94],"https://linqi-ye.github.io/video/unity25.mp4":[88],"code":[91],"is":[92],"available":[93],"https://github.com/loongOpen/Unity-RL-Playground/.":[95]},"counts_by_year":[],"updated_date":"2026-02-25T06:17:34.324206","created_date":"2026-02-24T00:00:00"}
