{"id":"https://openalex.org/W3149383640","doi":"https://doi.org/10.1109/ieeeconf49454.2021.9382693","title":"Accelerated Sim-to-Real Deep Reinforcement Learning: Learning Collision Avoidance from Human Player","display_name":"Accelerated Sim-to-Real Deep Reinforcement Learning: Learning Collision Avoidance from Human Player","publication_year":2021,"publication_date":"2021-01-11","ids":{"openalex":"https://openalex.org/W3149383640","doi":"https://doi.org/10.1109/ieeeconf49454.2021.9382693","mag":"3149383640"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf49454.2021.9382693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf49454.2021.9382693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/SICE International Symposium on System Integration (SII)","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/A5010068577","display_name":"Hanlin Niu","orcid":"https://orcid.org/0000-0003-0457-0871"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Hanlin Niu","raw_affiliation_strings":["the Department of Electrical & Electronic Engineering, The University of Manchester, Manchester, UK","Electronic Engineering, The University of Manchester, Manchester, UK","the Department of Electrical &amp"],"affiliations":[{"raw_affiliation_string":"the Department of Electrical & Electronic Engineering, The University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]},{"raw_affiliation_string":"Electronic Engineering, The University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]},{"raw_affiliation_string":"the Department of Electrical &amp","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068175770","display_name":"Ze Ji","orcid":"https://orcid.org/0000-0002-8968-9902"},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ze Ji","raw_affiliation_strings":["School of Engineering, Cardiff University, Cardiff, UK"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Cardiff University, Cardiff, UK","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005614248","display_name":"Farshad Arvin","orcid":"https://orcid.org/0000-0001-7950-3193"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Farshad Arvin","raw_affiliation_strings":["the Department of Electrical & Electronic Engineering, The University of Manchester, Manchester, UK","Electronic Engineering, The University of Manchester, Manchester, UK","the Department of Electrical &amp"],"affiliations":[{"raw_affiliation_string":"the Department of Electrical & Electronic Engineering, The University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]},{"raw_affiliation_string":"Electronic Engineering, The University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]},{"raw_affiliation_string":"the Department of Electrical &amp","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011590665","display_name":"Barry Lennox","orcid":"https://orcid.org/0000-0003-0905-8324"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Barry Lennox","raw_affiliation_strings":["the Department of Electrical & Electronic Engineering, The University of Manchester, Manchester, UK","the Department of Electrical &amp","Electronic Engineering, The University of Manchester, Manchester, UK"],"affiliations":[{"raw_affiliation_string":"the Department of Electrical & Electronic Engineering, The University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]},{"raw_affiliation_string":"the Department of Electrical &amp","institution_ids":[]},{"raw_affiliation_string":"Electronic Engineering, The University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055149475","display_name":"Hujun Yin","orcid":"https://orcid.org/0000-0002-9198-5401"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hujun Yin","raw_affiliation_strings":["the Department of Electrical & Electronic Engineering, The University of Manchester, Manchester, UK","the Department of Electrical &amp","Electronic Engineering, The University of Manchester, Manchester, UK"],"affiliations":[{"raw_affiliation_string":"the Department of Electrical & Electronic Engineering, The University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]},{"raw_affiliation_string":"the Department of Electrical &amp","institution_ids":[]},{"raw_affiliation_string":"Electronic Engineering, The University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024320684","display_name":"Joaqu\u00edn Carrasco","orcid":"https://orcid.org/0000-0002-7499-6408"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joaquin Carrasco","raw_affiliation_strings":["the Department of Electrical & Electronic Engineering, The University of Manchester, Manchester, UK","the Department of Electrical &amp","Electronic Engineering, The University of Manchester, Manchester, UK"],"affiliations":[{"raw_affiliation_string":"the Department of Electrical & Electronic Engineering, The University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]},{"raw_affiliation_string":"the Department of Electrical &amp","institution_ids":[]},{"raw_affiliation_string":"Electronic Engineering, The