{"id":"https://openalex.org/W3116722212","doi":"https://doi.org/10.1109/rcar49640.2020.9303044","title":"A Deep Reinforcement Learning Approach for the Pursuit Evasion Game in the Presence of Obstacles","display_name":"A Deep Reinforcement Learning Approach for the Pursuit Evasion Game in the Presence of Obstacles","publication_year":2020,"publication_date":"2020-09-28","ids":{"openalex":"https://openalex.org/W3116722212","doi":"https://doi.org/10.1109/rcar49640.2020.9303044","mag":"3116722212"},"language":"en","primary_location":{"id":"doi:10.1109/rcar49640.2020.9303044","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rcar49640.2020.9303044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Real-time Computing and Robotics (RCAR)","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/A5100406588","display_name":"Qi Qi","orcid":"https://orcid.org/0000-0003-3607-3570"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qi Qi","raw_affiliation_strings":["Institute of Robotics and Automatic Information System (IRAIS), Tianjin Key Laboratory of Intelligent Robotics (TJKLIR), Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Institute of Robotics and Automatic Information System (IRAIS), Tianjin Key Laboratory of Intelligent Robotics (TJKLIR), Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025392915","display_name":"Xuebo Zhang","orcid":"https://orcid.org/0000-0001-5308-6539"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuebo Zhang","raw_affiliation_strings":["Institute of Robotics and Automatic Information System (IRAIS), Tianjin Key Laboratory of Intelligent Robotics (TJKLIR), Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Institute of Robotics and Automatic Information System (IRAIS), Tianjin Key Laboratory of Intelligent Robotics (TJKLIR), Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078971977","display_name":"Xian Guo","orcid":"https://orcid.org/0000-0003-3793-1207"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Guo","raw_affiliation_strings":["Institute of Robotics and Automatic Information System (IRAIS), Tianjin Key Laboratory of Intelligent Robotics (TJKLIR), Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Institute of Robotics and Automatic Information System (IRAIS), Tianjin Key Laboratory of Intelligent Robotics (TJKLIR), Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100406588"],"corresponding_institution_ids":["https://openalex.org/I205237279"],"apc_list":null,"apc_paid":null,"fwci":6.2905,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.96758815,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"68","last_page":"73"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12158","display_name":"Guidance and Control Systems","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T12158","display_name":"Guidance and Control Systems","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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":0.998199999332428,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9933000206947327,"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/pursuer","display_name":"Pursuer","score":0.9742703437805176},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.837124228477478},{"id":"https://openalex.org/keywords/pursuit-evasion","display_name":"Pursuit-evasion","score":0.7691940069198608},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7134403586387634},{"id":"https://openalex.org/keywords/kinematics","display_name":"Kinematics","score":0.6897108554840088},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.5471231341362},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5354739427566528},{"id":"https://openalex.org/keywords/evasion","display_name":"Evasion (ethics)","score":0.5317351222038269},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.497113972902298},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.21410736441612244},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.103756844997406}],"concepts":[{"id":"https://openalex.org/C2776927521","wikidata":"https://www.wikidata.org/wiki/Q468489","display_name":"Pursuer","level":2,"score":0.9742703437805176},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.837124228477478},{"id":"https://openalex.org/C2778388243","wikidata":"https://www.wikidata.org/wiki/Q7261573","display_name":"Pursuit-evasion","level":2,"score":0.7691940069198608},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7134403586387634},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.6897108554840088},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.5471231341362},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5354739427566528},{"id":"https://openalex.org/C2781251061","wikidata":"https://www.wikidata.org/wiki/Q5416089","display_name":"Evasion (ethics)","level":3,"score":0.5317351222038269},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.497113972902298},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.21410736441612244},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.103756844997406},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C203014093","wikidata":"https://www.wikidata.org/wiki/Q101929","display_name":"Immunology","level":1,"score":0.0},{"id":"https://openalex.org/C8891405","wikidata":"https://www.wikidata.org/wiki/Q1059","display_name":"Immune system","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/rcar49640.2020.9303044","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rcar49640.2020.9303044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Real-time Computing and Robotics (RCAR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W40650588","https://openalex.org/W1522301498","https://openalex.org/W1581842928","https://openalex.org/W1976433617","https://openalex.org/W2031168329","https://openalex.org/W2086813915","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2296073425","https://openalex.org/W2296970238","https://openalex.org/W2762117857","https://openalex.org/W2766447205","https://openalex.org/W2793826897","https://openalex.org/W2904612118","https://openalex.org/W2914060209","https://openalex.org/W2964121744","https://openalex.org/W2973525135","https://openalex.org/W2982316857","https://openalex.org/W2985275943","https://openalex.org/W3014355579","https://openalex.org/W3118210634","https://openalex.org/W4297810554","https://openalex.org/W6631190155","https://openalex.org/W6745190604","https://openalex.org/W6767919266","https://openalex.org/W6788072495"],"related_works":["https://openalex.org/W2057376130","https://openalex.org/W2091926052","https://openalex.org/W4253161990","https://openalex.org/W2039546613","https://openalex.org/W2184611791","https://openalex.org/W3152565215","https://openalex.org/W1994748888","https://openalex.org/W114019308","https://openalex.org/W2546733891","https://openalex.org/W2119179514"],"abstract_inverted_index":{"In":[0,46,102],"a":[1,28,49],"pursuit-evasion":[2,59],"game,":[3,60],"the":[4,9,12,37,58,63,72,78,82,87,93,96,99,104,112,127],"pursuer":[5,94,135],"tries":[6],"to":[7,91],"capture":[8],"evader,":[10],"while":[11],"evader":[13,97,137],"actively":[14],"avoids":[15],"being":[16],"captured.":[17],"Traditional":[18],"approaches":[19],"usually":[20],"ignore":[21],"or":[22],"simplify":[23],"kinematic":[24],"constraints":[25],"by":[26],"using":[27],"grip":[29],"world":[30],"discrete":[31],"model":[32],"and":[33,71,95,136],"they":[34],"assume":[35],"that":[36,126],"game":[38],"is":[39,55,109],"played":[40],"in":[41,68,77],"free":[42],"space":[43],"without":[44],"obstacles.":[45],"this":[47],"paper,":[48],"curriculum":[50,107],"deep":[51],"reinforcement":[52],"learning":[53,108,118],"approach":[54,129],"proposed":[56,128],"for":[57,133],"which":[61],"considers":[62],"kinematics":[64],"of":[65,74,89,106],"mobile":[66],"robot":[67],"practical":[69],"applications":[70],"influence":[73],"static":[75],"obstacles":[76],"environment.":[79],"To":[80],"improve":[81],"system":[83],"performance,":[84],"we":[85],"use":[86],"mechanism":[88],"self-play":[90],"train":[92],"at":[98],"same":[100],"time.":[101],"addition,":[103],"method":[105],"used,":[110],"making":[111],"agent":[113],"learn":[114],"simpler":[115],"tasks":[116],"before":[117],"more":[119],"complicated":[120],"ones.":[121],"Comparative":[122],"simulation":[123],"results":[124],"show":[125],"presents":[130],"superior":[131],"performance":[132],"both":[134],"when":[138],"playing":[139],"against":[140],"intelligent":[141],"opponents.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}