Ship Encounter Research Articles

Collision Avoidance for Maritime Autonomous Surface Ships Based on Model Predictive Control Using Intention Data and Quaternion Ship Domain

With the increasing proportion of ships in logistics and the growing prosperity of traffic in maritime, negotiation and cooperative collision avoidance between ships is becoming more and more essential for navigational safety. This paper proposes a Model Predictive Control method that utilizes intention data of the target ship and a quaternion ship domain model to achieve collision avoidance while considering COLREGs, named IQMPC. Firstly, by utilizing the intention data of other ships, trajectories of the own ship and the target ship are well predicted to detect potential collision risks and take optimal avoidance actions in advance while risks exist. Secondly, the quaternion ship domain with its adjacent area is divided into four different parts to reflect the urgency of ship encounters. Collision risk evaluation functions are designed to determine avoidance actions conforming to COLREGs. Thirdly, several different ship encounter scenarios were simulated based on IQMPC to verify its capability.

Virtual Reality Fusion Testing-Based Autonomous Collision Avoidance of Ships in Open Water: Methods and Practices

With the rapid development of autonomous collision avoidance algorithms on ships, the technical demand for the testing and verification of autonomous collision avoidance algorithms is increasing; however, the current testing of autonomous collision avoidance algorithms is mainly based on the virtual simulation of the computer. To realize the testing and verification of the autonomous collision avoidance algorithm in the real ship scene, a method of virtual reality fusion testing in open water is proposed and real ship testing is carried out. Firstly, an autonomous ship collision avoidance test and evaluation system is established to research the test method of ship encounters in open water. Starting from the convention on the international regulations for preventing collisions at sea (COLREG), the main scenario elements of ship collision avoidance are analyzed. Based on the parametric modeling method of ship collision avoidance scenarios, a standard test scenario library for ship collision avoidance in open waters is established. Then, based on the demand for a ship collision avoidance function test, the evaluation index system of ship collision avoidance is constructed. Subsequently, for the uncertainty of the initial state of the real ship test at sea, the virtual–real space mapping method to realize the correspondence of the standard scenario in the real world is proposed. A standardized testing process to improve testing efficiency is established. Finally, the method of conducting virtual simulation and virtual reality fusion tests for various scenarios are verified, respectively. The test results show that the test method can effectively support the testing of autonomous collision avoidance algorithms for ships in open waters and provide a practical basis for improving the pertinence and practicability of ship collision avoidance testing.

Collision Avoidance for Unmanned Surface Vehicles in Multi-Ship Encounters Based on Analytic Hierarchy Process–Adaptive Differential Evolution Algorithm

Path planning and collision avoidance issues are key to the autonomous navigation of unmanned surface vehicles (USVs). This study proposes an adaptive differential evolution algorithm model integrated with the analytic hierarchy process (AHP-ADE). The traditional differential evolution algorithm is enhanced by introducing an elite archive strategy and adaptively adjusting the scale factor F and the crossover factor CR to balance global and local search capabilities, preventing premature convergence and improving the search accuracy. Additionally, the collision risk index (CRI) model is optimized and combined with the quaternion ship domain, enhancing the precision of CRI calculations and USV autonomous collision avoidance capabilities. The improved CRI model, the International Regulations for Preventing Collisions at Sea, and the optimal collision avoidance distance were incorporated as evaluation factors in a fitness function assessment, with weights determined through the AHP to enhance the rationality and accuracy of the fitness function. The proposed AHP-ADE algorithm was compared with the improved particle swarm algorithm, and the performance of the algorithm was comprehensively evaluated using safety, economy, and operational efficiency. Simulation experiments on the MATLAB platform demonstrated that the proposed AHP-ADE algorithm exhibited better performance in scenarios involving multiple ship encounters, thus proving its effectiveness.

Traffic advisory for ship encounter situation based on linear dynamic system

Enhancing Situation Awareness (SA) is crucial for maritime traffic safety. Various indicators have been developed to assess risks in encounter situations and support the SA of Vessel Traffic Service Operators (VTSOs) and Officers on Watch (OOW), including collision risk and traffic complexity. Despite the widespread use of these navigational aids, ship collision incidents have not been effectively reduced. This paper abstracts ship encounter situations as linear dynamic systems to enhance the understanding of traffic situations. A traffic advisory framework based on the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs) is proposed by integrating complexity metrics with risk indicators. The proposed method is validated through simulations of head-on, overtaking, and crossing scenarios, demonstrating its ability to accurately assess encounter complexity and issue advisories for free navigation, complexity, and resolution. Finally, we discuss the practical application of the proposed method through real-world experiments conducted in the waters of Qiongzhou Strait. The results indicate that the proposed method effectively quantifies the complexity of ship encounter situations and identifies high-collision-risk vessels from a microscopic perspective while providing insights into maritime traffic surveillance from a macro perspective.

