analiza aiqbench
This study demonstrates that applying memory-augmented neural networks to AIS data yields consistent performance gains for vessel trajectory prediction, outperforming standard deep learning baselines in maritime safety scenarios. The approach effectively addresses the underexplored potential of external memory mechanisms in this specific domain, offering a robust method for collision avoidance and route optimization.
AIS-Based Vessel Trajectory Prediction Using Memory-Augmented Neural Networks
arXiv:2606.06311v1 Announce Type: new Abstract: 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.
Abstract: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.
Artificial Intelligence (cs.AI)
arXiv:2606.06311 [cs.AI]
(or arXiv:2606.06311v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2606.06311 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 194 cuvinte
Subiecte conexe
What's Continual Learning, and Why Might We Expect To See It In Advanced LLM Agents?
LessWrong · 12 iun. 2026
The Von-Neumann State-Space Transformer for neural decoding
arXiv · 27 aug. 2026
Does preservation make sense before we know how to revive?
LessWrong · 15 iun. 2026
[AINews] not much happened today
Latent Space · 3 oct. 2026