Collison between ships is one of the major contributors to maritime accidents. To reduce ship collision accidents, the research on collision avoidance decision-making has been drawing much attention from various parties. In this research, extensive literature and expert knowledge are collected and analyzed to identify the common sense and discrepancies between collision avoidance decision-making for theoretical research and navigation practices. The key factors that are considered in the two perspectives are identified and discussed, based on which, the knowledge structures that can represent the development of the process in the two perspectives are established. A series of comparisons between the knowledge structure based on theoretical research and navigation practices are conducted. The comparisons indicate clear common sense and discrepancies between the theoretical research and navigation practices regarding collision avoidance decision-making. The potential causes of them are also analyzed. The research results would be beneficial for the development of collision avoidance decision-making for both autonomous and conventional manned ships in maritime traffic.

Maritime Autonomous Surface Ships (MASS) attract increasing attention in recent years. Researchers aim at developing fully autonomous systems that replace the role of human operators. Studies either focus on supporting conflict/collision detection (for manned ships) or solving conflict automatically (for unmanned ships). The cooperation between human and machine has been less focused on in existing studies. However, this type of cooperation is essential both in practice and in the future: firstly, demands on navigational assistance are still strong for supporting navigators in manned ships; secondly, MASS with different autonomy levels require increasing cooperation between human operators and machines, e.g. monitoring automation, remotely controlling the ship, etc.; thirdly, the intelligence of human and the machines is highly complementary. Moreover, fully autonomous ships cannot replace all the manual ships overnight. Therefore, the future waterborne transport system will be a system in which both human-operated vessels and autonomous vessels exist. In this article, we firstly provide an overview of existing modes of human-machine interaction (HMI) during ship collision avoidance. Then, we propose a framework of HMI oriented Collision Avoidance System (HMI-CAS) whose decision-making process is interpretable and interactive for human operators. The HMI-CAS facilitates automatic collision avoidance and enables the human operators to take over the control of the MASS safely. Moreover, the proposed framework acknowledges the under-actuated feature of ships. Simulations are carried out to demonstrate the proposed HMI-CAS. The results show that the proposed HMI-CAS can not only control the under-actuated MASS to avoid collision automatically but also share the decision-making with human operators and support the operators to control the MASS.

This article provides a comprehensive overview on cooperative control methods for waterborne transport. We first proposed a hierarchical architecture of cooperation in the waterborne transport systems. Three layers of cooperation are identified according to the range of communication and cooperation, i.e., the individual layer, the local layer, and the network layer. The individual layer is the basis layer where a controller controls the dynamics of an individual vessel. The local layer considers the vessel-to-vessel (V2V) and vessel-to-infrastructure (V2I) interactions. The network layer considers not only V2V and V2I interactions but also the interdependence of the interconnected infrastructures, i.e., infrastructure-to-infrastructure interactions. Existing research for cooperation at each layer is reviewed, and the main research gaps are provided.

Collision prevention is critical for navigation safety at sea. At early ages, researchers aimed at developing navigational assistance systems for enhancing situational awareness of human operators as human is at the core of collision avoidance. Recently, autonomous vehicles have gained a remarkable amount of attention with a focus on solving collision problems by machines. This results in two groups of studies, both working on preventing collisions but with different focuses: one aims at conflict detection, and the other focuses on conflict resolution. This paper offers a comprehensive overview of collision prevention techniques based on the three basic processes of determining evasive solutions, namely, motion prediction, conflict detection, and conflict resolution. The strengths and weaknesses of different methods for these three fundamental processes are discussed. Limitations and new challenges are highlighted. Moreover, this review points out the differences between the research for manned and unmanned ships and how the research in the two domains can learn from each other. A potential roadmap for the transition from existing manned ships to fully unmanned ships is provided in the end.

In this paper, a distributed control approach is proposed to enable fuel-efficient Vessel Train Formations (VTF) in inland waterways and port areas for addressing the efficiency and environmental issues of transport over water. For path tracking, collision avoidance, and consensus over the VTF speed a distributed Model Predictive Control (MPC) algorithm is adopted which uses the Alternating Direction Method of Multipliers (ADMM) to guarantee path following and consensus between vessels. The all-electric Direct Current (DC) configuration is considered for the Power and Propulsion Systems (PPS) of the autonomous vessels under study. Considering their PPS specification, the vessels negotiate with each other to agree on the most efficient speed for all the vessels in the VTF. Simulation results suggest that a significant amount of fuel saving can be obtained by using the proposed approach.

Numerous methods have been developed for ship collision prevention over the past decades. However, most studies are based on strong assumptions, such as the need for a constant velocity of the target-ship, the limitation to two-ship scenarios, the simplification of ships’ dynamics, etc. Generalized Velocity Obstacle (GVO) algorithm can bridge these gaps. This paper presents a GVO algorithm for ship collision avoidance and designs a collision avoidance system (GVO-CAS). The proposed system visualizes the changes of one ship's course and speed resulting in collisions, which can be used not only for supporting the officer on watch to prevent collisions, but also for collision prevention of Autonomous Surface Vessels (ASVs) and for human operators taking over the control of ASVs. Simulation experiments show that the proposed collision avoidance system can work properly in various maritime environments. Compared to the original Velocity Obstacle algorithm, the GVO algorithm is more reliable and suitable for close range ship collision avoidance. Moreover, the GVO-CAS can offer rule-compliant evasive actions with a minimum number of required actions for ships. These results show the great potential to use the GVO algorithm in both manned and unmanned ships at sea.