Perform assessment of COLREGs onboard a maritime autonomous surface ship: Narrow Channels and Traffic Separation Schemes

Abstract The usage of Maritime Autonomous Surface Ships in coastal and heavily used maritime environments necessitates advanced navigation systems capable of fully complying with the International Regulations for Preventing Collisions at Sea 1972 and not only open sea encounters. A significant challenge in this domain is enabling autonomous vessels to understand and navigate complex collision avoidance scenarios dictated by Rule 9 Narrow Channels and Rule 10 Traffic Separation Schemes. These rules are not well covered by research and only partial solutions have been proposed. To address this, we propose a ruleset for a system that can blend the traffic situation and geometric constraints extracted from Electronic Navigational Charts in S-57 format. The proposed ruleset extends our previous work on operationalization of COLREGs by introducing spatial features describing the maritime geometries relevant for traffic situations in Narrow Channels and Traffic Separation Schemes. We apply the ruleset to various traffic situations, showing how the inclusion of geometric context improves decision-making by reducing ambiguity and therefore enables the assessment of traffic situations and ship encounters in the vicinity of Narrow Channels and Traffic Separation Schemes. Our work outlines how the integration of spatial features into a rule-based system enables autonomous navigation capabilities of MASS for safe operations and compliance with maritime regulations.

Parametric Analysis of the Compact and Long-Term-Operable Passive Residual Heat Removal System

Differing from land-based systems, conventional passive residual heat removal systems (PRHRSs) in nuclear-powered ships encounter challenges for use as safety systems due to limited space and difficulties in adopting safety aids. To resolve this problem, the authors have previously suggested a compact and long-term-operable PRHRS that uses air cooling and seawater cooling in tandem, and its feasibility was confirmed through a design study and transient analysis. Nevertheless, the system performance depends on various parameters, and their sensitivities have yet to be analyzed. The purpose of the current study is to conduct a parametric analysis of the system focusing on four parameters: filling ratio, thermal center difference between heat source and sink, heeling angle, and heat source temperature. The Multi-dimensional Analysis of Reactor Safety (MARS-KS) code was used for the parametric analysis. The results show that the parameters are highly interrelated with each other, and consequently, the system exhibits significantly different behavior depending on the parameter conditions. In particular, the filling ratio determines the overall trends of the system. It was also found that the presence of two heat sinks with a single heat source in the natural circulation loop of the system complicate the natural circulation behavior. Based on the results, we conclude that a thorough examination and careful control of the parameters are necessary to implement the proposed system. The highlights are as follows: 1. Parametric analysis of compact and long-term-operable PRHRS is conducted. 2. Analysis reveals that the filling ratio is the most dominant parameter for system performance. 3. The unique behavior of the natural circulation loop with two heat sinks and a single heat source is analyzed.

An integrated decision support system for ship collision avoidance

The ship encounter process is divided into the stages of free action, risk of collision, close-quarter, and immediate danger according to the four-stage theory of ship encounters. Current research on ship collision avoidance primarily focuses on the risk of collision stage, aiming to prevent ships from entering the close-quarter stage. However, various navigational equipment and environmental factors may cause ships to enter the close-quarter or immediate danger stages. Therefore, this paper establishes an integrated decision support system for the above stages to ensure that ships can handle all situations. First, the system includes a new collision risk detection module based on the ship domain model and the four-stage theory. Subsequently, in the collision avoidance strategy formulation module, two sets of avoidance strategies are established based on the convention on the COLREGs and the most effective avoidance principle for ships in different stages. Finally, in the avoidance action optimization module, a new fitness function is constructed based on ship maneuverability, and the sparrow search algorithm is introduced to solve for the optimal avoidance actions. The results demonstrate the capability of the decision support system presented in this paper to effectively avoid other ships in different stages of the encounter process.

