{"id":"https://openalex.org/W4389665858","doi":"https://doi.org/10.1109/iros55552.2023.10342171","title":"Reinforcement Learning Based Multi-Layer Bayesian Control for Snake Robots in Cluttered Scenes","display_name":"Reinforcement Learning Based Multi-Layer Bayesian Control for Snake Robots in Cluttered Scenes","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389665858","doi":"https://doi.org/10.1109/iros55552.2023.10342171"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10342171","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iros55552.2023.10342171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5113325638","display_name":"Jessica Ziyu Qu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jessica Ziyu Qu","raw_affiliation_strings":["Canadian Academy,Kobe,Hyogo,Japan,658-0032"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Canadian Academy,Kobe,Hyogo,Japan,658-0032","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113069967","display_name":"William Ziming Qu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"William Ziming Qu","raw_affiliation_strings":["Canadian Academy,Kobe,Hyogo,Japan,658-0032"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Canadian Academy,Kobe,Hyogo,Japan,658-0032","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104063208","display_name":"Li Li","orcid":"https://orcid.org/0009-0006-7614-554X"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Li Li","raw_affiliation_strings":["Ritsumeikan University,Kusatsu,Shiga,Japan,525-8577"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ritsumeikan University,Kusatsu,Shiga,Japan,525-8577","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100669026","display_name":"Yuanyuan Jia","orcid":"https://orcid.org/0000-0001-9880-5090"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuanyuan Jia","raw_affiliation_strings":["Ritsumeikan University,Kusatsu,Shiga,Japan,525-8577"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ritsumeikan University,Kusatsu,Shiga,Japan,525-8577","institution_ids":["https://openalex.org/I135768898"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4702","last_page":"4708"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10653","display_name":"Robot Manipulation and Learning","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10868","display_name":"Soft Robotics and Applications","score":0.9923999905586243,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9725000262260437,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.738665759563446},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7361329793930054},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7060378193855286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6278431415557861},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5753918290138245},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.4621255099773407},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.4054705798625946},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35629791021347046}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.738665759563446},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7361329793930054},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7060378193855286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6278431415557861},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5753918290138245},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.4621255099773407},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.4054705798625946},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35629791021347046}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10342171","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iros55552.2023.10342171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W186521003","https://openalex.org/W644072891","https://openalex.org/W1573670163","https://openalex.org/W1739716134","https://openalex.org/W1964941426","https://openalex.org/W2043218551","https://openalex.org/W2082511574","https://openalex.org/W2108002878","https://openalex.org/W2530907443","https://openalex.org/W2912971983","https://openalex.org/W3100789280","https://openalex.org/W3103532359","https://openalex.org/W3130608495","https://openalex.org/W3132175036","https://openalex.org/W3182595669","https://openalex.org/W4388323202","https://openalex.org/W6617145748"],"related_works":["https://openalex.org/W2122871747","https://openalex.org/W3114279067","https://openalex.org/W2171912896","https://openalex.org/W1886477626","https://openalex.org/W2762381663","https://openalex.org/W4385196987","https://openalex.org/W1540467731","https://openalex.org/W218732962","https://openalex.org/W2538037439","https://openalex.org/W4317826762"],"abstract_inverted_index":{"The":[0,79],"majority":[1],"of":[2,81,129],"current":[3],"research":[4],"on":[5],"reinforcement":[6],"learning":[7,97],"(RL)":[8],"for":[9,17,46],"snake":[10,48,124],"robot":[11,25,49,111,125],"control":[12],"do":[13],"not":[14],"sufficiently":[15],"account":[16],"the":[18,24,96,130],"spatial":[19,108],"and":[20,55,75,88,113],"temporal":[21,114],"dependencies":[22],"within":[23],"or":[26],"its":[27,30],"interaction":[28],"with":[29,121,133],"environment":[31,82],"during":[32],"movement.":[33],"To":[34],"address":[35],"this":[36],"issue,":[37],"we":[38],"propose":[39],"an":[40,91],"RL":[41],"based":[42],"multi-layer":[43],"Bayesian":[44,68],"method":[45],"autonomous":[47],"control,":[50,72,74],"which":[51],"handles":[52],"challenging":[53,134],"scenarios":[54],"improves":[56],"navigation":[57],"efficiency.":[58],"There":[59],"are":[60],"three":[61],"major":[62],"contributions:":[63],"1)":[64],"An":[65],"innovative":[66],"hierarchical":[67],"framework":[69],"unifies":[70],"gait":[71],"locomotion":[73],"stimulus":[76,101],"reaction;":[77],"2)":[78],"dynamics":[80],"is":[83,104,136],"modeled":[84],"by":[85,90,106],"density":[86],"propagation":[87],"exploited":[89],"LSTM-based":[92],"agent":[93],"to":[94,138],"improve":[95],"process;":[98],"3)":[99],"A":[100],"reaction":[102],"model":[103],"derived":[105],"combining":[107],"correlation":[109],"among":[110],"modules":[112],"dependency":[115],"along":[116],"time":[117],"sequence.":[118],"Comparison":[119],"experiments":[120],"a":[122],"simulated":[123],"show":[126],"that":[127],"performance":[128],"proposed":[131],"approach":[132],"obstacles":[135],"superior":[137],"state-of-the-art":[139],"baseline.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}