{"id":"https://openalex.org/W4309675225","doi":"https://doi.org/10.1109/smc53654.2022.9945504","title":"Motion Planning and Obstacle Avoidance for Robot Manipulators Using Model Predictive Control-based Reinforcement Learning","display_name":"Motion Planning and Obstacle Avoidance for Robot Manipulators Using Model Predictive Control-based Reinforcement Learning","publication_year":2022,"publication_date":"2022-10-09","ids":{"openalex":"https://openalex.org/W4309675225","doi":"https://doi.org/10.1109/smc53654.2022.9945504"},"language":"en","primary_location":{"id":"doi:10.1109/smc53654.2022.9945504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc53654.2022.9945504","pdf_url":null,"source":{"id":"https://openalex.org/S4363607746","display_name":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5071020268","display_name":"Adel Baselizadeh","orcid":"https://orcid.org/0009-0005-7561-8889"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Adel Baselizadeh","raw_affiliation_strings":["University of Oslo,Department of Informatics,Oslo,Norway","Department of Informatics, University of Oslo, Oslo, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oslo,Department of Informatics,Oslo,Norway","institution_ids":["https://openalex.org/I184942183"]},{"raw_affiliation_string":"Department of Informatics, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061869177","display_name":"Weria Khaksar","orcid":"https://orcid.org/0000-0002-6400-3150"},"institutions":[{"id":"https://openalex.org/I54108979","display_name":"Norwegian University of Life Sciences","ror":"https://ror.org/04a1mvv97","country_code":"NO","type":"education","lineage":["https://openalex.org/I54108979"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Weria Khaksar","raw_affiliation_strings":["Norwegian University of Life Sciences,Faculty of Science and Technology,Ås,Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Norwegian University of Life Sciences,Faculty of Science and Technology,Ås,Norway","institution_ids":["https://openalex.org/I54108979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071144214","display_name":"Jim T\u00f8rresen","orcid":"https://orcid.org/0000-0003-0556-0288"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Jim Torresen","raw_affiliation_strings":["University of Oslo,Department of Informatics and RITMO Centre for Interdisciplinary Studies in Rhythm, Time and Motion,Oslo,Norway","Department of Informatics and RITMO Centre for Interdisciplinary Studies in Rhythm, Time and Motion, University of Oslo, Oslo, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oslo,Department of Informatics and RITMO Centre for Interdisciplinary Studies in Rhythm, Time and Motion,Oslo,Norway","institution_ids":["https://openalex.org/I184942183"]},{"raw_affiliation_string":"Department of Informatics and RITMO Centre for Interdisciplinary Studies in Rhythm, Time and Motion, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9343,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.76999735,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1584","last_page":"1591"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9940999746322632,"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":0.9940999746322632,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9819999933242798,"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/T11663","display_name":"Viral Infectious Diseases and Gene Expression in Insects","score":0.9692999720573425,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.7561355829238892},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7300972938537598},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.6760683059692383},{"id":"https://openalex.org/keywords/workspace","display_name":"Workspace","score":0.6614549160003662},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.6211960315704346},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5464687347412109},{"id":"https://openalex.org/keywords/robot-end-effector","display_name":"Robot end effector","score":0.5139421820640564},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.5107824802398682},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4720659554004669},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.46076086163520813},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3878628611564636},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3249412178993225},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2851036489009857},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.21384114027023315},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.19436585903167725}],"concepts":[{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.7561355829238892},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7300972938537598},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.6760683059692383},{"id":"https://openalex.org/C58581272","wikidata":"https://www.wikidata.org/wiki/Q12741163","display_name":"Workspace","level":3,"score":0.6614549160003662},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6211960315704346},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5464687347412109},{"id":"https://openalex.org/C8652668","wikidata":"https://www.wikidata.org/wiki/Q1340324","display_name":"Robot