{"id":"https://openalex.org/W4317242602","doi":"https://doi.org/10.1109/robio55434.2022.10011937","title":"Localisation-Safe Reinforcement Learning for Mapless Navigation","display_name":"Localisation-Safe Reinforcement Learning for Mapless Navigation","publication_year":2022,"publication_date":"2022-12-05","ids":{"openalex":"https://openalex.org/W4317242602","doi":"https://doi.org/10.1109/robio55434.2022.10011937"},"language":"en","primary_location":{"id":"doi:10.1109/robio55434.2022.10011937","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio55434.2022.10011937","pdf_url":null,"source":{"id":"https://openalex.org/S4363607789","display_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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/A5049338278","display_name":"Feiqiang Lin","orcid":"https://orcid.org/0000-0001-5528-0001"},"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":"Feiqiang Lin","raw_affiliation_strings":["School of Engineering, Cardiff University,Cardiff,UK","School of Engineering, Cardiff University, Cardiff, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering, Cardiff University,Cardiff,UK","institution_ids":["https://openalex.org/I79510175"]},{"raw_affiliation_string":"School of Engineering, Cardiff University, Cardiff, UK","institution_ids":["https://openalex.org/I79510175"]}]},{"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","School of Engineering, Cardiff University, Cardiff, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering, Cardiff University,Cardiff,UK","institution_ids":["https://openalex.org/I79510175"]},{"raw_affiliation_string":"School of Engineering, Cardiff University, Cardiff, UK","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066950886","display_name":"Changyun Wei","orcid":"https://orcid.org/0000-0002-5788-6573"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changyun Wei","raw_affiliation_strings":["College of Mechanical and Electrical Engineering, Hohai University,China","College of Mechanical and Electrical Engineering, Hohai University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mechanical and Electrical Engineering, Hohai University,China","institution_ids":["https://openalex.org/I163340411"]},{"raw_affiliation_string":"College of Mechanical and Electrical Engineering, Hohai University, China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101895660","display_name":"Raphael Grech","orcid":"https://orcid.org/0000-0002-9100-0633"},"institutions":[{"id":"https://openalex.org/I4210124032","display_name":"Spirent Communications (United Kingdom)","ror":"https://ror.org/02p5b1x56","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210124032"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Raphael Grech","raw_affiliation_strings":["Spirent Communications,Paignton,UK","Spirent Communications, Paignton, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Spirent Communications,Paignton,UK","institution_ids":["https://openalex.org/I4210124032"]},{"raw_affiliation_string":"Spirent Communications, Paignton, UK","institution_ids":["https://openalex.org/I4210124032"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4151,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.60477074,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1327","last_page":"1334"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9997000098228455,"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":0.9995999932289124,"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":0.7850695848464966},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.7618087530136108},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7604060769081116},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7033151388168335},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6892136931419373},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6464371085166931},{"id":"https://openalex.org/keywords/odometry","display_name":"Odometry","score":0.5741548538208008},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.48593130707740784},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.47314155101776123},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4388805627822876},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4272683560848236},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.40414202213287354},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.39694175124168396},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.29911401867866516},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.1958419382572174},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10816299915313721}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7850695848464966},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.7618087530136108},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7604060769081116},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7033151388168335},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