A Cooperative Multi-Vessel System (CMVS) is a system consisting of multiple coordinated vessels. Vessels utilize Vessel-2-Vessel and Vessel-2-Infrastructure communication to making decisions with negotiating and\or collaborating with each other for a common goal. Due to the geographic limitations of banks and navigation rules and regulations, in straight waterways, the cooperation of vessels usually results in train-like formations. This behavior is similar to the highway platooning of vehicles. A particular challenge arises when such platoons have to cross waterway intersections. At the intersections, the vessel trains need to interact with others. However, research on the interaction between vehicle platoons is still lacking.

This paper focuses on the cooperation of vessels at waterway intersections. We propose a framework for cooperative scheduling and control of CMVSs at intersections. The actions of the vessels are determined by solving two problems: Waterway Intersection Scheduling (WIS) and Vessel Train Formation (VTF). Firstly, the process of the vessels passing through an intersection is regarded as consumption of space and time. The WIS helps to find a conflict-free schedule for the vessels from different directions. By solving the WIS problem, each vessel’s desired time of arrival can be determined. Then, the actions of vessels are determined using a distributed Model Predictive Control algorithm in the VTF problem. Agreement among the vessels is achieved via serial iterative negotiations. Simulation experiments are carried out to illustrate the effectiveness of the proposed framework. We compare the passing time of each vessel, and the total passing time in three scenarios: non-cooperative case, partially-cooperative case, and fully-cooperative case. With the proposed cooperative framework, vessels can have smoother trajectories. The total passing time and the passing time for each vessel also benefit from the cooperation. Besides, the proposed framework can be extended to the whole waterway network where other infrastructure (bridges and locks) exists.

Recently, the cooperative control of multiple vessels has been gaining increasing attention because of the potential robustness, reliability and efficiency of multi-agent systems. In this paper, we propose the concept of Cooperative Multi-Vessel Systems (CMVSs) consisting of multiple coordinated autonomous vessels. We in particular focus on the so-called Vessel Train Formation (VTF) problem. The VTF problem considers not only cooperative collision avoidance, but also grouping of vessels. An MPC-based approach is proposed for addressing the VTF problem. A centralized and a distributed formulation based on the Alternating Direction of Multipliers Method (ADMM) are investigated. The distributed formulation adopts a single-layer serial iterative architecture, which gains the benefits of reduced communication requirements and robustness against failures. The impacts of information updating sequences and responsibility parameters are discussed. We furthermore analyze the scalability of the proposed method. Simulation experiments of a CMVS navigating from different terminals in the Port of Rotterdam to inland waterways are carried out to illustrate the effectiveness of our method. The proposed method successfully steers the vessels from different origins to form a vessel train. Due to the effective communication, vessels can timely respond to the velocity changes that others make. After the formation is formed, the distances between vessels become constant. The results show the potential to use CMVSs for inland shipping with enhanced safety.

Autonomous Surface Vessels (ASVs) have been developed for more than 20 years. Many ASV projects have been successfully realized, and as many are still under development. In literature there is a lack of research on the different applications and suitable environments for the deployment of ASV. Recently, a detailed definition and categorization of autonomy levels for ASVs has been proposed based on the characteristics of ASVs and existing classifications of autonomy. With this innovative autonomy level classification, this paper presents an extensive overview of existing ASV prototypes. The tendency and possible future developments of ASVs are analyzed according to the divisions obtained.

Autonomous Surface Vessels (ASVs) have been involved in numerous projects since the 1990s. Many ASV projects have been successfully realized, and as many are still under development. Together with the development of those new autonomous vessels, the research on classification about ASVs has become important. The classifications provide clarity to researchers, designers, shipbuilders, equipment manufacturers, ship owners and operators, enabling accurate specification of the desired level of autonomy in design and operations. Moreover, the involved research paves the way to a clearer understanding of the opportunity and challenges of research on autonomous vehicles. In this paper, we introduce the emerging concept of autonomous vessels. A multi-layer multi-agent control architecture of cooperative transport systems from the perspective of ASVs is proposed. Moreover, we provide an overview of existing research on the classification of autonomy. Based on the analysis, a detailed definition and categorization of autonomy levels for ASVs is proposed starting from the characteristics of ASVs and existing classification of autonomy. The proposed autonomy levels categorization assesses the overall autonomy level of a vessel by analyzing the automated sub-systems: Decision, Actions, Exceptions, and Cooperation. This categorization can be used to analyze existing ASV prototypes to gain insight into the status and trend of ASV research.