{"id":"https://openalex.org/W3009018467","doi":"https://doi.org/10.1109/ssci44817.2019.9002834","title":"Using Reinforcement Learning to Attenuate for Stochasticity in Robot Navigation Controllers","display_name":"Using Reinforcement Learning to Attenuate for Stochasticity in Robot Navigation Controllers","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3009018467","doi":"https://doi.org/10.1109/ssci44817.2019.9002834","mag":"3009018467"},"language":"en","primary_location":{"id":"doi:10.1109/ssci44817.2019.9002834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci44817.2019.9002834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-02324129","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055838954","display_name":"James B. Gillespie","orcid":"https://orcid.org/0000-0003-2721-8854"},"institutions":[{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"James Gillespie","raw_affiliation_strings":["Intelligent Systems Research Centre, Ulster University, Derry, Northern Ireland","Faculty of Computing and Engineering [University of Ulster] (St James' House\r\n10 Rosebery Avenue\r\nHolborn\r\nLondon\r\nEC1R 4TF - United Kingdom)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Systems Research Centre, Ulster University, Derry, Northern Ireland","institution_ids":["https://openalex.org/I138801177"]},{"raw_affiliation_string":"Faculty of Computing and Engineering [University of Ulster] (St James' House\r\n10 Rosebery Avenue\r\nHolborn\r\nLondon\r\nEC1R 4TF - United Kingdom)","institution_ids":["https://openalex.org/I138801177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074968710","display_name":"I\u00f1aki Ra\u00f1\u00f3","orcid":"https://orcid.org/0000-0002-0461-0258"},"institutions":[{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]},{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]}],"countries":["DK","GB"],"is_corresponding":false,"raw_author_name":"Inaki Rano","raw_affiliation_strings":["Embodied Systems for Robotics and Learning, University of Southern Denmark, Odnese, Denmark","Faculty of Computing and Engineering [University of Ulster] (St James' House\r\n10 Rosebery Avenue\r\nHolborn\r\nLondon\r\nEC1R 4TF - United Kingdom)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Embodied Systems for Robotics and Learning, University of Southern Denmark, Odnese, Denmark","institution_ids":["https://openalex.org/I177969490"]},{"raw_affiliation_string":"Faculty of Computing and Engineering [University of Ulster] (St James' House\r\n10 Rosebery Avenue\r\nHolborn\r\nLondon\r\nEC1R 4TF - United Kingdom)","institution_ids":["https://openalex.org/I138801177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012890130","display_name":"Nazmul Siddique","orcid":"https://orcid.org/0000-0002-0642-2357"},"institutions":[{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nazmul Siddique","raw_affiliation_strings":["Intelligent Systems Research Centre, Ulster University, Derry, Northern Ireland","Faculty of Computing and Engineering [University of Ulster] (St James' House\r\n10 Rosebery Avenue\r\nHolborn\r\nLondon\r\nEC1R 4TF - United Kingdom)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Systems Research Centre, Ulster University, Derry, Northern Ireland","institution_ids":["https://openalex.org/I138801177"]},{"raw_affiliation_string":"Faculty of Computing and Engineering [University of Ulster] (St James' House\r\n10 Rosebery Avenue\r\nHolborn\r\nLondon\r\nEC1R 4TF - United Kingdom)","institution_ids":["https://openalex.org/I138801177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037830755","display_name":"Jos\u00e9 Santos","orcid":"https://orcid.org/0000-0001-5604-1125"},"institutions":[{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]},{"id":"https://openalex.org/I4210156198","display_name":"OGT Amenity (Ireland)","ror":"https://ror.org/056k8rb32","country_code":"IE","type":"company","lineage":["https://openalex.org/I4210156198"]}],"countries":["GB","IE"],"is_corresponding":false,"raw_author_name":"Jose Santos","raw_affiliation_strings":["Pervasive Computing Research Group, Ulster University, Jordanstown, Northern Ireland","Faculty of Computing and Engineering [University of Ulster] (St James' House\r\n10 Rosebery