end effector","level":3,"score":0.5139421820640564},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.5107824802398682},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4720659554004669},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.46076086163520813},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3878628611564636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3249412178993225},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2851036489009857},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.21384114027023315},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.19436585903167725},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc53654.2022.9945504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc53654.2022.9945504","pdf_url":null,"source":{"id":"https://openalex.org/S4363607746","display_name":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6299999952316284,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W41554520","https://openalex.org/W161404398","https://openalex.org/W1971984830","https://openalex.org/W1982153978","https://openalex.org/W2101272984","https://openalex.org/W2133741402","https://openalex.org/W2153646384","https://openalex.org/W2576331223","https://openalex.org/W2586643027","https://openalex.org/W2618852836","https://openalex.org/W2734907804","https://openalex.org/W2783651432","https://openalex.org/W2788862220","https://openalex.org/W2822752092","https://openalex.org/W2883539312","https://openalex.org/W2902067689","https://openalex.org/W2930426397","https://openalex.org/W2963945659","https://openalex.org/W2992833799","https://openalex.org/W3010993956","https://openalex.org/W3015423984","https://openalex.org/W3195968524","https://openalex.org/W4200473109","https://openalex.org/W4225603049","https://openalex.org/W4237344756","https://openalex.org/W4246923680","https://openalex.org/W4294555834","https://openalex.org/W6738483526"],"related_works":["https://openalex.org/W3034420532","https://openalex.org/W2533172987","https://openalex.org/W1995214917","https://openalex.org/W3038610377","https://openalex.org/W4285817208","https://openalex.org/W4297833835","https://openalex.org/W1998108039","https://openalex.org/W2562391972","https://openalex.org/W3216202865","https://openalex.org/W1527317423"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,39,102,107,143],"Nonlinear":[4],"Model":[5],"Predictive":[6],"Control-based":[7],"Reinforcement":[8],"Learning":[9],"(NMPC-based":[10],"RL)":[11],"framework":[12,168],"for":[13,26,47],"robot":[14,27,108],"manipulators.":[15],"The":[16,34,71,96],"controller":[17,97,134],"is":[18,157],"developed":[19],"to":[20,86,101,115,146,178],"address":[21],"the":[22,30,48,57,60,66,76,81,84,88,92,117,125,132,138,151,154,160,164,171,174],"motion":[23],"planning":[24],"problem":[25],"manipulators":[28],"in":[29,124,141],"presence":[31],"of":[32,83,91,106,163,173],"obstacles.":[33,155],"proposed":[35,133,165],"control":[36,94,137,175],"scheme":[37],"includes":[38],"parametrized":[40],"NMPC":[41,58,85],"structure":[42],"used":[43],"as":[44,145],"an":[45],"approximator":[46],"RL":[49,167],"framework\u2019s":[50],"value":[51],"function":[52],"and":[53,65,153],"action-value":[54],"function.":[55],"In":[56],"structure,":[59],"cost":[61],"function,":[62],"system":[63],"constraints,":[64],"manipulator\u2019s":[67],"model":[68,105],"are":[69,123],"parameterized.":[70],"Q-Learning":[72],"algorithm":[73],"based":[74],"on":[75],"Temporal":[77],"Difference":[78],"method":[79],"adjusts":[80],"parameters":[82],"increase":[87],"closed-loop":[89],"performance":[90],"whole":[93],"scheme.":[95],"has":[98],"been":[99],"applied":[100],"6-degrees-of-freedom":[103],"(DoF)":[104],"manipulator,":[109],"aimed":[110],"at":[111],"moving":[112],"its":[113],"end-effector":[114],"reach":[116],"desired":[118],"pose":[119,140],"when":[120],"static":[121],"obstacles":[122],"robot\u2019s":[126],"workspace.":[127],"Numerical":[128],"simulations":[129],"demonstrate":[130],"that":[131,159],"can":[135,169],"effectively":[136],"end-effector\u2019s":[139],"such":[142],"way":[144],"avoid":[147],"any":[148],"collisions":[149],"between":[150],"manipulator":[152],"It":[156],"shown":[158],"learning":[161],"capability":[162],"NMPC-based":[166],"enhance":[170],"efficiency":[172],"loop":[176],"up":[177],"21%.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}