Predicting vehicle trajectories is crucial to ensuring automated vehicle operation efficiency and safety, particularly on congested multi-lane highways. In such dynamic environments, a vehicle's motion is determined by its historical behaviors as well as interactions with surrounding vehicles. These intricate interactions arise from unpredictable motion patterns, leading to a wide range of driving behaviors that warrant in-depth investigation. This study presents the Graph-based Interaction-aware Multi-modal Trajectory Prediction (GIMTP) framework, designed to probabilistically predict future vehicle trajectories by effectively capturing these interactions. Within this framework, vehicles' motions are conceptualized as nodes in a time-varying graph, and the traffic interactions are represented by a dynamic adjacency matrix. To holistically capture both spatial and temporal dependencies embedded in this dynamic adjacency matrix, the methodology incorporates the Diffusion Graph Convolutional Network (DGCN), thereby providing a graph embedding of both historical states and future states. Furthermore, we employ a driving intention-specific feature fusion, enabling the adaptive integration of historical and future embeddings for enhanced intention recognition and trajectory prediction. This model gives two-dimensional predictions for each mode of longitudinal and lateral driving behaviors and offers probabilistic future paths with corresponding probabilities, addressing the challenges of complex vehicle interactions and multi-modality of driving behaviors. Validation using real-world trajectory datasets demonstrates the efficiency and potential.

Drivers' risk perception plays a crucial role in understanding vehicle interactions and car-following behavior under complex conditions and physical appearances. Therefore, it is imperative to evaluate the variability of risks involved. With advancements in communication technology and computing power, real-time risk assessment has become feasible for enhancing traffic safety. In this study, a novel approach for evaluating driving interaction risk on freeways is presented. The approach involves the integration of an interaction risk perception model with car-following behavior. The proposed model, named the driving risk surrogate (DRS), is based on the potential field theory and incorporates a virtual energy attribute that considers vehicle size and velocity. Risk factors are quantified through sub-models, including an interactive vehicle risk surrogate, a restrictions risk surrogate, and a speed risk surrogate. The DRS model is applied to assess driving risk in a typical scenario on freeways, and car-following behavior. A sensitivity analysis is conducted on the effect of different parameters in the DRS on the stability of traffic dynamics in car-following behavior. This behavior is then calibrated using a naturalistic driving dataset, and then car-following predictions are made. It was found that the DRS-simulated car-following behavior has a more accurate trajectory prediction and velocity estimation than other car-following methods. The accuracy of the DRS risk assessments was verified by comparing its performance to that of traditional risk models, including TTC, DRAC, MTTC, and DRPFM, and the results show that the DRS model can more accurately estimate risk levels in free-flow and congested traffic states. Thus the proposed risk assessment model provides a better approach for describing vehicle interactions and behavior in the digital world for both researchers and practitioners.

This study proposes an AI-powered digital twin (DT) platform designed to support real-time traffic risk prediction, decision-making, and sustainable mobility in smart cities. The system integrates multi-source data—including static infrastructure maps, historical traffic records, telematics data, and camera feeds—into a unified cyber–physical platform. AI models are employed for data fusion, anomaly detection, and predictive analytics. In particular, the platform incorporates telematics–video fusion for enhanced trajectory accuracy and LiDAR–camera fusion for high-definition work-zone mapping. These capabilities support dynamic safety heatmaps, congestion forecasts, and scenario-based decision support. A pilot deployment on Madison’s Flex Lane corridor demonstrates real-time data processing, traffic incident reconstruction, crash-risk forecasting, and eco-driving control using a validated Vehicle-in-the-Loop setup. The modular API design enables integration with existing Advanced Traffic Management Systems (ATMSs) and supports scalable implementation. By combining predictive analytics with real-world deployment, this research offers a practical approach to improving urban traffic safety, resilience, and sustainability.