{"id":"https://openalex.org/W2963780790","doi":"https://doi.org/10.1109/iros.2018.8593702","title":"Deep Reinforcement Learning to Acquire Navigation Skills for Wheel-Legged Robots in Complex Environments","display_name":"Deep Reinforcement Learning to Acquire Navigation Skills for Wheel-Legged Robots in Complex Environments","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2963780790","doi":"https://doi.org/10.1109/iros.2018.8593702","mag":"2963780790"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2018.8593702","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8593702","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5119012082","display_name":"Xi Chen","orcid":"https://orcid.org/0000-0002-0588-6176"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xi Chen","raw_affiliation_strings":["School of Reliability and Systems Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Reliability and Systems Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038342432","display_name":"Ali Ghadirzadeh","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ali Ghadirzadeh","raw_affiliation_strings":["School of Reliability and Systems Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Reliability and Systems Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068942914","display_name":"John Folkesson","orcid":"https://orcid.org/0000-0002-7796-1438"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"John Folkesson","raw_affiliation_strings":["School of Reliability and Systems Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Reliability and Systems Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082269387","display_name":"M\u00e5rten Bj\u00f6rkman","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Marten Bjorkman","raw_affiliation_strings":["School of Reliability and Systems Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Reliability and Systems Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028082686","display_name":"Patric Jensfelt","orcid":"https://orcid.org/0000-0002-1170-7162"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Patric Jensfelt","raw_affiliation_strings":["School of Reliability and Systems Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Reliability and Systems Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5119012082"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":5.0494,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.96275105,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3110","last_page":"3116"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.9983999729156494,"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":0.881460428237915},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7281710505485535},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6177058815956116},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6033111810684204},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5619609951972961},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.5577479004859924},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.49341240525245667},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.46340227127075195},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3826054334640503},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37852954864501953},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3266298174858093}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.881460428237915},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7281710505485535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6177058815956116},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6033111810684204},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5619609951972961},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.5577479004859924},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.49341240525245667},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.46340227127075195},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3826054334640503},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37852954864501953},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3266298174858093},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros.2018.8593702","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8593702","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1771410628","https://openalex.org/W2082511574","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2173248099","https://openalex.org/W2460299708","https://openalex.org/W2534060593","https://openalex.org/W2592538810","https://openalex.org/W2605102758","https://openalex.org/W2726187156","https://openalex.org/W2736601468","https://openalex.org/W2739330054","https://openalex.org/W2766447205","https://openalex.org/W2962899390","https://openalex.org/W2963428623","https://openalex.org/W2963634205","https://openalex.org/W2963864421","https://openalex.org/W2964001908","https://openalex.org/W2964006217","https://openalex.org/W2964043796","https://openalex.org/W2964161785","https://openalex.org/W2964214518","https://openalex.org/W3101442004","https://openalex.org/W4294578467","https://openalex.org/W4300799055","https://openalex.org/W6638018090","https://openalex.org/W6639949747","https://openalex.org/W6682849425","https://openalex.org/W6692846177","https://openalex.org/W6740801417"],"related_works":["https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W2643884694","https://openalex.org/W2165180011","https://openalex.org/W4220829754","https://openalex.org/W3165944253","https://openalex.org/W2351343564","https://openalex.org/W2170052867"],"abstract_inverted_index":{"Mobile":[0],"robot":[1],"navigation":[2,51,84,94],"in":[3,37,117],"complex":[4],"and":[5,29,88,128],"dynamic":[6],"environments":[7],"is":[8],"a":[9,42,72,90,99,114],"challenging":[10],"but":[11],"important":[12],"problem.":[13],"Reinforcement":[14],"learning":[15,87],"approaches":[16],"fail":[17],"to":[18,24,45,49,66,69,71,80,103],"solve":[19],"these":[20],"tasks":[21],"efficiently":[22],"due":[23],"reward":[25],"sparsities,":[26],"temporal":[27],"complexities":[28],"high-dimensionality":[30],"of":[31,92,107,119,132],"sensorimotor":[32],"spaces":[33],"which":[34],"are":[35],"inherent":[36],"such":[38],"problems.":[39],"We":[40,78,96,111],"present":[41],"novel":[43],"approach":[44],"train":[46],"action":[47],"policies":[48],"acquire":[50,81],"skills":[52],"for":[53],"wheel-legged":[54],"robots":[55],"using":[56],"deep":[57],"reinforcement":[58],"learning.":[59],"The":[60],"policy":[61],"maps":[62],"height-map":[63],"image":[64],"observations":[65],"motor":[67],"commands":[68],"navigate":[70],"target":[73],"position":[74],"while":[75],"avoiding":[76],"obstacles.":[77],"propose":[79],"the":[82,105,108,130,133],"multifaceted":[83],"skill":[85],"by":[86],"exploiting":[89],"number":[91],"manageable":[93],"behaviors.":[95],"also":[97,129],"introduce":[98],"domain":[100],"randomization":[101],"technique":[102],"improve":[104],"versatility":[106],"training":[109],"samples.":[110],"demonstrate":[112],"experimentally":[113],"significant":[115],"improvement":[116],"terms":[118],"data-efficiency,":[120],"success":[121],"rate,":[122],"robustness":[123],"against":[124],"irrelevant":[125],"sensory":[126],"data,":[127],"quality":[131],"maneuver":[134],"skills.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}