The Assessment of Unmanned Vessel Operation in Heavy Traffic Areas. Case Study of the North Sea Crossing by Unmanned Surface Vessel Sea-Kit

With the fast development of unmanned systems technology and artificial intelligence, Unmanned Surface Vehicle (USV) following unmanned aerial vehicle and unmanned vehicle is becoming more and more popular in military and civilian applications, such as hydrographic survey, maritime search and rescue, coastal water environment monitoring, 3D mapping and enemy reconnaissance. One of the core technologies of the USV is the precise and autonomous navigation system, which is essential for the USV accomplishing a variety of missions without human interventions. Usually, Global Navigation Satellite Systems (GNSS) is integrated with Inertial Navigation System (INS) or other embedded sensors to obtain more accurate position, attitude, speed, heading, etc. To meet the high performance requirements for USV navigation, a sea-sky line detection aided GNSS/INS integration method is proposed in this paper. The proposed method uses sea-sky line as an aid to GNSS/INS integration for USV navigation, which uses the different system to compensate the drawbacks of each source. First, a novel image-based sea-sky line detection method is presented. Then, the detected sea-sky line is applied into a geometric model to determine the roll and pitch angle of the USV. Finally, the difference equation of the SSL is integrated into the GNSS/INS hybridization architecture to improve the performance of the navigation system. Experimental results demonstrate the effectiveness of our proposed algorithm over the existing GNSS/INS integration method in the navigation parameters estimation, which can be applied for USVs with a camera system available on board.

In recent years, autonomous ships have been one of the burning issues in the maritime sector. The projects currently being carried out regarding autonomous ships create great excitement around the world. As a matter of fact, autonomous ships have several advantages in commercial activities, such as operational and crew-related cost savings and low risk in perilous environments. For this very reason, they will most likely have a permanent role in world maritime trade. On the other hand, it could be stated that they have some drawbacks that cannot be ignored, new vulnerabilities related to information technologies in particular. There exist some reasons to speculate that autonomous ships might be primary targets for cybercrim- inals. First of all, integrated information technology and operational technology systems will be the backbone of remote and autonomous operations. Another reason is that even ensuring whether the au- tonomous vessel is secure will depend on data produced by the sensors or received from maritime support systems including GPS and AIS, which can be exposed to leading or following cyberattacks. In addition, it can be claimed that high-speed internet, which will be used by a shore centre to gather data from autonomous ships without delay, will serve the purpose of criminals to hack the system in a shorter time. Last but not least, in case of a cyberattack, autonomous ships will not have an onboard crew to protect and rectify the ship. Thus, these new ships might bring new players to the scene with the thought that autonomous technologies are more vulnerable targets. Considering all these, cyber risks on autonomous ships spark a wide range of legal issues. On this matter, the first question is whether the international law of the sea is capable of accommodating the cyber vulnerabilities of autonomous ships. This begs the question of whether these acts amount to piracy in the context of the United Nations Convention on Law of the Sea. A further issue involves whether the 1988 and 2005 Conventions for the Suppression of Unlawful Acts against the Safety of Maritime Navigation can resolve the challenges related to autono- mous ships. This paper provides, firstly, background information about autonomous ships and the dispute on the legal definition and classification of autonomous ships. After discussing the differences between traditional and autonomous ships in terms of cyber vulnerabilities, it canvasses the possible challenges over the course of cyberattacks on autonomous ships. Then, it analyses the legal issues originating from those threats in the context of the law of the sea. Finally, it reflects whether there is a need for new regu- lations or amendments in existing laws to combat emerging cyber threats related to autonomous ships.

