{"id":"https://openalex.org/W4221138933","doi":"https://doi.org/10.1109/icra46639.2022.9811965","title":"A Deep Reinforcement Learning Environment for Particle Robot Navigation and Object Manipulation","display_name":"A Deep Reinforcement Learning Environment for Particle Robot Navigation and Object Manipulation","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W4221138933","doi":"https://doi.org/10.1109/icra46639.2022.9811965"},"language":"en","primary_location":{"id":"doi:10.1109/icra46639.2022.9811965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9811965","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.06464","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040646757","display_name":"Jeremy Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeremy Shen","raw_affiliation_strings":["Stuyvesant High School,New York,NY,USA,10280"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stuyvesant High School,New York,NY,USA,10280","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077675826","display_name":"Erdong Xiao","orcid":"https://orcid.org/0000-0002-7689-8334"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erdong Xiao","raw_affiliation_strings":["New York University,Brooklyn,NY,USA,11201"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University,Brooklyn,NY,USA,11201","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuchen Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuchen Liu","raw_affiliation_strings":["New York University,Brooklyn,NY,USA,11201"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University,Brooklyn,NY,USA,11201","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chen Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Feng","raw_affiliation_strings":["New York University,Brooklyn,NY,USA,11201"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University,Brooklyn,NY,USA,11201","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6232","last_page":"6239"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.4156999886035919,"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":0.4156999886035919,"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/T11486","display_name":"Micro and Nano Robotics","score":0.21469999849796295,"subfield":{"id":"https://openalex.org/subfields/3104","display_name":"Condensed Matter Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.10080000013113022,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/robot","display_name":"Robot","score":0.7272144556045532},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7084472179412842},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6451943516731262},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5991643071174622},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5697380900382996},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5691947340965271},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.5126746892929077},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.494478702545166},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4472525715827942},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4240255355834961},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.37003910541534424},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.3189367949962616},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.26641952991485596}],"concepts":[{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7272144556045532},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7084472179412842},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6451943516731262},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5991643071174622},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5697380900382996},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5691947340965271},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.5126746892929077},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.494478702545166},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4472525715827942},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4240255355834961},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.37003910541534424},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3189367949962616},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.26641952991485596},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","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/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icra46639.2022.9811965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9811965","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"},{"id":"pmh:oai:arXiv.org:2203.06464","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.06464","pdf_url":"https://arxiv.org/pdf/2203.06464","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2203.06464","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2203.06464","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2203.06464","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.06464","pdf_url":"https://arxiv.org/pdf/2203.06464","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3841067017","display_name":"CPS: Medium: Accurate and Efficient Collective Additive Manufacturing by Mobile Robots","funder_award_id":"1932187","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3931422147","display_name":null,"funder_award_id":"CMMI-1932187","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337391","display_name":"Division of Civil, Mechanical and Manufacturing Innovation","ror":"https://ror.org/028yd4c30"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4221138933.pdf","grobid_xml":"https://content.openalex.org/works/W4221138933.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2800236838","https://openalex.org/W2924849247","https://openalex.org/W2963821308","https://openalex.org/W2973402182","https://openalex.org/W2982384915","https://openalex.org/W3003714583","https://openalex.org/W3007080643","https://openalex.org/W3056510116","https://openalex.org/W3117470911","https://openalex.org/W3158592412","https://openalex.org/W3186545145","https://openalex.org/W6692846177","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6746513637","https://openalex.org/W6753624969","https://openalex.org/W6767919266","https://openalex.org/W6775020266","https://openalex.org/W6779994605"],"related_works":["https://openalex.org/W1353223","https://openalex.org/W1323832","https://openalex.org/W929682","https://openalex.org/W1129023","https://openalex.org/W1061439","https://openalex.org/W7430954","https://openalex.org/W7978787","https://openalex.org/W13141533","https://openalex.org/W5176077","https://openalex.org/W13856871"],"abstract_inverted_index":{"Particle":[0],"robots":[1],"are":[2,145],"novel":[3],"biologically-inspired":[4],"robotic":[5],"systems":[6],"where":[7],"locomotion":[8,30],"can":[9],"be":[10,37],"achieved":[11],"collectively":[12],"and":[13,77,97,103,107],"robustly,":[14],"but":[15,144],"not":[16],"independently.":[17],"While":[18],"its":[19],"control":[20],"is":[21,161],"currently":[22],"limited":[23],"to":[24,109,125,148,165],"a":[25,33,56,87,127],"hand-crafted":[26,154],"policy":[27],"for":[28,45,61,131],"basic":[29],"tasks,":[31],"such":[32],"multi-robot":[34],"system":[35,54],"could":[36],"potentially":[38],"controlled":[39],"via":[40],"Deep":[41],"Reinforcement":[42],"Learning":[43],"(DRL)":[44],"different":[46],"tasks":[47,106,143],"more":[48],"efficiently.":[49],"However,":[50],"the":[51,69,78,93,100,111,117,132,142,150,153,167],"particle":[52,89,118],"robot":[53,76,90,119],"presents":[55],"new":[57,105],"set":[58,128],"of":[59,72,74,81,114,129,140,152,158],"challenges":[60,108],"DRL":[62,115,136,159],"differing":[63],"from":[64],"existing":[65],"swarm":[66],"robotics":[67],"systems:":[68],"low":[70],"degrees":[71],"freedom":[73],"each":[75],"increased":[79],"necessity":[80],"coordination":[82],"between":[83],"robots.":[84],"We":[85],"present":[86],"2D":[88],"simulator":[91],"using":[92],"OpenAI":[94],"Gym":[95],"interface":[96],"Pymunk":[98],"as":[99],"physics":[101],"engine,":[102],"introduce":[104],"research":[110],"underexplored":[112],"applications":[113],"in":[116,163],"system.":[120],"Moreover,":[121],"we":[122],"use":[123],"Stable-baselines3":[124],"provide":[126],"benchmarks":[130],"tasks.":[133,169],"Current":[134],"baseline":[135],"algorithms":[137,160],"show":[138],"signs":[139],"achieving":[141],"yet":[146],"unable":[147],"reach":[149],"performance":[151],"policy.":[155],"Further":[156],"development":[157],"necessary":[162],"order":[164],"accomplish":[166],"proposed":[168]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2022-04-03T00:00:00"}