{"id":"https://openalex.org/W4416582557","doi":"https://doi.org/10.1109/tro.2025.3636302","title":"DiffOG: Differentiable Policy Trajectory Optimization With Generalizability","display_name":"DiffOG: Differentiable Policy Trajectory Optimization With Generalizability","publication_year":2025,"publication_date":"2025-11-24","ids":{"openalex":"https://openalex.org/W4416582557","doi":"https://doi.org/10.1109/tro.2025.3636302"},"language":null,"primary_location":{"id":"doi:10.1109/tro.2025.3636302","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tro.2025.3636302","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1941-0468"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-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/A5100583938","display_name":"Zhengtong Xu","orcid":"https://orcid.org/0000-0002-2789-1910"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhengtong Xu","raw_affiliation_strings":["School of Industrial Engineering, Purdue University, West Lafayette, IN, USA","Purdue University, West Lafayette, USA"],"affiliations":[{"raw_affiliation_string":"School of Industrial Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063383026","display_name":"Zichen Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zichen Miao","raw_affiliation_strings":["School of Industrial Engineering, Purdue University, West Lafayette, IN, USA","Purdue University, West Lafayette, USA"],"affiliations":[{"raw_affiliation_string":"School of Industrial Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qiang Qiu","orcid":"https://orcid.org/0000-0003-2610-3502"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiang Qiu","raw_affiliation_strings":["School of Industrial Engineering, Purdue University, West Lafayette, IN, USA","Purdue University, West Lafayette, USA"],"affiliations":[{"raw_affiliation_string":"School of Industrial Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhe Zhang","orcid":"https://orcid.org/0009-0008-0204-0571"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhe Zhang","raw_affiliation_strings":["School of Industrial Engineering, Purdue University, West Lafayette, IN, USA","Purdue University, West Lafayette, USA"],"affiliations":[{"raw_affiliation_string":"School of Industrial Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018653973","display_name":"Yu She","orcid":"https://orcid.org/0000-0001-5914-3573"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu She","raw_affiliation_strings":["School of Industrial Engineering, Purdue University, West Lafayette, IN, USA","Purdue University, West Lafayette, USA"],"affiliations":[{"raw_affiliation_string":"School of Industrial Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100583938"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.43962215,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"42","issue":null,"first_page":"204","last_page":"223"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.5023000240325928,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.5023000240325928,"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"}},{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.10100000351667404,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.07829999923706055,"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/trajectory-optimization","display_name":"Trajectory optimization","score":0.7461000084877014},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6991999745368958},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6890000104904175},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.6597999930381775},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.4172999858856201},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.39489999413490295},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.38530001044273376},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.3772999942302704},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.36079999804496765}],"concepts":[{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.7461000084877014},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.723800003528595},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6991999745368958},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6890000104904175},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6597999930381775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5141000151634216},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.44749999046325684},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.4172999858856201},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.39489999413490295},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.38530001044273376},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3772999942302704},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36079999804496765},{"id":"https://openalex.org/C2776848632","wikidata":"https://www.wikidata.org/wiki/Q853463","display_name":"Clipping (morphology)","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33379998803138733},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.3034000098705292},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2944999933242798},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.28220000863075256},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C2989514635","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization problem","level":3,"score":0.2777999937534332},{"id":"https://openalex.org/C55660270","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.25760000944137573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tro.2025.3636302","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tro.2025.3636302","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1941-0468"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1502180988","display_name":null,"funder_award_id":"2322056","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2682039936","display_name":null,"funder_award_id":"2423068","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5578531746","display_name":null,"funder_award_id":"2023-67021-39072","funder_id":"https://openalex.org/F4320306114","funder_display_name":"U.S. Department of Agriculture"},{"id":"https://openalex.org/G6666185066","display_name":null,"funder_award_id":"2520136","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6754731134","display_name":null,"funder_award_id":"2024-67021-42878","funder_id":"https://openalex.org/F4320306114","funder_display_name":"U.S. Department of Agriculture"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306114","display_name":"U.S. Department of Agriculture","ror":"https://ror.org/01na82s61"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2142224528","https://openalex.org/W3027372030","https://openalex.org/W3117976796","https://openalex.org/W3174491581","https://openalex.org/W4230816475","https://openalex.org/W4352977012","https://openalex.org/W4385403811","https://openalex.org/W4385430674","https://openalex.org/W4401415287","https://openalex.org/W4402354026","https://openalex.org/W4402354045","https://openalex.org/W4402354112","https://openalex.org/W4402354127","https://openalex.org/W4402354171","https://openalex.org/W4402586286","https://openalex.org/W4403936678","https://openalex.org/W4405784982","https://openalex.org/W4406856990","https://openalex.org/W4414079054"],"related_works":[],"abstract_inverted_index":{"Imitation":[0],"learning-based":[1,91],"visuomotor":[2,98,166,197],"policies":[3,114,167],"excel":[4],"at":[5],"manipulation":[6],"tasks":[7,46,150],"but":[8],"often":[9],"produce":[10],"suboptimal":[11],"action":[12,122],"trajectories":[13,123],"compared":[14,193],"to":[15,22,54,72,96,124,194],"model-based":[16],"methods.":[17],"Directly":[18],"mapping":[19],"camera":[20],"data":[21],"actions":[23,75],"via":[24],"neural":[25,67],"networks":[26,68],"can":[27],"result":[28],"in":[29,34,42,66,76,141],"jerky":[30],"motions":[31],"and":[32,40,127,151,184],"difficulties":[33],"meeting":[35],"critical":[36],"constraints,":[37,55],"compromising":[38],"safety":[39],"robustness":[41,50],"real-world":[43,153],"deployment.":[44],"For":[45],"that":[47,158],"require":[48],"high":[49],"or":[51],"strict":[52],"adherence":[53],"ensuring":[56],"trajectory":[57,85,92,107,163,176,186],"quality":[58,164],"is":[59],"crucial.":[60],"However,":[61],"the":[62,102,134,162],"lack":[63],"of":[64,106,165],"interpretability":[65],"makes":[69],"it":[70],"challenging":[71],"generate":[73],"constraint-compliant":[74,129],"a":[77,90,116],"controlled":[78],"manner.":[79],"This":[80],"paper":[81],"introduces":[82],"differentiable":[83,104],"policy":[84,142,173],"optimization":[86,93,108,118],"with":[87,109,115,133],"generalizability":[88],"(DiffOG),":[89],"framework":[94],"designed":[95],"enhance":[97],"policies.":[99],"By":[100],"leveraging":[101],"proposed":[103],"formulation":[105],"transformer,":[110],"DiffOG":[111,120,146,159,189],"seamlessly":[112],"integrates":[113],"generalizable":[117],"layer.":[119],"refines":[121],"be":[125],"smoother":[126],"more":[128],"while":[130,168],"maintaining":[131],"alignment":[132],"original":[135],"demonstration":[136],"distribution,":[137],"thus":[138],"avoiding":[139],"degradation":[140],"performance.":[143],"We":[144],"evaluated":[145],"across":[147],"11":[148],"simulated":[149],"2":[152],"tasks.":[154],"The":[155],"results":[156],"demonstrate":[157],"significantly":[160],"enhances":[161],"having":[169],"minimal":[170],"impact":[171],"on":[172],"performance,":[174],"outperforming":[175],"processing":[177],"baselines":[178],"such":[179],"as":[180],"greedy":[181],"constraint":[182],"clipping":[183],"penalty-based":[185],"optimization.":[187],"Furthermore,":[188],"achieves":[190],"superior":[191],"performance":[192],"existing":[195],"constrained":[196],"policy.":[198]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-25T00:00:00"}