{"id":"https://openalex.org/W3129198075","doi":"https://doi.org/10.1109/iros45743.2020.9341620","title":"Efficient Exploration in Constrained Environments with Goal-Oriented Reference Path","display_name":"Efficient Exploration in Constrained Environments with Goal-Oriented Reference Path","publication_year":2020,"publication_date":"2020-10-24","ids":{"openalex":"https://openalex.org/W3129198075","doi":"https://doi.org/10.1109/iros45743.2020.9341620","mag":"3129198075"},"language":"en","primary_location":{"id":"doi:10.1109/iros45743.2020.9341620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","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/A5064968116","display_name":"Kei Ota","orcid":"https://orcid.org/0000-0002-5744-3027"},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]},{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kei Ota","raw_affiliation_strings":["Information Technology R&D Center, Mitsubishi Electric Corporation, Japan","National Institute of Advanced Industrial Science and Technology (AIST), Japan"],"affiliations":[{"raw_affiliation_string":"Information Technology R&D Center, Mitsubishi Electric Corporation, Japan","institution_ids":["https://openalex.org/I4210133125"]},{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102748358","display_name":"Yoko Sasaki","orcid":"https://orcid.org/0000-0002-1220-6124"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoko Sasaki","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010530960","display_name":"Devesh K. Jha","orcid":"https://orcid.org/0000-0002-7843-9545"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Devesh K. Jha","raw_affiliation_strings":["Mitsubishi Electric Research Labs, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Labs, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023347873","display_name":"Yusuke Yoshiyasu","orcid":"https://orcid.org/0000-0002-0433-9832"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Yoshiyasu","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045505869","display_name":"Asako Kanezaki","orcid":"https://orcid.org/0000-0003-3217-1405"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Asako Kanezaki","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Japan","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5064968116"],"corresponding_institution_ids":["https://openalex.org/I4210133125","https://openalex.org/I73613424"],"apc_list":null,"apc_paid":null,"fwci":3.0489,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.93058762,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9984999895095825,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9962000250816345,"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":0.834834098815918},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8000330924987793},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7003048658370972},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6207495927810669},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.6009941101074219},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.5580217242240906},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5538144707679749},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5486963987350464},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.47520264983177185},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.4459307789802551},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.4261513352394104},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3213996887207031},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.23129358887672424},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08288446068763733}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.834834098815918},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8000330924987793},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7003048658370972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6207495927810669},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.6009941101074219},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.5580217242240906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5538144707679749},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5486963987350464},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.47520264983177185},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.4459307789802551},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.4261513352394104},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3213996887207031},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.23129358887672424},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08288446068763733},{"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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros45743.2020.9341620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1424654272","https://openalex.org/W1771410628","https://openalex.org/W1969483458","https://openalex.org/W2006140353","https://openalex.org/W2099144379","https://openalex.org/W2104733512","https://openalex.org/W2128990851","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2173248099","https://openalex.org/W2194321275","https://openalex.org/W2194775991","https://openalex.org/W2766447205","https://openalex.org/W2775496939","https://openalex.org/W2781726626","https://openalex.org/W2787666871","https://openalex.org/W2894417726","https://openalex.org/W2905173465","https://openalex.org/W2912063360","https://openalex.org/W2919109858","https://openalex.org/W2962902376","https://openalex.org/W2962917939","https://openalex.org/W2963446712","https://openalex.org/W2963858432","https://openalex.org/W2963864421","https://openalex.org/W2964319688","https://openalex.org/W2964333597","https://openalex.org/W2967969632","https://openalex.org/W2968104655","https://openalex.org/W3003373508","https://openalex.org/W3021208093","https://openalex.org/W3029192705","https://openalex.org/W6638018090","https://openalex.org/W6674627687","https://openalex.org/W6675999342","https://openalex.org/W6684921986","https://openalex.org/W6747473740","https://openalex.org/W6759886010"],"related_works":["https://openalex.org/W2930076404","https://openalex.org/W4253519380","https://openalex.org/W2071957557","https://openalex.org/W2596413128","https://openalex.org/W2356867392","https://openalex.org/W2782776446","https://openalex.org/W2155948905","https://openalex.org/W4380590094","https://openalex.org/W3043170174","https://openalex.org/W2050548713"],"abstract_inverted_index":{"In":[0],"this":[1,124],"paper,":[2],"we":[3,57,106],"consider":[4],"the":[5,81,88,98,122,138,142,158,189],"problem":[6,83],"of":[7,60,90,121,167,171],"building":[8],"learning":[9,69,96,131,150,172],"agents":[10,26],"that":[11,27,48,112,164,184],"can":[12,28,113],"efficiently":[13,29],"learn":[14,30,134],"to":[15,24,31,35,79,133,135,145,195],"navigate":[16],"in":[17,51,71,157],"constrained":[18],"environments.":[19,197],"The":[20,75],"main":[21],"goal":[22],"is":[23,78,92,100,125],"design":[25],"understand":[32],"and":[33,67,86,182,192],"generalize":[34],"different":[36],"environments":[37],"using":[38],"high-dimensional":[39],"inputs":[40],"(a":[41],"2D":[42],"map),":[43],"while":[44,149],"following":[45],"feasible":[46],"paths":[47,116],"avoid":[49],"obstacles":[50],"obstacle-cluttered":[52],"environment.":[53],"To":[54],"achieve":[55,146],"this,":[56],"make":[58],"use":[59],"traditional":[61],"path":[62],"planning":[63,85],"algorithms,":[64],"supervised":[65,95],"learning,":[66],"reinforcement":[68,103,130],"algorithms":[70],"a":[72,108,119],"synergistic":[73],"way.":[74],"key":[76],"idea":[77],"decouple":[80],"navigation":[82],"into":[84],"control,":[87],"former":[89],"which":[91],"achieved":[93],"by":[94,102,128],"whereas":[97],"latter":[99],"done":[101],"learning.":[104],"Specifically,":[105],"train":[107],"deep":[109],"convolutional":[110],"network":[111],"predict":[114],"collision-free":[115],"based":[117],"on":[118],"map":[120],"environment-":[123],"then":[126],"used":[127],"an":[129],"algorithm":[132],"closely":[136],"follow":[137],"path.":[139],"This":[140],"allows":[141,165],"trained":[143],"agent":[144],"good":[147],"generalization":[148,193],"faster.":[151],"We":[152,174],"test":[153],"our":[154,176,185],"proposed":[155,160,177],"method":[156,178,186],"recently":[159],"Safety":[161],"Gym":[162],"suite":[163],"testing":[166],"safety-constraints":[168],"during":[169],"training":[170],"agents.":[173],"compare":[175],"with":[179],"existing":[180],"work":[181],"show":[183],"consistently":[187],"improves":[188],"sample":[190],"efficiency":[191],"capability":[194],"novel":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}