Keywords: Supervision and surveillance in marine applications, Intelligence and autonomy in marine systems and operations, Information systems and methods in marine applications
Abstract: Though general object detection with deep learning has achieved great success in the maritime domain, recognizing far-away and tiny objects is still challenging. However, an autonomous vessel must be aware of objects even several nautical miles away for early planning. In this paper, we propose a far-away and tiny object detection framework with deep learning by utilizing a high-resolution image. The framework is two-fold: Small Object Detector (SOD) and Large Object Detector (LOD). SOD investigates a region around the horizon with a fine-resolution image aiming to recognize far-away and small objects. LOD targets large objects that are identifiable in an even coarse image. We evaluate our approach on datasets including objects of various sizes inshore or offshore. The results verify that our proposed scheme is effective against even far-away and tiny objects while keeping computational costs low.

Keywords: Aquaculture, Intelligence and autonomy in marine systems and operations, Internet of things (IoT) in maritime domain
Abstract: Irrespective of the production principle, aquaculture farm facilities need to be maintained through day-to-day management routines to sustain the general production process, and more discrete operations to counter events that occur occasionally. To achieve the desired level of control over the production process in an aquaculture farm, it is essential that the required routines and operations are conducted with sufficient precision to make the impacts on the production process predictable. Adaptation of autonomous and robotic solutions become vital to addressing the challenges in the aquaculture industry towards three overarching goals of 1) low production costs, 2) improved efficiency and 3) increased profitability and sustainability. This talk will aims to introduce and present the trends and solutions adapted in salmon farming industry both from R&D and industry perspectives.

Keywords: Intelligence and autonomy in marine systems and operations, Maritime robotics (underwater, surface, aerial), Maritime safety and security for ports and ships
Abstract: Biofouling is a significant eco-economical problem. Because biofouling causes ships to experience skin friction drag and disturbs the ecosystem, the regulation of ship hull cleaning is being improved. However, the niche areas of a ship are difficult to clean using a vehicle-based robot because of the complex cleaning area and fast growth rate of biofouling. In this study, we developed an autonomous cleaning system using a multi-degree-of-freedom hydraulic manipulator for the niche area of a ship hull. Our system uses a manipulator to reach a complex niche area and recognizes the cleaning target surface using an underwater laser scanner. Based on the recognized cleaning area, the robot plans an optimal path considering the full coverage and normal vectors of the target area. Our proposed robot system was verified on the ground and under water and showed adequate cleaning performance.

Keywords: Autonomous and remotely operated (surface and underwater) marine vessels, Intelligence and autonomy in marine systems and operations, Guidance, navigation and control (GNC) of unmanned marine vehicles (surface and underwater)
Abstract: Fully or partial autonomous marine vessels are actively being developed by many industry actors. In many cases, the autonomous vessels will be operating close to shore, and within range of a Remote Control Center (RCC). Close to shore operation requires that the autonomous vessel is able to navigate in close proximity to other autonomous or manned vessels, and possibly in confined waters, while obeying the COLREGs on equal terms as any other vessel at sea. In confined waters however, certain COLREGs rules apply, which might alter the expected actions (give-way or stand-on), depending on the manoeuvrability of the vessels. This paper presents a Situation Awareness (SAS) framework for autonomous navigation that complies with COLREGs rule 9 (Narrow Channels). The proposed solution comprises a method for evaluating the manoeuvrability of a vessel in confined waters, for assessing the applicability of COLREGs rule 9. This feature is then integrated into an already existing SAS framework for facilitating COLREGs-compliant navigation in restricted waters. The applicability of the proposed method is demonstrated in simulation using a case study of a small autonomous passenger ferry.

Keywords: Autonomous and remotely operated (surface and underwater) marine vessels, Guidance, navigation and control (GNC) of unmanned marine vehicles (surface and underwater), Intelligence and autonomy in marine systems and operations
Abstract: Research into autonomous surface vehicles is noticeably limited in regards to the functionality of the vehicles themselves. Specifically, testing and evaluation typically occurs at speeds considerably lower than what is allowed in an operational setting. For a vessel to be able to take advantage of higher speeds, there must be a robust and tested method for determining localisation and navigation. With an emphasis of development for small vessels with higher impulse capabilities, working in confined and restricted environments, the decision was made to develop a method of navigation that relied solely upon lightweight sensors. For this, a single light ranging sensor was utilised to develop both simultaneous localisation and mapping for the vessel, using the normal distribution transform and iterative closest point methods. Evaluation of the algorithm accuracy as the vessel moved above speeds greater than two metres per second was conducted, and it was feasibly evaluated that there was no observable drift of mapping in horizontal planes, however, there was a accumulated drift in the vertical plane and a transient response in localisation deviation as the vessel changed impulse through the two metre per second window.

