No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Autonomous ships are on the horizon: here’s what we need to know
Abstract
Ships and ports are ripe for operation without humans — but only if the maritime industry can work through the practical, legal and economic implications first. Ships and ports are ripe for operation without humans — but only if the maritime industry can work through the practical, legal and economic implications first.
... Autonomous shipping, is not just a vision of the future; real projects are underway around the world (Negenborn et al., 2023). Over the past two years, a number of autonomous vessels have successfully carried out their trials, with ships from China, the UK and Norway. ...
... Autonomous technology, applied to ships with varying degrees of autonomy, is mainly about the use of sensors and 'artificial intelligence (AI) systems' to operate, navigate, steer and prevent collisions (Negenborn et al., 2023). Ultimately, fleets of autonomous ships might be monitored from 'maritime traffic control centres' on land, enabling the autonomous ships to interact with each other and avoid collisions (Zhang et al., 2021c). ...
... If so, the above legal ambiguities on roles of the shore-based remote-controllers and other key players and 'certificate of insurance or other financial security' need to be clarified to embrace the autonomous ships. As for fully autonomous ships, which are expected to have sophisticated 'sensors and artificial intelligence (AI) systems to navigate, steer and avoid collisions' (Negenborn et al., 2023), will shipowners of such ships be even more liable in the event of a collision with conventional ships, because the reason for the collision could be that the autonomous ships are not sufficiently smart and safe for navigation? 43 Autonomous ships may only be able to navigate in dedicated autonomous shipping areas in the near future, before they can become truly seaworthy for ocean voyages (Negenborn et al., 2023). ...
Autonomous ships are seen as the next generation of ships to meet sustainability challenges. While abundant studies have noted the potential of autonomous ships to be emission-free and reduce air pollution, research has paid scant attention to the significant uncertainties of the autonomous shipping that may lead to new environmental risks such as traffic incidents and oil spills. It is therefore necessary to assess the compatibility of the autonomous ships with international environmental laws and regulations. An analytical framework of international law on ship-source pollution has been proposed to contemplate such a legal assessment. Autonomous ships would challenge the relevant treaty provisions on preventing, combating and compensating for ship-source pollution and raise a number of new legal issues, resulting in a current lack of legal predictability and certainty. Only as autonomous ships become more widely tested, recognised and trusted will a robust roadmap for legalising MASS become clearer.
... With the development of increasing automation, information technology and artificial intelligence, the development of maritime autonomous surface ships (MASS) is emerging rapidly due to their potential to improve safety and efficiency. MASS is defined as several degrees of autonomy (DoA), considering its functional levels, decision location etc. [1]. Compared to the highest DoA -"Highly autonomous", in which MASS can navigate without human intervention, the DoAs involve "remote operation" are believed to be more feasible and realistic in current studies [2,3]. ...
... Compared to the highest DoA -"Highly autonomous", in which MASS can navigate without human intervention, the DoAs involve "remote operation" are believed to be more feasible and realistic in current studies [2,3]. Hence, humans will still participate in MASS operation, and human errors may remain, even be in new forms [1,4]. To cope with this challenge, in the current early phase of MASS development, researchers have been dedicated to developing the assistance systems for human operators, as well as to carry out safety analysis serving to the human-oriented and safety-critical strategies for MASS design [5,6]. ...
... The mA2 ferry is designed to cross a 100 m canal in Trondheim in Norway, and it is used for research and development. 1 The virtual version of the mA2 in the Gemini platform can be considered its "digital twin", as it shares its precise geometrical features and inertial characteristics [65], as shown in Fig. 6. ...
Human-autonomy collaboration plays a pivotal role in the development of Maritime autonomous surface ships (MASS), as Shore control center (SCC) operators may engage in the control loop by directly operating the MASS, or, in the supervisory loop, monitoring the MASS and taking over control when needed. Thus, efficient human performance during takeover control and operation is crucial for the safety of MASS operations. However, since the MASS is still in the early phase of development, the mechanism of human errors is unknown, and the data on human-autonomy collaborative operation is scarce. Human reliability analysis (HRA) aims to assess human errors qualitatively and quantitatively, and is widely used in various complex systems to help safety analysis. This study is dedicated to incorporating advanced HRA methods elements to identify and quantify human errors during taking over control and operation of a MASS in collision avoidance scenarios. It presents virtual experimental results, combined with theoretical human error identification and assessment methods. At first, we apply the Human-System Interaction in Autonomy (H-SIA) method to identify potential human errors; secondly, we identify relevant Performance Shaping Factors (PSFs) including Experience, Boredom, Task complexity, Available time and Pre-warning, and performance measures of the human errors, and implement them in the virtual experiment based on a full-scale autonomous ferry research vessel called milliAmpere2. Finally, we build a Bayesian Network (BN) to present causal and probabilistic relationships between PSFs and human errors through experimental data. The results show that available time has the highest impact on takeover performance of operators, followed by task complexity and pre-warning. Boredom does not present a significant sole impact unless combined with available time. Experience does not show a significant impact on human performance. In addition to the relevance of the human errors analysis to the safe development and operational design of MASS, the developed method benefits other human-autonomy collaborative systems. The developed BN model shows adaptability to assess human error probabilities, and the practical significance of integrating experimental data into the existing HRA methodologies for complex systems.
... Maritime accidents continue to occur, and ship collisions are recognized as a major event based on maritime accident statistics in major countries, such as the EU, Canada, and Japan [1][2][3]. To provide a solution to such collisions, autonomous ships are being developed based on advances in artificial intelligence (AI) systems and technologies [4]. As the development of autonomous ships is still in its early stages, ship collisions are a major threat to the navigation safety at sea [5]. ...
... A crucial challenge for autonomous ships is the development of a system that ensures safety by including an autopilot system [4]. In this context, an autopilot system is one that performs autonomous navigation using algorithms based on AI and deep learning. ...
