{"id":"https://openalex.org/W4285102596","doi":"https://doi.org/10.1109/icra46639.2022.9811572","title":"Hierarchical Policy Learning for Mechanical Search","display_name":"Hierarchical Policy Learning for Mechanical Search","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W4285102596","doi":"https://doi.org/10.1109/icra46639.2022.9811572"},"language":"en","primary_location":{"id":"doi:10.1109/icra46639.2022.9811572","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9811572","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","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 International Conference on Robotics and Automation (ICRA)","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/A5054325024","display_name":"Oussama Zenkri","orcid":"https://orcid.org/0009-0006-4169-1460"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Oussama Zenkri","raw_affiliation_strings":["Karlsruhe Institute of Technology (KIT)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology (KIT)","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043775193","display_name":"Ngo Anh Vien","orcid":"https://orcid.org/0000-0001-9646-267X"},"institutions":[{"id":"https://openalex.org/I4210151956","display_name":"Robert Bosch (India)","ror":"https://ror.org/04my8ty22","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210151956","https://openalex.org/I889804353"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ngo Anh Vien","raw_affiliation_strings":["Bosch Center for Artificial Intelligence (BCAI)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bosch Center for Artificial Intelligence (BCAI)","institution_ids":["https://openalex.org/I4210151956"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110467801","display_name":"Gerhard Neumann","orcid":"https://orcid.org/0000-0002-5483-4225"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Neumann","raw_affiliation_strings":["Karlsruhe Institute of Technology (KIT)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology (KIT)","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1954","last_page":"1960"},"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":0.9990000128746033,"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":0.9952999949455261,"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/computer-science","display_name":"Computer science","score":0.8371619582176208},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7085888385772705},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.5696866512298584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5639802813529968},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4546014964580536},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.4449550211429596},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4137493968009949},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.4108751714229584},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.10482677817344666},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08314254879951477}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8371619582176208},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7085888385772705},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.5696866512298584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5639802813529968},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4546014964580536},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.4449550211429596},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4137493968009949},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.4108751714229584},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.10482677817344666},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08314254879951477},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra46639.2022.9811572","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9811572","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","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 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W143499627","https://openalex.org/W2049783975","https://openalex.org/W2145339207","https://openalex.org/W2174072647","https://openalex.org/W2271240761","https://openalex.org/W2561079189","https://openalex.org/W2600030077","https://openalex.org/W2603737562","https://openalex.org/W2745471877","https://openalex.org/W2781726626","https://openalex.org/W2904207885","https://openalex.org/W2918333121","https://openalex.org/W2962793652","https://openalex.org/W2963262099","https://openalex.org/W2964239605","https://openalex.org/W2966885779","https://openalex.org/W3004003541","https://openalex.org/W3004091482","https://openalex.org/W3090679498","https://openalex.org/W3091905774","https://openalex.org/W3098945452","https://openalex.org/W3130791072","https://openalex.org/W3132114951","https://openalex.org/W3135445321","https://openalex.org/W3205159809","https://openalex.org/W3208348590","https://openalex.org/W6703271639","https://openalex.org/W6747473740","https://openalex.org/W6784305363","https://openalex.org/W6802974684"],"related_works":["https://openalex.org/W2051058708","https://openalex.org/W154868527","https://openalex.org/W1494268238","https://openalex.org/W2015051472","https://openalex.org/W2168501056","https://openalex.org/W2120009678","https://openalex.org/W2912947802","https://openalex.org/W2037601570","https://openalex.org/W2123856982","https://openalex.org/W1530089576"],"abstract_inverted_index":{"Retrieving":[0],"objects":[1,39],"from":[2,74,185,200],"clutters":[3],"is":[4,51],"a":[5,52,59,128,132,141,158],"complex":[6,97],"task,":[7],"which":[8,57,106],"requires":[9],"multiple":[10,201],"interactions":[11,23],"with":[12],"the":[13,16,38,43,114,124,147,169,177,182,194],"environment":[14],"until":[15],"target":[17,183],"object":[18,55,184],"can":[19],"be":[20],"extracted.":[21],"These":[22],"involve":[24],"executing":[25],"action":[26,163],"primitives":[27],"like":[28],"grasping":[29],"or":[30],"pushing":[31,63],"as":[32,34,100,131],"well":[33],"setting":[35],"priorities":[36],"for":[37,54,62,67,110,146,197],"to":[40,45,189,203],"manipulate":[41],"and":[42,64,161],"actions":[44,199],"execute.":[46],"Mechanical":[47],"Search":[48],"(MS)":[49],"[1]":[50],"framework":[53],"retrieval,":[56],"uses":[58],"heuristic":[60],"algorithm":[61],"rule-based":[65,71],"algorithms":[66],"high-level":[68],"planning.":[69],"While":[70],"policies":[72,112],"profit":[73],"human":[75],"intuition":[76],"in":[77,85,96,113,127],"how":[78],"they":[79,81],"work,":[80,120],"usually":[82],"perform":[83],"sub-optimally":[84],"many":[86],"cases.":[87],"Deep":[88],"reinforcement":[89],"learning":[90,144],"(RL)":[91],"has":[92],"shown":[93],"great":[94],"performance":[95],"tasks":[98],"such":[99],"taking":[101],"decisions":[102],"through":[103],"evaluating":[104],"pixels,":[105],"makes":[107],"it":[108],"suitable":[109],"training":[111],"context":[115],"of":[116,180],"object-retrieval.":[117],"In":[118],"this":[119,137],"we":[121,139,152],"first":[122],"formulate":[123],"MS":[125,148],"problem":[126],"principled":[129],"formulation":[130],"hierarchical":[133,142,170],"POMDP.":[134],"Based":[135],"on":[136],"formulation,":[138],"propose":[140],"policy":[143,160],"approach":[145],"problem.":[149],"For":[150],"demonstration,":[151],"present":[153],"two":[154],"main":[155],"parameterized":[156],"sub-policies:":[157],"push":[159,198],"an":[162],"selection":[164],"policy.":[165],"When":[166],"integrated":[167],"into":[168],"POMDP's":[171],"policy,":[172],"our":[173],"proposed":[174],"sub-policies":[175],"increase":[176],"success":[178],"rate":[179],"retrieving":[181],"less":[186,204],"than":[187,205],"32%":[188],"nearly":[190],"80%,":[191],"while":[192],"reducing":[193],"computation":[195],"time":[196],"seconds":[202],"10":[206],"milliseconds.":[207]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}