{"id":"https://openalex.org/W3146487107","doi":"https://doi.org/10.1109/lra.2021.3068955","title":"Learning to Herd Agents Amongst Obstacles: Training Robust Shepherding Behaviors Using Deep Reinforcement Learning","display_name":"Learning to Herd Agents Amongst Obstacles: Training Robust Shepherding Behaviors Using Deep Reinforcement Learning","publication_year":2021,"publication_date":"2021-03-25","ids":{"openalex":"https://openalex.org/W3146487107","doi":"https://doi.org/10.1109/lra.2021.3068955","mag":"3146487107"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2021.3068955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3068955","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5027873519","display_name":"Jixuan Zhi","orcid":"https://orcid.org/0000-0001-6839-7487"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jixuan Zhi","raw_affiliation_strings":["Department of Computer Science, George Mason University, Fairfax, VA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6839-7487","affiliations":[{"raw_affiliation_string":"Department of Computer Science, George Mason University, Fairfax, VA, USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019967864","display_name":"Jyh\u2010Ming Lien","orcid":"https://orcid.org/0000-0002-0840-6131"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jyh-Ming Lien","raw_affiliation_strings":["Department of Computer Science, George Mason University, Fairfax, VA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0840-6131","affiliations":[{"raw_affiliation_string":"Department of Computer Science, George Mason University, Fairfax, VA, USA","institution_ids":["https://openalex.org/I162714631"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5027873519"],"corresponding_institution_ids":["https://openalex.org/I162714631"],"apc_list":null,"apc_paid":null,"fwci":2.5244,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.91066264,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"6","issue":"2","first_page":"4163","last_page":"4168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9998000264167786,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9908999800682068,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7576091289520264},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6977493166923523},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6357029676437378},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.5354132056236267},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.499222993850708},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4964337944984436},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.48681017756462097},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4480484127998352},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.44622087478637695},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.41768038272857666},{"id":"https://openalex.org/keywords/drone","display_name":"Drone","score":0.41646286845207214}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7576091289520264},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6977493166923523},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6357029676437378},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.5354132056236267},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.499222993850708},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4964337944984436},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.48681017756462097},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4480484127998352},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.44622087478637695},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.41768038272857666},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.41646286845207214},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2021.3068955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3068955","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/14","score":0.41999998688697815,"display_name":"Life below water"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1512866498","https://openalex.org/W1515655759","https://openalex.org/W1522301498","https://openalex.org/W1572260348","https://openalex.org/W2123950347","https://openalex.org/W2128990851","https://openalex.org/W2145339207","https://openalex.org/W2150256377","https://openalex.org/W2150312211","https://openalex.org/W2155540178","https://openalex.org/W2155968351","https://openalex.org/W2170591991","https://openalex.org/W2171126290","https://openalex.org/W2201581102","https://openalex.org/W2295904058","https://openalex.org/W2300722861","https://openalex.org/W2587233709","https://openalex.org/W2612076083","https://openalex.org/W2746553466","https://openalex.org/W2769558701","https://openalex.org/W2845027230","https://openalex.org/W2963477884","https://openalex.org/W2964121744","https://openalex.org/W2997791494","https://openalex.org/W3146487107","https://openalex.org/W6630802251","https://openalex.org/W6631190155","https://openalex.org/W6682815447","https://openalex.org/W6687681856","https://openalex.org/W6697152052","https://openalex.org/W6697961617","https://openalex.org/W6772942796","https://openalex.org/W6778277606"],"related_works":["https://openalex.org/W4229448053","https://openalex.org/W2059768187","https://openalex.org/W4247925126","https://openalex.org/W4312858960","https://openalex.org/W4386036939","https://openalex.org/W4327774218","https://openalex.org/W3206445629","https://openalex.org/W2605096541","https://openalex.org/W3200286695","https://openalex.org/W4379143281"],"abstract_inverted_index":{"Robotic":[0],"shepherding":[1,122,139],"problem":[2,41],"considers":[3],"the":[4,25,51,81,97,116,137,148,153,168,183],"control":[5],"and":[6,66,129,179,201],"navigation":[7],"of":[8,11,17,22,27,88,163],"a":[9,15,20,85,121,161,172],"group":[10,154],"coherent":[12],"agents":[13,105],"(e.g.,":[14],"flock":[16],"bird":[18],"or":[19,157],"fleet":[21],"drones)":[23],"through":[24],"motion":[26],"an":[28,43],"external":[29],"robot,":[30],"called":[31],"shepherd.":[32],"Machine":[33],"learning":[34,112],"based":[35],"methods":[36,76,186],"have":[37],"successfully":[38],"solved":[39],"this":[40],"in":[42,59,83,193],"environment":[44],"with":[45,64,115,160],"no":[46],"obstacles.":[47,107],"Rule-based":[48],"methods,":[49],"on":[50],"other":[52],"hand,":[53],"can":[54,103],"handle":[55],"more":[56,194,198],"complex":[57],"scenarios":[58,196],"which":[60],"environments":[61,159],"are":[62,77,190],"cluttered":[63],"obstacles":[65],"allow":[67],"multiple":[68],"shepherds":[69],"to":[70,80,147],"work":[71],"collaboratively.":[72],"However,":[73],"these":[74,93],"rule-based":[75,184],"fragile":[78],"due":[79],"difficulty":[82],"defining":[84],"comprehensive":[86],"set":[87],"behavioral":[89,130,155,185],"rules.":[90],"To":[91],"overcome":[92],"limitations,":[94],"we":[95,119],"propose":[96],"first":[98],"known":[99],"learning-based":[100],"method":[101,170],"that":[102,136],"herd":[104],"amongst":[106],"By":[108],"using":[109,124],"deep":[110],"reinforcement":[111],"techniques":[113],"combined":[114],"probabilistic":[117],"roadmaps,":[118],"train":[120],"model":[123],"noisy":[125],"but":[126],"controlled":[127],"environmental":[128],"parameters.":[131],"Our":[132],"experimental":[133],"results":[134],"show":[135],"trained":[138],"controller":[140],"is":[141,145],"robust,":[142],"namely,":[143],"it":[144],"insensitive":[146],"uncertainties":[149],"originated":[150],"from":[151,158],"either":[152],"models":[156],"small":[162],"path":[164,180],"homotopy":[165],"classes.":[166],"Consequently,":[167],"proposed":[169],"has":[171],"higher":[173],"success":[174],"rate,":[175],"shorter":[176],"completion":[177],"time":[178],"length":[181],"than":[182],"have.":[187],"These":[188],"advantages":[189],"particularly":[191],"prominent":[192],"challenging":[195],"involving":[197],"difficult":[199],"groups":[200],"strenuous":[202],"passages.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}