用AIS数据和记忆网络提升船舶轨迹预测精度
AIS-Based Vessel Trajectory Prediction Using Memory-Augmented Neural Networks
- 引入外部记忆机制，从历史AIS数据中动态检索关键信息
- 在墨西哥湾和纽约湾数据上显著优于无记忆的深度学习基线
- 适合需要高精度船舶路径预判的海事安全与调度场景
精准的船舶轨迹预测对海上安全与高效运营至关重要，可实现避碰和路线优化。尽管记忆增强神经网络近年来在行人与道路车辆轨迹预测中表现出色，通过从外部记忆中选择性检索相关信息，但其在船舶轨迹预测中的潜力尚未充分探索。本文基于自动识别系统（AIS）数据，对基于记忆的轨迹预测进行了实证研究。在墨西哥湾和纽约湾的数据集上，该方法相比多种不使用外部记忆的深度学习基线模型，均展现出一致且显著的性能提升。
原文摘要 · Abstract (English)
Accurate vessel trajectory prediction is essential for safe and efficient maritime operations, enabling collision avoidance and supporting route optimization. Although memory-augmented neural networks have recently shown strong performance in pedestrian and road-vehicle trajectory prediction by selectively retrieving relevant information from an external memory, their potential for vessel trajectory prediction remains underexplored. This paper presents an empirical investigation of memory-based trajectory prediction using Automatic Identification System (AIS) data. Experiments on data from the Gulf of Mexico and the New York Bight demonstrate consistent and substantial performance gains over a range of deep learning baselines that do not incorporate an external memory.
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。