The wide spread of the Automatic Identification System (AIS) and related tools has motivated several maritime analytics operations. One of the most critical operations for the purpose of maritime safety is the so-called Vessel Collision Risk Assessment and Forecasting (VCRA/F), with the difference between the two lying in the time horizon when the collision risk is calculated: either at current time by assessing the current collision risk (i.e., VCRA) or in the (near) future by forecasting the anticipated locations and corresponding collision risk (i.e., VCRF). Accurate VCRA/F is a difficult task, since maritime traffic can become quite volatile due to various factors, including weather conditions, vessel manoeuvres, etc. Addressing this problem by using complex models introduces a trade-off between accuracy (in terms of quality of assessment / forecasting) and responsiveness. In this paper, we propose a deep learning-based framework that discovers encountering vessels and assesses/predicts their corresponding collision risk probability, in the latter case via state-of-the-art vessel route forecasting methods. Our experimental study on a real-world AIS dataset demonstrates that the proposed framework balances the aforementioned trade-off while presenting up to 70% improvement in R 2 score, with an overall accuracy of around 96% for VCRA and 77% for VCRF.

This paper presents a method for energy efficient weather routing of a ferry in Norway. Historical operational data from the ferry and environmental data are used to develop two models that predict the energy consumption. The first is a purely data-driven linear regression energy model, while the second is as a hybrid model, combining physical models with data-driven models using machine learning techniques. With an established energy model, it is possible to develop a route optimization that proposes efficient routes with less energy usage compared to fixed speed and heading control.

This study presents a method in which historical AIS data are used to predict the future trajectory of a selected vessel. This is facilitated via a system intelligence-based approach that can be subsequently utilized to provide enhanced situation awareness to navigators and future autonomous ships, aiding proactive collision avoidance. By evaluating the historical ship behavior in a given geographical region, the method applies machine learning techniques to extrapolate commonalities in relevant trajectory segments. These commonalities represent historical behavior modes that correspond to the possible future behavior of the selected vessel. Subsequently, the selected vessel is classified to a behavior mode, and a trajectory with respect to this mode is predicted. This is achieved via an initial clustering technique and subsequent trajectory extraction. The extracted trajectories are then compressed using the Karhunen–Loéve transform, and clustered using a Gaussian Mixture Model. The approach in this study differs from others in that trajectories are not clustered for an entire region, but rather for relevant trajectory segments. As such, the extracted trajectories provide a much better basis for clustering relevant historical ship behavior modes. A selected vessel is then classified to one of these modes using its observed behavior. Trajectory predictions are facilitated using an enhanced subset of data that likely correspond to the future behavior of the selected vessel. The method yields promising results, with high classification accuracy and low prediction error. However, vessels with abnormal behavior degrade the results in some situations, and have also been discussed in this study.

Vessel trajectory clustering using historical AIS data has been a popular research topic in recent years. However, few studies have investigated applying deep learning techniques. In this study, deep representaion learning is investigated for use in clustering historical AIS trajctories to provide insight into navigation patterns to support maritime situation awareness. A recurrent autoencoder and β -variational recurrent autoencoder are investigated to generate fixed size vector representations of the AIS trajectories. Subsequently, clustering is facilitated by applying the Hierarchical Density-Based Spatial Clustering of Applications with Noise algorithm to the representations. The method was tested on historical AIS data for a region surrounding Tromsø, Norway, with successful results. The results also indicate that the β -variational recurrent autoencoder was able to generate representations of the AIS trajectories that resulted in more compact clusters.

Autonomous ship technology is developing at a rapid pace, with the aim of facilitating safe ship operations. Collision avoidance is one of the most critical tasks that autonomous ships must handle. To support the level of safety associated with collision avoidance, this study suggests to provide autonomous ships with the ability to conduct proactive collision avoidance maneuvers. Proactive collision avoidance entails predicting future encounter situations, such that they can preemptively be avoided. However, any such actions must adhere to relevant navigation rules and regulations. As such, it is suggested to predict encounter situations far in advance, i.e. prior to risk of collision existing. Any actions can, therefore, be conducted prior to the applicability of the COLREGs. As such, simple corrective measures, e.g. minor speed and/or heading alterations, can prevent close encounter situations from arising, reducing the overall risk associated with autonomous ship operations, as well as improving traffic flow. This study suggests to facilitate this ability by emulating the development of situation awareness in ship navigators through machine learning. By leveraging historical AIS data to serve as artificial navigational experience, long-range trajectory predictions can be facilitated in a similar manner those conducted by human navigators, where such predictions provide the basis for proactive collision avoidance actions. The development of human situation awareness is, therefore, presented, and relevant machine learning techniques are discussed to emulate the same mechanisms.

