{"id":"https://openalex.org/W4405937736","doi":"https://doi.org/10.1109/iccais63750.2024.10814522","title":"Reinforcement Learning Timing Optimization for Safe Robot Navigation in Dynamic Environments","display_name":"Reinforcement Learning Timing Optimization for Safe Robot Navigation in Dynamic Environments","publication_year":2024,"publication_date":"2024-11-26","ids":{"openalex":"https://openalex.org/W4405937736","doi":"https://doi.org/10.1109/iccais63750.2024.10814522"},"language":"en","primary_location":{"id":"doi:10.1109/iccais63750.2024.10814522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccais63750.2024.10814522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 13th International Conference on Control, Automation and Information Sciences (ICCAIS)","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/A5037663704","display_name":"X. K. Zhou","orcid":"https://orcid.org/0000-0002-5055-9596"},"institutions":[{"id":"https://openalex.org/I21741975","display_name":"Suzhou University of Technology","ror":"https://ror.org/05g6ben79","country_code":"CN","type":"education","lineage":["https://openalex.org/I21741975"]},{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Zhou","raw_affiliation_strings":["School of Mechanical Engineering; School of Automation, Changshu Institute of Technology; Nanjing University of Science and Technology,Suzhou, Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering; School of Automation, Changshu Institute of Technology; Nanjing University of Science and Technology,Suzhou, Nanjing,China","institution_ids":["https://openalex.org/I21741975","https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038564706","display_name":"Benlian Xu","orcid":"https://orcid.org/0000-0002-6709-6583"},"institutions":[{"id":"https://openalex.org/I308837","display_name":"Suzhou University of Science and Technology","ror":"https://ror.org/04en8wb91","country_code":"CN","type":"education","lineage":["https://openalex.org/I308837"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Benlian Xu","raw_affiliation_strings":["School of Electronic and Information Engineering, Suzhou University of Science and Technology,Suzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Suzhou University of Science and Technology,Suzhou,China","institution_ids":["https://openalex.org/I308837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017792564","display_name":"Mingli Lu","orcid":"https://orcid.org/0000-0002-8668-4495"},"institutions":[{"id":"https://openalex.org/I21741975","display_name":"Suzhou University of Technology","ror":"https://ror.org/05g6ben79","country_code":"CN","type":"education","lineage":["https://openalex.org/I21741975"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingli Lu","raw_affiliation_strings":["School of Electrical and Automatic Engineering, Changshu Institute of Technology,Suzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Automatic Engineering, Changshu Institute of Technology,Suzhou,China","institution_ids":["https://openalex.org/I21741975"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100691319","display_name":"Jun Li","orcid":"https://orcid.org/0000-0002-6239-2922"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Li","raw_affiliation_strings":["School of Automation, Nanjing University of Science and Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Nanjing University of Science and Technology,Nanjing,China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22889262,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9919000267982483,"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"}},"topics":[{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9919000267982483,"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/T10933","display_name":"Real-Time Systems Scheduling","score":0.9753000140190125,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9034000039100647,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8135448694229126},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.706255316734314},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5768455266952515},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4886210560798645},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.45134350657463074},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.40694183111190796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4024512767791748},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.3517773747444153}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8135448694229126},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.706255316734314},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5768455266952515},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4886210560798645},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.45134350657463074},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.40694183111190796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4024512767791748},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3517773747444153}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccais63750.2024.10814522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccais63750.2024.10814522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 13th International Conference on Control, Automation and Information Sciences (ICCAIS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1969483458","https://openalex.org/W1971086298","https://openalex.org/W2105078254","https://openalex.org/W2130178506","https://openalex.org/W2134491302","https://openalex.org/W2146881125","https://openalex.org/W2211552581","https://openalex.org/W2524241275","https://openalex.org/W2607500080","https://openalex.org/W2963105220","https://openalex.org/W2963809389","https://openalex.org/W2971481292","https://openalex.org/W4214717370","https://openalex.org/W4286206354","https://openalex.org/W4389257093","https://openalex.org/W4390693582","https://openalex.org/W4396599679","https://openalex.org/W6639175102","https://openalex.org/W6675423570","https://openalex.org/W6682367392","https://openalex.org/W6735677848"],"related_works":["https://openalex.org/W2122871747","https://openalex.org/W3114279067","https://openalex.org/W2930863966","https://openalex.org/W2581059419","https://openalex.org/W2401800146","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W1603042966","https://openalex.org/W2612216462"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,22,31,67,87,104,108,111,123],"theoretically":[2],"needs":[3],"to":[4,39,44,60,119,133,135],"keep":[5],"re-learning":[6,54,72,153],"new":[7,34],"optimal":[8,84,152],"policies":[9],"for":[10],"autonomous":[11],"robot":[12,50],"navigation":[13],"when":[14,38,42],"the":[15,26,48,66,78,83,100,103,107,114,122,126,173],"environment":[16,136],"is":[17,23,131],"dynamic.":[18],"Given":[19],"no":[20],"reinforcement":[21,30],"failure-free,":[24],"however,":[25],"practical":[27],"deployment":[28],"of":[29,86,95,172],"raises":[32],"a":[33,70,93],"but":[35],"fundamental":[36],"question:":[37],"re-learn":[40],"and":[41,62,106,121,138,164,175],"not":[43],"be":[45],"safer":[46],"in":[47,65],"long-term":[49],"navigation?":[51],"An":[52],"early":[53,174],"could":[55],"encounter":[56],"more":[57],"failures":[58,75,158],"due":[59],"unnecessary":[61],"unsafe":[63],"explorations":[64],"process":[68],"while":[69],"late":[71,176],"cannot":[73],"avoid":[74],"caused":[76],"by":[77],"deteriorating":[79],"policy.":[80],"To":[81],"determine":[82],"timing":[85,154],"with":[88,117,155,161],"minimal":[89],"failures,":[90],"we":[91],"propose":[92],"Value":[94],"Learning":[96],"approach":[97,148],"that":[98,146],"maximizes":[99],"difference":[101],"between":[102],"gain":[105,112],"cost.":[109],"The":[110],"estimates":[113],"performance":[115],"improvement":[116],"respect":[118],"time":[120],"cost":[124],"evaluates":[125],"learning-induced":[127],"failure":[128],"risk,":[129],"which":[130,167],"assumed":[132],"relate":[134],"changes":[137],"exploration":[139],"strategies.":[140],"A":[141],"dynamic":[142],"maze":[143],"experiment":[144],"validates":[145],"our":[147],"can":[149],"find":[150],"an":[151],"significantly":[156],"fewer":[157],"if":[159],"compared":[160],"\u201calways":[162],"learning\u201d":[163],"\u201cno":[165],"learning\u201d,":[166],"are":[168],"two":[169],"representative":[170],"cases":[171],"learning.":[177]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}