Keywords: Dynamic positioning & position mooring systems for ships & platforms, Autonomous and remotely operated (surface and underwater) marine vessels, Maritime robotics (underwater, surface, aerial)
Abstract: With the international community pushing for a computer vision based option to the laws requiring a look-out for marine vehicles, there is now a significant motivation to provide digital solutions for navigation using these envisioned mandatory visual sensors. This paper explores the monocular direct sparse odometry algorithm when applied to a typical marine environment. The method uses a single camera to estimate a vessel's motion and position over time and is then compared to ground truth to establish feasibility as both a local and global navigation system. Whilst it was inconsistent in accurately estimating vessel position, it was found that it could consistently estimate the vessel's orientation in the majority of the situations the vessel was tasked with. It is therefore shown that monocular direct sparse odometry is partially suitable as a standalone navigation system and is a strong base for a multi-sensor solution.

Keywords: Guidance, navigation and control (GNC) of marine vessels, Information systems and methods in marine applications, Intelligence and autonomy in marine systems and operations
Abstract: Safe navigation at sea depends on reliable position information. The easy to use and readily available navigation satellite systems are providing round the clock position information for seafarers, but denial of these services by jamming or spoofing techniques have become frequent, and other means are needed to validate critical navigation information. This paper revisits traditional methods to estimate position and heading of a vessel and offers a framework for computerized calculation of these basic observables without the use of radio-borne external information. Using radar and sea chart information, the paper investigates the quality of navigation information based on observed location of beacons, landmarks, coastlines and buoys. The paper demonstrates convincing accuracy in both position and heading estimation.

Keywords: Cooperative navigation and control, Autonomous and remotely operated (surface and underwater) marine vessels
Abstract: There exist several collision avoidance algorithms for autonomous ships. But the majority of them do not utilize information about other ships' intentions, except for observed position and velocity. As the attention for large-sized autonomous ships to be used in logistics is growing, autonomous ships will need to collaborate and negotiate with other ships to prevent reactive and agile collision avoidance maneuvers. As a first step towards a collaborative collision avoidance algorithm, we implemented a reactive short-range algorithm by utilizing other ships' trajectory plans. We aimed to improve the existing Scenario-Based Model Predictive Control (SB-MPC) algorithm by including route exchange-based trajectory predictions and called it the Informed SB-MPC. Additionally, we introduce adaptive and conditional parameter selection methods for the SB-MPC design. Hereby we implemented the compliance with the COLREGs Rule 18 concerning responsibility between vessels in addition to the existing Rules 13-17. The performance of the new method is demonstrated with head-on, crossing, overtaking, and multiple ships scenarios.

Keywords: Guidance, navigation and control (GNC) of unmanned marine vehicles (surface and underwater), Intelligence and autonomy in marine systems and operations, Marine traffic systems & intelligent marine transportation systems
Abstract: Machine Learning (ML) techniques have gained significant traction as a means of improving the autonomy of marine vehicles over the last few years. This article surveys the recent ML approaches utilised for ship collision avoidance (COLAV) and mission planning. Following an overview of the ever-expanding ML exploitation for maritime vehicles, key topics in the mission planning of ships are outlined. Notable papers with direct and indirect applications to the COLAV subject are technically reviewed and compared. Critiques, challenges, and future directions are also identified. The outcome clearly demonstrates the thriving research in this field, even though commercial marine ships incorporating machine intelligence able to perform autonomously under all operating conditions are still a long way off.

Keywords: Autonomous and remotely operated (surface and underwater) marine vessels, Nonlinear and optimal control in marine systems, Intelligence and autonomy in marine systems and operations
Abstract: This paper presents a rule-compliant trajectory optimization method for the guidance and control of autonomous surface vessels. The method builds on Model Predictive Contouring Control and incorporates the International Regulations for Preventing Collisions at Sea---known as COLREGs---relevant for motion planning. We use these traffic rules to derive a trajectory optimization algorithm that guarantees safe navigation in mixed-traffic conditions, that is, in traffic environments with human operated vessels. The choice of an optimization-based approach enables the formalization of abstract verbal expressions, such as traffic rules, and their incorporation in the trajectory optimization algorithm along with the dynamics and other constraints that dictate the system's evolution over a sufficiently long receding horizon. The ability to plan considering different types of constraints over a long horizon in a unified manner leads to a proactive motion planner that mimics rule-compliant maneuvering behavior. The efficacy of the derived algorithm is validated in different simulation scenarios.

