Accurately forecasting the motion of surrounding vehicles is a crucial prerequisite for achieving safe autonomous driving (AD). Methods for trajectory prediction encompass both physics- and learning-based approaches. Despite the significant advancements made by learning-based methods in enhancing performance, ensuring that predicted trajectories are realistic, interpretable, and physically feasible remains a challenging problem. In this study, we propose a physics-based deep learning (DL) framework founded on an encoder–decoder architecture, modeling the historical motion of traffic agents effectively coupled with the surrounding environment information through attention mechanisms. Our model incorporates the vehicle dynamic model (VDM) to couple with vehicle motion and utilizes the Kalman filter to fuse scene context information for multistep accurate and feasible multimodal trajectory prediction. Our method leverages the strengths of both learning- and physics-based models. The extensive experiment results on the Lyft l5 dataset demonstrate that our model outperforms various baseline approaches in terms of metrics including prediction errors, feasibility, and explainability.