A Spatio-Temporal Graph Network with Informer-TCN Fusion for Vehicle Trajectory Prediction on Highways

Abstract

Accurate vehicle trajectory prediction is essential for the driving safety and efficiency of autonomous vehicles. However, this task remains challenging due to the complex spatial interactions among traffic participants and the wide range of temporal dependencies in motion sequences. To address these issues, this paper proposes a novel hybrid deep learning framework suitable for cloud-based control platforms, providing a foundational algorithmic solution for vehicle-infrastructure cooperative perception and decision-making. The proposed architecture employs an Adaptive Graph Convolutional Network (AGCN) to adaptively learn spatial relationships and interactions among vehicles. It also utilizes the Informer model, known for its efficient ProbSparse self-attention mechanism, to capture long-term temporal dependencies in trajectory sequences. Furthermore, a Temporal Convolutional Network (TCN) is integrated to enhance the model’s ability to learn fine-grained local temporal features. The proposed model is evaluated on the NGSIM dataset. The dataset is chronologically ordered and split into training (80%), validation (10%), and testing (10%) sets. Experimental results show that the proposed method achieves an average minADE of 2.032 m and minFDE of 2.866 m over a 5-second prediction horizon, outperforming several baseline models such as LSTM, CNN-LSTM, and Social-GAN. These results indicate the effectiveness of the AGCN-Informer-TCN combination for trajectory prediction. The study suggests potential for integration into intelligent transportation cloud control platforms.