{"id":"https://openalex.org/W7129002908","doi":"https://doi.org/10.1109/lra.2026.3665076","title":"Learning Goal-Directed Rolling: Spherical Robot Point-to-Point Control Through Reinforcement Learning","display_name":"Learning Goal-Directed Rolling: Spherical Robot Point-to-Point Control Through Reinforcement Learning","publication_year":2026,"publication_date":"2026-02-16","ids":{"openalex":"https://openalex.org/W7129002908","doi":"https://doi.org/10.1109/lra.2026.3665076"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2026.3665076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3665076","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5121983869","display_name":"Junjie An","orcid":null},"institutions":[{"id":"https://openalex.org/I4391767838","display_name":"State Key Laboratory of Industrial Control Technology","ror":"https://ror.org/03a33a786","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767838","https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junjie An","raw_affiliation_strings":["State Key Laboratory of Industrial Control Technology, Institute of Cyber Systems and Control, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-5334-993X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Industrial Control Technology, Institute of Cyber Systems and Control, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4391767838"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124795740","display_name":"Runhua Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4391767838","display_name":"State Key Laboratory of Industrial Control Technology","ror":"https://ror.org/03a33a786","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767838","https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runhua Zhang","raw_affiliation_strings":["State Key Laboratory of Industrial Control Technology, Institute of Cyber Systems and Control, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0006-4842-7048","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Industrial Control Technology, Institute of Cyber Systems and Control, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4391767838"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376138","display_name":"Yifan Liu","orcid":"https://orcid.org/0000-0001-8866-6322"},"institutions":[{"id":"https://openalex.org/I4391767838","display_name":"State Key Laboratory of Industrial Control Technology","ror":"https://ror.org/03a33a786","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767838","https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Liu","raw_affiliation_strings":["State Key Laboratory of Industrial Control Technology, Institute of Cyber Systems and Control, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8866-6322","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Industrial Control Technology, Institute of Cyber Systems and Control, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4391767838"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126135317","display_name":"Xiaoqing Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I4391767838","display_name":"State Key Laboratory of Industrial Control Technology","ror":"https://ror.org/03a33a786","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767838","https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqing Guan","raw_affiliation_strings":["State Key Laboratory of Industrial Control Technology, Institute of Cyber Systems and Control, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3398-0415","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Industrial Control Technology, Institute of Cyber Systems and Control, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4391767838"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111293114","display_name":"You Wei Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4391767838","display_name":"State Key Laboratory of Industrial Control Technology","ror":"https://ror.org/03a33a786","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767838","https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"You Wang","raw_affiliation_strings":["State Key Laboratory of Industrial Control Technology, Institute of Cyber Systems and Control, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2766-1581","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Industrial Control Technology, Institute of Cyber Systems and Control, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4391767838"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126147805","display_name":"Jie Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142178","display_name":"Hangzhou DAC Biotech (China)","ror":"https://ror.org/04hy71c73","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210142178"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Hao","raw_affiliation_strings":["The Luoteng Hangzhou Techonlogy Company, Ltd., Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1276-2363","affiliations":[{"raw_affiliation_string":"The Luoteng Hangzhou Techonlogy Company, Ltd., Hangzhou, China","institution_ids":["https://openalex.org/I4210142178"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126114538","display_name":"Guang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4391767838","display_name":"State Key Laboratory of Industrial Control Technology","ror":"https://ror.org/03a33a786","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767838","https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guang Li","raw_affiliation_strings":["State Key Laboratory of Industrial Control Technology, Institute of Cyber Systems and Control, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-1253-3985","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Industrial Control Technology, Institute of Cyber Systems and Control, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4391767838"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5121983869"],"corresponding_institution_ids":["https://openalex.org/I4391767838"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32474333,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"4","first_page":"4251","last_page":"4258"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11615","display_name":"Control