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, limiting their generalization under distribution shifts. This work revisits interaction modeling through the structure and dynamics of traffic networks, proposing SWIFT (Small-World Interaction Framework for Trajectory prediction) 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.
Blogger's Review: The SWIFT framework successfully addresses the trajectory prediction challenge in autonomous driving by combining small-world networks and traffic flow theory. Its structure-aware design not only enhances prediction accuracy but also improves the model's adaptability in dynamic traffic environments, showcasing a promising future for intelligent transportation systems.