[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85696-en":3,"doc-seo-85696-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},85696,137441390410,"Hazel","https://ap-avatar.wpscdn.com/avatar/2000252f4ab5702993?_k=1776741390130283984",8,"Research & Report","SWIFT A Small-World Interaction Framework for Flow-Aware Trajectory Prediction in Autonomous Driving","Accurate trajectory prediction in autonomous driving depends on capturing dynamic, context-dependent interactions among traffic agents. Most current methods rely mainly on data-driven representations and lack structural priors, weakening performance under distribution shifts. SWIFT revisits interaction modeling using traffic-network structure and dynamics, combining small-world networks and traffic-flow theory. It adds a Small-World Interaction Network for local-to-global inductive bias, a Flow Regime Encoder for scene-level adaptation, and a multi-relational graph module for higher-order reasoning, improving accuracy, generalization, robustness, and sample efficiency on nuScenes, MoCAD, and NGSIM.","SWIFT: A Small-World Interaction Framework for Flow-Aware Trajectory Prediction in Autonomous  \nDriving  \nChengyue Wang, Bin Rao, Haicheng Liao, Bonan Wang, Chengzhong Xu, Fellow, IEEE and Zhenning Li†  \narXiv :2607 .0974 1v 1 [ cs .RO] 3 Jul 2026  \nAbstract—Accurate trajectory prediction in autonomous driving hinges on modeling dynamic and context-dependent interactions among traffic agents. However, most existing approaches are purely data-driven and lack structural priors, which limits their generalization under distribution shifts. In this work, interaction modeling is revisited through the structure and dynamics of traffic networks, and SWIFT (Small-World Interaction Framework for Trajectory prediction) is proposed as a unified framework that integrates small-world networks with traffic flow theory. SWIFT introduces structural inductive biases via a Small-World Interaction Network that captures both local and global dependencies, and a Flow Regime Encoder that adapts the interaction structure to scene-level traffic states. Interaction reasoning is further enhanced through a multi-relational graph module that explicitly encodes direct and higher-order agent relationships. Extensive experiments on three real-world datasets, nuScenes, MoCAD, and NGSIM, show that SWIFT consistently outperforms strong baselines in prediction accuracy across diverse traffic regimes. Beyond accuracy, SWIFT exhibits improved generalization to unseen locations and regimes, robustness under noisy observations, and strong performance with limited training data, supporting the effectiveness of its structure-aware design.  \nIndex Terms—Autonomous Driving, Trajectory Prediction, Interaction Modeling, Small-world Networks  \nI. INTRODUCTION  \nTRAJECTORY prediction is a foundational task in au  \ntonomous driving, serving as a critical input for downstream modules such as risk assessment, planning, and control [1] . It involves forecasting the future motion of surrounding traffic agents, including vehicles, pedestrians, and cyclists, based on their historical trajectories and environmental context. Recent advances in deep learning have markedly improved prediction accuracy by learning data-driven representations, as shown in Fig. 1(a), of interaction patterns between traffic agents [2], [3] . Despite these advancements,  \n† Corresponding author. E-mails: [zhenningli@um.edu.mo](zhenningli@um.edu.mo)  \nChengyue Wang, Bin Rao, Haicheng Liao, Bonan Wang, Chengzhong Xu, and Zhenning Li are with the State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau. Chengyue Wang and Zhenning Li are also affiliated with the Department of Civil and Environmental Engineering, University of Macau, Macau.  \nThis work was supported by the Science and Technology Development Fund of Macau [0122/2024/RIB2, 0215/2024/AGJ, 001/2024/SKL], the Research Services and Knowledge Transfer Office, University of Macau [SRG2023-00037-IOTSC, MYRG-GRG2024-00284-IOTSC], the Shenzhen-Hong Kong-Macau Science and Technology Program Category C [SGDX20230821095159012], the Science and Technology Planning Project of Guangdong [2025A0505010016], National Natural Science Foundation of China [52572354], the State Key Lab of Intelligent Transportation System [2024-B001], and the Jiangsu Provincial Science and Technology Program [BZ2024055] .  \nFig. 1: Conceptual comparison between (a) existing approach and (b) our proposed SWIFT. While existing approaches learn unstructured latent spaces and interactions purely from data, SWIFT introduces flow-aware latent spaces inspired by traffic flow theory and models agent interactions via a Small-World Interaction Network guided by structural priors.  \nfundamental challenges remain that limit the generalizability, robustness, and interpretability of current models, especially in complex traffic conditions [4], [5] .  \nA key limitation lies in how inter-agent interactions are modeled structurally. Many state-of-the-art methods construct ","cbCaima9x4xu540t","https://ap.wps.com/l/cbCaima9x4xu540t","pdf",17608820,1,16,"English","en",105,"# Introduction\n## Structural modeling of inter-agent interactions\n## Limitations of current static interaction assumptions","[{\"question\":\"Why is trajectory prediction difficult in autonomous driving?\",\"answer\":\"It requires modeling dynamic interactions among multiple agents and their context, because traffic behavior changes with scene conditions and can involve long-range effects.\"},{\"question\":\"What limitation do many existing trajectory prediction methods have?\",\"answer\":\"They often construct interaction structures without structural priors (e.g., via proximity thresholds or self-attention) and may fail to capture global dependencies or small-world properties.\"},{\"question\":\"How does SWIFT address interaction modeling?\",\"answer\":\"SWIFT proposes a unified framework using a Small-World Interaction Network to capture local and global dependencies, a Flow Regime Encoder to adapt to scene-level traffic states, and a multi-relational graph module to encode direct and higher-order relationships.\"}]",1784205657,40,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"swift-a-small-world-interaction-framework-for-flow-aware-trajectory-prediction-in-autonomous-driving","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/swift-a-small-world-interaction-framework-for-flow-aware-trajectory-prediction-in-autonomous-driving/85696/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is trajectory prediction difficult in autonomous driving?","Question",{"text":75,"@type":76},"It requires modeling dynamic interactions among multiple agents and their context, because traffic behavior changes with scene conditions and can involve long-range effects.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What limitation do many existing trajectory prediction methods have?",{"text":80,"@type":76},"They often construct interaction structures without structural priors (e.g., via proximity thresholds or self-attention) and may fail to capture global dependencies or small-world properties.",{"name":82,"@type":73,"acceptedAnswer":83},"How does SWIFT address interaction modeling?",{"text":84,"@type":76},"SWIFT proposes a unified framework using a Small-World Interaction Network to capture local and global dependencies, a Flow Regime Encoder to adapt to scene-level traffic states, and a multi-relational graph module to encode direct and higher-order relationships.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":28,"slug":118},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]