... In this context, an autopilot system is one that performs autonomous navigation using algorithms based on AI and deep learning. Autonomous navigation can provide a solution to the issues of maritime collisions [4,11]. To prevent maritime collisions, research is currently being conducted in areas under the categories of ship motion prediction, own ship (OS) trajectory prediction, collision situation detection, and collision avoidance (CA) algorithm development [12]. ...
Ship collisions are a major maritime accident; various systems have been proposed to prevent them. Through investigating and analyzing the causes of maritime accidents, it has been established that ship collisions can either caused by delaying actions or not taking the sufficient actions to avoid them. Recognizing the limitations in providing quantitative numerical values for avoiding ship collisions, this study aimed to use Bayesian regularized artificial neural networks (BRANNs) to suggest the proper time and sufficient actions required for ship collision avoidance consistent with the Convention on the International Regulations for Preventing Collisions at Sea. We prepared the data by calculating the proper times and sufficient actions based on precedent research and used them to train, validate, and assess the BRANNs. Subsequently, an artificial neural network controller was designed and proposed. The data of the proposed neural network controller were verified via simulation, validating the controller. This study is limited in cases such as overtaking a ship in front. However, it is expected that this controller can be improved by establishing the criteria for an appropriate overtaking distance after further examining the closest point of approach (CPA) and time to the CPA (TCPA) for overtaking a ship in front and using the method presented herein.
... Automation of ship guidance is a current and urgent problem, as the ship is considered the most important and environmentally friendly means of transport in global trade and the shipping industry suffers from a shortage of skippers [1]. Automatic vessel trajectory prediction (VTP) is a fundamental, safety-critical task required in this endeavor, as it supports collision avoidance, route planning, and anomaly detection applications [2]. ...
... In a recent review on the subject [2] a growth of the share of publications reporting the usage of DL methods in the overall VTP literature from 38 % in 2018 to 77 % in 2021 is mentioned. Most approaches are developed for maritime 1 vessels and use vessel movement data extracted from Automatic Identification System (AIS) logs [2]. Especially in the case of inland VTP, these data alone are insufficient for realistic predictions as the limitation of the navigable area is unknown. ...
Physics-related and model-based vessel trajectory prediction is highly accurate but requires specific knowledge of the vessel under consideration which is not always practical. Machine learning-based trajectory prediction models do not require expert knowledge, but rely on the implicit knowledge extracted from massive amounts of data. Several deep learning (DL) methods for vessel trajectory prediction have recently been suggested. The DL models developed typically only process information about the (dis)location of vessels defined with respect to a global reference system. In the context of inland navigation, this can be problematic, since without knowledge of the limited navigable space, irrealistic trajectories are likely to be determined. If spatial constraintes are introduced, e.g., by implementing an additional submodule to process map data, however, overall complexity increases. Instead of processing the vessel displacement information on the one hand and the spatial information on the other hand, the paper proposes the merging of both information. Here, fairway-related and navigation-related displacement information are used directly. In this way, the previously proposed context-sensitive Classification Transformer (CSCT) shows an improved spatial awareness. Additionally, the CSCT is adapted to assess the model uncertainty by enabling dropout during inference. This approach is trained on different inland waterways to analyze its generalizability. As the improved CSCT obtains lower prediction errors and enables to estimate the trustworthiness of each prediction, it is more suitable for safety-critical applications in inland navigation than previously developed models.
... The International Maritime Organization is preparing regulations for MASS operation, and many researchers are investigating MASS-related AI technology (Chun et al., 2021). Japan announced that it successfully conducted a field experiment of MASS operation (MEGURI, 2022;Negenborn et al., 2023), and Norway conducted a field experiment with a 120-TEU autonomous ship (Smartmaritime, 2020;Yara, 2020;Negenborn et al., 2023). ...
... The International Maritime Organization is preparing regulations for MASS operation, and many researchers are investigating MASS-related AI technology (Chun et al., 2021). Japan announced that it successfully conducted a field experiment of MASS operation (MEGURI, 2022;Negenborn et al., 2023), and Norway conducted a field experiment with a 120-TEU autonomous ship (Smartmaritime, 2020;Yara, 2020;Negenborn et al., 2023). ...
One of the most important factors for the development of maritime autonomous surface ships (MASSs) is collision avoidance. Various artificial intelligence models have been applied to collision avoidance; however, they have a limited ability to understand the International Regulations for Preventing Collisions at Sea (COLREGS), which are qualitative in nature and do not provide specific timings for ships to take action. Herein, we quantified Rules 8, 16, and 17 of the COLREGS to help MASSs understand them. Further, we proposed specific timings for the engine control of a give-way ship to avoid imminent collision and the collision avoidance cooperative actions of a stand-on ship based on the sea conditions in the Singapore Main Strait. To evaluate the proposed approach, we used a convolutional neural network-long short-term memory (CNN-LSTM) model to predict ship trajectories in different scenarios and performed collision assessment according to the computed distance at collision. Two types of own ships were assessed: one with a good course changing performance and one with a poor curse changing performance.
... However, the emergence of autonomous vessels has created a new problem in that navigators should now consider differences in navigations between manned ships and machine-operated unmanned ships in addition to existing ship navigations operated only by navigators [47,64,71]. The navigations between manned ships and machine-operated unmanned ships are considered as an additional variable compared with existing marine transportation, which considers only manned ships. ...
... Notably, several studies have been initiated to explore the necessity of revising COLREGs in response to the challenges related to developing measures for avoiding ship collisions [35,37,47,52,54,64] although no revisions are currently included in the MASS code. In the long term, any revision of the COLREGs agreement should focus on discussing the relationships between the existing sailing and autonomous ships, power-driven vessels and autonomous ships, and other relevant aspects rather than undertaking extensive and immediate revisions. ...
