{"id":"https://openalex.org/W4416750047","doi":"https://doi.org/10.1109/iros60139.2025.11245839","title":"Embodied Escaping: End-to-End Reinforcement Learning for Robot Navigation in Narrow Environment","display_name":"Embodied Escaping: End-to-End Reinforcement Learning for Robot Navigation in Narrow Environment","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750047","doi":"https://doi.org/10.1109/iros60139.2025.11245839"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11245839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245839","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5100693362","display_name":"Han Zheng","orcid":"https://orcid.org/0000-0003-4032-4299"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Zheng","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025230810","display_name":"Jiale Zhang","orcid":"https://orcid.org/0009-0006-6523-9479"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiale Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002118929","display_name":"Mingyang Jiang","orcid":"https://orcid.org/0000-0002-3277-9536"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyang Jiang","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064589038","display_name":"Peiyuan Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144102","display_name":"Wuhu Hit Robot Technology Research Institute","ror":"https://ror.org/049w4dp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144102"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiyuan Liu","raw_affiliation_strings":["Cleanix Robotics Co., Ltd.,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cleanix Robotics Co., Ltd.,China","institution_ids":["https://openalex.org/I4210144102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076306018","display_name":"Danni Liu","orcid":"https://orcid.org/0000-0001-5419-1963"},"institutions":[{"id":"https://openalex.org/I4210144102","display_name":"Wuhu Hit Robot Technology Research Institute","ror":"https://ror.org/049w4dp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144102"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Danni Liu","raw_affiliation_strings":["Cleanix Robotics Co., Ltd.,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cleanix Robotics Co., Ltd.,China","institution_ids":["https://openalex.org/I4210144102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101960817","display_name":"Tong Qin","orcid":"https://orcid.org/0000-0001-8177-0573"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Qin","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030464887","display_name":"Ming Yang","orcid":"https://orcid.org/0000-0002-4470-3467"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Yang","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]}],"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":"9719","last_page":"9726"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.6850000023841858,"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"}},"topics":[{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.6850000023841858,"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":0.09459999948740005,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.05889999866485596,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7763000130653381},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7185999751091003},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.7016000151634216},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6201000213623047},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.5246999859809875},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4871000051498413},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.4731000065803528},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.45509999990463257},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.45159998536109924}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7763000130653381},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7185999751091003},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.7016000151634216},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6201000213623047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6087999939918518},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6029999852180481},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.5246999859809875},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4871000051498413},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.4731000065803528},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.45509999990463257},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.45159998536109924},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.4453999996185303},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3880999982357025},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.37279999256134033},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.35740000009536743},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3431999981403351},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.34290000796318054},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C2778835581","wikidata":"https://www.wikidata.org/wiki/Q2916098","display_name":"Autonomous