With the rapid development of artificial intelligence technology, unmanned surface vehicles (USVs) in marine Internet of Things (MIoTs) have become an important paradigm for marine environment exploration. However, in MIoTs, when collecting environmental information, USVs face a series of threats such as engine failure, grounding and collision, etc., resulting in damage to shipboard memory, vessel breakage and sinking, which may cause loss or damage of stored data. The USV fleet consisting of multiple USVs is recently advocated to enable collaborative communication and storage resource sharing. As such, in this paper, the USV fleet-assisted data backup scheme for the damaged USVs is proposed to guarantee the availability of stored data. First, a data backup framework for USV fleets is designed, where the USVs are classified into high-risk USVs and low-risk USVs according to the damage risk probability of sailing. Within the USV fleet, high-risk USVs (i.e., requesters) back up data to low-risk USVs (i.e., assistants) under emergency time. Second, the coalition game based on cost sharing is utilized to incentivize individual USVs to form the optimal USV fleets by maximizing the expected revenues, where the cost sharing fashion effectively ensures the stability of the coalitions. Finally, the joint optimization problem of the requesters’ allocating data decisions and the assistants’ receiving data decisions is formulated to maximize the average amount of data backup. The predictor-corrector interior point method (PIPM) and Q-learning method are leveraged to derive the reasonable solution of the formulated problem, with achieving the optimal allocating data decision and receiving data decision. Extensive simulation results demonstrate that the proposed scheme outperforms the benchmark schemes in terms of individual expected revenue, participation degree and the average amount of data backup.

: The accomplishment of Launch and Recovery of Unmanned Surface Vehicles (USVs)at sea poses new and unique technology development challenges. USV, USV host ship, and USV/host ship interface equipment design are simultaneously evolving and require specialized interfaces. The approach taken to solve these challenges influences the design of both USV and host ship and creates a new category of equipment. The development of technology that addresses the most difficult of these challenges is subject to a wide band of design and development process considerations for the sake of compatibility with USV and host ship. Coupled with these challenges is the need for a high level of craft control and equipment reliability to mitigate risk of damage from at-sea docking. Autonomous Launch and Recovery systems under development should all meet the same general set of safety, reliability and performance criteria and minimize impact to both USV and host ship. This paper identifies some of the unique operational conditions that exist when trying to recover USVs and proposes a set of general Launch and Recovery considerations based upon current at-sea testing being performed by Naval Surface Warfare Center Carderock Division(NSWC CD), Code 23. The goal of this paper will be to provide an Autonomous Launch and Recovery baseline and make recommendations for future USV Autonomous Launch and Recovery development. Lessons learned will influence future designers by providing a more balanced perspective about Autonomous USV Launch and Recovery technology development considerations. This paper is based on technology development work at Naval Surface Warfare Carderock Division, Code 23 funded by the ONR(Code 33)Unmanned Sea Surface Vehicle program.

With the rapid development of artificial intelligence technology and autonomous navigation technology, the unmanned surface vessel (USV) industry has developed accordingly, and it has played an important role in the fields of water quality monitoring, maritime inspection, and maritime safety assurance. However, USV is easily affected by the external lighting environment. In the case of insufficient lighting, the collected images have the characteristics of low brightness, low contrast and low resolution, and are extremely susceptible to external noise interference, making USV difficult obtain input requirements that meet the visual tasks such as target recognition and semantic segmentation. In this paper, we propose a deep learning-based low-light image enhancement and noise suppression method (LENet). Specifically, LENet is used to map the low-light image to the normal-light image through a deep Unet network, and CBM3D further suppresses the interference noise in the image to achieve the enhancement of the low-light image. We enhance the generalization ability and robustness of the deep network by embedding dilated convolutions and dense blocks in the deep Unet network. Structural similarity (SSIM) and norm are used as the loss function to further improve the quality of the enhanced image. The experimental results show that the deep network proposed in this paper improves the brightness and contrast of the images collected by the USV under insufficient lighting conditions, which can meet the input requirements of the USV visual task.