The Convention on the International Regulations for Preventing Collisions at Sea (COLREGs) comprises rules to prevent collisions at sea and is based on the qualitative rules and ordinary practice of seamen. However, because the criteria of the sailing rule interpretation are different, the problem of misunderstanding occurs owing to the difference in the interpretation between navigators and collision-avoidance algorithm designers. Therefore, this study aims to clarify the collision situations by understanding in the sailing rule interpretation of COLREGs. To identify the understanding of collision situations, we surveyed the navigators’ understanding of collision situations and reviewed the collision-avoidance algorithms used in recent studies. The survey results were analyzed based on head-on and crossing (HC) and crossing and overtaking (OC) situations. Results showed that navigators were unsure about whether the HC situation sailing rule should be applied to incoming vessels from the 008° and whether the overtaking or crossing situation should be applied to coming vessels at 160°. In OC situations, as the angle increased from 130°, it became difficult for navigators to interpret the navigation rules. A notable disparity emerged between the navigators’ understanding and the automated collision-avoidance algorithms. Moreover, it was confirmed that practical navigators exhibited divergent interpretations of these regulations. This study contributes to provide an understanding of COLREGs sailing rules based on the understanding of navigators and researchers.
... The fast uptake of MASSs must be supported by the emerging technologies development and is driven by economic, environmental and societal needs for enhancing the shipping operations sustainability, the supply chain resilience, reducing accidents, and providing better working conditions shifting jobs from sea to shore (Munim, 2019;Iannaccone et al., 2020;Li and Yuen, 2022). The recent advancements in robotics, machine learning, deep learning, artificial intelligence (Li and Yuen, 2022;Nielsen et al., 2022), communications and cyber-security (Bolbot et al., 2020;Weaver et al., 2022) enable the development of the required technologies for safe autonomous and remote navigation (Heffner and Rødseth, 2019;Negenborn et al., 2023). The principal economic motivation is related to the reduction of the ship's operational costs, which is achieved by an increase in the ship sailing efficiency (Kretschmann et al., 2017;Munim, 2019), lower maintenance cost (Cullum et al., 2018;Cheliotis et al., 2020), higher operational efficiency (Shaw and Lin, 2021;Yuan et al., 2021), as well as by transfer of crew from sea to shore (Kooij et al., 2021;Jovanović et al., 2022a). ...
... Robust and reliable communications between the ship and RCC are needed for autonomous operations (MUNIN, 2015;Munim, 2019;Heffner and Rødseth, 2019;Negenborn et al., 2023), with more demanding requirements for data transfer and connectivity links bandwidth compared to conventional ships. This is expected to considerably increase the communications cost (Santos and Guedes Soares, 2018). ...
Despite the pursued autonomous ships initiatives, the lack of information on emerging technologies and their costs along with the limited investigations of the autonomy effects on logistics render these vessels feasibility assessment challenging. This study aims at developing an overarching framework to support decisions for the transition to autonomous shipping. The ship lifetime capital, operational and voyage expenditures are estimated to quantify the economic-environmental impact and required investments. Several scenarios are defined to address the input data uncertainty. The case of a short-sea shipping cargo vessel operating in the Norwegian waters is studied, considering its conversion to operate autonomously, as well as the next generation crewless ship design. The derived results demonstrate that the converted autonomous ships can reduce the lifetime present value by 1-12% and the carbon emissions by 4%, whereas the next-generation autonomous ships design leads to their further reductions by 3-4% and 4-7%, respectively. These savings can further increase by 6-7% by reducing the autonomous ships sailing speed, as crew replacement periods are not required. The estimated economic margin indicates that the next-generation autonomous ships can adopt greener technologies, such as hydrogen or green ammonia, to achieve the targeted carbon emissions reduction.
... MASS ships on the other hand are usually large and designed for civil purposes like transporting goods or people. In a pilot project in Norway, the container ship Yara Birkeland (80 m) is expected to convey fertilizer autonomously with zero emissions from a manufacturing plant to an export port which is expected to be operational in 2024 (Negenborn et al., 2023). In China, a 120-m electric container ship called Zhi Wei has demonstrated to shuttle remotely and sometimes autonomously between two ports in Shandong province. ...
The growth of maritime shipping is leading to the creation of larger vessels. However, this expansion in size brings with it several challenges, including the development of maritime infrastructure, the potential for growth in third-world countries, and the emission of greenhouse gases. In response to these challenges, this research explores the feasibility of designing an autonomous ship capable of transporting a single standardized 40 ft. container overseas using mainly passive propulsion methods. Using advanced design tools, including CAD software and CFD simulations, as well as conducting a comprehensive analysis of relevant literature, the designs for a hull and sails were developed, and an overview of the potential active control systems required for autonomous operation was provided. The study also performed an initial analysis of strength, stability, and velocity to validate the design choices. The ship proves to adhere to the basic strength and stability requirements while reaching its maximum hull velocity at certain wind speeds. The results of the study indicate that it is possible to design and manufacture a mainly passively propelled ship capable of transporting a 40 ft. standardized container overseas and rethink the logistics at scale.
... With the increasing presence of Artificial Intelligence (AI) and high level of autonomy in the sociotechnical applications technical system e.g., navigation systems will be assisting and collaborating with highly skilled human operators [15]. It could be similar to an aviation pilot monitoring the automated navigation in place, or a remote operator like a drone pilot controlling it from a remote location [16]. However, with the improvement and increasing reliability of the system, over time, human supervision might be reduced on a large scale and will only be required in emergencies. ...
The introduction of automated solutions for inland waterways shipping supports the European vision for a sustainable and greener shift within maritime management and logistics. Despite increasing investments, impressive technological advancements, and active discussion to solve the regulatory and business model barriers, socio-technical aspects are still less studied in the preparation for the future of autonomous shipping. This study examines stakeholder and technology roles to map the gaps and challenges created in this emerging space using a system theory approach, specifically a recently developed work design system analysis tool named Change Agent Infrastructure (CHAI) analysis [1]. This framework was chosen to better understand the likely changes of the system with the introduction of automated technology and higher degrees of automation and digitalization in the European inland waterways. The analysis identifies that there are multiple receivers of the change and regulatory bodies will also be actors with considerable responsibilities to direct these changes.
