Maritime Situation Monitoring and Awareness Using Learning Mechanisms

TLDR

Learned patterns encompass routine, illegal, unsafe, threatening, and anomalous vessel behaviors. This paper addresses maritime situation awareness by employing cognitively inspired algorithms to learn behavioral patterns across conceptual, spatial, and temporal levels. The system processes real‑time vessel tracking data with continuous on‑the‑fly learning, integrating unsupervised clustering and supervised mapping to recognize motion patterns, allowing operator input to guide learning and describing event‑level features from simulated and recorded data. Continuous learning enables the models to adapt to evolving situations while maintaining high performance.

Abstract

This paper addresses maritime situation awareness by using cognitively inspired algorithms to learn behavioral patterns at a variety of conceptual, spatial, and temporal levels. The algorithms form the basis for a system that takes real-time tracking information and uses continuous on-the-fly learning that enables concurrent recognition of patterns of current motion states of single vessels in local vicinity. Learned patterns include routine behaviors as well as illegal, unsafe, threatening, and anomalous behaviors. Continuous learning enables the models to adapt well to evolving situations while maintaining high levels of performance. The learning combines two components: an unsupervised clustering algorithm, and a supervised mapping and labeling algorithm. Operator input can guide system learning. Event-level features of our learning system using simulated and recorded data are described