The accurate prediction of autonomous vessel CO2 emissions is critical for achieving IMO 2050 carbon neutrality and optimizing low-carbon maritime operations. Traditional models face limitations in real-time multi-source data analysis and dynamic cross-variable dependency modeling, hindering data-driven decision-making for sustainable autonomous shipping. This study proposes a Multi-scale Channel-aligned Transformer (MCAT) model, integrated with a 5G–satellite–IoT communication architecture, to address these challenges. The MCAT model employs multi-scale token reconstruction and a dual-level attention mechanism, effectively capturing spatiotemporal dependencies in heterogeneous data streams (AIS, sensors, weather) while suppressing high-frequency noise. To enable seamless data collaboration, a hybrid transmission framework combining satellite (Inmarsat/Iridium), 5G URLLC slicing, and industrial Ethernet is designed, achieving ultra-low latency (10 ms) and nanosecond-level synchronization via IEEE 1588v2. Validated on a 22-dimensional real autonomous vessel dataset, MCAT reduces prediction errors by 12.5% MAE and 24% MSE compared to state-of-the-art methods, demonstrating superior robustness under noisy scenarios. Furthermore, the proposed architecture supports smart autonomous shipping solutions by providing demonstrably interpretable emission insights through its dual-level attention mechanism (visualized via attention maps) for route optimization, fuel efficiency enhancement, and compliance with CII regulations. This research bridges AI-driven predictive analytics with green autonomous shipping technologies, offering a scalable framework for digitalized and sustainable maritime operations.

The role of the human element within complex socio-technical systems is continually being transformed and redefined by technological advancement. Autonomous operations across varying transport domains are in differing stages of realisation and practical implementation, and specifically within maritime operations, is still in its infancy. This study explores the potential effects of autonomous technologies on future work organisation and roles of humans within maritime operations. Ten Subject-Matter Experts working within industry and academia were interviewed to elicit their perspectives on the current state and future implications of autonomous technologies. Four main themes emerged: (i) Trust, (ii) Awareness and Understanding, (iii) Control, (iv) Training and Organisation of Work. A fuzzier fifth theme also appeared in the data analysis: (v) Practical Implementation Considerations, which encompassed various sub-topics related to real-world implementation of autonomous ships. The results provide a framework of human element issues relevant for the organisation and implementation of autonomous maritime operations. Practitioner summary: As autonomous shipping rapidly moves closer to real-world implementation, it is critical to develop an understanding of future roles of humans in autonomous maritime operations. By eliciting expert knowledge from academics and practitioners, we establish a framework of relevant issues facing humans in emerging autonomous systems and operations at sea.

With the continuous progress of contemporary science and technology and the increasing requirements for marine vehicles in various fields, the intelligence and automation of ships have become a general trend. The autonomous control of surface Unmanned Surface Vessel (USV) generally covers the USV path planning, path tracking control, and autonomous collision avoidance control. But in the whole navigation process of USV, autonomous berthing is also a crucial part. And the research on the algorithm of the automatic berthing process of the USV is less. Mature USV autonomous berthing technology can effectively reduce the cost of human and material resources and financial resources while reducing the accident rate reasonably and safely. Therefore, it is of great importance to comprehensively promote the development of USV autonomous berthing technology.

Detection of oil spills with aerial or space-born remote sensing resources has been deeply studied and developed over recent years. However, all these technologies still rely on in-situ verification with direct monitoring and sampling for validation. This paper presents the design, fabrication, simulation, and testing of an unmanned surface vehicle (USV), specifically designed for hydrodynamic efficiency and effective oil spill sampling. The USV's design, featuring a customized platform for the oil sampling mechanism, underwent an extensive simulation process using computational fluid dynamics (CFD) to validate its stability and analyze its impact on water flow dynamics. The design and fabrication process involved hull construction, integration of the control and power systems, and testing in a laboratory environment. The CFD analysis and testing revealed exceptional stability in the USV, showing only minimal rocking and pitching, which translates to consistent speed and precise navigation for the USV during operation. Using CFD for the design analysis allowed for the optimization of water flow dynamics between the two hulls, resulting in reduced drag and enhanced maneuverability for the USV. Turbulent flow patterns were observed at higher speeds, which notably provided valuable insights into the USV's hydrodynamic behavior and its possible interaction with any unforeseen marine conditions, such as encounters with marine life or debris. The key findings demonstrate the USV's potential to revolutionize environmental response efforts, especially in the context of oil spill disasters in remote areas. The accuracy of the CFD simulations was pivotal in anticipating the USV's performance in various marine conditions, which demonstrates the importance of collaboration between theoretical models and practical applications. This paper introduces an innovative integration between autonomous technology and environmental responsiveness, which showcases the possibilities of advancements in the field of autonomous maritime solutions. The involvement of this research extends beyond its immediate scope and offers a new prototype for monitoring and protecting marine environments. This advancement significantly contributes to the broader discussion for safer, more sustainable offshore exploration and environmental management.