... Situational awareness forms the foundation for achieving maritime navigation in autonomous ships (Thombre et al., 2022). In the navigation system of autonomous vessels, detecting the surrounding environment and consistently tracking moving objects on the sea surface is crucial for guiding subsequent collision avoidance decisions (Perera et al., 2011;Negenborn et al., 2023). Multi-object tracking technology, a key component in intelligent perception, is pivotal in this context. ...
A novel Maritime Multi-Object Tracking method is proposed, combining a deep learning-based object detector with target association algorithms to achieve robust sea-surface multi-object tracking. Specifically, the Multi-Object Tracking employs You Only Look Once version 7 detector for object detection. In the data association part, a module for onboard camera motion compensation is developed, a maritime dynamic spatial information-based intersection-over-union is presented as a similarity metric, and a progressive refinement cascade matching strategy is designed to enhance the tracker's sea-surface multi-object tracking capabilities. The Jari Maritime Tracking Dataset is utilised to validate the effectiveness performance of the proposed method. Experimental results demonstrate that compared to the earlier process, the proposed method exhibits a significant enhancement in multiple object tracking accuracy, with an increase of 27.8% and an achieved score of 81.3. In particular, it reduces the number of identifications switching and missed targets, achieving holistically preferable performance. Meanwhile, the speed of the proposed Multi-Object Tracking fulfils the engineering application requirements for an autonomous ship navigation system.
... Autonomous vehicles represent a promising avenue for enhancing safety and optimizing energy and fuel efficiency within traffic systems, making them a vital element of future sustainable transportation networks [1]. While the general public often fixates on self-driving cars [2], the potential benefits of autonomous vehicles extend to other modes of transportation, such as autonomous vessels [3] and aircraft systems [4]. Regardless of whether a vehicle is under human or autonomous control, the paramount concern in all traffic operations remains ensuring safety by preventing collisions with other vehicles and stationary obstacles [5,6]. ...
... Sensors were installed in various locations to measure parameters like pH, dissolved oxygen, turbidity, and the presence of contaminants such as heavy metals and hydrocarbons. AI algorithms processed these data to detect anomalies and potential pollution events [2,78,256]. ...
The maritime industry, responsible for moving approximately 90% of the world's goods, significantly contributes to environmental pollution, accounting for around 2.5% of global greenhouse gas emissions. This review explores the integration of artificial intelligence (AI) in promoting sustainability within the maritime sector, focusing on shipping and port operations. By addressing emissions, optimizing energy use, and enhancing operational efficiency, AI offers transformative potential for reducing the industry's environmental impact. This review highlights the application of AI in fuel optimization, predictive maintenance, route planning, and smart energy management, alongside its role in autonomous shipping and logistics management. Case studies from Maersk Line and the Port of Rotterdam illustrate successful AI implementations, demonstrating significant improvements in fuel efficiency, emission reduction, and environmental monitoring. Despite challenges such as high implementation costs, data privacy concerns, and regulatory complexities, the prospects for AI in the maritime industry are promising. Continued advancements in AI technologies , supported by collaborative efforts and public-private partnerships, can drive substantial progress towards a more sustainable and efficient maritime industry.
... Autonomous surface vehicles (ASVs), have the potential to revolutionize the marine sector. Significant efficiency gains are possible by the removal or reduction of crew from often hazardous working conditions, where the space, energy, and design constraints imposed by life-support systems can be relaxed, and where mission times can be extended by the reduced needs for resupply [42], [43]. This benefits most vessel applications, including commercial shipping, defense, aquaculture, surveying, research, and the servicing of marine infrastructure. ...
Radar systems operating within the 220 GHz atmospheric transmission window are comparatively rare despite the benefits they offer in high angular, range, and Doppler resolutions. Given the growing availability of solid-state signal generation components designed for this frequency range, interest in the sensing potential of this region is increasing. This paper presents the development and characterization of ‘Theseus’, a 207 GHz FMCW Doppler radar designed for sea clutter and marine target characterization but also capable of a large variety of other close-range environmental sensing uses. The radar carrier frequency is tunable between 200-208 GHz with a maximum chirp bandwidth of 2 GHz resulting in a range resolution of 7.5 cm, and a chirp repetition interval (CRI) of 67.59 μs giving a maximum unambiguous velocity of ±5.36 ms
-1
. Several measurement application examples are presented, showcasing a wealth of micro-Doppler and micro-range information gathered from a variety of targets and clutter including sea clutter, humans swimming and running, UAV flight, a plan position indicator (PPI) scan of a terrestrial environment, and rain clutter. Data in this frequency band are very rare in the open literature, and thus the high range and Doppler resolution measurement capabilities of this radar present an opportunity to expand the knowledge in this area.
... Nevertheless, this transportation activity generates substantial carbon dioxide (CO 2 ) emissions. In 2018, the shipping industry produced approximately 3% (equivalent to approximately 1 billion metric tons) of the world's CO 2 emissions (Negenborn et al., 2023). Moreover, this percentage is expected to increase to 12%-18% by 2050 (Damian et al., 2022). ...
As governments attach importance to carbon neutrality, achieving carbon emission reductions in port operations through the use of subsidies and emerging technology has become a research hotspot. In this paper, we establish a three-stage Stackelberg game model to discuss stakeholders' strategies in a shipping supply chain consisting of the government, the port authority, and the shipping company. Low-carbon transportation preferences and the low-carbon trust of cargo owners in the port authority are included in our model. Four policy scenarios are created depending on whether the government adopts blockchain technology and two subsidy schemes, namely, a low-carbon technology subsidy scheme and a low-carbon quantity subsidy scheme, for ports. We find that i) the applicability of the two subsidy schemes varies with the low-carbon transportation preferences of cargo owners. ii) The low-carbon quantity scheme provides greater benefits to stakeholders compared to the low-carbon technology subsidy scheme. iii) A decrease in unit investment cost for port equipment upgrades leads to an increase in the total amount of subsidy. iv) The introduction of blockchain technology results in an increase in transportation demand, social welfare, and all stakeholders' profits. These findings enrich the theory of low-carbon port construction in the context of blockchain technology applications. They may also provide managerial insights into the government's low-carbon governance strategy and inform port authorities' low-carbon investment and pricing decisions.
