{"id":"https://openalex.org/W4401724148","doi":"https://doi.org/10.1145/3674746.3674762","title":"Reward Design for Training Robotic Insertion Tasks Using Low-Dimensional Observation","display_name":"Reward Design for Training Robotic Insertion Tasks Using Low-Dimensional Observation","publication_year":2024,"publication_date":"2024-06-27","ids":{"openalex":"https://openalex.org/W4401724148","doi":"https://doi.org/10.1145/3674746.3674762"},"language":"en","primary_location":{"id":"doi:10.1145/3674746.3674762","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3674746.3674762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 4th International Conference on Robotics and Control Engineering","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/A5048582500","display_name":"Xinyi Li","orcid":"https://orcid.org/0000-0002-7438-062X"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyi Li","raw_affiliation_strings":["School of Instrument Science and Engineering, Southeast University, China"],"raw_orcid":"https://orcid.org/0000-0002-7438-062X","affiliations":[{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048327458","display_name":"Aiguo Song","orcid":"https://orcid.org/0000-0002-1982-6780"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aiguo Song","raw_affiliation_strings":["School of Instrument Science and Engineering, Southeast University, China"],"raw_orcid":"https://orcid.org/0000-0002-1982-6780","affiliations":[{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114310276","display_name":"Huijun Li","orcid":"https://orcid.org/0000-0002-4395-2461"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huijun Li","raw_affiliation_strings":["School of Instrument Science and Engineering, Southeast University, China"],"raw_orcid":"https://orcid.org/0000-0002-4395-2461","affiliations":[{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xinke Wang","orcid":"https://orcid.org/0009-0007-9837-6776"},"institutions":[{"id":"https://openalex.org/I3174185376","display_name":"China South Industries Group (China)","ror":"https://ror.org/04n0f2b96","country_code":"CN","type":"company","lineage":["https://openalex.org/I3174185376"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinke Wang","raw_affiliation_strings":["Automation Research Institute, China South Industries Group Corporation, China"],"raw_orcid":"https://orcid.org/0009-0007-9837-6776","affiliations":[{"raw_affiliation_string":"Automation Research Institute, China South Industries Group Corporation, China","institution_ids":["https://openalex.org/I3174185376"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111826705","display_name":"Ming Quan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I3174185376","display_name":"China South Industries Group (China)","ror":"https://ror.org/04n0f2b96","country_code":"CN","type":"company","lineage":["https://openalex.org/I3174185376"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Yang","raw_affiliation_strings":["Automation Research Institute, China South Industries Group Corporation, China"],"raw_orcid":"https://orcid.org/0009-0002-3557-8462","affiliations":[{"raw_affiliation_string":"Automation Research Institute, China South Industries Group Corporation, China","institution_ids":["https://openalex.org/I3174185376"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"102","last_page":"107"},"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":0.9973000288009644,"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":0.9944999814033508,"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/computer-science","display_name":"Computer science","score":0.6891117095947266},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6689131855964661},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4926164746284485},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4469152092933655},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.42907610535621643},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32644903659820557}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6891117095947266},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6689131855964661},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4926164746284485},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4469152092933655},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42907610535621643},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32644903659820557},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3674746.3674762","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3674746.3674762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 4th International Conference on Robotics and Control Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2736601468","https://openalex.org/W2964043796","https://openalex.org/W3020712699","https://openalex.org/W3022324591","https://openalex.org/W3130717831","https://openalex.org/W3167898434","https://openalex.org/W4288781446","https://openalex.org/W4319996426","https://openalex.org/W4389282406"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,63,97],"reward":[4,27,64,105],"design":[5,28,65],"method":[6,66,121],"for":[7,37],"peg-in-hole":[8],"insertion":[9,146],"in":[10,128,143],"uncertain":[11,144],"environments":[12],"using":[13,149],"low-dimensional":[14],"observation":[15,124],"of":[16,87,132,140],"robot":[17],"end-effector":[18],"forces.":[19],"Recent":[20],"reinforcement":[21],"learning":[22],"(RL)":[23],"studies":[24],"often":[25],"avoid":[26,58],"by":[29,71],"incorporating":[30],"prior":[31],"knowledge,":[32],"which":[33],"increases":[34],"data":[35],"requirements":[36],"RL":[38,99],"training.":[39],"Other":[40],"approaches":[41],"use":[42],"sparse":[43],"rewards":[44],"to":[45,51,57],"reduce":[46],"human-engineering":[47],"effort":[48],"but":[49],"fail":[50],"provide":[52],"non-zero":[53],"values":[54],"frequently":[55],"enough":[56],"wandering":[59,133],"traps.":[60],"We":[61,101],"propose":[62],"that":[67],"offers":[68],"improved":[69],"performance":[70],"utilizing":[72],"raw":[73],"3-dimensional":[74],"force":[75],"observations":[76],"and":[77,109,130],"action":[78],"elements":[79],"defined":[80],"through":[81],"Markov":[82],"Decision":[83],"Process":[84],"(MDP),":[85],"instead":[86],"the":[88],"commonly":[89],"used":[90],"vision-based":[91],"observations.":[92],"The":[93],"training":[94],"framework":[95],"employs":[96],"policy-based":[98],"algorithm.":[100],"compare":[102,119],"our":[103,120],"proposed":[104],"with":[106,113,122],"various":[107],"penalty":[108],"encouragement":[110],"settings,":[111],"trained":[112,148],"different":[114],"scale":[115],"parameters.":[116],"Additionally,":[117],"we":[118],"multi-modal":[123],"approaches,":[125],"demonstrating":[126],"advantages":[127],"stability":[129],"reduction":[131],"steps,":[134],"achieving":[135],"an":[136],"average":[137],"success":[138],"rate":[139],"approximately":[141],"80%":[142],"position":[145],"tasks,":[147],"Proximal":[150],"Policy":[151],"Optimization":[152],"(PPO).":[153]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}