{"id":"https://openalex.org/W3191572904","doi":"https://doi.org/10.24963/ijcai.2021/679","title":"Planning and Reinforcement Learning for General-Purpose Service Robots","display_name":"Planning and Reinforcement Learning for General-Purpose Service Robots","publication_year":2021,"publication_date":"2021-08-01","ids":{"openalex":"https://openalex.org/W3191572904","doi":"https://doi.org/10.24963/ijcai.2021/679","mag":"3191572904"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2021/679","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/679","pdf_url":"https://www.ijcai.org/proceedings/2021/0679.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2021/0679.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032392594","display_name":"Yuqian Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuqian Jiang","raw_affiliation_strings":["The University of Texas at Austin","University of Texas at Austin, Texas, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"University of Texas at Austin, Texas, US","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5032392594"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":0.1127,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.40593489,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4895","last_page":"4896"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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":0.9988999962806702,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9979000091552734,"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/robot","display_name":"Robot","score":0.8146741390228271},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7997720837593079},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6972998380661011},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6209402084350586},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.61720871925354},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.6016056537628174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5993445515632629},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5932477712631226},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.5855143070220947},{"id":"https://openalex.org/keywords/automated-planning-and-scheduling","display_name":"Automated planning and scheduling","score":0.5472897291183472},{"id":"https://openalex.org/keywords/service-robot","display_name":"Service robot","score":0.5214756727218628},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.44919583201408386},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.30398234724998474},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19705137610435486},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.13367778062820435},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.059571921825408936}],"concepts":[{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.8146741390228271},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7997720837593079},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6972998380661011},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6209402084350586},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.61720871925354},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.6016056537628174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5993445515632629},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5932477712631226},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.5855143070220947},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.5472897291183472},{"id":"https://openalex.org/C2776228582","wikidata":"https://www.wikidata.org/wiki/Q7455797","display_name":"Service robot","level":3,"score":0.5214756727218628},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.44919583201408386},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.30398234724998474},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19705137610435486},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.13367778062820435},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.059571921825408936},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2021/679","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/679","pdf_url":"https://www.ijcai.org/proceedings/2021/0679.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2021/679","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/679","pdf_url":"https://www.ijcai.org/proceedings/2021/0679.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3191572904.pdf","grobid_xml":"https://content.openalex.org/works/W3191572904.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1777239053","https://openalex.org/W2101915445","https://openalex.org/W2884628842","https://openalex.org/W2928506096","https://openalex.org/W2955770737","https://openalex.org/W2963733582","https://openalex.org/W3004011906","https://openalex.org/W3026908267","https://openalex.org/W3040033820","https://openalex.org/W3132865807","https://openalex.org/W4294982428","https://openalex.org/W4312272037"],"related_works":["https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3033920833","https://openalex.org/W3127551068","https://openalex.org/W2165180011","https://openalex.org/W3165944253","https://openalex.org/W4220829754","https://openalex.org/W2351343564","https://openalex.org/W2170052867"],"abstract_inverted_index":{"Despite":[0],"recent":[1],"progress":[2],"in":[3,16],"AI":[4],"and":[5,20,34,43,60],"robotics":[6],"research,":[7],"especially":[8],"learned":[9],"robot":[10,41,74],"skills,":[11],"there":[12],"remain":[13],"significant":[14,83],"challenges":[15],"building":[17],"robust,":[18],"scalable,":[19],"general-purpose":[21,87],"systems":[22],"for":[23,72],"service":[24,73,88],"robots.":[25,89],"This":[26],"Ph.D.":[27],"research":[28],"aims":[29],"to":[30,37,45,57],"combine":[31],"symbolic":[32],"planning":[33,53],"reinforcement":[35,66],"learning":[36,67],"reason":[38],"about":[39],"high-level":[40],"tasks":[42],"adapt":[44,56],"the":[46,58],"real":[47],"world.":[48],"We":[49],"will":[50,80],"introduce":[51],"task":[52],"algorithms":[54],"that":[55,69],"environment":[59],"other":[61],"agents,":[62],"as":[63,65],"well":[64],"methods":[68],"are":[70],"practical":[71],"systems.":[75],"Taken":[76],"together,":[77],"this":[78],"work":[79],"make":[81],"a":[82],"step":[84],"towards":[85],"creating":[86]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}