{"id":"https://openalex.org/W2922294417","doi":"https://doi.org/10.1109/robio.2018.8665328","title":"Sparse Reward Based Manipulator Motion Planning by Using High Speed Learning from Demonstrations","display_name":"Sparse Reward Based Manipulator Motion Planning by Using High Speed Learning from Demonstrations","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2922294417","doi":"https://doi.org/10.1109/robio.2018.8665328","mag":"2922294417"},"language":"en","primary_location":{"id":"doi:10.1109/robio.2018.8665328","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio.2018.8665328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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/A5017790030","display_name":"Guoyu Zuo","orcid":"https://orcid.org/0000-0002-7624-4728"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoyu Zuo","raw_affiliation_strings":["Faculty of Information Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005512500","display_name":"Jiahao Lu","orcid":"https://orcid.org/0000-0002-6384-6842"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahao Lu","raw_affiliation_strings":["Faculty of Information Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030734015","display_name":"Tingting Pan","orcid":"https://orcid.org/0000-0003-2100-6797"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingting Pan","raw_affiliation_strings":["Faculty of Information Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.20047667,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"8","issue":null,"first_page":"518","last_page":"523"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.998199999332428,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9966999888420105,"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/hindsight-bias","display_name":"Hindsight bias","score":0.9353572130203247},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7754228115081787},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6689786911010742},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6648480892181396},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.534139096736908},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.523735523223877},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.5224758386611938},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.5168381333351135},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5044368505477905},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35818225145339966},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11203768849372864},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07266756892204285}],"concepts":[{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.9353572130203247},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7754228115081787},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6689786911010742},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6648480892181396},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.534139096736908},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.523735523223877},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.5224758386611938},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.5168381333351135},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5044368505477905},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35818225145339966},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11203768849372864},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07266756892204285},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio.2018.8665328","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio.2018.8665328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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":10,"referenced_works":["https://openalex.org/W2126909264","https://openalex.org/W2575705757","https://openalex.org/W2741122588","https://openalex.org/W2963099939","https://openalex.org/W2963277051","https://openalex.org/W2963864421","https://openalex.org/W4300799055","https://openalex.org/W6684921986","https://openalex.org/W6740801417","https://openalex.org/W7042995194"],"related_works":["https://openalex.org/W3197854638","https://openalex.org/W3140454661","https://openalex.org/W4245029315","https://openalex.org/W2139970489","https://openalex.org/W1492315459","https://openalex.org/W1512434910","https://openalex.org/W2540910169","https://openalex.org/W3089780453","https://openalex.org/W3148904318","https://openalex.org/W2022803902"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposed":[2,141],"a":[3,35],"high":[4],"speed":[5,118],"learning":[6],"from":[7,65],"demonstrations":[8,36,136,164],"(LfD)":[9],"method":[10,76,134,142],"for":[11,47],"sparse":[12,94,147],"reward":[13],"based":[14],"motion":[15,89],"planning":[16,90],"problem":[17],"of":[18,163],"manipulator":[19,88],"by":[20],"using":[21],"hindsight":[22,53],"experience":[23,49,54,63,82],"replay":[24,37,43,55,68],"(HER)":[25],"mechanism":[26,56],"and":[27,39,51,84,101,149],"deep":[28,72,130],"deterministic":[29,73,131],"policy":[30,74,132],"gradient":[31,75,133],"(DDPG)":[32],"method.":[33],"First,":[34],"buffer":[38,44],"an":[40],"agent":[41,151],"exploration":[42],"are":[45],"created":[46],"storing":[48],"data,":[50],"the":[52,62,66,71,81,87,93,99,107,111,116,129,140,146,150,155,159],"is":[57,77,119],"subsequently":[58],"used":[59,78],"to":[60,79,121,128],"acquire":[61],"data":[64,83],"two":[67],"buffers.":[69],"Then,":[70],"learn":[80],"finally":[85],"fulfil":[86],"tasks":[91,103],"under":[92,158],"reward.":[95],"Last,":[96],"experiments":[97],"on":[98],"pushing":[100],"pick-and-place":[102],"were":[104],"conducted":[105],"in":[106,110],"robotics":[108],"environment":[109],"gym.":[112],"Results":[113],"show":[114],"that":[115],"training":[117],"increased":[120],"at":[122],"least":[123],"10":[124],"times":[125],"as":[126],"compared":[127],"without":[135],"data.":[137,165],"In":[138],"addition,":[139],"can":[143,152],"effectively":[144],"utilize":[145],"reward,":[148],"quickly":[153],"complete":[154],"task":[156],"even":[157],"low":[160],"success":[161],"rate":[162]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}