Avenue\r\nHolborn\r\nLondon\r\nEC1R 4TF - United Kingdom)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pervasive Computing Research Group, Ulster University, Jordanstown, Northern Ireland","institution_ids":["https://openalex.org/I4210156198","https://openalex.org/I138801177"]},{"raw_affiliation_string":"Faculty of Computing and Engineering [University of Ulster] (St James' House\r\n10 Rosebery Avenue\r\nHolborn\r\nLondon\r\nEC1R 4TF - United Kingdom)","institution_ids":["https://openalex.org/I138801177"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016381589","display_name":"Mehdi Khamassi","orcid":"https://orcid.org/0000-0002-2515-1046"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210150358","display_name":"Institut Syst\u00e8mes Intelligents et de Robotique","ror":"https://ror.org/05neq8668","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mehdi Khamassi","raw_affiliation_strings":["Institute of Intelligent Systems and Robotics, Sorbonne Universit\u00e9, CNRS, Paris, France","ISIR - Institut des Syst\u00e8mes Intelligents et de Robotique (Sorbonne-Universit\u00e9, Boite courrier 173 4 Place JUSSIEU 75252 Paris cedex 05 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Intelligent Systems and Robotics, Sorbonne Universit\u00e9, CNRS, Paris, France","institution_ids":["https://openalex.org/I4210150358","https://openalex.org/I39804081","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"ISIR - Institut des Syst\u00e8mes Intelligents et de Robotique (Sorbonne-Universit\u00e9, Boite courrier 173 4 Place JUSSIEU 75252 Paris cedex 05 - France)","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I4210150358"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"62","issue":null,"first_page":"705","last_page":"713"},"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9945999979972839,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9879999756813049,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8377505540847778},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6474525928497314},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6228059530258179},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4922572672367096},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.47336432337760925},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.32862937450408936},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19672343134880066}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8377505540847778},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6474525928497314},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6228059530258179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4922572672367096},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.47336432337760925},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.32862937450408936},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19672343134880066}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ssci44817.2019.9002834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci44817.2019.9002834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"},{"id":"pmh:oai:sdu.dk:openaire_cris_publications/9406cd8b-3d14-4bef-ab5e-58800856a8eb","is_oa":false,"landing_page_url":"https://portal.findresearcher.sdu.dk/da/publications/9406cd8b-3d14-4bef-ab5e-58800856a8eb","pdf_url":null,"source":{"id":"https://openalex.org/S4306400423","display_name":"University of Southern Denmark Research Portal (University of Southern Denmark)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177969490","host_organization_name":"University of Southern Denmark","host_organization_lineage":["https://openalex.org/I177969490"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Gillespie, J, Rano, I, Siddique, N, Santos, J & Khamassi, M 2019, Using Reinforcement Learning to Attenuate for Stochasticity in Robot Navigation Controllers. in 2019 IEEE Symposium Series on Computational Intelligence (SSCI)., hal-02324129f, IEEE, pp. 705-713, The 2019 IEEE Symposium Series on Computational Intelligence, Xiamen, China, 06/12/2019. https://doi.org/10.1109/SSCI44817.2019.9002834","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:HAL:hal-02324129v1","is_oa":true,"landing_page_url":"https://hal.science/hal-02324129","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2019 