robot","level":4,"score":0.33079999685287476},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.3093000054359436},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.303600013256073},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2996000051498413},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.2989000082015991},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.29789999127388},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2890999913215637},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2888999879360199},{"id":"https://openalex.org/C19766214","wikidata":"https://www.wikidata.org/wiki/Q4880688","display_name":"Behavior-based robotics","level":4,"score":0.28790000081062317},{"id":"https://openalex.org/C26990112","wikidata":"https://www.wikidata.org/wiki/Q6887224","display_name":"Mobile robot navigation","level":5,"score":0.262800008058548},{"id":"https://openalex.org/C162947575","wikidata":"https://www.wikidata.org/wiki/Q2005645","display_name":"Social robot","level":5,"score":0.25999999046325684},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11245839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245839","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1963926535","https://openalex.org/W1969483458","https://openalex.org/W2041717818","https://openalex.org/W2117211893","https://openalex.org/W2142332594","https://openalex.org/W2345973286","https://openalex.org/W2363637015","https://openalex.org/W2557741120","https://openalex.org/W2724806769","https://openalex.org/W2910504340","https://openalex.org/W2951360122","https://openalex.org/W3015470607","https://openalex.org/W3037164854","https://openalex.org/W3100789280","https://openalex.org/W3147503465","https://openalex.org/W3159846780","https://openalex.org/W3197167612","https://openalex.org/W3198919602","https://openalex.org/W3206426202","https://openalex.org/W3207011427","https://openalex.org/W3212923689","https://openalex.org/W4200004515","https://openalex.org/W4286375451","https://openalex.org/W4322730824","https://openalex.org/W4327522515","https://openalex.org/W4364379138","https://openalex.org/W4387129524","https://openalex.org/W4388240413","https://openalex.org/W4388918852","https://openalex.org/W4391770052","https://openalex.org/W4396910085","https://openalex.org/W4401415884","https://openalex.org/W4401417422","https://openalex.org/W4408859815"],"related_works":[],"abstract_inverted_index":{"Autonomous":[0],"navigation":[1],"is":[2,17,142,199],"a":[3,64,89,106,117,145],"fundamental":[4],"task":[5],"for":[6,73],"robot":[7,141,163],"vacuum":[8],"cleaners":[9],"in":[10,27,85,183],"indoor":[11],"environments.":[12],"Since":[13],"their":[14],"core":[15],"function":[16],"to":[18,37,40,110,128],"clean":[19],"entire":[20],"areas,":[21],"robots":[22],"inevitably":[23],"encounter":[24],"dead":[25,74,169],"zones":[26],"cluttered":[28],"and":[29,47,100,135,148,153,179,188,196],"narrow":[30],"scenarios.":[31],"Existing":[32],"planning":[33,178],"methods":[34,182],"often":[35],"fail":[36],"escape":[38,166],"due":[39],"complex":[41],"environmental":[42],"constraints,":[43],"high-dimensional":[44],"search":[45],"spaces,":[46],"high":[48],"difficulty":[49,158],"maneuvers.":[50],"To":[51,77],"address":[52],"these":[53],"challenges,":[54],"this":[55],"paper":[56],"proposes":[57],"an":[58,69,124],"embodied":[59],"escaping":[60],"model":[61],"that":[62,93,161],"leverages":[63],"reinforcement":[65,180],"learning-based":[66],"policy":[67,92],"with":[68,116,144],"efficient":[70],"action":[71,102,108,114,125],"mask":[72,126],"zone":[75],"escaping.":[76],"alleviate":[78],"the":[79,82,112],"issue":[80],"of":[81,185],"sparse":[83],"reward":[84],"training,":[86],"we":[87,104,122],"introduce":[88],"hybrid":[90],"training":[91],"improves":[94],"learning":[95,181],"efficiency.":[96,136],"In":[97,137],"handling":[98],"redundant":[99],"ineffective":[101],"options,":[103],"design":[105],"novel":[107],"representation":[109],"reshape":[111],"discrete":[113],"space":[115],"uniform":[118],"turning":[119],"radius.":[120],"Furthermore,":[121],"develop":[123],"strategy":[127],"select":[129],"valid":[130],"actions":[131],"quickly,":[132],"balancing":[133],"precision":[134],"real-world":[138,197],"experiments,":[139],"our":[140,162,172,194],"equipped":[143],"Lidar,":[146],"IMU,":[147],"two-wheel":[149],"encoders.":[150],"Extensive":[151],"quantitative":[152],"qualitative":[154],"experiments":[155],"across":[156],"varying":[157],"levels":[159],"demonstrate":[160],"can":[164],"consistently":[165],"from":[167],"challenging":[168],"zones.":[170],"Moreover,":[171],"approach":[173],"significantly":[174],"outperforms":[175],"compared":[176],"path":[177],"terms":[184],"success":[186],"rate":[187],"collision":[189],"avoidance.":[190],"A":[191],"video":[192],"showcasing":[193],"methodology":[195],"demonstrations":[198],"available":[200],"at":[201],"https://youtu.be/kBaaYWGhNuE.":[202]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}