... While there have been notable advancements in autonomous ship technologies, there are concerns regarding their alignment with existing regulatory frameworks (IMO, 2021). The slow-paced nature of regulation-making processes, typically characterized by careful considerations of safety and operational implications, contrasts with the rapid evolution of autonomous systems (Negenborn et al., 2023). The International Maritime Organization (IMO) has introduced four autonomy levels to define the progressive integration of autonomous functionalities in ships (IMO, 2021). ...
This study presents an approach to enhance human-machine collaboration in autonomous ship trajectory planning. A decision support system is developed, considering crucial environmental factors such as ocean currents, wind, and tidal information, alongside the integration of narrow channel geometry, squat effect, and Under-keel-clearance (UKC). The Dynamic Consequence Analysis (DCA) risk assessment method is utilized to establish dynamic safety domains, incorporating ship maneuvering characteristics and potential failure scenarios. The Multi-objective Particle Swarm Optimization (MOPSO) algorithm is then employed to generate alternative trajectories, optimizing five objective functions: minimizing safety domain violation, consecutive speed changes, path length, deviation from the initial plan, and deviation from the initial estimated time of arrival. Furthermore, two Multi-criteria Decision Making (MCDM) methods, Multi-Objective Optimization by Ratio Analysis (MOORA) with user preferences, and the Entropy Weight Method (EWM) with automatic weight allocation, are employed to rank alternative solutions from the Pareto front. Finally, a clustering method is employed on the Pareto front solutions. The outcomes that serve as representatives for these clusters are then merged with the highest-rated alternative solutions from MCDM methods. This combined set forms the basis for the final decision-making process carried out by the operator. While dynamic obstacles are not considered in this study, evaluation across three scenarios demonstrates the effectiveness of the proposed decision support system for trajectory planning.
... A ship needs more situational information to decide the optimal engine settings and direction. This information needs to be processed by the captain or, more and more often by partial or fully autonomous systems [4]. In this research, we focus on the question on how to provide situational awareness to autonomous ships. ...
This study integrates strategic decisions and operational control systems in autonomous shipping. By providing ships with situational information and adding a virtual operator, we show that vessels can make informed choices regarding their route and engine settings. To demonstrate this integration, we developed new components and put these to the test in three lab experiments. The green routing capability experiment showed the bridge between the control system of the autonomous vessel, operated via Robot Operating System (ROS), to the simulation environment of OpenCLSim. We developed a real-time variant of OpenCLSim and a communication component that could expose the state of the OpenCLSim simulation with the ROS system. This experiment showed that an autonomous vessel could follow a path provided by the simulation. The green steaming capability experiment showed that the ship could also adapt its speed based on information from the simulations. We developed an additional communication component capable of advising the vessel about its velocity. Together with the green-routing capability, this forms the basis for more complex experiments. The port layout experiment showed a potential use case of the green-routing and green-steaming capabilities. We created a waypoint layout similar to the port. While a ship is sailing, twelve simulations are computed every five seconds. The scenarios vary in engine order, route choices, resulting in varying emissions, fuel, and cost. We evaluated the impact of different tactics such as green-routing, green-steaming, and full-speed sailing on operational behavior like steering and engine order. Our approach, using a real-time version of a Vessel in the OpenCLSim simulation software, enabled predictive simulations to facilitate the chosen tactic based on a given strategy. Integrating simulations to evaluate the options with the control systems can develop into a valuable tool for optimizing vessel performance and reducing environmental impact in autonomous shipping operations.
... Autonomous Ships (AS) are on the horizon, yet the progress on the amendments required to enable such ships is rather slow (Negenborn et al. 2023). A potential way to accelerate the AS adoption is by focusing on the Key Enabling Technologies (KET) for AS, by following the classical "divide and conquer" approach (Machiavelli 1521). ...
Novel advanced systems, employing information and communication technology, are emerging. An example of such a system is the electronic lookout (e-lookout), which functions as the visual lookout performed by humans on ships. In this paper, we investigated what types of requirements may arise for e-lookout based on an analysis of statutory documents and existing class society guidelines for autonomous ships. To this end, first, we identified elookout functions based on a functional breakdown, considering both existing maritime function classifications as well as experts' opinion. Second, we investigated the class society guidelines for autonomous ships concerning elookout and the applicability of existing regulatory requirements for conventional human lookout including those specified by STCW, COLREGS, and SOLAS. Considering the existing regulatory requirements for lookout, we proposed alternative equivalent requirements for e-lookout. Specifically, based on the analysis, we specified seventeen novel requirements for functionality, reliability, availability, maintainability, and safety. It is expected that the analysis implemented, and methodology presented will support the development of an appropriate regulatory framework for e-lookout and autonomous ships.
... Accidents investigation and analysis have demonstrated that human error is one of the multiple contributors to the marine casualties and incidents (EMSA, 2022). Utilizing artificial intelligence and advanced automation techniques, Maritime Autonomous Surface Ship (MASS) can reduce the need for human control (Abaei et al., 2022;Chaal et al., 2022;IMO, 2021;Negenborn et al., 2023) and therefore the likelihood of human error (Wróbel et al., 2017). Although large ships are not anticipated to be fully autonomous in the near future (Bolbot et al., 2022b), the competition and collaboration among countries and companies have brought significant research developments (Munim, 2019). ...