IEEE Symposium Series on Computational Intelligence (SSCI 2019), Dec 2019, Xiamen, China. ⟨10.1109/SSCI44817.2019.9002834⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-02324129v1","is_oa":true,"landing_page_url":"https://hal.science/hal-02324129","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2019 IEEE Symposium Series on Computational Intelligence (SSCI 2019), Dec 2019, Xiamen, China. ⟨10.1109/SSCI44817.2019.9002834⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1481615754","https://openalex.org/W1514887169","https://openalex.org/W1522301498","https://openalex.org/W1535977321","https://openalex.org/W1949804828","https://openalex.org/W1969019211","https://openalex.org/W1977655452","https://openalex.org/W1993281582","https://openalex.org/W1995837155","https://openalex.org/W2010818426","https://openalex.org/W2037494070","https://openalex.org/W2053211384","https://openalex.org/W2063282235","https://openalex.org/W2073360733","https://openalex.org/W2087751887","https://openalex.org/W2089496638","https://openalex.org/W2119717200","https://openalex.org/W2135376858","https://openalex.org/W2160638931","https://openalex.org/W2462906003","https://openalex.org/W2529601334","https://openalex.org/W2603249661","https://openalex.org/W2736558185","https://openalex.org/W2964121744","https://openalex.org/W3022803644","https://openalex.org/W4243206564","https://openalex.org/W6628861149","https://openalex.org/W6630825244","https://openalex.org/W6631190155","https://openalex.org/W6718836005"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2122871747","https://openalex.org/W3114279067"],"abstract_inverted_index":{"Braitenberg":[0,86,122,149],"vehicles":[1,123],"are":[2,109,221],"bio-inspired":[3,91],"controllers":[4,83],"for":[5,84,96,148],"sensor-based":[6],"local":[7],"navigation":[8,48,187],"of":[9,68,93,103,114,181,189,226],"wheeled":[10,97],"robots":[11,98],"that":[12,121,130,143],"have":[13,119],"been":[14,78],"used":[15,56,79],"in":[16,135,160,183],"multiple":[17,117],"real":[18],"world":[19],"robotic":[20],"implementations.":[21],"The":[22,170],"common":[23],"approach":[24],"to":[25,37,44,80,111,177],"implement":[26],"such":[27],"non-linear":[28],"control":[29,132,214],"mechanisms":[30,133],"is":[31,173],"through":[32,223],"neural":[33,62,82,146,197,213],"networks":[34,70],"connecting":[35],"sensing":[36],"motor":[38],"action,":[39],"yet":[40],"tuning":[41],"the":[42,66,101,179,184,190,196,212,227],"weights":[43,67],"obtain":[45],"appropriate":[46],"closed-loop":[47,228],"behaviours":[49],"can":[50,152],"be":[51,153],"very":[52],"challenging.":[53],"Standard":[54],"approaches":[55],"hand":[57,206],"tuned":[58,207],"spiking":[59],"or":[60,64],"recurrent":[61],"networks,":[63],"learnt":[65,154,171,199],"feedforward":[69],"using":[71,155,200],"evolutionary":[72],"approaches.":[73],"Recently,":[74],"Reinforcement":[75,201],"Learning":[76,202],"has":[77],"learn":[81],"simulated":[85,191],"vehicle":[87,150],"3a":[88,151],"\u2013":[89,99],"a":[90,144,166,204,217],"model":[92],"target":[94],"seeking":[95],"under":[100],"assumption":[102],"noiseless":[104],"sensors.":[105],"Real":[106],"sensors,":[107],"however,":[108],"subject":[110],"different":[112],"levels":[113],"noise,":[115],"and":[116,137,175,209],"works":[118],"shown":[120],"work":[124,134],"even":[125],"on":[126],"outdoor":[127],"robots,":[128],"demonstrating":[129],"these":[131],"harsh":[136],"dynamic":[138],"environments.":[139],"This":[140],"paper":[141],"shows":[142],"robust":[145,174],"controller":[147,172,198,208],"policy":[156],"gradient":[157],"reinforcement":[158],"learning":[159],"scenarios":[161],"where":[162],"sensor":[163],"noise":[164,182],"plays":[165],"non":[167],"negligible":[168],"role.":[169],"tries":[176],"attenuate":[178],"effects":[180],"closed-":[185],"loop":[186],"behaviour":[188],"stochastic":[192,229],"vehicle.":[193],"We":[194],"compare":[195],"with":[203],"simple":[205],"show":[210],"how":[211],"mechanism":[215],"outperforms":[216],"na\u00efve":[218],"controller.":[219],"Results":[220],"illustrated":[222],"computer":[224],"simulations":[225],"system.":[230]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}