Generation and complexity analysis of ship encounter scenarios using AIS data for collision avoidance algorithm testing

Collision avoidance algorithms are critical for enhancing ship navigation safety. To ensure the reliability of these algorithms, comprehensive testing is imperative prior to their deployment. A pivotal aspect of such testing is the strategic formulation of testing scenarios, which plays a vital role in securing the trust of testing phase results. This study proposes a systematic method for generating ship encounter scenarios and analyzing their complexity using Automatic Identification System (AIS) data, to support the implementation of collision avoidance algorithm testing. Firstly, real-world ship encounter scenarios are extracted from AIS data by considering the spatial and temporal dependencies among ships. Subsequently, a complexity evaluation model based on encounter topology evolution is designed to assess the complexity of these scenarios. Finally, detailed strategies for using these scenarios in collision avoidance algorithm testing are explored based on the complexity evaluation results. Real AIS data from the waters off Ningbo-Zhoushan Port is collected to validate the performance of the proposed method. Research findings indicate that the proposed method successfully separates numerous ship encounter scenarios from historical AIS data and comprehensively evaluates their complexity. Based on this foundation, valuable guidance is provided for the application of extracted scenarios in collision avoidance algorithm testing.

Ship Trajectory Planning and Optimization via Ensemble Hybrid A* and Multi-Target Point Artificial Potential Field Model

Ship path planning is the core problem of autonomous driving of smart ships and the basis for avoiding obstacles and other ships reasonably. To achieve this goal, this study improved the traditional A* algorithm to propose a new method for ship collision avoidance path planning by combining the multi-target point artificial potential field algorithm (MPAPF). The global planning path was smoothed and segmented into multi-target sequence points with the help of an improved A* algorithm and fewer turning nodes. The improved APF algorithm was used to plan the path of multi-target points locally, and the ship motion constraints were considered to generate a path that was more in line with the ship kinematics. In addition, this method also considered the collision avoidance situation when ships meet, carried out collision avoidance operations according to the International Regulations for Preventing Collisions at Sea (COLREGs), and introduced the collision risk index (CRI) to evaluate the collision risk and obtain a safe and reliable path. Through the simulation of a static environment and ship encounter, the experimental results show that the proposed method not only has good performance in a static environment but can also generate a safe path to avoid collision in more complex encounter scenarios.

A novel regional ship collision risk assessment framework for multi-ship encounters in complex waters

To address the issue of precisely quantifying ship collision risk and identifying collision hotspots in complex waters, this study proposed a regional ship collision risk assessment framework that includes a multi-ship encounter recognition model, a multi-ship comprehensive collision risk assessment model, and a collision hotspot recognition model. Firstly, the directed distance density-based spatial clustering of applications with noise (DBSCAN) algorithm was proposed. Based on this algorithm, a multi-ship encounter recognition model was established to cluster ship positions and obtain ship encounter clusters. Subsequently, the multi-ship comprehensive collision risk assessment model was constructed for multi-ship encounter situations based on the hierarchical classification method, enabling the determination of each ship's Comprehensive Collision Risk Value (CCRV). Finally, the collision hotspot recognition model was built using the grid analysis method, which can identify areas with a higher risk of ship collision. The automatic identification system (AIS) data of the Yangtze River estuary were used to validate the effectiveness of our framework. The results show that our framework can accurately measure ship collisions risks and identify areas with high collision risks, offering valuable insights to maritime authorities, providing actionable insights for real-time ship collision risk monitoring.

Ship Trajectory Classification Prediction at Waterway Confluences: An Improved KNN Approach

This study presents a method to support ship trajectory prediction at waterway confluences using historical Automatic Identification System (AIS) data. The method is meant to improve the recognition accuracy of ship behavior trajectory, assist in the proactive avoidance of collisions, and clarify ship collision responsibility, to ensure the safety of waterway transportation systems in the event of ship encounters induced by waterway confluence or channel limitation. In this study, the ship trajectory based on AIS data is considered from five aspects: time, location, heading, speed, and trajectory by using the piecewise cubic Hermite interpolation method and then quickly clustered by regional navigation rules. Then, an improved K-Nearest Neighbor Algorithm considering the sensitivity of data characteristics (SKNN) is proposed to predict the trajectory of ships, which considers the influence weights of various parameters on ship trajectory prediction. The method is trained and verified using the AIS data of the Yangtze River and Han River intersection in Wuhan. The results show that the accuracy of SKNN is better than that of conventional KNN and Naive Bayes (NB) in the same test case. The accuracy of the ship trajectory prediction method is above 99% and the performance metrics of the SKNN surpass those of both the conventional KNN and NB classifiers, which is helpful for early warning of collision encounters to ensure avoidance.

