{"id":"https://openalex.org/W4313043113","doi":"https://doi.org/10.1109/iros47612.2022.9981784","title":"Graph-based Reinforcement Learning meets Mixed Integer Programs: An application to 3D robot assembly discovery","display_name":"Graph-based Reinforcement Learning meets Mixed Integer Programs: An application to 3D robot assembly discovery","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4313043113","doi":"https://doi.org/10.1109/iros47612.2022.9981784"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9981784","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981784","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5003044858","display_name":"Niklas Funk","orcid":"https://orcid.org/0000-0002-9682-1529"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Niklas Funk","raw_affiliation_strings":["Technical University of Darmstadt,Department of Computer Science","Department of Computer Science, Technical University of Darmstadt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt,Department of Computer Science","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Department of Computer Science, Technical University of Darmstadt","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000544535","display_name":"Svenja Menzenbach","orcid":null},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Svenja Menzenbach","raw_affiliation_strings":["Technical University of Darmstadt,Department of Computer Science","Department of Computer Science, Technical University of Darmstadt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt,Department of Computer Science","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Department of Computer Science, Technical University of Darmstadt","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026055366","display_name":"Georgia Chalvatzaki","orcid":"https://orcid.org/0000-0002-5055-199X"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Georgia Chalvatzaki","raw_affiliation_strings":["Technical University of Darmstadt,Department of Computer Science","Department of Computer Science, Technical University of Darmstadt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt,Department of Computer Science","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Department of Computer Science, Technical University of Darmstadt","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063321196","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0001-9328-3078"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Peters","raw_affiliation_strings":["Technical University of Darmstadt,Department of Computer Science","Department of Computer Science, Technical University of Darmstadt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt,Department of Computer Science","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Department of Computer Science, Technical University of Darmstadt","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10215","last_page":"10222"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9991000294685364,"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":0.9991000294685364,"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/T11159","display_name":"Manufacturing Process and Optimization","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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":0.996999979019165,"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":0.8212047815322876},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.729705810546875},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5735830068588257},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5222547650337219},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5190271139144897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4813319146633148},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.47763791680336},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.43799275159835815},{"id":"https://openalex.org/keywords/integer-programming","display_name":"Integer programming","score":0.4263904094696045},{"id":"https://openalex.org/keywords/control-reconfiguration","display_name":"Control reconfiguration","score":0.4227175712585449},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36614498496055603},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15867355465888977},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12333524227142334},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10464966297149658}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8212047815322876},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.729705810546875},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5735830068588257},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5222547650337219},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5190271139144897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4813319146633148},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.47763791680336},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.43799275159835815},{"id":"https://openalex.org/C56086750","wikidata":"https://www.wikidata.org/wiki/Q6042592","display_name":"Integer