{"id":"https://openalex.org/W2979421998","doi":null,"title":"Knowledge Induced Deep Q-Network for a Slide-to-Wall Object Grasping.","display_name":"Knowledge Induced Deep Q-Network for a Slide-to-Wall Object Grasping.","alternate_titles":[],"publication_year":2019,"publication_date":"2019-10-09","ids":{"openalex":"https://openalex.org/W2979421998","mag":"2979421998"},"language":"en","primary_location":{"id":"mag:2979421998","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.03781","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"parent_works":[],"lineage":["https://openalex.org/W2979421998"],"child_works_count":0,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.03781","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061526336","display_name":"Hengyue Liang","orcid":"https://orcid.org/0000-0001-9498-6402","observed_orcids":["https://orcid.org/0000-0001-9498-6402"]},"institutions":[],"countries":[],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Hengyue Liang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-9498-6402","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022469639","display_name":"Xibai Lou","orcid":"https://orcid.org/0009-0006-4242-847X","observed_orcids":["https://orcid.org/0009-0006-4242-847X"]},"institutions":[],"countries":[],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Xibai Lou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057994317","display_name":"Changhyun Choi","orcid":"https://orcid.org/0000-0003-4715-3576","observed_orcids":["https://orcid.org/0000-0003-4715-3576"]},"institutions":[],"countries":[],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Chang-Hyun Choi","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4715-3576","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6615999937057495,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6615999937057495,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.33739998936653137,"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/T10868","display_name":"Soft Robotics and Applications","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/robotic-grasping","display_name":"robotic grasping","score":0.6439999938011169},{"id":"https://openalex.org/keywords/deep-q-network","display_name":"deep Q-network","score":0.8519999980926514},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.75},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.8220000267028809},{"id":"https://openalex.org/keywords/generalization-to-unseen-environments","display_name":"generalization to unseen environments","score":0.8989999890327454},{"id":"https://openalex.org/keywords/object-pushing","display_name":"object pushing","score":0.382999986410141},{"id":"https://openalex.org/keywords/robotic-manipulation","display_name":"robotic manipulation","score":0.33000001311302185}],"concepts":[{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.9205322861671448},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7884474992752075},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6849169731140137},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6667101979255676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6485039591789246},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6426210403442383},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6223284006118774},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5468137860298157},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5293277502059937},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.47648972272872925},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3220112919807434},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2194320559501648},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0904916524887085},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2979421998","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.03781","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:2979421998","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.03781","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1969583232","https://openalex.org/W2042882799","https://openalex.org/W2051620263","https://openalex.org/W2100235553","https://openalex.org/W2139053308","https://openalex.org/W2145339207","https://openalex.org/W2201581102","https://openalex.org/W2334782222","https://openalex.org/W2405660904","https://openalex.org/W2761873684","https://openalex.org/W2794537597","https://openalex.org/W2808278571","https://openalex.org/W2902907165","https://openalex.org/W2933823921","https://openalex.org/W2963446712"],"related_works":["https://openalex.org/W4312930054","https://openalex.org/W3127026099","https://openalex.org/W3206181916","https://openalex.org/W4406803022","https://openalex.org/W4384341894","https://openalex.org/W4383108592","https://openalex.org/W4401277438","https://openalex.org/W3131554325","https://openalex.org/W4383097676","https://openalex.org/W7106157512"],"abstract_inverted_index":{"In":[0,76],"robotic":[1],"grasping":[2,24,95],"tasks,":[3],"robots":[4,173],"usually":[5],"avoid":[6],"any":[7],"collisions":[8],"with":[9,15,31,163],"the":[10,16,20,32,47,55,59,86,93,137,156],"environment":[11,21,33,87,128],"and":[12,102,166],"exclusively":[13],"interact":[14],"target":[17,60],"objects.":[18,90],"However,":[19],"can":[22,73,167],"facilitate":[23],"rather":[25],"than":[26],"being":[27],"obstacles.":[28],"Indeed,":[29],"interacting":[30],"sometimes":[34],"provides":[35],"an":[36,81],"alternative":[37],"strategy":[38],"when":[39],"it":[40,121],"is":[41,54,115],"not":[42,123,148],"possible":[43],"to":[44,63,88,126],"grasp":[45,72,89],"from":[46,133],"top.":[48],"One":[49],"example":[50],"of":[51,117],"such":[52],"tasks":[53],"Slide-to-Wall":[56,94],"grasping,":[57],"where":[58],"object":[61],"needs":[62],"be":[64,74,168],"pushed":[65],"towards":[66],"a":[67,70,98,104,109,142],"wall":[68],"before":[69],"feasible":[71],"applied.":[75],"this":[77],"paper,":[78],"we":[79,140],"propose":[80,103,141],"approach":[82],"that":[83,130,147],"actively":[84],"exploits":[85],"We":[91],"formulate":[92],"problem":[96],"as":[97],"Markov":[99],"Decision":[100],"Process":[101],"reinforcement":[105],"learning":[106],"approach.":[107],"Though":[108],"standard":[110,157],"Deep":[111],"Q-Network":[112],"(DQN)":[113],"method":[114],"capable":[116],"solving":[118],"MDP":[119],"problems,":[120],"does":[122],"effectively":[124],"generalize":[125],"unseen":[127,164],"settings":[129],"are":[131],"different":[132],"training.":[134],"To":[135],"tackle":[136],"generalization":[138],"challenge,":[139],"Knowledge":[143],"Induced":[144],"DQN":[145,158,177],"(KI-DQN)":[146],"only":[149],"trains":[150],"more":[151],"effectively,":[152],"but":[153],"also":[154],"outperforms":[155],"significantly":[159],"in":[160],"testing":[161],"cases":[162],"walls,":[165],"directly":[169],"tested":[170],"on":[171],"real":[172],"without":[174],"fine-tuning":[175],"while":[176],"cannot.":[178]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2979421998","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5}],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2019-10-18T00:00:00"}
