DyTTP：基于无归一化Transformer的轨迹预测
DyTTP: Trajectory Prediction with Normalization-Free Transformers
AI总结：
本文提出DyTTP，首次将DynamicTanh引入轨迹预测以替代层归一化，并结合快照集成策略，在Argoverse数据集上显著提升预测精度、推理速度与鲁棒性。
摘要：
准确的轨迹预测是自动驾驶系统安全运行的基石，其中理解周围智能体的动态行为至关重要。基于Transformer的架构在捕捉复杂的时空依赖性方面已展现出显著潜力。然而，它们对归一化层的依赖可能导致计算开销和训练不稳定性。在本工作中，我们提出一种双重方法来应对这些挑战。首先，我们将DynamicTanh（DyT）这一最新的Transformer改进方法集成到骨干网络中，以取代传统的层归一化。这一修改简化了网络架构并提高了推理的稳定性。我们是首个将DyT部署到轨迹预测任务中的工作。作为补充，我们采用快照集成策略来进一步提升轨迹预测性能。利用循环学习率调度，在单次训练过程中捕获多个模型快照。随后在推理时通过简单平均对这些快照进行聚合，使模型能够从多样化的假设中获益，而不会产生大量额外的计算成本。在Argoverse数据集上的大量实验表明，我们的组合方法在不同驾驶场景中显著提高了预测精度、推理速度和鲁棒性。本工作凸显了无归一化Transformer设计结合轻量级集成技术在推进自动驾驶车辆轨迹预测方面的潜力。
英文摘要：
Accurate trajectory prediction is a cornerstone for the safe operation of autonomous driving systems, where understanding the dynamic behavior of surrounding agents is crucial. Transformer-based architectures have demonstrated significant promise in capturing complex spatio-temporality dependencies. However, their reliance on normalization layers can lead to computation overhead and training instabilities. In this work, we present a two-fold approach to address these challenges. First, we integrate DynamicTanh (DyT), which is the latest method to promote transformers, into the backbone, replacing traditional layer normalization. This modification simplifies the network architecture and improves the stability of the inference. We are the first work to deploy the DyT to the trajectory prediction task. Complementing this, we employ a snapshot ensemble strategy to further boost trajectory prediction performance. Using cyclical learning rate scheduling, multiple model snapshots are captured during a single training run. These snapshots are then aggregated via simple averaging at inference time, allowing the model to benefit from diverse hypotheses without incurring substantial additional computational cost. Extensive experiments on Argoverse datasets demonstrate that our combined approach significantly improves prediction accuracy, inference speed and robustness in diverse driving scenarios. This work underscores the potential of normalization-free transformer designs augmented with lightweight ensemble techniques in advancing trajectory forecasting for autonomous vehicles.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