A dynamic topology analysis method for multi-ship encounters based on multi time-space network trees

This paper innovatively proposes a novel approach of topological analysis in the dynamic time-space domain of ship encounters under the joint action of multi-space network structural elements, based on the GIS spatial information platform and spatial topology analysis theory. The proposed method based on the ship's navigational motion information, encounter dynamic mode, relative time-space position distribution, etc., the method divides and intersects the time-space domain of the ship's encounter dynamics, and establishes an encountering dynamic time-space network tree in which space and attribute elements are collaboratively associated during the navigation. From the perspective of network topology analysis, the high-precision analysis of the spatial coupling characteristics and time-space trends of potential encountered dangers during ships dynamic navigation is achieved. To verify the effectiveness of the method, real encounter scenarios of M/T SANCHI and M/V CF Crystal were used as analysis cases. The results showed that the proposed method can precisely extract spatial relationships and spatio-temporal coupling feature information of potential hazards encountered between ships, with an average error of about 2.54% and an overall error between 1.94% and 3.53%.Simultaneously, the method's time efficiency results are thoroughly studied and compared, and it is discovered that the proposed method has good stability.

Multi-ship encounter situation graph structure learning for ship collision avoidance based on AIS big data with spatio-temporal edge and node attention graph convolutional networks

With the increasing number of ships on the sea, the frequency multi-ship encounters situation was becoming more common than two-ship encounter. The complexity and risk of the navigation will exponentially increase with the more ships involved. Relying solely on the International Regulations for Preventing Collisions at Sea (COLREGS) (objective knowledge) was insufficient to handle the multi-ship intelligent collision avoidance problem, also needed the ship officer's good seamanship (subjective knowledge). In this study, we propose a methodology that combines subjective insights from AIS big data with objective analysis through multi-ship encounters recognition with graph convolutional networks (GCN). (1) The ship encounter 8-azimuths map was utilized to identify the two-ship encounter situation (25 types) from the AIS data. (2) Identify the multi-ship encounters trajectory data by cross-matching the two-ship encounter data. (3) To handle the intricate relationship information between the multiple ships which were transformed into a graph structure using graph theory. (4) Finally, a spatial-temporal edge and node attention graph convolutional network (ST-ENAGCN) was proposed with the graph convolutional unit and long short-term memory (LSTM) unit. The 2022 Ningbo Sea area AIS big data was utilized to achieve graph-structured learning regarding human experiences during the multi-ship encounters situation. The results indicate that the ST-ENAGCN model can understand the complex marine traffic situation to make the own ship collision avoidance decisions. This study contributes significantly to the increased efficiency and safety of sea operations in complex marine traffic conditions and support autonomous navigation of swarm of MASSs under the human-machine hybrid (HMH) conditions to better understand the collision avoidance intention of the ship officer in the multi-ship encounters situation.

Research on Dynamic Quaternion Ship Domain Model in Open Water Based on AIS Data and Navigator State

During the process of establishing the analytical quaternion ship domain model, the impact of ship traffic conditions and navigator state was not taken into consideration. However, the significance of these factors in the ship domain cannot be ignored. To create a more realistic representation of changes in the ship domain in real navigation environments, this study further considers the influence of ship encounter course, waterway traffic intensity, relative ship velocity, and the navigator state based on the quaternion ship domain model. As a result, a new dynamic quaternion ship domain model is proposed. To assess the changes in the size and shape of the ship domain under various navigation environments, ship domain scaling and shape transformation functions are introduced. Specifically, this study focuses on analyzing the ship traffic near the Lao Tie Shan Waterway, simulating the size and shape changes of the ship domain during the navigation process in this area. The findings indicate that the size of the ship domain dynamically adjusts to the traffic conditions. Additionally, when the navigator state is excellent, the ship domain takes on an irregular diamond shape with the smallest area, whereas when the navigator state is poor, the shape approximates a rectangle with the largest area. Furthermore, the dynamic quaternion ship domain model proposed in this study is compared to the ship domain models put forth by Goodwin, Davis, and co-authors. The results demonstrate that the dynamic quaternion ship domain model is more compatible and suitable for open waters compared to the static quaternion ship domain model.