University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5010068577"],"corresponding_institution_ids":["https://openalex.org/I28407311"],"apc_list":null,"apc_paid":null,"fwci":4.1064,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.94600915,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"144","last_page":"149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9980000257492065,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9846000075340271,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7397893667221069},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7323974370956421},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.6995683908462524},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6590191125869751},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.5817039012908936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47524213790893555},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.40609076619148254},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.4007340371608734},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.35788655281066895},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34122568368911743}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7397893667221069},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7323974370956421},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.6995683908462524},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6590191125869751},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.5817039012908936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47524213790893555},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.40609076619148254},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.4007340371608734},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.35788655281066895},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34122568368911743},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ieeeconf49454.2021.9382693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf49454.2021.9382693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/SICE International Symposium on System Integration (SII)","raw_type":"proceedings-article"},{"id":"pmh:oai:https://orca.cardiff.ac.uk:138349","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401195","display_name":"ORCA Online Research @Cardiff (Cardiff University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79510175","host_organization_name":"Cardiff University","host_organization_lineage":["https://openalex.org/I79510175"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5391253235","display_name":null,"funder_award_id":"EP/S03286X/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1923344279","https://openalex.org/W2604216058","https://openalex.org/W2741122588","https://openalex.org/W2890001928","https://openalex.org/W2891234582","https://openalex.org/W2908713228","https://openalex.org/W2908846937","https://openalex.org/W2909564046","https://openalex.org/W2909710443","https://openalex.org/W2910367420","https://openalex.org/W2963019567","https://openalex.org/W2963428623","https://openalex.org/W2963821308","https://openalex.org/W2964319688","https://openalex.org/W2967847744","https://openalex.org/W6631190155","https://openalex.org/W6742461812"],"related_works":["https://openalex.org/W2756881483","https://openalex.org/W2963821308","https://openalex.org/W2742483371","https://openalex.org/W2123582700","https://openalex.org/W2047788632","https://openalex.org/W2123436641","https://openalex.org/W2965672371","https://openalex.org/W2118648141","https://openalex.org/W2151698195","https://openalex.org/W3108596256"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,31,41,71,113,120,214],"sensor-level":[4],"mapless":[5],"collision":[6,180],"avoidance":[7],"algorithm":[8,99],"for":[9,221],"use":[10],"in":[11,26,106,158,165,181,192,217],"mobile":[12,68],"robots":[13],"that":[14,131,164,227],"map":[15],"raw":[16],"sensor":[17],"data":[18,49,86,89],"to":[19,39,43,60,65,70,124],"linear":[20],"and":[21,24,50,73,87,100,117,161,186,255],"angular":[22],"velocities":[23],"navigate":[25],"an":[27],"unknown":[28],"environment":[29,220],"without":[30,243],"map.":[32],"An":[33],"efficient":[34],"training":[35,101,146,190],"strategy":[36,102],"is":[37,58,76],"proposed":[38,98,133,176,207],"allow":[40,61],"robot":[42,69,216],"learn":[44],"from":[45],"both":[46],"human":[47,63,74,84],"experience":[48,94],"self-exploratory":[51],"data.":[52],"A":[53],"game":[54],"format":[55],"simulation":[56,233],"framework":[57],"designed":[59],"the":[62,67,80,126,132,136,145,150,169,175,193,218,228,232,240],"player":[64,85],"tele-operate":[66],"goal":[72],"action":[75],"also":[77,200,210],"scored":[78],"using":[79,92,141],"reward":[81,140],"function.":[82],"Both":[83],"self-playing":[88],"are":[90,257],"sampled":[91],"prioritized":[93],"replay":[95],"algorithm.":[96],"The":[97,198,206,253],"have":[103],"been":[104,211],"evaluated":[105],"two":[107,194],"different":[108],"experimental":[109],"configurations:":[110],"Environment":[111,118,159,166],"1,":[112],"simulated":[114,121],"cluttered":[115],"environment,":[116,123],"2,":[119],"corridor":[122],"investigate":[125],"performance.":[127],"It":[128],"was":[129],"demonstrated":[130],"method":[134,157,177,199,208],"achieved":[135,178],"same":[137],"level":[138],"of":[139,144,163,171,189],"only":[142],"16%":[143],"steps":[147],"required":[148],"by":[149],"standard":[151],"Deep":[152],"Deterministic":[153],"Policy":[154],"Gradient":[155],"(DDPG)":[156],"1":[160],"20%":[162],"2.":[167],"In":[168],"evaluation":[170],"20":[172],"random":[173],"missions,":[174],"no":[179],"less":[182],"than":[183,204,251],"2":[184],"h":[185,188],"2.5":[187],"time":[191],"Gazebo":[195],"environments":[196],"respectively.":[197],"generated":[201],"smoother":[202],"trajectories":[203],"DDPG.":[205,252],"has":[209],"implemented":[212],"on":[213],"real":[215],"real-world":[219,241],"performance":[222],"evaluation.":[223],"We":[224],"can":[225,235],"confirm":[226],"trained":[229],"model":[230],"with":[231],"software":[234],"be":[236],"directly":[237],"applied":[238],"into":[239],"scenario":[242],"further":[244,246],"fine-tuning,":[245],"demonstrating":[247],"its":[248],"higher":[249],"robustness":[250],"video":[254],"code":[256],"available:":[258],"https://youtu.be/BmwxevgsdGc":[259],"https://github.com/hanlinniu/turtlebot3_ddpg_collision_avoidance":[260]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":4}],"updated_date":"2026-01-16T23:16:36.188383","created_date":"2025-10-10T00:00:00"}