STS-DGNN: Vehicle Trajectory Prediction via Dynamic Graph Neural Network With Spatial-Temporal Synchronization

Accurate prediction of vehicle trajectories is crucial to the safety and comfort of autonomous vehicles. Although several graph-based models have exhibited substantial progress in acquiring spatiotemporal dependencies among vehicles in the driving environment, the potential for additional exploration in this domain persists. The main reason is that they concentrated on independently capturing the spatial relations and temporal dependencies, neglecting to incorporate the temporal feature into the spatial feature for co-training, which limits their ability to yield satisfactory predictive accuracy. Typically, spatial and temporal correlations are coupled and should be modeled jointly. Inspired by this, a novel dynamic graph neural network with spatial-temporal synchronization (STS-DGNN) for vehicle trajectory prediction is proposed, which constructs the driving scene as dynamic graphs and can jointly extract spatial-temporal features. Specifically, low-order and high-order dynamics of vehicle trajectories are considered collaboratively in a one-stage framework rather than independently modeling the spatial relationship and temporal correlations of vehicles in two-stage models. The proposed model also considers the dynamic nature of graph sequence by utilizing gate recurrent unit (GRU) to update the graph neural network (GNN) parameters dynamically. The spatial-temporal features are subsequently conveyed to convolutional neural networks (CNNs) and processed by a multilayer perceptron (MLP) to generate the ultimate trajectories. Finally, to illustrate the effectiveness of the STSDGNN model, the model is assessed on three well-known datasets, namely highD, EWAP, and UCY. The results confirm that our model performs better at making predictions than cuttingedge models. The visualization results intuitively explain that our method can extract sophisticated and subtle multivehicle interactions, resulting in accurate predictions.