{"id":"https://openalex.org/W4401413780","doi":"https://doi.org/10.1109/icra57147.2024.10610107","title":"PathRL: An End-to-End Path Generation Method for Collision Avoidance via Deep Reinforcement Learning","display_name":"PathRL: An End-to-End Path Generation Method for Collision Avoidance via Deep Reinforcement Learning","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401413780","doi":"https://doi.org/10.1109/icra57147.2024.10610107"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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/A5114860703","display_name":"Wenhao Yu","orcid":"https://orcid.org/0000-0002-9671-8652"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenhao Yu","raw_affiliation_strings":["University of Science and Technology of China (USTC),Institute of Advanced Technology,Hefei,China,230026"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),Institute of Advanced Technology,Hefei,China,230026","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068172501","display_name":"Jie Peng","orcid":"https://orcid.org/0000-0002-2874-4744"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Peng","raw_affiliation_strings":["USTC,School of Data Science,Hefei,China,230026"],"affiliations":[{"raw_affiliation_string":"USTC,School of Data Science,Hefei,China,230026","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077632761","display_name":"Quecheng Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quecheng Qiu","raw_affiliation_strings":["USTC,School of Computer Science and Technology,Hefei,China,230026"],"affiliations":[{"raw_affiliation_string":"USTC,School of Computer Science and Technology,Hefei,China,230026","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060039195","display_name":"Hanyu Wang","orcid":"https://orcid.org/0000-0002-1110-7693"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanyu Wang","raw_affiliation_strings":["USTC,School of Data Science,Hefei,China,230026"],"affiliations":[{"raw_affiliation_string":"USTC,School of Data Science,Hefei,China,230026","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100388661","display_name":"Lu Zhang","orcid":"https://orcid.org/0000-0002-7492-6047"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu Zhang","raw_affiliation_strings":["Hefei Comprehensive National Science Center,Institute of Artificial Intelligence,China,230088"],"affiliations":[{"raw_affiliation_string":"Hefei Comprehensive National Science Center,Institute of Artificial Intelligence,China,230088","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061104105","display_name":"Jianmin Ji","orcid":"https://orcid.org/0000-0002-1515-0402"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianmin Ji","raw_affiliation_strings":["USTC,School of Computer Science and Technology,Hefei,China,230026"],"affiliations":[{"raw_affiliation_string":"USTC,School of Computer Science and Technology,Hefei,China,230026","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5114860703"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":2.8174,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.90546304,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"9278","last_page":"9284"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.9994000196456909,"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/T11500","display_name":"Evacuation and Crowd Dynamics","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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/end-to-end-principle","display_name":"End-to-end principle","score":0.9192208051681519},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.685139000415802},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.6691902875900269},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6234164834022522},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5620025396347046},{"id":"https://openalex.org/keywords/dead-end","display_name":"Dead end","score":0.5611896514892578},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.45981818437576294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39411717653274536},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2114405333995819},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1541338562965393},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.10379898548126221},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.05074077844619751}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.9192208051681519},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.685139000415802},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.6691902875900269},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6234164834022522},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5620025396347046},{"id":"https://openalex.org/C2986709869","wikidata":"https://www.wikidata.org/wiki/Q398589","display_name":"Dead