Keywords: Fault tolerant control and fault handling for marine vessels, Autonomous and remotely operated (surface and underwater) marine vessels, Nonlinear and optimal control in marine systems
Abstract: In this paper, a disturbance observer based control strategy is developed to provide fault tolerance to thruster faults for a remotely operated vehicle. The scheme relies on the vehicle's position, orientation and velocity information only, without the need for additional measurements from the thrusters such as voltage, current, and rotation speed. Because the system is over-actuated, a bank of observers is designed for purposes of fault detection and isolation. A nonlinear disturbance observer is designed to restructure itself, according to the fault isolation outcome, to estimate the fault magnitude. The fault estimation is finally exploited by the control law using an active fault tolerant control strategy. The solution is designed for the cases where at most one faulty thruster is expected. The fault tolerant control strategy is tested in simulation, where a severe thruster fault is injected.

Keywords: Guidance, navigation and control (GNC) of marine vessels, Nonlinear and optimal control in marine systems, Maritime robotics (underwater, surface, aerial)
Abstract: This paper presents a trajectory tracking scheme for a class of underactuated non-minimum phase marine vessels. Through proper coordinates transformations, the vessels tracking model can be transformed into two-input-two-output strict-feedback form for which general backstepping method can be applicable to solve the control problem. To avoid possible singularity problem in the recursive control design, an AMO (asymptotic modification of orientation) concept is applied. In this case, the vessels are forced to track this modified trajectory instead of directly tracking the predefined reference trajectory. Since the vessels' tracking model is transformed into two-input-two-output strict-feedback form with invertible control gain matrix, the non-minimum phase problem can be easily handled by the proposed method. Proposed tracking method can guarantee the asymptotic stability of closed-loop system in terms of polar coordinates. Simulation studies are also carried out to demonstrate the effectiveness of presented tracking scheme.

Keywords: Nonlinear and optimal control in marine systems, Hybrid power generation in marine systems, Autonomous and remotely operated (surface and underwater) marine vessels
Abstract: The Super-Twisting Algorithm is employed to control the voltage of a Bidirectional DC-to-DC Converter of an on-board propulsion system in presence of large load variations. The Bidirectional DC-to-DC Converter is modeled using average value modeling, and it is shown by an alternative approach that the zero dynamics for the converter topology supplying a Constant Power Load are unstable with the DC bus voltage as output, and stable for the inductor current as output. Here, a derivation of the controller gains is presented based on the average model of the system. The gains are described with respect to the inductor current and its bounded perturbations. The performance of the proposed controller is compared to a conventional cascaded PI controller, and exhibits strong robustness with respect to external system variations

Keywords: Nonlinear and optimal control in marine systems, Modeling, identification, simulation, and control of marine systems, Guidance, navigation and control (GNC) of marine vessels
Abstract: For marine vessels, autopilot systems require global stability, even under input constraints. This study proposes a straight-path-following control law that guarantees global asymptotic stabilization in the presence of input constraints. We consider a kinematic model based on the pivoting point as a marine vessel maneuvering model and design a control Lyapunov function (CLF) using the minimum projection method. Finally, a smooth angular velocity input is obtained. This controller satisfies the constraint by determining the range of controller gain. The effectiveness of the proposed method was confirmed by a computer simulation.

Keywords: Nonlinear and optimal control in marine systems, Adaptive and robust control in marine systems, Autonomous and remotely operated (surface and underwater) marine vessels
Abstract: This paper describes a tube-based model predictive control (TMPC) approach to robust path tracking and obstacle avoidance for surface vehicles. The TMPC algorithm consists of a nominal model predictive control and a state feedback control, which ensure that the state and input constraints are always satisfied under uncertain environmental disturbances. For obstacle avoidance, a robust positively invariant (RPI) set that contains the vehicle's position must be effectively calculated. To this end, the vehicle's dynamics are decoupled into surge and sway-yaw subsystems based on the vehicle's error dynamics with regard to the desired path, and zonotopes are used for the RPI set calculation. A TMPC is then designed using the obtained RPI set for each subsystem. Simulation results are presented to verify the effectiveness of the proposed control algorithm.

