{"id":"https://openalex.org/W7141450135","doi":"https://doi.org/10.48550/arxiv.2603.24936","title":"TIGFlow-GRPO: Trajectory Forecasting via Interaction-Aware Flow Matching and Reward-Guided Optimization","display_name":"TIGFlow-GRPO: Trajectory Forecasting via Interaction-Aware Flow Matching and Reward-Guided Optimization","publication_year":2026,"publication_date":"2026-03-26","ids":{"openalex":"https://openalex.org/W7141450135","doi":"https://doi.org/10.48550/arxiv.2603.24936"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.24936","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24936","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.24936","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054978768","display_name":"Xuepeng Jing","orcid":"https://orcid.org/0000-0002-3836-338X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing, Xuepeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082286929","display_name":"Wenhuan Lu","orcid":"https://orcid.org/0000-0002-7951-8907"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Wenhuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130811186","display_name":"Hao Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130771665","display_name":"Zhizhi Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Zhizhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102878210","display_name":"Jianguo Wei","orcid":"https://orcid.org/0009-0000-9204-8631"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Jianguo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.31040000915527344,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.31040000915527344,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.2838999927043915,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.05180000141263008,"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/trajectory","display_name":"Trajectory","score":0.8264999985694885},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6362000107765198},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6165000200271606},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5033000111579895},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.47909998893737793},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.40799999237060547},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3716000020503998},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3474999964237213}],"concepts":[{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.8264999985694885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7064999938011169},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6362000107765198},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6165000200271606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5080999732017517},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5033000111579895},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.47909998893737793},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4616999924182892},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.40799999237060547},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3716000020503998},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3474999964237213},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.3050000071525574},{"id":"https://openalex.org/C43555835","wikidata":"https://www.wikidata.org/wiki/Q2300258","display_name":"Conditional probability distribution","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C44492722","wikidata":"https://www.wikidata.org/wiki/Q327069","display_name":"Conditional probability","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C186215838","wikidata":"https://www.wikidata.org/wiki/Q772232","display_name":"Conditional expectation","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2574000060558319}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.24936","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24936","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.24936","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24936","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Human":[0],"trajectory":[1,32,72,138,205],"forecasting":[2,178],"is":[3,130],"important":[4],"for":[5,115],"intelligent":[6],"multimedia":[7,212],"systems":[8],"operating":[9],"in":[10,30,55,210],"visually":[11],"complex":[12],"environments,":[13],"such":[14],"as":[15,132],"autonomous":[16],"driving":[17],"and":[18,50,96,105,140,172,180,190],"crowd":[19],"surveillance.":[20],"Although":[21],"Conditional":[22],"Flow":[23],"Matching":[24],"(CFM)":[25],"has":[26],"shown":[27],"strong":[28],"ability":[29],"modeling":[31,206],"distributions":[33],"from":[34],"spatio-temporal":[35],"observations,":[36],"existing":[37],"approaches":[38],"still":[39],"focus":[40],"primarily":[41],"on":[42,169],"supervised":[43],"fitting,":[44],"which":[45],"may":[46],"leave":[47],"social":[48,146],"norms":[49],"scene":[51],"constraints":[52],"insufficiently":[53],"reflected":[54],"generated":[56],"trajectories.":[57],"To":[58],"address":[59],"this":[60],"issue,":[61],"we":[62,81,122],"propose":[63],"TIGFlow-GRPO,":[64],"a":[65,83,87,141],"two-stage":[66],"generative":[67],"approach":[68,198],"that":[69,176,185,195],"aligns":[70],"flow-based":[71],"generation":[73],"with":[74,86,148,207],"behavioral":[75],"rules.":[76],"In":[77,118],"the":[78,119,170,196],"first":[79],"stage,":[80,121],"build":[82],"CFM-based":[84],"predictor":[85],"Trajectory-Interaction-Graph":[88],"(TIG)":[89],"module":[90],"to":[91,136,203],"model":[92],"fine-grained":[93],"visual-spatial":[94],"interactions":[95],"strengthen":[97],"context":[98],"encoding.":[99],"This":[100],"stage":[101],"captures":[102],"both":[103],"agent-agent":[104],"agent-scene":[106],"relations":[107],"more":[108,111,187],"effectively,":[109],"providing":[110],"informative":[112],"conditional":[113],"features":[114],"subsequent":[116],"alignment.":[117],"second":[120],"perform":[123],"Flow-GRPO":[124],"post-training,":[125],"where":[126],"deterministic":[127],"flow":[128],"rollout":[129],"reformulated":[131],"stochastic":[133],"ODE-to-SDE":[134],"sampling":[135],"enable":[137],"exploration,":[139],"composite":[142],"reward":[143],"combines":[144],"view-aware":[145],"compliance":[147],"map-aware":[149],"physical":[150],"feasibility.":[151],"By":[152],"evaluating":[153],"trajectories":[154],"explored":[155],"through":[156],"SDE":[157],"rollout,":[158],"GRPO":[159],"progressively":[160],"steers":[161],"multimodal":[162],"predictions":[163],"toward":[164],"behaviorally":[165],"plausible":[166],"futures.":[167],"Experiments":[168],"ETH/UCY":[171],"SDD":[173],"datasets":[174],"show":[175],"TIGFlow-GRPOimproves":[177],"accuracy":[179],"long-horizon":[181],"stability":[182],"while":[183],"generatingtrajectories":[184],"are":[186],"socially":[188],"compliant":[189],"physically":[191],"feasible.These":[192],"results":[193],"suggest":[194],"proposed":[197],"provides":[199],"an":[200],"effective":[201],"way":[202],"connectflow-based":[204],"behavior-aware":[208],"alignment":[209],"dynamic":[211],"environments.":[213]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-28T00:00:00"}