end","level":3,"score":0.5611896514892578},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.45981818437576294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39411717653274536},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2114405333995819},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1541338562965393},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.10379898548126221},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.05074077844619751},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W192919555","https://openalex.org/W1503438515","https://openalex.org/W2109910161","https://openalex.org/W2148961728","https://openalex.org/W2167052694","https://openalex.org/W2212786010","https://openalex.org/W2231327593","https://openalex.org/W2296073425","https://openalex.org/W2752551597","https://openalex.org/W2895974005","https://openalex.org/W2902711054","https://openalex.org/W2948072728","https://openalex.org/W2962917939","https://openalex.org/W2963428623","https://openalex.org/W2967975754","https://openalex.org/W3022159334","https://openalex.org/W3048659003","https://openalex.org/W3081171811","https://openalex.org/W3196525377","https://openalex.org/W4220840735","https://openalex.org/W4226150156","https://openalex.org/W4285102644","https://openalex.org/W4312776746","https://openalex.org/W4362014203","https://openalex.org/W4379930841","https://openalex.org/W4385416220","https://openalex.org/W6678081342","https://openalex.org/W6689594162","https://openalex.org/W6747473740","https://openalex.org/W6756675569","https://openalex.org/W6763429879"],"related_works":["https://openalex.org/W1819938260","https://openalex.org/W2340892746","https://openalex.org/W3005999311","https://openalex.org/W3179968364","https://openalex.org/W3016188207","https://openalex.org/W4293268064","https://openalex.org/W4400488565","https://openalex.org/W2218833963","https://openalex.org/W2964709658","https://openalex.org/W4240479622"],"abstract_inverted_index":{"Robot":[0],"navigation":[1,22,70,193,257],"using":[2,82],"deep":[3],"reinforcement":[4],"learning":[5,218],"(DRL)":[6],"has":[7],"shown":[8],"great":[9],"potential":[10,114],"in":[11,161,166,272],"improving":[12],"the":[13,33,52,55,69,74,78,94,126,148,152,155,158,169,188,192,196,214,223,227,234,267],"performance":[14],"of":[15,51,128,141,154,270],"mobile":[16],"robots.":[17],"Nevertheless,":[18],"most":[19],"existing":[20],"DRL-based":[21],"methods":[23,211],"primarily":[24],"focus":[25],"on":[26],"training":[27,102,224],"a":[28,64,103,138,142,182],"policy":[29,66,105,189],"that":[30,67,106,186],"directly":[31],"commands":[32],"robot":[34,53,75,156,263],"with":[35,172],"low-level":[36,122],"controls,":[37],"like":[38],"linear":[39],"and":[40,48,85,206,248,261,276],"angular":[41,250],"velocities,":[42],"which":[43,124,146],"leads":[44],"to":[45,62,93,121,136,150,176,190,212,221,254],"unstable":[46],"speeds":[47],"unsmooth":[49],"trajectories":[50],"during":[54],"long-term":[56],"execution.":[57],"An":[58],"alternative":[59],"method":[60,185],"is":[61,219],"train":[63],"DRL":[65,104,184,256],"outputs":[68,107],"path":[71,80,139,149,194],"directly.":[72],"Then":[73],"can":[76],"follow":[77],"generated":[79],"smoothly":[81],"sophisticated":[83],"velocity-planning":[84],"path-following":[86],"controllers,":[87],"whose":[88],"parameters":[89],"are":[90],"specified":[91],"according":[92],"hardware":[95],"platform.":[96],"However,":[97],"two":[98],"roadblocks":[99],"arise":[100],"for":[101,113,195],"paths:":[108],"(1)":[109],"The":[110],"action":[111,202],"space":[112,203,209],"paths":[115],"often":[116],"involves":[117],"higher":[118],"dimensions":[119],"comparing":[120],"commands,":[123],"increases":[125],"difficulties":[127],"training;":[129],"(2)":[130],"It":[131],"takes":[132,231],"multiple":[133,162,277],"time":[134,144,163],"steps":[135],"track":[137],"instead":[140],"single":[143],"step,":[145],"requires":[147],"predicate":[151],"interactions":[153],"w.r.t.":[157],"dynamic":[159],"environment":[160],"steps.":[164],"This,":[165],"turn,":[167],"amplifies":[168],"challenges":[170],"associated":[171,215],"training.":[173],"In":[174,240],"response":[175],"these":[177],"challenges,":[178],"we":[179,199],"propose":[180],"PathRL,":[181],"novel":[183],"trains":[187],"generate":[191],"robot.":[197],"Specifically,":[198],"employ":[200],"specific":[201],"discretization":[204],"techniques":[205],"tailored":[207],"state":[208],"representation":[210],"address":[213],"challenges.":[216],"Curriculum":[217],"employed":[220],"expedite":[222],"process,":[225],"while":[226],"reward":[228],"function":[229],"also":[230],"into":[232],"account":[233],"smooth":[235,262],"transition":[236],"between":[237],"adjacent":[238],"paths.":[239],"our":[241],"experiments,":[242],"PathRL":[243,271],"achieves":[244],"better":[245],"success":[246],"rates":[247],"reduces":[249],"rotation":[251],"variability":[252],"compared":[253],"other":[255],"methods,":[258],"facilitating":[259],"stable":[260],"movement.":[264],"We":[265],"demonstrate":[266],"competitive":[268],"edge":[269],"both":[273],"real-world":[274],"scenarios":[275],"challenging":[278],"simulation":[279],"environments.":[280]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}