{"id":"https://openalex.org/W3027805788","doi":"https://doi.org/10.1109/cis-ram47153.2019.9095849","title":"Trajectory-Tracking Control of Robotic System via Proximal Policy Optimization","display_name":"Trajectory-Tracking Control of Robotic System via Proximal Policy Optimization","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3027805788","doi":"https://doi.org/10.1109/cis-ram47153.2019.9095849","mag":"3027805788"},"language":"en","primary_location":{"id":"doi:10.1109/cis-ram47153.2019.9095849","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cis-ram47153.2019.9095849","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE Conference on Robotics, Automation and Mechatronics (RAM)","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/A5070751669","display_name":"Shansi Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Shansi Zhang","raw_affiliation_strings":["School of Electrical & Electronic Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Electrical & Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088773457","display_name":"Yipeng Pang","orcid":"https://orcid.org/0000-0002-6488-9991"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yipeng Pang","raw_affiliation_strings":["School of Electrical & Electronic Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Electrical & Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050664552","display_name":"Guoqiang Hu","orcid":"https://orcid.org/0000-0002-8618-5581"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Guoqiang Hu","raw_affiliation_strings":["School of Electrical & Electronic Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Electrical & Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5070751669"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.9801,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.82976118,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"518","issue":null,"first_page":"380","last_page":"385"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.996399998664856,"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"}},{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.984499990940094,"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/initialization","display_name":"Initialization","score":0.9069292545318604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7997620105743408},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.7720358967781067},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.5764744281768799},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5291339159011841},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5287648439407349},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5205262899398804},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5195532441139221},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.434490829706192},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16735520958900452}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.9069292545318604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7997620105743408},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7720358967781067},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.5764744281768799},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5291339159011841},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5287648439407349},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5205262899398804},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5195532441139221},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.434490829706192},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16735520958900452},{"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/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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cis-ram47153.2019.9095849","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cis-ram47153.2019.9095849","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE Conference on Robotics, Automation and Mechatronics (RAM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1658008008","https://openalex.org/W1757796397","https://openalex.org/W1771410628","https://openalex.org/W2064675550","https://openalex.org/W2121092017","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2165150801","https://openalex.org/W2173248099","https://openalex.org/W2173564293","https://openalex.org/W2298546714","https://openalex.org/W2303006894","https://openalex.org/W2726187156","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2786036274","https://openalex.org/W2786928559","https://openalex.org/W2787613197","https://openalex.org/W2796290181","https://openalex.org/W2949980113","https://openalex.org/W2951799221","https://openalex.org/W2962938178","https://openalex.org/W2963184621","https://openalex.org/W2963296584","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2964291307","https://openalex.org/W3104515094","https://openalex.org/W4293542549","https://openalex.org/W4297797010","https://openalex.org/W4298857966","https://openalex.org/W4302570325","https://openalex.org/W6627932998","https://openalex.org/W6636881020","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6677939520","https://openalex.org/W6684205842","https://openalex.org/W6685444567","https://openalex.org/W6692846177","https://openalex.org/W6740222838","https://openalex.org/W6741002519","https://openalex.org/W6748554570","https://openalex.org/W6748638692"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W2903025760","https://openalex.org/W2373557848","https://openalex.org/W2088970451","https://openalex.org/W2122871747","https://openalex.org/W2002488624","https://openalex.org/W2157008402","https://openalex.org/W2592302855","https://openalex.org/W3114279067"],"abstract_inverted_index":{"This":[0],"paper":[1],"aims":[2],"to":[3,32,59,63,77,85,121,133,142],"solve":[4,103],"the":[5,34,41,47,56,61,67,79,87,96,104,123,135,144,147,161],"trajectory":[6],"tracking":[7,162],"problem":[8,105],"of":[9,30,36,43,93,98,106,146],"manipulator":[10,124],"and":[11,39,81,83,90,117,125],"mobile":[12,126],"robot":[13,62,127],"by":[14],"using":[15],"proximal":[16],"policy":[17],"optimization":[18],"(PPO)":[19],"with":[20,113,128,157],"generalized":[21],"advantage":[22],"estimation":[23],"(GAE).":[24],"We":[25],"adopt":[26],"a":[27],"distributed":[28,155],"framework":[29],"PPO":[31,112,156],"improve":[33,160],"speed":[35],"sample":[37],"collection":[38],"reduce":[40],"correlation":[42],"transitions":[44],"when":[45],"updating":[46],"networks.":[48],"Random":[49],"reference":[50,68],"state":[51,89,92],"initialization":[52,97],"is":[53,119],"used":[54],"during":[55],"training":[57],"process":[58],"enable":[60],"learn":[64],"effectively":[65],"from":[66],"trajectory.":[69],"Additionaly,":[70],"we":[71],"introduce":[72],"Long":[73],"Short-term":[74],"Memory":[75],"(LSTM)":[76],"represent":[78],"actor":[80],"critic,":[82],"buffers":[84],"store":[86],"cell":[88],"hidden":[91],"LSTM":[94,109,118,158],"for":[95],"each":[99],"episode,":[100],"which":[101],"helps":[102],"inaccurate":[107],"inital":[108],"states.":[110],"Distributed":[111],"fully-connected":[114],"neural":[115],"networks":[116],"utilized":[120],"train":[122],"an":[129],"exponential":[130],"reward":[131],"function":[132],"track":[134],"given":[136],"trajectories.":[137],"Numerical":[138],"simulations":[139],"are":[140],"provided":[141],"demonstrate":[143],"effectiveness":[145],"proposed":[148],"method.":[149],"It":[150],"can":[151,159],"be":[152],"seen":[153],"that":[154],"performance.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}