programming","level":2,"score":0.4263904094696045},{"id":"https://openalex.org/C119701452","wikidata":"https://www.wikidata.org/wiki/Q5165881","display_name":"Control reconfiguration","level":2,"score":0.4227175712585449},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36614498496055603},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15867355465888977},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12333524227142334},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10464966297149658},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9981784","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981784","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W83318670","https://openalex.org/W1990470929","https://openalex.org/W2072803231","https://openalex.org/W2119709400","https://openalex.org/W2240053161","https://openalex.org/W2334782222","https://openalex.org/W2403069916","https://openalex.org/W2766447205","https://openalex.org/W2805516822","https://openalex.org/W2907424612","https://openalex.org/W2951846985","https://openalex.org/W2962918443","https://openalex.org/W2963990127","https://openalex.org/W2993335716","https://openalex.org/W2998544442","https://openalex.org/W3000351149","https://openalex.org/W3086207594","https://openalex.org/W3089482831","https://openalex.org/W3091677803","https://openalex.org/W3169676024","https://openalex.org/W3174979795","https://openalex.org/W3200650887","https://openalex.org/W3207196785","https://openalex.org/W4206752580","https://openalex.org/W4226088469","https://openalex.org/W4255385909","https://openalex.org/W4293456076","https://openalex.org/W4297733535","https://openalex.org/W4385245566","https://openalex.org/W6713184877","https://openalex.org/W6713200026","https://openalex.org/W6718856663","https://openalex.org/W6739901393","https://openalex.org/W6758687306","https://openalex.org/W6761037857","https://openalex.org/W6771066560","https://openalex.org/W6802171045"],"related_works":["https://openalex.org/W2163296013","https://openalex.org/W2743859443","https://openalex.org/W2326995835","https://openalex.org/W165915117","https://openalex.org/W2059402478","https://openalex.org/W2123347777","https://openalex.org/W4387804363","https://openalex.org/W2477150073","https://openalex.org/W2357657342","https://openalex.org/W2019547100"],"abstract_inverted_index":{"Robot":[0],"assembly":[1,185],"discovery":[2],"(RAD)":[3],"is":[4,21,116,144],"a":[5,24,57,64,94,139,177,198],"challenging":[6],"problem":[7,46],"that":[8,82,143,167],"lives":[9],"at":[10,72],"the":[11,38,45,75,89,105,111,122,158,173,183],"intersection":[12],"of":[13,27,47,59,101,124,161,200],"resource":[14],"allocation":[15],"and":[16,63,104,148,164,179,208,211],"motion":[17,180],"planning.":[18],"The":[19],"goal":[20],"to":[22,29,109,119,215],"combine":[23],"predefined":[25,50],"set":[26,58,199],"objects":[28],"form":[30],"something":[31],"new":[32],"while":[33],"considering":[34],"task":[35,77],"execution":[36],"with":[37,152],"robot-in-the-loop.":[39],"In":[40],"this":[41],"work,":[42],"we":[43,92],"tackle":[44],"building":[48,61],"arbitrary,":[49],"target":[51],"structures":[52],"entirely":[53],"from":[54,85,138],"scratch":[55],"using":[56],"Tetris-like":[60],"blocks":[62],"robotic":[65,165],"manipulator.":[66],"Our":[67],"novel":[68],"hierarchical":[69],"approach":[70],"aims":[71],"efficiently":[73,120],"decomposing":[74],"overall":[76],"into":[78,187],"three":[79],"feasible":[80],"levels":[81],"benefit":[83],"mutually":[84],"each":[86],"other.":[87],"On":[88],"high":[90],"level,":[91],"run":[93],"classical":[95],"mixed-integer":[96],"program":[97],"for":[98,157],"global":[99],"optimization":[100],"block-type":[102],"selection":[103],"blocks'":[106],"final":[107],"poses":[108],"recreate":[110],"desired":[112,184],"shape.":[113],"Its":[114],"output":[115],"then":[117],"exploited":[118],"guide":[121],"exploration":[123],"an":[125,216],"underlying":[126],"reinforcement":[127],"learning":[128],"(RL)":[129],"policy.":[130],"This":[131],"RL":[132],"policy":[133],"draws":[134],"its":[135],"generalization":[136],"properties":[137],"flexible":[140],"graph-based":[141],"representation":[142],"learned":[145],"through":[146],"Q-learning":[147],"can":[149],"be":[150,169],"refined":[151],"search.":[153],"Moreover,":[154],"it":[155],"accounts":[156],"necessary":[159],"conditions":[160],"structural":[162],"stability":[163],"feasibility":[166],"cannot":[168],"effectively":[170],"reflected":[171],"in":[172],"previous":[174],"layer.":[175],"Lastly,":[176],"grasp":[178],"planner":[181],"transforms":[182],"commands":[186],"robot":[188],"joint":[189],"movements.":[190],"We":[191],"demonstrate":[192],"our":[193],"proposed":[194],"method's":[195],"performance":[196,210],"on":[197],"competitive":[201],"simulated":[202],"RAD":[203],"environments,":[204],"showcase":[205],"real-world":[206],"transfer,":[207],"report":[209],"robustness":[212],"gains":[213],"compared":[214],"unstructured":[217],"end-to-end":[218],"approach.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}