The development of autonomous and remote operation technologies has raised significant questions regarding the sustainability and applicability of the current law of the sea and maritime security law, both of which were originally formulated with conventional ships in mind. Specifically, the presence and responsibilities of the master, officers, and crew on ships are emphasised in various international legal instruments, including the United Nations Convention on the Law of the Sea and the International Maritime Organisation’s conventions. This prompts an inquiry into whether these legal frameworks can accommodate unmanned operations, and if not, what legal amendments might be necessary to ensure their compliance. This thesis examines the applicability of the law of the sea and maritime security law to unmanned ships, with a focus on potential future legal reforms. The analysis draws on a range of primary legal sources, including customary international law, treaty law, judicial decisions, and general principles of law, alongside secondary sources such as the International Maritime Organisation’s guidelines, scholarly books, and articles. The discussions cover the introduction of unmanned ships, their classification under the law of the sea, their navigational rights and freedoms across various maritime zones, and their compliance with maritime safety regulations, rules, and standards. Additionally, the thesis explores the application of maritime security rules, particularly in relation to the use of unmanned ships for committing or suppressing crimes, as well as scenarios where unmanned ships may themselves be victims of unlawful acts. The research concludes that, while the law of the sea is generally capable of recognising unmanned ships as ‘ships’, specific amendments to the existing legal framework may be required. In this regard, the International Maritime Organisation is expected to play a central role in shaping future legal standards for unmanned ships.

The development of autonomous ship operation technology is progressing in the marine domain, necessitating risk analysis implementation in the development of such technology. However, a risk analysis method tailored for autonomous ship operation is yet to be established at this stage. Autonomous ships rely on software to perform tasks such as recognition, judgment, and operation, which are conventionally performed by human operators. In addition, these functions are exclusively utilized within their predetermined Operational Design Domains (ODDs), which represent assumed operational conditions. Therefore, when conducting a risk analysis for autonomous ships, in addition to the conventional equipment-based perspective, considering tasks and deviations from ODD is crucial. This study utilized an extended SWIFT method, Task-Based HAZID (TB-HAZID), using Unified Modeling Language (UML) class diagrams for hazard identification. In this paper, we present the hazards identification process through TB-HAZID for a hypothetical autonomous ship, and provide the trial results. In this paper, we show an example of hazard identification using TB-HAZID for a hypothetical autonomous ship, with the task illustrated as the focus point. Our proposed method can be applied to risk analysis of autonomous ships, which are expected to be developed based on various concepts in the future, and that the hazard identification examples can be used as a reference.

