Future Directions for Human-Centered Transparent Systems for Engine Room Monitoring in Shore Control Centers

Many autonomous ship projects have reflected the increasing interest in incorporating the concept of autonomy into the maritime transportation sector. However, autonomy is not a silver bullet, as exemplified by many incidents in the past involving human and machine interaction; rather it introduces new Human Factor (HF) challenges. These challenges are especially critical for Engine Room Monitoring (ERM) in Shore Control Centre (SCCs) due to the system’s complexity and the absence of human senses in the decision-making process. A transparent system is one of the potential solutions, providing a rationale behind its suggestion. However, diverse implementations of transparency schemes have resulted in prevalent inconsistencies in its effects. This literature review paper investigates 17 transparency studies published over the last eight years to identify (a) different approaches to developing transparent systems, (b) the effects of transparency on key HFs, and (c) the effects of information presentation methods and uncertainty information. The findings suggest that the explicit presentation of information could strengthen the benefits of the transparent system and could be promising for performance improvements in ERM tasks in the SCC.

Autonomous ships in maritime education model course 7.01

The fourth industrial revolution is already a fact. It is manifested in the emerging automation of many processes in shipping, which until recently have been highly dependent on the competence of the people who manage them. The analysis of navigational accidents invariably touches the human factor and involves it in the reasons for their occurrence. The statistics are discouraging and the lack of competence of seafarers is always present in the reports of the investigating authorities. The idea of creating and implementing autonomous ships is cited as a lifeline to overcome the shortcomings that disturb the industry due to the human factor. A few authors in their publications point out many unresolved issues, one of which is related to the education and competence of service personnel. The existing International Convention for Standards of Training, Certification and Watchkeeping of Seafarers does not cover unmanned ships. The mandatory and recommended competencies in it are addressed to the people on board. Some maritime educational institutions have introduced the concept of “autonomous ship” in their curricula, such as Nikola Vaptsarov Naval Academy, Varna and Faculty of Maritime Study, Split. There are probably others who think ahead, but this approach is not enough because unmanned ships are already a fact in the maritime industry. This article aims at exploring the possibilities for supplementing the curricula of maritime training institutions with appropriate subjects for the new realities in shipping.

Navigation Situation Clustering Model of Human-Operated Ships for Maritime Autonomous Surface Ship Collision Avoidance Tests

The collision avoidance system is one of the core systems of MASS (Maritime Autonomous Surface Ships). The collision avoidance system was validated using scenario-based experiments. However, the scenarios for the validation were designed based on COLREG (International Regulations for Preventing Collisions at Sea) or are arbitrary. Therefore, the purpose of this study is to identify and systematize objective navigation situation scenarios for the validation of autonomous ship collision avoidance algorithms. A data-driven approach was applied to collect 12-month Automatic Identification System data in the west sea of Korea, to extract the ship’s trajectory, and to hierarchically cluster the data according to navigation situations. Consequently, we obtained the hierarchy of navigation situations and the frequency of each navigation situation for ships that sailed the west coast of Korea during one year. The results are expected to be applied to develop a collision avoidance test environment for MASS.

VECTOR FIELD GUIDANCE LAW FOR CURVED PATH FOLLOWING OF AN UNDERACTUATED AUTONOMOUS SHIP MODEL

A vector field guidance law and control system for curved path following of an underactuated surface ship model is presented in this paper. In order to obtain the curved path, continuous derivatives piecewise cubic Hermite interpolation is applied for path generation based on the predefined waypoints. A heading autopilot controller is designed based on 2nd order Nomoto’s model and its stability is guaranteed by the Diagram of Vyshnegradsky method. The parameters of Nomoto model are estimated using least square support vector machine based on the manoeuvring tests. The vector field guidance law is applied for both straight and curved path-following control of an underactuated surface ship model. In order to demonstrate the performance, the classical guidance law based on line-of-sight, is adopted for comparison. The results show that the vector field method is capable to solve the guidance problem of underactuated surface ships.

Survey on Deep Learning-Based Marine Object Detection

We present a survey on marine object detection based on deep neural network approaches, which are state-of-the-art approaches for the development of autonomous ship navigation, maritime surveillance, shipping management, and other intelligent transportation system applications in the future. The fundamental task of maritime transportation surveillance and autonomous ship navigation is to construct a reachable visual perception system that requires high efficiency and high accuracy of marine object detection. Therefore, high-performance deep learning-based algorithms and high-quality marine-related datasets need to be summarized. This survey focuses on summarizing the methods and application scenarios of maritime object detection, analyzes the characteristics of different marine-related datasets, highlights the marine detection application of the YOLO series model, and also discusses the current limitations of object detection based on deep learning and possible breakthrough directions. The large-scale, multiscenario industrialized neural network training is an indispensable link to solve the practical application of marine object detection. A widely accepted and standardized large-scale marine object verification dataset should be proposed.

Gird Based Line Segment Detector and Application: Vision System for Autonomous Ship Small Assembly Line

The shipbuilding industry demands intelligent robot, which is capable of various tasks without laborious pre-teaching or programming. Vision system guided robots could be a solution for autonomous working. This paper introduces the principle and technique details of a vision system that guides welding robots in ship small assembly production. TOF sensors are employed to collect spatial points of workpieces. Huge data amount and complex topology bring great difficulty in the reconstruction of small assemblies. A new unsupervised line segment detector is proposed to reconstruct ship small assemblies from spatial points. Verified using data from actual manufacturing, the method of this paper demonstrated good robustness which is a great advantage for industrial applications. This paper’s work has been implemented in shipyards and shows good commercial potential. Intelligent, flexible industrial robots could be implemented with the findings of this study, which will push forward intelligent manufacturing in the shipbuilding industry.

Risk assessment of collisions of an autonomous passenger ferry

Autonomous transportation is an increasingly popular concept and is gradually becoming a reality. This transformation also changes the way people travel. For example, the autonomous ferry is an emerging alternative for residents living in coastal areas. To evaluate the safety of an autonomous ferry, a thorough safety review is necessary. This paper makes an initial attempt by developing a model for performing a risk assessment of collisions between an autonomous ship with manned vessels and applying this to a specific ferry operating in a canal. The safety barriers to prevent a collision are identified, as well as the respective failure modes. A Bayesian belief network is employed to model the collision and to quantitively assess the collision risk of the autonomous ferry. Relevant data are collected to perform a quantitative risk analysis. By running the model, the likelihood of a collision is calculated. A sensitivity analysis is also performed to identify the most contributing causes.

Intention modelling and inference for autonomous collision avoidance at sea

The open wording of the traffic rules of the sea, COLREGS, and the existence of unwritten rules, make it essential for an autonomous ship to understand the intentions of meeting traffic. This article uses a dynamic Bayesian network (DBN) to model and infer the intentions of other ships based on their observed real-time behavior. Multiple intention nodes are included to describe the different ways a ship can interpret and conflict with the behavioral rules outlined in CORLEGS. The prior distributions of the intention nodes are adapted to the current situation based on observable characteristics such as location and relative ship size. When a new observation is made, the probability distributions of the intention variables are updated by excluding all combinations of intention states that conflict with the observed behavior. This way of modeling makes the intention probabilities independent of how often observations are made. The resulting model is able to identify situations that are prone to cause misunderstandings and infer the state of multiple intention variables that describe the behavior. Different collision avoidance algorithms can use the resulting intention information to better know if, when, and how to act.