Spatial-Temporal Motion Prediction in Cooperative Autonomous Driving System

Cooperative autonomous driving (AD) systems have increasingly become key elements of future intelligent transportation systems owing to the provisioning of dependable, safe, and effective urban mobility operations. In particular, the utilization of motion prediction can contribute to achieving a high-performance cooperative AD planning strategy of the vehicle platoon system. However, realizing accurate spatial-temporal motion prediction is a challenge since most existing work unilaterally considers the spatial or temporal feature in predicting vehicle motion trajectories. To address the problem, we design a novel spatial-temporal Transformer (ST-Transformer) motion prediction model to predict vehicle motion trajectories with highfidelity simulator. In particular, we integrate both the convolutional and transformer-based networks to capture the spatial-temporal feature of vehicle states. Case studies demonstrate the superiority of the proposed model in predicting autonomous vehicle (AV) trajectories over the existing baseline models, which can greatly support AV motion planning tasks.