The rise of artificial intelligence and advanced automation techniques have supported the development of Maritime Autonomous Surface Ships (MASS). Countries and companies are competing and collaborating to become leaders in this arising market. The Collision Avoidance System (CAS) replicates the human operator with its decision-making ability to ensure navigational safety of MASS. The CAS employs advanced algorithms to implement a wide spectrum of functions from collision avoidance to route optimization. However, the verification of the CAS dependability is highly reliant on the coverage of implemented scenarios during testing, which directly influences its trustworthiness. Scenarios in previous research from manually designed approaches have a limited coverage, while those from simulation-based approaches based on algorithms are disconnected from the scenarios occurring in the actual operational contexts. Others from real data-based approaches using Automatic Identification System (AIS) data propose an unbearably large number of scenarios. Considering that critical risk scenarios can constitute the basis for the development of CAS testing, this study proposes a method for identifying critical encounter scenarios based on AIS data. The method uses safety indices to identify hazardous encounter scenarios. Then, a muti-ship encounter scenario classification method based on COLREGs is proposed to categorize these scenarios. For each category, the risk value of each scenario is evaluated by Time-varying Risk Vectors (TRV). Scenarios with the lowest and highest risk are then used as representative for the whole. In this study, AIS data from Singapore Strait covering one month of operation is used for scenario identification. The results are discussed indicating good effectiveness in identifying critical scenarios in water area.
... Traditionally, the navigation and control of inland vessels is performed by human operators, and recent research began to investigate the use of autonomous surface vehicles (ASVs) for such inland operations (Gan et al., 2022;Vanneste et al., 2022). For a comprehensive understanding of ASV systems, we refer to Liu et al. (2016), Fossen (2021), and Negenborn et al. (2023). ...
This paper proposes a realistic modularized framework for controlling autonomous surface vehicles (ASVs) on inland waterways (IWs) based on deep reinforcement learning (DRL). The framework comprises two levels: a high-level local path planning (LPP) unit and a low-level path following (PF) unit, each consisting of a DRL agent. The LPP agent is responsible for planning a path under consideration of nearby vessels, traffic rules, and the geometry of the waterway. We thereby leverage a recently proposed spatial-temporal recurrent neural network architecture, which is transferred to continuous action spaces. The PF agent is responsible for low-level actuator control while accounting for shallow water influences on the marine craft and the environmental forces winds, waves, and currents. Both agents are thoroughly validated in simulation, employing the lower Elbe in northern Germany as an example case and using real AIS trajectories to model the behavior of other ships.
... In recent years, the idea of autonomous and unmanned ships has emerged as a potential solution for enhancing the efficiency and safety of maritime transportation (Negenborn et al., 2023). In 2012, the MUNIN project was launched as the first European initiative to explore the feasibility of unmanned and autonomous ships (Rødseth and Burmeister, 2012). ...
The safety and reliability of autonomous ships are critical for the successful realization of an autonomous maritime ecosystem. Research and collaboration between governments, industry, and academia are vital in achieving this goal. This paper conducts a bibliometric review of the research on the risk, safety, and reliability of autonomous ships aiming to provide researchers and maritime stakeholders with a structured overview of the topics, development trends, and collaboration networks in this research field. 417 papers published between 2011 and 2022 were identified covering 940 authors, 31 countries, and 227 journals. Three main themes were determined in this research domain: “safety engineering and risk assessment for decision making”, “navigation safety and collision avoidance”, and “cybersecurity risk analysis”. Meanwhile, it was identified that research on cybersecurity in autonomous shipping is moving to overlap with safety, which requires future co-analysis methods. Additionally, the analysis of the most cited 30 papers suggests that further research is needed in the topics of unmanned machinery operation risks, online risk tools, system-theoretic safety analysis, human factor, and the determination of suitable risk acceptance criteria for safety assessment of autonomous ships. Furthermore, the analysis revealed that the development of unambiguous COLREGs regulation is crucial for the development of safe collision avoidance algorithms for MASS. It was identified that the publication by Fan et al., (2020) is a key publication in this research field, while the journals of Ocean Engineering, Reliability Engineering & System Safety, and Safety Science are the key journals publishing on autonomous ship safety and reliability.
... The automation of transport is well underway: autonomous passenger trains are already operational [1], autonomous freight ships are being tested [2], autonomous vehicle (AV) trials are in progress [3], and flying autonomous taxis are being developed [4]. AVs are predicted to comprise a substantial proportion of passenger vehicles by 2050 [5]. ...
(1) Background: The automation of transport systems is well underway; however, it is unclear how this will affect people’s mobility choices. Changes in these choices have implications for health and the sustainability and efficiency of transport systems, making it important to understand how the advent of autonomous vehicles might affect people’s transport behaviors. The aim of the present study was to address this knowledge gap in the Australian context. (2) Methods: Respondents reported their demographic information, current transport behaviors, the perceived importance of transport-related factors, and attitudes toward autonomous vehicles. They then read a vignette describing a future scenario involving autonomous vehicles that was informed by expert stakeholders. After reading the vignette, the respondents selected those transport options that they would anticipate using in the depicted scenario. Descriptive analyses were conducted to examine changes in transport choices, while regression models were employed to identify the predictors of choices in the future scenario. (3) Results: Most respondents envisaged making greater use of active, shared, and public transport options in an autonomous future, compared to their current use of these options. The intended use of private transport options halved. The most consistent predictor for selecting a certain mode of transport was the current use of that option or its non-autonomous equivalent. (4) Conclusion: Overall, favorable changes in the envisaged use of transport were observed for the hypothetical scenario, which was characterized by improved public transport, a practical active transport infrastructure, and relatively cheap shared autonomous vehicles. If policymakers can act to realize these outcomes, the autonomation of transport is likely to lead to positive societal change.
... According to [1], 80% of global trade is transported by sea each year. Ships deploy sensors and AI systems to improve safety, increase efficiency, reduce environmental impacts, and avoid collision avoidance [2]. The International Maritime Organization (IMO) proposed the concept of a maritime autonomous surface ship (MASS) in 2017 and defines it as a ship that can operate independently of human interaction. ...