How can autonomous technology be used beyond end-customer autonomous driving features? This position paper addresses this problem by exploring a novel autonomous transport solution applied in the automotive logistics domain. We propose that factory-complete cars can be transformed to become their own autonomous guided vehicles and thus transport themselves when being moved from the factory for shipment. Cars equipped with such a system are driverless and use an onboard autonomous transport solution combined with the advanced driver assistance systems pre-installed in the car for end-customer use. The solution uses factory-equipped sensors as well as the connectivity infrastructure installed in the car. This means that the solution does not require any extra components to enable the car to transport itself autonomously to complete a transport mission in the logistics chain. The solution also includes an intelligent off-board traffic control system that defines the transport mission and manages the interaction between vehicles during systems operation. A prototype of the system has been developed which was tested successfully in live trials at the Volvo Car Group plant in Gothenburg Sweden in 2017. In the paper, autonomous transport is positioned in between autonomous guided vehicles and autonomous driving technology. A review of the literature on autonomous vehicle technology offers contextual background to this positioning. The paper also presents the solution and displays lessons learned from the live trials. Finally, other use areas are introduced for driverless autonomous transport beyond the automotive logistics domain that is the focus of this paper.

: With recent advances in research and technology, autonomous surface vessel capabilities have steadily increased. These autonomous surface vessel technologies enable missions and tasks to be performed without the direction of human operators, and have changed the way scientists and engineers approach problems. Because these robotic devices can work without manned guidance, they can execute missions that are too difficult, dangerous, expensive, or tedious for human operators to attempt. The United States government is currently expanding the use of autonomous surface vessel technologies through the United States Navy's Spartan Scout unmanned surface vessel (USV) and NASA,s Ocean-Atmosphere Sensor Integration System (OASIS) USV. These USVs are well-suited to complete monotonous, dangerous, and time-consuming missions. The USVs provide better performance, lower cost, and reduced risk to human life than manned systems. In this thesis, we explore how to plan multiple USV observation schedules for two significant notional observation scenarios, collecting water temperatures ahead of the path of a hurricane, and collecting fluorometer readings to observe and track a harmful algal bloom. A control system must be in place that coordinates a fleet of USVs to targets in an efficient manner. We develop three algorithms to solve the unmanned surface vehicle observation-planning problem. A greedy construction heuristic runs fastest, but produces suboptimal plans; a 3-phase algorithm which combines a greedy construction heuristic with an improvement phase and an insertion phase, requires more execution time, but generates significantly better plans; an optimal mixed integer programming algorithm produces optimal plans, but can only solve small problem instances.

Within the next several years, there will be a high level of autonomous technology that will be available for widespread use, which will reduce labor costs, increase safety, save energy, enable difficult unmanned tasks in harsh environments, and eliminate human error. Compared to software development for other autonomous vehicles, maritime software development, especially in aging but still functional fleets, is described as being in a very early and emerging phase. This presents great challenges and opportunities for researchers and engineers to develop maritime autonomous systems. Recent progress in sensor and communication technology has introduced the use of autonomous surface vehicles (ASVs) in applications such as coastline surveillance, oceanographic observation, multi-vehicle cooperation, and search and rescue missions. Advanced artificial intelligence technology, especially deep learning (DL) methods that conduct nonlinear mapping with self-learning representations, has brought the concept of full autonomy one step closer to reality. This article reviews existing work on the implementation of DL methods in fields related to ASV. First, the scope of this work is described after reviewing surveys on ASV developments and technologies, which draws attention to the research gap between DL and maritime operations. Then, DL-based navigation, guidance, control (NGC) systems and cooperative operations are presented. Finally, this survey is completed by highlighting current challenges and future research directions.

The emergence of unmanned merchant ships will challenge the existing international shipping law and practice. Many legal issues regarding unmanned ships under international law await clarification, and the issues involving navigational rights are at the top of the list. This article aims to examine the navigational rights of unmanned merchant ships under the established international regulatory framework for global shipping. We find that many States, particularly the coastal States, may hold a cautious view regarding the international navigation of unmanned ships, because of uncertainties in terms of safety and reliability, questions about seaworthiness and manning, and the potential ship-source pollution incidents. Hence, we make the following suggestions: first, the International Maritime Organization plays a more proactive role in interpreting and implementing the existing rules on international navigation. Second, that flag States, coastal States, port States collaborate and consider filling the existing regulatory gaps to facilitate the development of unmanned merchant ships and to justify their navigational rights.