Hybrid energy saving performance of translucent CdTe photovoltaic window on small ship under sailing condition

Deck photovoltaic (PV) system has been widely investigated on ocean-going ships to reduce oil consumption. However, its adoption on smaller ship encounters obstacles such as limited deck space, reduced energy efficiency, and cumbersome support structures. This paper explores the application of vertical PV windows on small ships as an alternative solution. By retrofitting standard glass with PV windows, the electricity generation area is expanded without occupying valuable deck space or requiring heavy brackets. Unlike deck PV system that solely generate electricity, PV windows also have the added benefit of reducing cooling load inside cabin, enhancing the overall energy-saving effect. Solar energy received by vertical surface is related to heading angles during navigation, a factor that has received scant attention in previous studies. Therefore, hybrid energy saving performance of PV window system is investigated under sailing condition by experiment and simulation methods. The electricity performance of PV window exhibits periodic fluctuations in closed-route trails, with sailing resulting in better electricity performance than mooring. Annual simulation research indicates that PV window system can generate 300.0 kWh of electricity actively, decrease 374.4 kWh of air conditioning load passively and reduce 472.0 kg of CO2 emission. The optimal transmittance of PV window is 0.4%.

Bayesian Inference of Collision Avoidance Intent During Ship Encounters

Bayesian Inference of Collision Avoidance Intent During Ship Encounters

Uncertainty-Aware Decision Making for Safe Navigation of Autonomous Ships

During ship encounters, uncertainty surrounding other vessels’ intentions and future trajectories can complicate situation assessment. When encountering an erratic vessel, navigators will take precautionary actions to avoid any risk of collision. This paper introduces a new decision-making algorithm tailored to address uncertainty in vessel encounters at sea. The proposed method achieves this by defining the risk of a future scenario as the combination of two factors: the probability of collision and the magnitude of the uncertainty. As this method does not assume deterministic future trajectories for either of the vessels, it can therefore be applied to any pair of vessels, and it allows the use for anticipation of future behaviours of other vessels in a scene. The method is verified through a simulation study.

Deep learning–based framework for regional risk assessment in a multi–ship encounter situation based on the transformer network

Deep learning–based framework for regional risk assessment in a multi–ship encounter situation based on the transformer network

Deep reinforcement learning based collision avoidance system for autonomous ships

Autonomous ships is a key to avoid accidents caused by human errors and improve maritime safety. However, unlike the autonomous vehicles counterpart, collision avoidance for autonomous ships faces many challenges due to the hash driving environments, difficult ship control and large stopping distance. In this paper, we investigate a collision avoidance system for autonomous ships under complex encounter scenarios, such as busy ports. In the system various sensors are used to detect objects and perceive the maritime environments. To help the autonomous ships handle the complex and dynamic scenarios that may be encountered, a collision map used to describe the ships encounter scenarios is generated and utilized as the input of a deep reinforcement learning (DRL) model. The DRL model is applied to make collision avoidance and safe driving decisions. New reward functions are proposed to train the DRL model to generate safe ship maneuver actions to reduce collisions and ensure compliance with the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs). Furthermore, a self-adaptive parameters sharing approach is designed for fast convergence and collision avoidance performance of the DRL model, where the parameters of the fully connected layers are shared and the correlation layers are self adapted for the DRL critic and actor networks. Simulation results show that the proposed system has high DRL convergence speed and excellent collision avoidance.

Ship encounter scenario generation for collision avoidance algorithm testing based on AIS data

Collision avoidance algorithms play a crucial role in assisting onboard officers and ensuring navigation safety. To ensure the effectiveness of these algorithms, comprehensive testing with a wide range of scenarios is necessary before widespread deployment. However, there are currently few systematic methods available for generating such testing scenarios. In this paper, a general framework is proposed to generate testing scenarios based on Automatic Identification System (AIS) data, consisting of three modules: encounter scenario extraction, scenario importance evaluation, and testing scenario sampling. Firstly, ship encounter scenarios are extracted from the AIS data according to spatial-temporal proximity relationships between ships. Subsequently, a two-factor model is developed to evaluate the importance of extracted scenarios, considering both exposure frequency and collision risk. Finally, the unequal probability sampling method, which takes into account the importance of each scenario, is utilized to construct the testing scenario set. The proposed framework is validated through a systematic experiment using real AIS data. The results demonstrate that the framework effectively extracts diverse encounter scenarios from AIS data and rationally evaluates their importance. On this basis, an appropriate scenario set can be generated for collision avoidance algorithm testing. The generated scenario set ensures comprehensive coverage while prioritizing high-importance scenarios.