and Dynamics of Mobile Robots","score":0.2648000121116638,"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/T11615","display_name":"Control and Dynamics of Mobile Robots","score":0.2648000121116638,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.15289999544620514,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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":0.11550000309944153,"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/waypoint","display_name":"Waypoint","score":0.6592000126838684},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6255000233650208},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.6212000250816345},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5360999703407288},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.504800021648407},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5040000081062317},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.49619999527931213},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4740999937057495},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.4429999887943268}],"concepts":[{"id":"https://openalex.org/C2781271823","wikidata":"https://www.wikidata.org/wiki/Q138081","display_name":"Waypoint","level":2,"score":0.6592000126838684},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6255000233650208},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6212000250816345},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5767999887466431},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5360999703407288},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.504800021648407},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5040000081062317},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.49619999527931213},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4740999937057495},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.4429999887943268},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4424000084400177},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4336000084877014},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.421099990606308},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.41769999265670776},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.39959999918937683},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.366100013256073},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C164660894","wikidata":"https://www.wikidata.org/wiki/Q2037833","display_name":"Piecewise","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2833999991416931},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27379998564720154},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.27090001106262207},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2026.3665076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3665076","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1503296932","https://openalex.org/W2021446769","https://openalex.org/W2103374161","https://openalex.org/W2117728510","https://openalex.org/W2164049425","https://openalex.org/W2338399048","https://openalex.org/W2921580667","https://openalex.org/W2963683522","https://openalex.org/W2963906246","https://openalex.org/W2968736515","https://openalex.org/W2972943615","https://openalex.org/W2996127443","https://openalex.org/W3112664346","https://openalex.org/W3134153520","https://openalex.org/W3206620955","https://openalex.org/W3207033168","https://openalex.org/W4205295909","https://openalex.org/W4205430897","https://openalex.org/W4281659317","https://openalex.org/W4321380998","https://openalex.org/W4385430550","https://openalex.org/W4399619317","https://openalex.org/W4401415792","https://openalex.org/W4402354114","https://openalex.org/W4402409305","https://openalex.org/W4402659240","https://openalex.org/W4407450436","https://openalex.org/W4407467457","https://openalex.org/W4413925046","https://openalex.org/W4414079285"],"related_works":[],"abstract_inverted_index":{"Point-to-point":[0],"navigation":[1],"is":[2,46],"an":[3,36],"important":[4],"ability":[5],"for":[6,18,48,145],"spherical":[7,78,88],"robots.":[8],"Traditional":[9],"methods":[10],"usually":[11],"use":[12],"a":[13,16,28,52,87,96,122,142],"planner":[14],"and":[15,65,100,116,162,171],"tracker":[17],"short-range":[19],"target":[20],"control.":[21],"However,":[22],"this":[23,32],"hierarchical":[24],"method":[25,144],"suffers":[26],"from":[27],"mismatch":[29],"issue.":[30],"In":[31],"work,":[33],"we":[34,90,140],"propose":[35],"end-to-end":[37],"controller":[38,70],"based":[39],"on":[40],"reinforcement":[41],"learning.":[42,102],"The":[43],"proposed":[44],"approach":[45],"designed":[47,92],"waypoint":[49],"tracking":[50],"after":[51],"path":[53],"has":[54],"been":[55],"planned.":[56],"Taking":[57],"proprioceptive":[58],"information":[59],"such":[60],"as":[61,67],"the":[62,77,83,131,137,151,158],"robot's":[63],"position":[64],"orientation":[66],"input,":[68],"our":[69,106,165],"directly":[71],"outputs":[72],"motor":[73],"commands":[74],"to":[75,82,118,136,148,167],"control":[76],"robot.":[79],"To":[80,129],"adapt":[81],"unique":[84],"characteristics":[85],"of":[86,125],"robot,":[89],"have":[91],"various":[93],"reward":[94],"functions,":[95],"long":[97],"history":[98],"encoder,":[99],"curriculum":[101],"We":[103],"demonstrate":[104],"that":[105],"policy":[107,132,166],"can":[108],"execute":[109],"point-to-point":[110],"tasks":[111],"with":[112],"high":[113,169],"efficiency":[114,172],"stability":[115,170],"adaptability":[117],"uncertain":[119],"environments,":[120],"achieving":[121],"success":[123],"rate":[124],"88.87%":[126],"in":[127,134,173],"simulation.":[128],"transfer":[130],"trained":[133],"simulation":[135,161],"real":[138],"world,":[139],"developed":[141],"MC-CMA-ES":[143],"system":[146],"identification":[147],"accurately":[149],"model":[150],"simulator's":[152],"parameters.":[153],"This":[154],"process":[155],"significantly":[156],"narrows":[157],"gap":[159],"between":[160],"reality,":[163],"enabling":[164],"achieve":[168],"real-world":[174],"scenarios.":[175]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-02-17T00:00:00"}
