CRHT模型通过在线聚类采样提升船舶轨迹预测精度，兼顾实时性与航行真实性。
CRHT: A Continuous Regression Hybrid Transformer for Vessel Trajectory Prediction with Online Cluster Sampling
- 采用在线K-means聚类采样，缓解稀有航行动作的数据不平衡问题。
- 在1小时预测范围内误差最低，短期轨迹预测性能领先。
- 适合需要高精度实时监控的海上交通管理系统使用。
准确的船舶轨迹预测对航海安全与异常检测至关重要，但现有模型常面临地理偏差和航行真实性的挑战。本文提出连续回归混合注意力网络（CRHT），基于自动识别系统（AIS）数据预测船舶运动。为缓解空间数据不平衡，引入在线K-means聚类采样策略，确保训练过程中充分覆盖罕见航行动作。模型融合一维卷积层提取局部运动特征与多头注意力机制捕捉全局时序上下文。实验表明，CRHT在短时预测中表现优异，1小时预测误差最低；尽管离散模型在长时预测中更具导航稳定性，但CRHT在精度与机动性追踪间取得更优平衡，适用于实时海上监视场景。
原文摘要 · Abstract (English)
Accurate vessel trajectory prediction is critical for maritime safety and anomaly detection, yet existing models often struggle with geographic bias and navigational realism. We propose the Continuous Regression Hybrid Transformer (CRHT), a deep learning framework designed to forecast vessel motion using Automatic Identification System (AIS) data. To mitigate spatial data imbalance, we introduce an online K-means cluster sampling strategy that ensures diverse exposure to rare maneuvers during training. Our hybrid architecture integrates 1D convolutional layers for local kinematic feature extraction with a multi-head attention mechanism for global temporal context. CRHT demonstrates superior performance in short-term forecasting, achieving the lowest errors at the 1-hour horizon. The results demonstrate that while discrete models provide high navigational stability over long horizons, CRHT offers an optimal balance of precision and maneuver tracking for real-time maritime surveillance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。