6892136931419373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6464371085166931},{"id":"https://openalex.org/C49441653","wikidata":"https://www.wikidata.org/wiki/Q2014717","display_name":"Odometry","level":4,"score":0.5741548538208008},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.48593130707740784},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.47314155101776123},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4388805627822876},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4272683560848236},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.40414202213287354},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.39694175124168396},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.29911401867866516},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.1958419382572174},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10816299915313721},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/robio55434.2022.10011937","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio55434.2022.10011937","pdf_url":null,"source":{"id":"https://openalex.org/S4363607789","display_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"},{"id":"pmh:oai:https://orca.cardiff.ac.uk:153473","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":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1967740178","https://openalex.org/W2023259872","https://openalex.org/W2562788852","https://openalex.org/W2565555125","https://openalex.org/W2771880063","https://openalex.org/W2775496939","https://openalex.org/W2796447411","https://openalex.org/W2810957722","https://openalex.org/W2892378191","https://openalex.org/W2912063360","https://openalex.org/W2918849077","https://openalex.org/W2950872548","https://openalex.org/W2962730596","https://openalex.org/W2963129648","https://openalex.org/W2963428623","https://openalex.org/W2972350003","https://openalex.org/W2976792479","https://openalex.org/W3004264147","https://openalex.org/W3149383640","https://openalex.org/W3159400523","https://openalex.org/W3201759799","https://openalex.org/W3209772338","https://openalex.org/W4249898853","https://openalex.org/W4297795161","https://openalex.org/W6729556111","https://openalex.org/W6731334075","https://openalex.org/W6746951839","https://openalex.org/W6750185400"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W1589140671","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W3096874164","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2294884454","https://openalex.org/W2937181779","https://openalex.org/W2386410636"],"abstract_inverted_index":{"Most":[0],"reinforcement":[1],"learning":[2],"(RL)-based":[3],"works":[4],"for":[5,22,45,93],"mapless":[6,94],"point":[7],"goal":[8],"navigation":[9,95],"tasks":[10],"assume":[11],"the":[12,15,166],"availability":[13],"of":[14,157],"robot":[16,46,68,77],"ground-truth":[17],"poses,":[18],"which":[19,106],"is":[20],"unrealistic":[21],"real":[23],"world":[24],"applications.":[25],"In":[26],"this":[27,136],"work,":[28],"we":[29],"remove":[30],"such":[31,39,85],"an":[32],"assumption":[33],"and":[34,57,150,160],"deploy":[35],"observation-based":[36],"localisation":[37,86,116,148],"algorithms,":[38,50],"as":[40],"Lidar-based":[41],"or":[42,81,118],"visual":[43],"odometry,":[44],"self-pose":[47],"estimation.":[48],"These":[49],"despite":[51],"having":[52],"widely":[53],"achieved":[54],"promising":[55],"performance":[56],"being":[58],"robust":[59],"to":[60,66,109,141,164,176,183],"various":[61],"harsh":[62],"environments,":[63],"may":[64],"fail":[65],"track":[67],"locations":[69],"under":[70],"many":[71],"scenarios,":[72],"where":[73],"observations":[74],"perceived":[75],"along":[76],"trajectories":[78],"are":[79],"insufficient":[80],"ambiguous.":[82],"Hence,":[83],"using":[84],"algorithms":[87],"will":[88,99],"introduce":[89],"new":[90,102],"unstudied":[91],"problems":[92],"tasks.":[96],"This":[97,125],"work":[98],"propose":[100],"a":[101,112,138,151,169,177],"RL-based":[103],"algorithm,":[104],"with":[105],"robots":[107],"learn":[108],"navigate":[110],"in":[111,121,135,147],"way":[113],"that":[114,155],"prevents":[115],"failures":[117],"getting":[119],"trapped":[120],"local":[122,185],"minimum":[123],"regions.":[124],"ability":[126],"can":[127],"be":[128],"learned":[129],"by":[130],"deploying":[131],"two":[132],"techniques":[133],"suggested":[134],"work:":[137],"reward":[139],"metric":[140],"decide":[142],"punishment":[143],"on":[144],"behaviours":[145],"resulting":[146],"failures;":[149],"reconfigured":[152],"state":[153],"representation":[154],"consists":[156],"current":[158],"observation":[159],"history":[161],"trajectory":[162],"information":[163],"transfer":[165],"problem":[167],"from":[168],"partially":[170],"observable":[171],"Markov":[172,178],"decision":[173],"process":[174],"(POMDP)":[175],"Decision":[179],"Process":[180],"(MDP)":[181],"model":[182],"avoid":[184],"minimum.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}