Maritime autonomous surface ships (MASSs) have received increased attention in both academic research and industrial applications in the global shipping and shipbuilding industry in recent years. According to its definition, a MASS can independently operate without human interaction. This brings the problem of how to test and evaluate the capabilities of the autonomous navigation control system developed for MASS. This paper proposes the novel concept of a variable stability ship and the design of its control system. A variable stability ship consists of a model-scaled ship, a model-following controller, and a hardware and software platform to implement its functions. The variable stability ship can replicate the dynamic responses of different reference ships despite their dissimilarities in physical parameters and hydrodynamic characteristics with the design of the model-following controller. Therefore, it can be used to test the performance of different control strategies on various ship types such that the R&D costs of physical model-based tests can be reduced, as well as shortening the time spent in developing physical ship models. Preliminary simulations are carried out to show its effectiveness and applicability.
... Several real-life application of autonomous vessels have been demonstrated, including in open water environments (e.g., Kim et al., 2022), inland waterways (e. g., Peeters et al., 2020), and constrained urban waterways (e.g., Brekke et al., 2022). However, despite constituting one of the major trends in ocean engineering research today (Tavakoli et al., 2023), relatively little is known about the role of the human operator of remotely controlled and autonomous vessels (Negenborn et al., 2023). Specifically, knowledge gaps persist concerning maritime human factor influences on human supervisory control. ...
Autonomous ships require remote supervision from a human operator to ensure safety. However, there are knowledge gaps concerning human factor influences on remote supervisory control. We investigate the influence of five factors on remote supervisory control during simulated intervention scenarios: (i) Skillset, represented by gamers and navigators; (ii) Monitoring Time, represented by either 5 or 30 min of passive monitoring; (iii) Number of Vessels, represented by either one or three vessels; (iv) Available Time, represented by 20- or 60-s critical time windows; (v) Decision Support System (DSS), represented by availability of a DSS. The experiment was a randomized factorial design where participants (n = 32) completed two interventions: first a handover (automation detects a critical event and hands over control) and then a takeover (operator detects a critical event and takes over control). We observed: (i) gamers and navigators both demonstrated transferrable skillsets, but neither group excelled over the other; (ii) monitoring time affected boredom, but this translated to minor performance effects. Moreover, performance was reduced under conditions of (iii) supervising three vessels, (iv) low time availability, and (v) unavailable DSS. These outcomes contribute to the empirical basis for assessing maritime human factors in remotely controlled and autonomous ship design.
This chapter introduces the fundamental aspects of the SAFETY I concept and its relation to the management of safety in the maritime domain. These fundamental aspects are also reviewed in the context of their potential contribution to the development of the MASS concepts. The chapter includes the descriptions of methodologies for risk and safety analysis and it discusses the essential characteristics these methodologies offer for supporting a transition toward the design and operation of an autonomous maritime ecosystem.
The chapter intends to include MASS developments into broader perspectives, using a system thinking lens, meaning, mixing disciplines and approaches. First, the main drivers of the evolution of shipping technology are contextualized. Second, the paper argues that MASS development is influenced by technology providers and States supporting national competitiveness. Third, it is recalled that the promotion of autonomy of technical systems originated from the military sector, which prompted unmanned vehicle developments, later followed by the growing ITC sector. Fourth, the prudent approach to autonomy at sea of shipping companies is stressed, suggesting a gap between technology developers and targeted buyers. Fifth, the narrative behind the promotion of MASS in the maritime sector is discussed, and some milestones are proposed. Sixth, assumptions and beliefs underpinning MASS promotion are briefly discussed, suggesting a growing representation gap between technology designers and operators. Seventh, the chapter points out MASS researchers’ obsession with machine-driven navigation but the omission of self-repairing functions continuously performed by seafarers at sea. Finally, the chapter argues that MASS development requires the multiplication of analytical perspectives as proposed by system thinking.
Accurate ship trajectory prediction (STP) is crucial to realise the early warning of ship collision and ensure maritime safety. Driven by advancements in artificial intelligence technology, deep learning-based STP has become a predominant approach in the research field of ship collision avoidance. This paper, based on a state-of-the-art survey of the existing STP research progress, aims to develop a new bi-directional information fusion-driven prediction model that enables the achievement of more accurate STP results by addressing the drawbacks of the classical methods in the field. In this context, a cascading network model is developed by combining two bi-directional networks in a specific order. It incorporates the Bi-directional Long Short-Term Memory (BiLSTM) and the Bi-directional Gated Recurrent Unit (BiGRU) neural network into a single three-layer, information-enhanced network. It takes advantage of both networks to realise more accurate prediction of ship trajectories. Furthermore, the performance of the proposed model is comprehensively evaluated using Automatic Identification System (AIS) data from three water areas representing traffic scenarios of different safety concerns. The superiority of the proposed model is verified through comparative analysis with twenty other methods, including the state-of-the-art STP in the literature. The finding reveals that the new model is better than all the benchmarked ones, and thus, the new STP solution in this paper makes new contributions to improving autonomous navigation and maritime safety.
Introduction
Physical activity is beneficial to health, yet a substantial proportion of people do not meet minimum physical activity recommendations. The introduction of autonomous vehicles is likely to bring about changes that both promote and discourage people from being physically active. However, attempts to predict how autonomous vehicles will affect engagement in physical activity have yielded mixed results. The present study used a novel approach to better understand how people's lifestyles might be affected, and whether some people may be more vulnerable to increased inactivity.
Method
In total, 1078 respondents completed an online survey that included a vignette describing a future scenario where autonomous vehicles are in common use. Respondents reported their anticipated changes in exercise levels and associated reasons. Frequency analyses were conducted to examine predicted changes in physical activity and two generalised linear models were run to identify factors associated with predicted decreases and increases in exercise.
Results
Only minor changes in anticipated levels of physical activity were observed. However, younger people, those who were less active, and those who spent more time using cars and public transport, were more likely to expect they would be increasingly sedentary in the scenario. Less incidental exercise, widespread convenient delivery services, and increased access to door-to-door transport were cited as being the main reasons for anticipating being less active.
Conclusions
The introduction of autonomous vehicles and delivery services will need to be carefully managed to avoid reduced physical activity among certain groups. Proactively employing harm-reduction strategies is a potential means to foster active lifestyles in an autonomous future.
