<p>Vehicle trajectory prediction is essential for safe and efficient autonomous driving and intelligent transportation systems. However, accurately forecasting vehicle movements remains challenging due to complex spatial interactions between vehicles and temporal dependencies in traffic dynamics. This study proposes a Deep Spatial Temporal Graph Convolutional Network with residual connections to enhance trajectory prediction accuracy and computational efficiency. The framework models spatial relationships between vehicles using graph convolutional layers while temporal dependencies are captured using gated recurrent units. Residual connections are introduced to improve information flow across layers and preserve critical spatial features. The proposed model was evaluated using benchmark vehicle trajectory dataset and compared with several state-of-the-art methods, including Convolutional Long Short-Term Memory, Spatio Temporal Interactive Graph Convolutional Network, and Graph Attention Network with Long Short-Term Memory. Experimental results demonstrate that the proposed model achieves improved prediction accuracy across multiple prediction horizons while maintaining lower model complexity and faster inference speed. These findings indicate that the integration of spatial temporal graph convolution with residual learning provides an effective and computationally efficient approach for real time vehicle trajectory prediction in autonomous driving systems.</p>