{"id":"https://openalex.org/W7131126365","doi":"https://doi.org/10.1109/robio66223.2025.11378438","title":"A Multi-Strategy Autonomous Switching Mobile Robot Capture Method Based on Hierarchical Reinforcement Learning","display_name":"A Multi-Strategy Autonomous Switching Mobile Robot Capture Method Based on Hierarchical Reinforcement Learning","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7131126365","doi":"https://doi.org/10.1109/robio66223.2025.11378438"},"language":null,"primary_location":{"id":"doi:10.1109/robio66223.2025.11378438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio66223.2025.11378438","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":"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/A5126615199","display_name":"Ruibo Niu","orcid":null},"institutions":[{"id":"https://openalex.org/I27599042","display_name":"Xi'an Polytechnic University","ror":"https://ror.org/03442p831","country_code":"CN","type":"education","lineage":["https://openalex.org/I27599042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruibo Niu","raw_affiliation_strings":["School of Electronic and Information, Xi'an Polytechnic University,Xi'an,China,710048"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information, Xi'an Polytechnic University,Xi'an,China,710048","institution_ids":["https://openalex.org/I27599042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341840","display_name":"Xun Li","orcid":"https://orcid.org/0000-0001-7749-2902"},"institutions":[{"id":"https://openalex.org/I27599042","display_name":"Xi'an Polytechnic University","ror":"https://ror.org/03442p831","country_code":"CN","type":"education","lineage":["https://openalex.org/I27599042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Li","raw_affiliation_strings":["School of Electronic and Information, Xi'an Polytechnic University,Xi'an,China,710048"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information, Xi'an Polytechnic University,Xi'an,China,710048","institution_ids":["https://openalex.org/I27599042"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhuoliang Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I27599042","display_name":"Xi'an Polytechnic University","ror":"https://ror.org/03442p831","country_code":"CN","type":"education","lineage":["https://openalex.org/I27599042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuoliang Shen","raw_affiliation_strings":["School of Electronic and Information, Xi'an Polytechnic University,Xi'an,China,710048"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information, Xi'an Polytechnic University,Xi'an,China,710048","institution_ids":["https://openalex.org/I27599042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074464143","display_name":"Yangzhi Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I27599042","display_name":"Xi'an Polytechnic University","ror":"https://ror.org/03442p831","country_code":"CN","type":"education","lineage":["https://openalex.org/I27599042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangzhi Wu","raw_affiliation_strings":["School of Electronic and Information, Xi'an Polytechnic University,Xi'an,China,710048"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information, Xi'an Polytechnic University,Xi'an,China,710048","institution_ids":["https://openalex.org/I27599042"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27599042"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"377","last_page":"382"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11615","display_name":"Control and Dynamics of Mobile Robots","score":0.10339999943971634,"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/T11615","display_name":"Control and Dynamics of Mobile Robots","score":0.10339999943971634,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.08540000021457672,"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/T12288","display_name":"Optimization and Search Problems","score":0.06800000369548798,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7554000020027161},{"id":"https://openalex.org/keywords/timeout","display_name":"Timeout","score":0.692799985408783},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5922999978065491},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5472999811172485},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.546999990940094},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.520799994468689},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.4537999927997589},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4487999975681305}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7554000020027161},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7373999953269958},{"id":"https://openalex.org/C31691690","wikidata":"https://www.wikidata.org/wiki/Q1753979","display_name":"Timeout","level":2,"score":0.692799985408783},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5922999978065491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5861999988555908},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5472999811172485},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.546999990940094},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.520799994468689},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.4537999927997589},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4487999975681305},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.4377000033855438},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.4323999881744385},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.39879998564720154},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3547999858856201},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3506999909877777},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3386000096797943},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2806999981403351},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2728999853134155},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.2651999890804291},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.25870001316070557},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.25839999318122864},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio66223.2025.11378438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio66223.2025.11378438","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":[{"id":"https://openalex.org/G7176147759","display_name":null,"funder_award_id":"62403368","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2055504162","https://openalex.org/W2145339207","https://openalex.org/W2413454671","https://openalex.org/W2790268363","https://openalex.org/W2918849077","https://openalex.org/W3035782080","https://openalex.org/W3046106022","https://openalex.org/W3093345403","https://openalex.org/W3116722212","https://openalex.org/W4213246061","https://openalex.org/W4221155562","https://openalex.org/W4312691966","https://openalex.org/W4324119087","https://openalex.org/W4361857614"],"related_works":[],"abstract_inverted_index":{"To":[0],"address":[1],"the":[2,13,38,79,90,120],"challenges":[3],"of":[4,104],"learning":[5],"capture":[6,131],"tasks":[7],"in":[8,126,144],"complex":[9],"obstacle":[10,47],"environments":[11],"and":[12,52,55,69,118,136,142,149],"reliance":[14],"on":[15,31],"manually":[16],"defined":[17],"strategy":[18],"switching,":[19],"this":[20],"paper":[21],"proposes":[22],"a":[23,56,62,95],"Hierarchical":[24],"Deep":[25,83,96],"Reinforcement":[26],"Learning":[27],"(HDRL)":[28],"method":[29,36,122],"based":[30],"autonomous":[32,102],"sub-strategy":[33,44,58],"switching.":[34],"The":[35,73],"divides":[37],"overall":[39],"task":[40,67],"into":[41],"three":[42],"lower-level":[43,74],"modules":[45,75],"(navigation":[46],"avoidance,":[48,51],"navigation":[49,53],"collision":[50,134],"capture)":[54],"higher-level":[57,91],"switching":[59,92],"module,":[60],"using":[61,78],"modular":[63],"design":[64],"to":[65,100,111],"reduce":[66],"complexity":[68],"enhance":[70],"generalisation":[71],"capabilities.":[72],"are":[76],"trained":[77],"Multi-Agent":[80],"Dual":[81],"Delay":[82],"Deterministic":[84],"Policy":[85],"Gradient":[86],"(MATD3)":[87],"algorithm,":[88],"while":[89],"module":[93],"employs":[94],"Double":[97],"Q-Network":[98],"(DDQN)":[99],"achieve":[101],"scheduling":[103],"sub-strategies.":[105],"Experimental":[106],"results":[107],"demonstrate":[108],"that":[109],"compared":[110],"traditional":[112],"non-hierarchical":[113],"methods":[114],"(such":[115],"as":[116,130],"MADDPG":[117],"MATD3),":[119],"proposed":[121],"achieves":[123],"superior":[124],"performance":[125],"key":[127],"metrics":[128],"such":[129],"success":[132],"rate,":[133,135,138],"timeout":[137],"validating":[139],"its":[140],"effectiveness":[141],"practicality":[143],"enabling":[145],"efficient":[146],"multi-agent":[147],"collaboration":[148],"dynamic":[150],"decision-making.":[151]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-24T00:00:00"}