Accurate and efficient real-time prediction of ship maneuvering motion in waves is essential for designing the motion controller to realize the autonomous navigation function of maritime autonomous surface ship (MASS) at sea. This study innovatively proposes an improved reduced-order model (ROM) based on higher order dynamic mode decomposition (HODMD) to predict ship maneuvering motion in waves for at least one wave period. Specifically, the improved ROM is built based on the original ROM by dividing the 6-DOF maneuvering motion in waves into two subsets, i.e., the low-frequency one and the high-frequency one, which are then predicted separately. Notably, neither the original ROM nor the improved ROM requires online updates of the model structure and the hyperparameters during the real-time prediction of ship maneuvering motion. Taking the KCS container ship as the study object and using the proposed method, the real-time prediction of turning circle maneuver in regular waves is carried out. The results indicate that the improved ROM has higher accuracy and stronger robustness compared to the original ROM.
The “Aegean Ro-boat Race” is an international university level competition, challenging teams to design and develop innovative autonomous robotic systems that can perform at sea in real world conditions. This is an innovation race amongst universities, but with the support of industry, that merges visionary thinking from different fields to solve problems in marine robotics and autonomous systems. Topics to be judged include autonomous behavior, sensor fusion, object detection, path planning, reliability, and overall innovation. This year's competition took place in Syros, Greece on the 12th of July 2023, and consisted of three mission tasks, focused on i) high speed and performance ii) collision avoidance and iii) endurance. This work details what happened during the first “Aegean Ro-boat Race”, while presenting the results of this unique learning experience and discussing advances achieved in terms of innovation.
The safety assurance of autonomous vessels is a major issue for their implementation, and it is necessary to prove their equivalent safety compared to the existing vessels. Two “model-based approaches” are important to identify and quantify the risks of such complex systems: systemic risk analysis using descriptive models, and system simulation using numerical models. This paper proposes a method for defining test scenarios from risk assessment in the design phase of the autonomous vessel and shows the flow of simulation-based verification and validation (V&V) using model-based simulation. Specifically, we extended the System-Theoretic Process Analysis (STPA) and extracted specific risk-based critical scenarios. Then we picked up a specific scenario for the short-range voyage planning function and presented a simulation-based verification flow using a ship avoidance maneuvering simulator. The results of this study are expected to be utilized in discussions regarding the verification and certification process of autonomous systems and the functional requirements of the simulators for verification.
Seaborne trade plays a vital role in global trade by facilitating the movement of cargo across the globe. However, maritime transactions are characterized by inherent complexity and frequently exhibit deficiencies in transparency and operational efficiency. This is due to primary factors such as substantial amount of paperwork, ineffective data sharing and processing, system incompatibilities, and a lack of logistic transparency and real-time traceability. Blockchain is a decentralized information technology that offers a promising solution to the ongoing challenges in maritime business. We comprehensively review the literature on blockchain and conduct a synthesis analysis of the benefits and challenges of implementing blockchain in the maritime industry. We demonstrate that blockchain could improve operational efficiency, enhance logistics security and transparency, reduce transaction costs and time, improve sustainability, as well as build trust among participants.
The autonomous shipping industry is increasingly focusing on enhancing the safety and reliability of software-based systems. Conducting a risk assessment is a requirement for demonstrating the safety equivalence of autonomous ships based on such systems to conventional vessels. Traditional risk assessment models, however, primarily focus on hardware failures, often overlooking potential software-related failures and functional inadequacies. This study proposes a framework integrating Software Failure Mode and Effects Analysis (FMEA), System–Theoretic Process Analysis (STPA), and Bayesian Network (BN) for risk identification of autonomous ship software systems. The results of a case study reveal that the framework sufficiently addresses the multifaceted nature of risks related to software in autonomous ships. Based on the findings of this study, we suggest the need for standardization of software architecture development in the autonomous ship industry and highlight the necessity for an enhanced understanding of AI-specific risks and the development of tailored risk assessment methodologies.
Autonomous ships represent an emerging paradigm within the maritime sector, poised to bring multiple advantages. Although numerous prototypes have been developed, the deployment of large autonomous ships has predominantly remained confined to domestic waters or specialized military applications. The extensive adoption of autonomous ships is hampered by several challenges, primarily centered around safety. However, the direct assessment of autonomous technologies on large-scale vessels can be very costly. Small-scale autonomy testing may provide a cheaper option. This study reviews the current small autonomous ship models used by maritime researchers and industry practitioners. It aims to evaluate how these autonomous models currently augment and can augment safety assurances on larger autonomous ships. The review identifies relevant very small Unmanned Surface Vessels (USVs), the main research groups behind them and their applications. Then, the current use of USVs for safety and safety assurance is analyzed. Finally, the paper suggests innovative strategies and research directions for using USVs for the safety assurance of larger autonomous ships.
Physics-related and model-based vessel trajectory prediction is highly accurate but requires specific knowledge of the vessel under consideration which is not always practical. Machine learning-based trajectory prediction models do not require expert knowledge, but rely on the implicit knowledge extracted from massive amounts of data. Several deep learning (DL) methods for vessel trajectory prediction have recently been suggested. The DL models developed typically only process information about the (dis)location of vessels defined with respect to a global reference system. In the context of inland navigation, this can be problematic, since without knowledge of the limited navigable space, irrealistic trajectories are likely to be determined. If spatial constraintes are introduced, e.g., by implementing an additional submodule to process map data, however, overall complexity increases. Instead of processing the vessel displacement information on the one hand and the spatial information on the other hand, the paper proposes the merging of both information. Here, fairway-related and navigation-related displacement information are used directly. In this way, the previously proposed context-sensitive Classification Transformer (CSCT) shows an improved spatial awareness. Additionally, the CSCT is adapted to assess the model uncertainty
by enabling dropout during inference. This approach is trained on different inland waterways to analyze its generalizability. As the improved CSCT obtains lower prediction errors and enables to estimate the trustworthiness of each prediction, it is more suitable for safety-critical applications in inland navigation than
previously developed models.
ResearchGate has not been able to resolve any references for this publication.