Keywords: Guidance, navigation and control (GNC) of unmanned marine vehicles (surface and underwater), Automation of ship’s systems, Decision support and safe operation
Abstract: The main question investigated in this paper is whether additional decision steps can improve vessel behavior produced by the collision avoidance method scenario based model predictive control (SBMPC). The method, which functions by predicting alternative paths resulting from a finite number of alternative control behaviors, then selecting which behavior to apply by use of a cost function, was originally intended to allow switching between several behaviors on the prediction horizon. However, current implementations have been limited to a single behavior. To compare the single-step and multi-step SBMPC, a simulation study was performed, where different configurations for the number, positioning and possible control actions were tested. In the course of the simulation study it became clear that identifying situations producing a significant difference between the two methods was di cult to identify and the multi-step SBMPC led to only minor improvements in very few scenarios.

Keywords: Intelligence and autonomy in marine systems and operations, Automation of ship’s systems, Actuators, thrusters, propulsion systems, and sensors in marine systems
Abstract: Detecting when and where contact with the quay appears is an important ability for ships undergoing a docking maneuver. The motion of the quay, environmental forces, and hydrodynamic effects caused by the interaction between the ship and the quay are all important factors that affect if a docking procedure succeeds or not. This paper studies how contact with the quay can be detected using conventional motion sensors. This includes sensor data from inertial measurement units, global navigation satellite systems, and estimates from an inertial navigation system. The contact detection task can be interpreted as a binary classification problem deciding if contact has occurred or not. Three conventional supervised machine learning methods are studied using experimental data captured in full-scale experiments. Logistic regression, a support vector machine and a long-term short memory network have been trained and investigated. The results are promising and a proof of concept illustrating that supervised machine learning is a viable strategy for quay contact detection using motion sensors.

Keywords: Decision support and safe operation, Automation of ship’s systems, Condition-based monitoring in marine systems
Abstract: Onboard guidance systems have emerged to improve the safety of fishing vessels providing to the skipper with simplified stability information. In the last years, the authors have developed a stability monitoring system that automatically estimates the natural roll frequency of the vessel. Although the performance was acceptable, there were some specific situations where the influence of external excitations reduced the accuracy of the stability estimations. In this work, a methodology to automatically estimate the wave encounter frequency from ship motions is proposed. Then, this methodology is included in the stability monitoring system. Towing tank tests of a mid-sized stern trawler in different conditions have been used to analyse the improvements obtained with this approach.

Keywords: Marine cyber-physical systems, Surface and underwater vehicles, Aquaculture
Abstract: Cooperation of a remotely operated vehicle (ROV) and an autonomous surface vehicle (ASV) in prolonged robotic inspections missions in mariculture requires a tether management system (TMS) with a docking system mounted onto the ASV. The autonomous surface developed in the scope of HEKTOR (Heterogeneous Autonomous Robotic System in Viticulture and Mariculture) project is shortly presented. Furthermore, mechanical and electrical design of the TMS, the control scheme and communication protocol of the TMS with the ASV, and TMS-ROS interface for future high-level mission control are described. Laboratory pool and at-sea field trials of the TMS show that the chosen concept works in various settings.

Keywords: Monitoring, diagnosis and fault handling, Fault tolerant control and fault handling for marine vessels, Condition-based monitoring in marine systems
Abstract: This paper proposes a virtual sensor scheme designed to compensate for sensor fault effects in marine fuel engines. The proposed scheme design follows a distributed approach, where the marine fuel engine is decomposed in several subsystems. Then, for each subsystem we design a monitoring agent that can actively compensate for the effects of sensor faults occurring in the specific subsystem. This is realized using virtual sensors that can estimate the sensor fault in order to reconstruct the faulty measurements. Due to the Differential-Algebraic mathematical description of marine fuel engine dynamics, we design three types of virtual sensors; using adaptive observers, Set Inversion via Interval Analysis (SIVIA) and static models. Simulation results are used to illustrate the efficiency of the method.

Keywords: Hybrid power generation in marine systems, Modeling, identification, simulation, and control of marine systems
Abstract: Shaft generators with variable frequency drive are used for electrical power production on large marine vessels. They are connected to the large two-stroke main engine for vessel propulsion. This shaft generator setup may unfortunately destabilize the engine speed. The main engine control system must stabilize the speed, but because of inherent delays in the engine, this is a difficult task. MAN has mitigated the challenge by adjusting the engine speed governor controller gains and by introducing new sets of limits to the shaft generator power.