Accurate trajectory prediction is crucial for the safe and efficient operation of autonomous vehicles. The growing popularity of deep learning has led to the development of numerous methods for trajectory prediction. While deterministic deep learning models have been widely used, deep generative models have gained popularity as they learn data distributions from training data and account for trajectory uncertainties. In this study, we propose EquiDiff, a deep generative model for predicting future vehicle trajectories. EquiDiff is based on the conditional diffusion model, which generates future trajectories by incorporating historical information and random Gaussian noise. The backbone model of EquiDiff is an SO(2)-equivariant transformer that fully utilizes the geometric properties of location coordinates. In addition, we employ Recurrent Neural Networks and Graph Attention Networks to extract social interactions from historical trajectories. To evaluate the performance of EquiDiff, we conduct extensive experiments on the NGSIM dataset. Our results demonstrate that EquiDiff outperforms other baseline models in short-term prediction, but has slightly higher errors for long-term prediction. Furthermore, we conduct an ablation study to investigate the contribution of each component of EquiDiff to the prediction accuracy. Additionally, we present a visualization of the generation process of our diffusion model, providing insights into the uncertainty of the prediction.

翻译：精确的轨迹预测对于自动驾驶车辆的安全高效运行至关重要。深度学习的日益普及推动了多种轨迹预测方法的发展。尽管确定性深度学习模型已被广泛应用，但深度生成模型因其能从训练数据中学习数据分布并考虑轨迹不确定性而受到青睐。本研究提出了EquiDiff，一种用于预测未来车辆轨迹的深度生成模型。EquiDiff基于条件扩散模型，通过融合历史信息和随机高斯噪声生成未来轨迹。该模型的主干网络采用SO(2)等变Transformer，能充分利用位置坐标的几何特性。此外，我们利用循环神经网络和图注意力网络从历史轨迹中提取社会交互特征。为了评估EquiDiff的性能，我们在NGSIM数据集上进行了大量实验。结果表明，EquiDiff在短期预测中优于其他基线模型，但在长期预测中误差略高。同时，我们通过消融研究探讨了EquiDiff各组件对预测准确性的贡献。此外，我们还展示了扩散模型生成过程的可视化结果，为理解预测的不确定性提供了洞见。