{"id":"https://openalex.org/W3003010287","doi":"https://doi.org/10.1109/robio49542.2019.8961560","title":"Learning to Solve a Rubik\u2019s Cube with a Dexterous Hand","display_name":"Learning to Solve a Rubik\u2019s Cube with a Dexterous Hand","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3003010287","doi":"https://doi.org/10.1109/robio49542.2019.8961560","mag":"3003010287"},"language":"en","primary_location":{"id":"doi:10.1109/robio49542.2019.8961560","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio49542.2019.8961560","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 Robotics and Biomimetics (ROBIO)","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/A5083545249","display_name":"Tingguang Li","orcid":"https://orcid.org/0000-0003-1161-9987"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tingguang Li","raw_affiliation_strings":["The Chinese University of Hong Kong,Robotics,Hong Kong SAR,China","Robotics, The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Robotics,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Robotics, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059763149","display_name":"Weitao Xi","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weitao Xi","raw_affiliation_strings":["Tencent AI Lab,Shenzhen,China","Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100400497","display_name":"Meng Fang","orcid":"https://orcid.org/0000-0003-0793-9187"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Fang","raw_affiliation_strings":["Tencent AI Lab,Shenzhen,China","Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100659427","display_name":"Jia Xu","orcid":"https://orcid.org/0000-0002-6000-5271"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Xu","raw_affiliation_strings":["Tencent AI Lab,Shenzhen,China","Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021531143","display_name":"Max Q.\u2010H. Meng","orcid":"https://orcid.org/0000-0002-5255-5898"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Max Q.-H. Meng","raw_affiliation_strings":["The Chinese University of Hong Kong,Robotics,Hong Kong SAR,China","Robotics, The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Robotics,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Robotics, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5083545249"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":1.0076,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.77951304,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1387","last_page":"1393"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998000264167786,"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":0.9998000264167786,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9897000193595886,"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/cube","display_name":"Cube (algebra)","score":0.8938602209091187},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.686302661895752},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.6417183876037598},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5747898817062378},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5564296841621399},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5498478412628174},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.5096113681793213},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.44331398606300354},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4279690980911255},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41603347659111023},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.41348594427108765},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35036909580230713},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2401430308818817},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1529611051082611},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12693431973457336}],"concepts":[{"id":"https://openalex.org/C53051483","wikidata":"https://www.wikidata.org/wiki/Q861555","display_name":"Cube (algebra)","level":2,"score":0.8938602209091187},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.686302661895752},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.6417183876037598},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5747898817062378},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5564296841621399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5498478412628174},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.5096113681793213},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.44331398606300354},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4279690980911255},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41603347659111023},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.41348594427108765},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35036909580230713},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2401430308818817},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1529611051082611},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12693431973457336},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio49542.2019.8961560","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio49542.2019.8961560","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 Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1570792896","https://openalex.org/W2019165997","https://openalex.org/W2037122143","https://openalex.org/W2089788585","https://openalex.org/W2148043942","https://openalex.org/W2158782408","https://openalex.org/W2161697934","https://openalex.org/W2165040934","https://openalex.org/W2173248099","https://openalex.org/W2416041116","https://openalex.org/W2534060593","https://openalex.org/W2791412343","https://openalex.org/W2798705390","https://openalex.org/W2803281228","https://openalex.org/W2804694653","https://openalex.org/W2883869105","https://openalex.org/W2891234582","https://openalex.org/W2909255538","https://openalex.org/W2910820787","https://openalex.org/W2950614095","https://openalex.org/W2963262099","https://openalex.org/W2963411833","https://openalex.org/W2963864421","https://openalex.org/W2964001908","https://openalex.org/W2964208980","https://openalex.org/W2970393539","https://openalex.org/W2990747716","https://openalex.org/W3130548322","https://openalex.org/W4243385754","https://openalex.org/W4294578467","https://openalex.org/W4300799055","https://openalex.org/W6683526187","https://openalex.org/W6684921986","https://openalex.org/W6703271639","https://openalex.org/W6729130418","https://openalex.org/W6740801417","https://openalex.org/W6744563498","https://openalex.org/W6752089545","https://openalex.org/W6760958334","https://openalex.org/W6767047803","https://openalex.org/W6770858630"],"related_works":["https://openalex.org/W2381850946","https://openalex.org/W4380449851","https://openalex.org/W3125091513","https://openalex.org/W4318832338","https://openalex.org/W2186864281","https://openalex.org/W4283690284","https://openalex.org/W4255427455","https://openalex.org/W1919390113","https://openalex.org/W3180808905","https://openalex.org/W4248383205"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,7,11,50,75,96,101,111],"learning-based":[3],"approach":[4],"to":[5,83,149],"solving":[6,23],"Rubik's":[8,102,121],"cube":[9,63,73,77],"with":[10,49,110],"multi-fingered":[12],"dexterous":[13,20],"hand.":[14,114],"Despite":[15],"the":[16,72,124,138],"promising":[17],"performance":[18],"of":[19,126,134],"in-hand":[21],"manipulation,":[22],"complex":[24],"tasks":[25],"which":[26,56,99],"involve":[27],"multiple":[28],"steps":[29],"and":[30,59,74,144],"diverse":[31],"internal":[32],"object":[33,105],"structure":[34],"has":[35],"remained":[36],"an":[37,66,104,130],"important,":[38],"yet":[39],"challenging":[40],"task.":[41],"In":[42],"this":[43,47],"paper,":[44],"we":[45,94,140],"tackle":[46],"challenge":[48],"hierarchical":[51],"deep":[52],"reinforcement":[53],"learning":[54],"method,":[55,128],"separates":[57],"planning":[58],"manipulation.":[60],"A":[61],"model-based":[62],"solver":[64],"finds":[65],"optimal":[67],"move":[68,86],"sequence":[69],"for":[70],"restoring":[71],"model-free":[76],"operator":[78],"controls":[79],"all":[80],"five":[81],"fingers":[82],"execute":[84],"each":[85],"step":[87],"by":[88],"step.":[89],"To":[90,136],"train":[91],"our":[92,127,142],"models,":[93],"build":[95],"high-fidelity":[97],"simulator":[98,143],"manipulates":[100],"Cube,":[103],"containing":[106],"high-dimensional":[107],"state":[108],"space,":[109],"24-DoF":[112],"robot":[113],"Extensive":[115],"experiments":[116],"on":[117],"1400":[118],"randomly":[119],"scrambled":[120],"cubes":[122],"demonstrate":[123],"effectiveness":[125],"achieving":[129],"average":[131],"success":[132],"rate":[133],"90.3%.":[135],"benefit":[137],"community,":[139],"make":[141],"source":[145],"code":[146],"publicly":[147],"available":[148],"advance":[150],"future":[151],"research":[152],"<sup":[153],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[154],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[155],".":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}