Crossfusor: A Cross-Attention Transformer Enhanced Conditional Diffusion Model for Car-Following Trajectory Prediction

TL;DR

Crossfusor tackles car-following trajectory prediction by embedding detailed inter-vehicle dynamics into a conditional diffusion framework. It combines a history-conditioned forward diffusion with a cross-attention transformer in the reverse denoising stage, supported by a temporal encoding pipeline that uses GRU, location-based attention, and Fourier embeddings. Empirical results on the NGSIM dataset show improved accuracy, especially for long horizons, and ablations confirm the value of each architectural component. The work advances autonomous driving prediction by delivering more realistic, interaction-aware trajectory forecasts that better capture microscopic car-following behavior.

Abstract

Vehicle trajectory prediction is crucial for advancing autonomous driving and advanced driver assistance systems (ADAS), enhancing road safety and traffic efficiency. While traditional methods have laid foundational work, modern deep learning techniques, particularly transformer-based models and generative approaches, have significantly improved prediction accuracy by capturing complex and non-linear patterns in vehicle motion and traffic interactions. However, these models often overlook the detailed car-following behaviors and inter-vehicle interactions essential for real-world driving scenarios. This study introduces a Cross-Attention Transformer Enhanced Conditional Diffusion Model (Crossfusor) specifically designed for car-following trajectory prediction. Crossfusor integrates detailed inter-vehicular interactions and car-following dynamics into a robust diffusion framework, improving both the accuracy and realism of predicted trajectories. The model leverages a novel temporal feature encoding framework combining GRU, location-based attention mechanisms, and Fourier embedding to capture historical vehicle dynamics. It employs noise scaled by these encoded historical features in the forward diffusion process, and uses a cross-attention transformer to model intricate inter-vehicle dependencies in the reverse denoising process. Experimental results on the NGSIM dataset demonstrate that Crossfusor outperforms state-of-the-art models, particularly in long-term predictions, showcasing its potential for enhancing the predictive capabilities of autonomous driving systems.

Figures (8)

• Figure 1: Overall Framework of Crossfusor
• Figure 2: Structure of Historical Trajectory Feature Extraction and Forward Process
• Figure 3: Architecture of Reverse Process
• Figure 4: Structure of Cross-Attention Transformer Block
• Figure 5: Adapted U-Net for Noise Prediction