{"id":"https://openalex.org/W4416749103","doi":"https://doi.org/10.1109/iros60139.2025.11247412","title":"Non-differentiable Reward Optimization for Diffusion-based Autonomous Motion Planning","display_name":"Non-differentiable Reward Optimization for Diffusion-based Autonomous Motion Planning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749103","doi":"https://doi.org/10.1109/iros60139.2025.11247412"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247412","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247412","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":"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/A5024313815","display_name":"Giwon Lee","orcid":"https://orcid.org/0000-0002-6832-658X"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Giwon Lee","raw_affiliation_strings":["KAIST,Department of Mechanical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Department of Mechanical Engineering","institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210099236"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101688558","display_name":"Dae-Hee Park","orcid":"https://orcid.org/0000-0002-3961-6932"},"institutions":[{"id":"https://openalex.org/I193352282","display_name":"Daegu Gyeongbuk Institute of Science and Technology","ror":"https://ror.org/03frjya69","country_code":"KR","type":"education","lineage":["https://openalex.org/I193352282"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Daehee Park","raw_affiliation_strings":["DGIST,Department of Electrical Engineering and Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DGIST,Department of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I193352282"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060718300","display_name":"Jaewoo Jeong","orcid":"https://orcid.org/0000-0001-8789-792X"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Jaewoo Jeong","raw_affiliation_strings":["KAIST,Department of Mechanical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Department of Mechanical Engineering","institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210099236"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110557165","display_name":"Kuk-Jin Yoon","orcid":"https://orcid.org/0000-0002-1634-2756"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Kuk-Jin Yoon","raw_affiliation_strings":["KAIST,Department of Mechanical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Department of Mechanical Engineering","institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210099236"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4985,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70899738,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"13215","last_page":"13222"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.5073000192642212,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.5073000192642212,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.15700000524520874,"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":0.07590000331401825,"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":0.5623999834060669},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.5526000261306763},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5385000109672546},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.38830000162124634},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.3831999897956848},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.3569999933242798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7001000046730042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5874999761581421},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5623999834060669},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.5526000261306763},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5385000109672546},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4690000116825104},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.3831999897956848},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.3569999933242798},{"id":"https://openalex.org/C2781220375","wikidata":"https://www.wikidata.org/wiki/Q814208","display_name":"Flocking (texture)","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.266400009393692},{"id":"https://openalex.org/C2777113093","wikidata":"https://www.wikidata.org/wiki/Q221488","display_name":"Pedestrian","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247412","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247412","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/F4320311419","display_name":"Ministry of Health","ror":null},{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322107","display_name":"Korea Health Industry Development Institute","ror":"https://ror.org/00fdzyk40"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1970206276","https://openalex.org/W1971086298","https://openalex.org/W1976930960","https://openalex.org/W2076337359","https://openalex.org/W2145339207","https://openalex.org/W2532516272","https://openalex.org/W2890001928","https://openalex.org/W2924607344","https://openalex.org/W3003329097","https://openalex.org/W3023076313","https://openalex.org/W3109791956","https://openalex.org/W3110109289","https://openalex.org/W3182751084","https://openalex.org/W4200134104","https://openalex.org/W4312305613","https://openalex.org/W4312396550","https://openalex.org/W4312945815","https://openalex.org/W4312991107","https://openalex.org/W4313131073","https://openalex.org/W4313147057","https://openalex.org/W4381198967","https://openalex.org/W4386076407","https://openalex.org/W4389666419","https://openalex.org/W4393147477","https://openalex.org/W4401042519","https://openalex.org/W4401413933","https://openalex.org/W4402753718","https://openalex.org/W4403760824","https://openalex.org/W4413157019"],"related_works":[],"abstract_inverted_index":{"Safe":[0],"and":[1,43,88,124,144,170],"effective":[2,142,171],"motion":[3,34,76,110,172],"planning":[4,77,111],"is":[5],"crucial":[6],"for":[7,108,168],"autonomous":[8],"robots.":[9],"Diffusion":[10],"models":[11,32,53,146],"excel":[12],"at":[13],"capturing":[14,67],"complex":[15,41],"agent":[16],"interactions,":[17],"a":[18,103,129,136],"fundamental":[19],"aspect":[20],"of":[21,75,165],"decision-making":[22,70],"in":[23,39,56,79],"dynamic":[24,131],"environments.":[25],"Recent":[26],"studies":[27],"have":[28,54],"successfully":[29],"applied":[30],"diffusion":[31,52,109],"to":[33,115,134,159],"planning,":[35],"demonstrating":[36],"their":[37,50],"competence":[38],"handling":[40],"scenarios":[42],"accurately":[44],"predicting":[45],"multi-modal":[46],"future":[47],"trajectories.":[48],"Despite":[49],"effectiveness,":[51],"limitations":[55],"training":[57,106,143],"objectives,":[58,82],"as":[59,84],"they":[60],"approximate":[61],"data":[62],"distributions":[63],"rather":[64],"than":[65],"explicitly":[66,121],"the":[68,73,163],"underlying":[69],"dynamics.":[71],"However,":[72],"crux":[74],"lies":[78],"non-differentiable":[80,118],"downstream":[81],"such":[83],"safety":[85,123],"(collision":[86],"avoidance)":[87],"effectiveness":[89],"(goal-reaching),":[90],"which":[91],"conventional":[92],"learning":[93],"algorithms":[94],"cannot":[95],"directly":[96],"optimize.":[97],"In":[98],"this":[99],"paper,":[100],"we":[101,127],"propose":[102],"reinforcement":[104],"learning-based":[105],"scheme":[107],"models,":[112],"enabling":[113],"them":[114],"effectively":[116],"learn":[117],"objectives":[119],"that":[120],"measure":[122],"effectiveness.":[125],"Specifically,":[126],"introduce":[128],"reward-weighted":[130],"thresholding":[132],"algorithm":[133],"shape":[135],"dense":[137],"reward":[138],"signal,":[139],"facilitating":[140],"more":[141],"outperforming":[145],"trained":[147],"with":[148],"differentiable":[149],"objectives.":[150],"State-of-the-art":[151],"performance":[152],"on":[153],"pedestrian":[154],"datasets":[155],"(CrowdNav,":[156],"ETH-UCY)":[157],"compared":[158],"various":[160],"baselines":[161],"demonstrates":[162],"versatility":[164],"our":[166],"approach":[167],"safe":[169],"planning.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}