This study presents a deep learning framework to support regional ship behavior prediction using historical AIS data. The framework is meant to aid in proactive collision avoidance, in order to enhance the safety of maritime transportation systems. In this study, it is suggested to decompose the historical ship behavior in a given geographical region into clusters. Each cluster will contain trajectories with similar behavior characteristics. For each unique cluster, the method generates a local model to describe the local behavior in the cluster. In this manner, higher fidelity predictions can be facilitated compared to training a model on all available historical behavior. The study suggests to cluster historical trajectories using a variational recurrent autoencoder and the Hierarchical Density-Based Spatial Clustering of Applications with Noise algorithm. The past behavior of a selected vessel is then classified to the most likely clusters of behavior based on the softmax distribution. Each local model consists of a sequence-to-sequence model with attention. When utilizing the deep learning framework, a user inputs the past trajectory of a selected vessel, and the framework outputs the most likely future trajectories. The model was evaluated using a geographical region as a test case, with successful results.

Situation awareness is essential in conducting effective collision avoidance in potential ship encounter situations. It has been shown that data driven trajectory prediction techniques, utilizing historical AIS data, have the potential to aid in providing such awareness. However, such data driven techniques will not perform well for unusual ship behavior, i.e. anomalous trajectories. Additionally, such anomalies in the dataset can corrupt the predictions. In this study, an unsupervised approach to anomaly detection is presented to aid such trajectory predictions. Gaussian Mixture Models are used to cluster trajectories, such that clusters of both normal and anomalous trajectories are discovered. Further, anomalies are discovered within clusters of normal behavior. Novel trajectories can then also be evaluated based on a parametric description of the historical ship traffic. The approach is shown to be effective in detecting anomalies relevant in such a trajectory prediction scheme.

Advances in artificial intelligence are driving the development of intelligent transportation systems, with the purpose of enhancing the safety and efficiency of such systems. One of the most important aspects of maritime safety is effective collision avoidance. In this study, a novel dual linear autoencoder approach is suggested to predict the future trajectory of a selected vessel. Such predictions can serve as a decision support tool to evaluate the future risk of ship collisions. Inspired by generative models, the method suggests to predict the future trajectory of a vessel based on historical AIS data. Using unsupervised learning to facilitate trajectory clustering and classification, the method utilizes a cluster of historical AIS trajectories to predict the trajectory of a selected vessel. Similar methods predict future states iteratively, where states are dependent upon the prior predictions. The method in this study, however, suggests predicting an entire trajectory, where all states are predicted jointly. Further, the method estimates a latent distribution of the possible future trajectories of the selected vessel. By sampling from this distribution, multiple trajectories are predicted. The uncertainties of the predicted vessel positions are also quantified in this study.

Autonomous ship navigation in a mixed environment, where remote-controlled, autonomous and manned vessels are interacting, is considered. Since these vessels can have various encounter situations, adequate knowledge on such situations should be acquired to take appropriate navigation actions. That has often been categorized as situation awareness in a mixed environment, where appropriate tools and techniques to extract the respective knowledge on ship encounter situations should be developed. The collision risk assessment procedure has an important role in the same knowledge and that can eventually be used towards the respective collision avoidance actions. Hence, possible ship collision and near-miss situations can be avoided by both humans as well as systems due to their actions. Ship collision avoidance actions are regulated by the International Regulations for Preventing Collisions at Sea 1972 (COLREGs) in open sea areas and additional local navigation rules and regulations can also enforce especially in confined waters and maritime traffic lanes. It is expected that the COLREGs and other navigation rules and regulations will be interpreted by both humans as well as systems in future vessels and those interpretations will be executed as collision avoidance actions by the respective vessels in a mixed environment. Adequate understanding on situation awareness should be achieved to overcome possible regulatory failure due to human and system decisions in these situations. Hence, this study focuses on identifying such challenges in future ship encounters with possible solutions to improve situation awareness in a mixed environment as the main contribution.

This study presents a method to predict the future trajectory of a target vessel using historical AIS data. The purpose of such a prediction is to aid in collision avoidance in future vessels. The method presented in this study extracts all trajectories present in an initial cluster centered about a vessel position. Features for each trajectory are then generated using Principle Component Analysis and used in clustering via unsupervised Gaussian mixture modeling. Each resultant cluster represents a possible future route the vessel may follow. A trajectory prediction is then conducted with respect to each cluster of trajectories discovered. This results in a prediction of multiple possible trajectories. The results indicate that the algorithm is effective in clustering the trajectories, where at least one cluster corresponds to the true trajectory of the vessel. The resultant predicted trajectories are also found to be reasonably accurate.

Autonomous vehicles will be an integral part of future transportation systems, and the maritime industry is working towards developing methods to ensure safe autonomous ship operations. One of the major challenges in realizing autonomous ships is ensuring effective collision avoidance technologies. Autonomous vessels must have a higher degree of situation awareness to detect other vessels, predict their future intentions, and evaluate the respective collision risk. One step in achieving this goal is to predict other vessel trajectories accurately. In this paper, a data-driven approach to vessel trajectory prediction for time horizons of 5-30 minutes utilizing historical AIS data is evaluated. A clustering based Single Point Neighbor Search Method is investigated along with a novel Multiple Trajectory Extraction Method. Predictions have been conducted using these methods and compared with the Constant Velocity Method. Additionally, the Multiple Trajectory Extraction Method is utilized to evaluate estimated ship routes.