{"id":"https://openalex.org/W4383108566","doi":"https://doi.org/10.1109/icra48891.2023.10161310","title":"RTAW: An Attention Inspired Reinforcement Learning Method for Multi-Robot Task Allocation in Warehouse Environments","display_name":"RTAW: An Attention Inspired Reinforcement Learning Method for Multi-Robot Task Allocation in Warehouse Environments","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383108566","doi":"https://doi.org/10.1109/icra48891.2023.10161310"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10161310","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161310","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","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/A5012625793","display_name":"Aakriti Agrawal","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aakriti Agrawal","raw_affiliation_strings":["University of Maryland,The Department of Computer Science,College Park,MD,USA","The Department of Computer Science, University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland,The Department of Computer Science,College Park,MD,USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"The Department of Computer Science, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039563144","display_name":"Amrit Singh Bedi","orcid":"https://orcid.org/0000-0002-8807-2695"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amrit Singh Bedi","raw_affiliation_strings":["University of Maryland,The Department of Computer Science,College Park,MD,USA","The Department of Computer Science, University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland,The Department of Computer Science,College Park,MD,USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"The Department of Computer Science, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004194238","display_name":"Dinesh Manocha","orcid":"https://orcid.org/0000-0001-7047-9801"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dinesh Manocha","raw_affiliation_strings":["University of Maryland,The Department of Computer Science,College Park,MD,USA","The Department of Computer Science, University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland,The Department of Computer Science,College Park,MD,USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"The Department of Computer Science, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5012625793"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":1.9583,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.85692677,"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":"1393","last_page":"1399"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11942","display_name":"Transportation and Mobility Innovations","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11942","display_name":"Transportation and Mobility Innovations","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.996399998664856,"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"}},{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9958000183105469,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8778634071350098},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.780830979347229},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6342716813087463},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6317558288574219},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.6307937502861023},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6143791079521179},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5778133869171143},{"id":"https://openalex.org/keywords/satisficing","display_name":"Satisficing","score":0.49985551834106445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49484485387802124},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.38763487339019775},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.34798943996429443},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3395422697067261},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32216060161590576},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09507635235786438}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8778634071350098},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.780830979347229},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6342716813087463},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6317558288574219},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.6307937502861023},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6143791079521179},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5778133869171143},{"id":"https://openalex.org/C94822996","wikidata":"https://www.wikidata.org/wiki/Q1777902","display_name":"Satisficing","level":2,"score":0.49985551834106445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49484485387802124},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.38763487339019775},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34798943996429443},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3395422697067261},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32216060161590576},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09507635235786438},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10161310","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161310","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6289338561","display_name":null,"funder_award_id":"W911NF1910069,W911NF2110026","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1430351163","https://openalex.org/W1500007717","https://openalex.org/W1508840430","https://openalex.org/W1968326804","https://openalex.org/W1972391046","https://openalex.org/W1976290517","https://openalex.org/W2048240571","https://openalex.org/W2059480483","https://openalex.org/W2113257089","https://openalex.org/W2126045901","https://openalex.org/W2157488300","https://openalex.org/W2162844575","https://openalex.org/W2167236498","https://openalex.org/W2168424616","https://openalex.org/W2217985647","https://openalex.org/W2622453669","https://openalex.org/W2736601468","https://openalex.org/W2742211145","https://openalex.org/W2808475207","https://openalex.org/W2903998385","https://openalex.org/W2914154006","https://openalex.org/W2962969317","https://openalex.org/W2964997335","https://openalex.org/W2970026324","https://openalex.org/W2971587637","https://openalex.org/W3003899243","https://openalex.org/W3035846111","https://openalex.org/W3087801177","https://openalex.org/W3109546547","https://openalex.org/W3158757609","https://openalex.org/W3186615143","https://openalex.org/W4230129068","https://openalex.org/W4287755401","https://openalex.org/W4295997114","https://openalex.org/W4312641903","https://openalex.org/W4385245566","https://openalex.org/W6627932998","https://openalex.org/W6738126737","https://openalex.org/W6739901393","https://openalex.org/W6741002519","https://openalex.org/W6766840111","https://openalex.org/W6767941141","https://openalex.org/W6842988725"],"related_works":["https://openalex.org/W4292701710","https://openalex.org/W2970347269","https://openalex.org/W4287863949","https://openalex.org/W4287102143","https://openalex.org/W1850488217","https://openalex.org/W3096874164","https://openalex.org/W2945119207","https://openalex.org/W3182614517","https://openalex.org/W2937181779","https://openalex.org/W2386410636"],"abstract_inverted_index":{"We":[0,16,57,133,161],"present":[1],"a":[2,20,27,67,73,96],"novel":[3,28],"reinforcement":[4,31],"learning":[5,32],"based":[6,127],"algorithm":[7,62,111],"for":[8,63,95,152],"multi-robot":[9],"task":[10,158],"allocation":[11],"problem":[12],"in":[13,142,177],"ware-house":[14],"environments.":[15],"formulate":[17],"it":[18],"as":[19,119],"Markov":[21],"Decision":[22],"Process":[23],"and":[24,65,125,157],"solve":[25],"via":[26],"deep":[29],"multi-agent":[30],"method":[33],"(called":[34],"RTAW)":[35],"with":[36,146,172],"attention":[37],"inspired":[38],"policy":[39,44,60,78],"architecture.":[40],"Hence,":[41],"our":[42,101,109,167],"proposed":[43],"network":[45],"uses":[46],"global":[47],"embeddings":[48],"that":[49],"are":[50],"independent":[51],"of":[52,55,108,114,137,150,166],"the":[53,93,106,115,164],"number":[54],"robots/tasks.":[56],"utilize":[58],"proximal":[59],"optimization":[61],"training":[64],"use":[66],"carefully":[68],"designed":[69],"reward":[70],"to":[71,84,112,174],"obtain":[72],"converged":[74,77],"policy.":[75],"The":[76],"ensures":[79],"cooperation":[80],"among":[81],"different":[82,130,153],"robots":[83,176],"minimize":[85],"total":[86],"travel":[87],"delay":[88],"(TTD)":[89],"which":[90],"ultimately":[91],"improves":[92],"makespan":[94],"sufficiently":[97],"large":[98],"task-list.":[99],"In":[100],"extensive":[102],"experiments,":[103],"we":[104],"compare":[105],"performance":[107,171],"RTAW":[110],"state":[113],"art":[116],"methods":[117],"such":[118],"myopic":[120],"pickup":[121],"distance":[122],"minimization":[123],"(greedy)":[124],"regret":[126],"baselines":[128],"on":[129,144],"navigation":[131],"schemes.":[132,160],"show":[134],"an":[135],"improvement":[136],"upto":[138],"14%":[139],"(25\u20131000":[140],"seconds)":[141],"TTD":[143],"scenarios":[145],"hundreds":[147],"or":[148],"thousands":[149],"tasks":[151],"challenging":[154],"warehouse":[155],"layouts":[156],"generation":[159],"also":[162],"demonstrate":[163],"scalability":[165],"approach":[168],"by":[169],"showing":[170],"up":[173],"1000":[175],"simulations.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}