{"id":"https://openalex.org/W2103085926","doi":"https://doi.org/10.1109/robot.2006.1642211","title":"Using reinforcement learning to improve exploration trajectories for error minimization","display_name":"Using reinforcement learning to improve exploration trajectories for error minimization","publication_year":2006,"publication_date":"2006-07-10","ids":{"openalex":"https://openalex.org/W2103085926","doi":"https://doi.org/10.1109/robot.2006.1642211","mag":"2103085926"},"language":"en","primary_location":{"id":"doi:10.1109/robot.2006.1642211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot.2006.1642211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006.","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/A5073644080","display_name":"Thomas Kollar","orcid":"https://orcid.org/0000-0003-2598-8118"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"T. Kollar","raw_affiliation_strings":["Computer Science and AI Laboratory, MIT, Cambridge, MA, USA","Comput. Sci. & AI Lab., MIT, Cambridge, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and AI Laboratory, MIT, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"Comput. Sci. & AI Lab., MIT, Cambridge, MA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004980809","display_name":"Nicholas Roy","orcid":"https://orcid.org/0000-0002-4277-2928"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"N. Roy","raw_affiliation_strings":["Computer Science and AI Laboratory, MIT, Cambridge, MA, USA","Comput. Sci. & AI Lab., MIT, Cambridge, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and AI Laboratory, MIT, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"Comput. Sci. & AI Lab., MIT, Cambridge, MA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.687,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.9095162,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3338","last_page":"3343"},"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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":0.9994000196456909,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8381853103637695},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6858409643173218},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6843556761741638},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6553122997283936},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5907270908355713},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5669413208961487},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5230054259300232},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5069275498390198},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.45912277698516846},{"id":"https://openalex.org/keywords/motion-control","display_name":"Motion control","score":0.44285038113594055},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.42987504601478577},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3925282955169678},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37878578901290894}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8381853103637695},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6858409643173218},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6843556761741638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6553122997283936},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5907270908355713},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5669413208961487},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5230054259300232},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5069275498390198},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.45912277698516846},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.44285038113594055},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.42987504601478577},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3925282955169678},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37878578901290894},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/robot.2006.1642211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot.2006.1642211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.208.2506","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.208.2506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://tkollar.csail.mit.edu/TK/Publications/icra06-tk/","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1601740268","https://openalex.org/W1684737195","https://openalex.org/W2091107301","https://openalex.org/W2118429180","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2143864104","https://openalex.org/W2143964548","https://openalex.org/W2145938889","https://openalex.org/W2150184961","https://openalex.org/W2165421048","https://openalex.org/W2168359464","https://openalex.org/W2336416123","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W3022404379","https://openalex.org/W4214717370","https://openalex.org/W4242606736","https://openalex.org/W4285719527","https://openalex.org/W4298023569","https://openalex.org/W6684096483"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"The":[0,12],"mapping":[1,17,109],"and":[2,29,101],"localization":[3],"problems":[4],"have":[5],"received":[6],"considerable":[7],"attention":[8],"in":[9,107],"robotics":[10],"recently.":[11],"exploration":[13,48,86,130],"problem":[14],"that":[15,134],"drives":[16],"has":[18,67,79],"started":[19],"to":[20,40,57,98,119],"generate":[21,120],"similar":[22],"attention,":[23],"as":[24],"the":[25,37,45,53,74,76,81,103,108,135,139,145],"ease":[26],"of":[27,31,90,105,147],"construction":[28],"quality":[30,83],"map":[32,82,141],"is":[33,73],"strongly":[34],"dependent":[35],"on":[36,51,80],"strategy":[38],"used":[39,118],"acquire":[41],"sensor":[42],"data":[43],"for":[44,63],"map.":[46],"Most":[47],"strategies":[49],"concentrate":[50],"selecting":[52],"next":[54],"best":[55],"measurement":[56],"take,":[58],"trading":[59],"off":[60],"information":[61,128],"gathering":[62,129],"regular":[64],"relocalization.":[65],"What":[66],"not":[68],"been":[69],"studied":[70],"so":[71],"far":[72],"effect":[75],"robot":[77,91,151],"controller":[78],"while":[84,124],"executing":[85,125],"plans.":[87],"Certain":[88],"kinds":[89],"motion":[92,122,152],"(e.g,":[93],"sharp":[94],"turns)":[95],"are":[96],"hard":[97],"estimate":[99],"correctly,":[100],"increase":[102],"likelihood":[104],"errors":[106],"process.":[110],"We":[111,132],"show":[112,133],"how":[113],"reinforcement":[114],"learning":[115],"can":[116],"be":[117],"good":[121],"control":[123],"a":[126],"simple":[127],"strategy.":[131],"learned":[136],"policy":[137],"reduces":[138],"overall":[140],"uncertainty":[142,148],"by":[143,150],"reducing":[144],"amount":[146],"generated":[149]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}